2024-11-18 05:18:53,671 main DEBUG Apache Log4j Core 2.17.2 initializing configuration org.apache.logging.log4j.core.config.properties.PropertiesConfiguration@302c971f 2024-11-18 05:18:53,707 main DEBUG Took 0.033155 seconds to load 1 plugins from package org.apache.hadoop.hbase.logging 2024-11-18 05:18:53,708 main DEBUG PluginManager 'Core' found 129 plugins 2024-11-18 05:18:53,708 main DEBUG PluginManager 'Level' found 0 plugins 2024-11-18 05:18:53,710 main DEBUG PluginManager 'Lookup' found 16 plugins 2024-11-18 05:18:53,711 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-11-18 05:18:53,726 main DEBUG PluginManager 'TypeConverter' found 26 plugins 2024-11-18 05:18:53,749 main DEBUG LoggerConfig$Builder(additivity="null", level="ERROR", levelAndRefs="null", name="org.apache.hadoop.metrics2.util.MBeans", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-11-18 05:18:53,750 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-11-18 05:18:53,753 main DEBUG LoggerConfig$Builder(additivity="null", level="DEBUG", levelAndRefs="null", name="org.apache.hadoop.hbase.logging.TestJul2Slf4j", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-11-18 05:18:53,753 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-11-18 05:18:53,754 main DEBUG LoggerConfig$Builder(additivity="null", level="ERROR", levelAndRefs="null", name="org.apache.zookeeper", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-11-18 05:18:53,755 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-11-18 05:18:53,756 main DEBUG LoggerConfig$Builder(additivity="null", level="WARN", levelAndRefs="null", name="org.apache.hadoop.metrics2.impl.MetricsSinkAdapter", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-11-18 05:18:53,756 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-11-18 05:18:53,757 main DEBUG LoggerConfig$Builder(additivity="null", level="ERROR", levelAndRefs="null", name="org.apache.hadoop.metrics2.impl.MetricsSystemImpl", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-11-18 05:18:53,757 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-11-18 05:18:53,758 main DEBUG LoggerConfig$Builder(additivity="false", level="WARN", levelAndRefs="null", name="org.apache.directory", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-11-18 05:18:53,760 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-11-18 05:18:53,760 main DEBUG LoggerConfig$Builder(additivity="null", level="DEBUG", levelAndRefs="null", name="org.apache.hadoop.hbase.ipc.FailedServers", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-11-18 05:18:53,761 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-11-18 05:18:53,761 main DEBUG LoggerConfig$Builder(additivity="null", level="WARN", levelAndRefs="null", name="org.apache.hadoop.metrics2.impl.MetricsConfig", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-11-18 05:18:53,762 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-11-18 05:18:53,762 main DEBUG LoggerConfig$Builder(additivity="null", level="INFO", levelAndRefs="null", name="org.apache.hadoop.hbase.ScheduledChore", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-11-18 05:18:53,762 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-11-18 05:18:53,763 main DEBUG LoggerConfig$Builder(additivity="null", level="DEBUG", levelAndRefs="null", name="org.apache.hadoop.hbase.regionserver.RSRpcServices", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-11-18 05:18:53,763 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-11-18 05:18:53,764 main DEBUG LoggerConfig$Builder(additivity="null", level="WARN", levelAndRefs="null", name="org.apache.hadoop", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-11-18 05:18:53,764 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-11-18 05:18:53,765 main DEBUG LoggerConfig$Builder(additivity="null", level="DEBUG", levelAndRefs="null", name="org.apache.hadoop.hbase", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-11-18 05:18:53,766 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-11-18 05:18:53,767 main DEBUG LoggerConfig$Builder(additivity="null", level="DEBUG", levelAndRefs="null", name="org.apache.hbase.thirdparty.io.netty.channel", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-11-18 05:18:53,767 main DEBUG Building Plugin[name=root, class=org.apache.logging.log4j.core.config.LoggerConfig$RootLogger]. 2024-11-18 05:18:53,769 main DEBUG LoggerConfig$RootLogger$Builder(additivity="null", level="null", levelAndRefs="INFO,Console", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-11-18 05:18:53,771 main DEBUG Building Plugin[name=loggers, class=org.apache.logging.log4j.core.config.LoggersPlugin]. 2024-11-18 05:18:53,774 main DEBUG createLoggers(={org.apache.hadoop.metrics2.util.MBeans, org.apache.hadoop.hbase.logging.TestJul2Slf4j, org.apache.zookeeper, org.apache.hadoop.metrics2.impl.MetricsSinkAdapter, org.apache.hadoop.metrics2.impl.MetricsSystemImpl, org.apache.directory, org.apache.hadoop.hbase.ipc.FailedServers, org.apache.hadoop.metrics2.impl.MetricsConfig, org.apache.hadoop.hbase.ScheduledChore, org.apache.hadoop.hbase.regionserver.RSRpcServices, org.apache.hadoop, org.apache.hadoop.hbase, org.apache.hbase.thirdparty.io.netty.channel, root}) 2024-11-18 05:18:53,775 main DEBUG Building Plugin[name=layout, class=org.apache.logging.log4j.core.layout.PatternLayout]. 2024-11-18 05:18:53,776 main DEBUG PatternLayout$Builder(pattern="%d{ISO8601} %-5p [%t%notEmpty{ %X}] %C{2}(%L): %m%n", PatternSelector=null, Configuration(PropertiesConfig), Replace=null, charset="null", alwaysWriteExceptions="null", disableAnsi="null", noConsoleNoAnsi="null", header="null", footer="null") 2024-11-18 05:18:53,777 main DEBUG PluginManager 'Converter' found 47 plugins 2024-11-18 05:18:53,789 main DEBUG Building Plugin[name=appender, class=org.apache.hadoop.hbase.logging.HBaseTestAppender]. 2024-11-18 05:18:53,793 main DEBUG HBaseTestAppender$Builder(target="SYSTEM_ERR", maxSize="1G", bufferedIo="null", bufferSize="null", immediateFlush="null", ignoreExceptions="null", PatternLayout(%d{ISO8601} %-5p [%t%notEmpty{ %X}] %C{2}(%L): %m%n), name="Console", Configuration(PropertiesConfig), Filter=null, ={}) 2024-11-18 05:18:53,795 main DEBUG Starting HBaseTestOutputStreamManager SYSTEM_ERR 2024-11-18 05:18:53,796 main DEBUG Building Plugin[name=appenders, class=org.apache.logging.log4j.core.config.AppendersPlugin]. 2024-11-18 05:18:53,796 main DEBUG createAppenders(={Console}) 2024-11-18 05:18:53,797 main DEBUG Configuration org.apache.logging.log4j.core.config.properties.PropertiesConfiguration@302c971f initialized 2024-11-18 05:18:53,798 main DEBUG Starting configuration org.apache.logging.log4j.core.config.properties.PropertiesConfiguration@302c971f 2024-11-18 05:18:53,798 main DEBUG Started configuration org.apache.logging.log4j.core.config.properties.PropertiesConfiguration@302c971f OK. 2024-11-18 05:18:53,799 main DEBUG Shutting down OutputStreamManager SYSTEM_OUT.false.false-1 2024-11-18 05:18:53,799 main DEBUG OutputStream closed 2024-11-18 05:18:53,800 main DEBUG Shut down OutputStreamManager SYSTEM_OUT.false.false-1, all resources released: true 2024-11-18 05:18:53,800 main DEBUG Appender DefaultConsole-1 stopped with status true 2024-11-18 05:18:53,800 main DEBUG Stopped org.apache.logging.log4j.core.config.DefaultConfiguration@505fc5a4 OK 2024-11-18 05:18:53,927 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6 2024-11-18 05:18:53,931 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=StatusLogger 2024-11-18 05:18:53,933 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=ContextSelector 2024-11-18 05:18:53,934 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name= 2024-11-18 05:18:53,935 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.directory 2024-11-18 05:18:53,936 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.metrics2.impl.MetricsSinkAdapter 2024-11-18 05:18:53,936 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.zookeeper 2024-11-18 05:18:53,937 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.hbase.logging.TestJul2Slf4j 2024-11-18 05:18:53,937 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.metrics2.impl.MetricsSystemImpl 2024-11-18 05:18:53,938 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.metrics2.util.MBeans 2024-11-18 05:18:53,938 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.hbase 2024-11-18 05:18:53,941 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop 2024-11-18 05:18:53,942 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.hbase.ipc.FailedServers 2024-11-18 05:18:53,942 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.hbase.regionserver.RSRpcServices 2024-11-18 05:18:53,943 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.metrics2.impl.MetricsConfig 2024-11-18 05:18:53,943 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hbase.thirdparty.io.netty.channel 2024-11-18 05:18:53,944 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.hbase.ScheduledChore 2024-11-18 05:18:53,945 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Appenders,name=Console 2024-11-18 05:18:53,949 main DEBUG org.apache.logging.log4j.core.util.SystemClock supports precise timestamps. 2024-11-18 05:18:53,949 main DEBUG Reconfiguration complete for context[name=1dbd16a6] at URI jar:file:/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-logging/target/hbase-logging-2.7.0-SNAPSHOT-tests.jar!/log4j2.properties (org.apache.logging.log4j.core.LoggerContext@39de3d36) with optional ClassLoader: null 2024-11-18 05:18:53,949 main DEBUG Shutdown hook enabled. Registering a new one. 2024-11-18 05:18:53,952 main DEBUG LoggerContext[name=1dbd16a6, org.apache.logging.log4j.core.LoggerContext@39de3d36] started OK. 2024-11-18T05:18:54,305 DEBUG [main {}] hbase.HBaseTestingUtility(348): Setting hbase.rootdir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/e1a8447b-7280-f5aa-cebe-d7c1b39671e7 2024-11-18 05:18:54,309 main DEBUG AsyncLogger.ThreadNameStrategy=UNCACHED (user specified null, default is UNCACHED) 2024-11-18 05:18:54,310 main DEBUG org.apache.logging.log4j.core.util.SystemClock supports precise timestamps. 2024-11-18T05:18:54,349 INFO [main {}] hbase.HBaseClassTestRule(94): Test class org.apache.hadoop.hbase.client.TestAsyncReplicationAdminApi timeout: 26 mins 2024-11-18T05:18:54,386 INFO [Time-limited test {}] hbase.HBaseTestingUtility(1126): Starting up minicluster with option: StartMiniClusterOption{numMasters=1, masterClass=null, numRegionServers=1, rsPorts=, rsClass=null, numDataNodes=1, dataNodeHosts=null, numZkServers=1, createRootDir=false, createWALDir=false} 2024-11-18T05:18:54,390 INFO [Time-limited test {}] hbase.HBaseZKTestingUtility(82): Created new mini-cluster data directory: /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/e1a8447b-7280-f5aa-cebe-d7c1b39671e7/cluster_b7a7248c-30f6-7402-42f2-d4751190cb92, deleteOnExit=true 2024-11-18T05:18:54,390 INFO [Time-limited test {}] hbase.HBaseTestingUtility(1140): STARTING DFS 2024-11-18T05:18:54,391 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting test.cache.data to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/e1a8447b-7280-f5aa-cebe-d7c1b39671e7/test.cache.data in system properties and HBase conf 2024-11-18T05:18:54,392 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting hadoop.tmp.dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/e1a8447b-7280-f5aa-cebe-d7c1b39671e7/hadoop.tmp.dir in system properties and HBase conf 2024-11-18T05:18:54,393 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting hadoop.log.dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/e1a8447b-7280-f5aa-cebe-d7c1b39671e7/hadoop.log.dir in system properties and HBase conf 2024-11-18T05:18:54,393 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting mapreduce.cluster.local.dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/e1a8447b-7280-f5aa-cebe-d7c1b39671e7/mapreduce.cluster.local.dir in system properties and HBase conf 2024-11-18T05:18:54,394 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting mapreduce.cluster.temp.dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/e1a8447b-7280-f5aa-cebe-d7c1b39671e7/mapreduce.cluster.temp.dir in system properties and HBase conf 2024-11-18T05:18:54,395 INFO [Time-limited test {}] hbase.HBaseTestingUtility(811): read short circuit is OFF 2024-11-18T05:18:54,563 WARN [Time-limited test {}] util.NativeCodeLoader(60): Unable to load native-hadoop library for your platform... using builtin-java classes where applicable 2024-11-18T05:18:54,697 DEBUG [Time-limited test {}] fs.HFileSystem(310): The file system is not a DistributedFileSystem. Skipping on block location reordering 2024-11-18T05:18:54,702 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting yarn.node-labels.fs-store.root-dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/e1a8447b-7280-f5aa-cebe-d7c1b39671e7/yarn.node-labels.fs-store.root-dir in system properties and HBase conf 2024-11-18T05:18:54,703 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting yarn.node-attribute.fs-store.root-dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/e1a8447b-7280-f5aa-cebe-d7c1b39671e7/yarn.node-attribute.fs-store.root-dir in system properties and HBase conf 2024-11-18T05:18:54,704 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting yarn.nodemanager.log-dirs to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/e1a8447b-7280-f5aa-cebe-d7c1b39671e7/yarn.nodemanager.log-dirs in system properties and HBase conf 2024-11-18T05:18:54,706 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting yarn.nodemanager.remote-app-log-dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/e1a8447b-7280-f5aa-cebe-d7c1b39671e7/yarn.nodemanager.remote-app-log-dir in system properties and HBase conf 2024-11-18T05:18:54,706 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting yarn.timeline-service.entity-group-fs-store.active-dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/e1a8447b-7280-f5aa-cebe-d7c1b39671e7/yarn.timeline-service.entity-group-fs-store.active-dir in system properties and HBase conf 2024-11-18T05:18:54,707 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting yarn.timeline-service.entity-group-fs-store.done-dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/e1a8447b-7280-f5aa-cebe-d7c1b39671e7/yarn.timeline-service.entity-group-fs-store.done-dir in system properties and HBase conf 2024-11-18T05:18:54,708 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting yarn.nodemanager.remote-app-log-dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/e1a8447b-7280-f5aa-cebe-d7c1b39671e7/yarn.nodemanager.remote-app-log-dir in system properties and HBase conf 2024-11-18T05:18:54,708 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting dfs.journalnode.edits.dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/e1a8447b-7280-f5aa-cebe-d7c1b39671e7/dfs.journalnode.edits.dir in system properties and HBase conf 2024-11-18T05:18:54,709 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting dfs.datanode.shared.file.descriptor.paths to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/e1a8447b-7280-f5aa-cebe-d7c1b39671e7/dfs.datanode.shared.file.descriptor.paths in system properties and HBase conf 2024-11-18T05:18:54,710 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting nfs.dump.dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/e1a8447b-7280-f5aa-cebe-d7c1b39671e7/nfs.dump.dir in system properties and HBase conf 2024-11-18T05:18:54,710 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting java.io.tmpdir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/e1a8447b-7280-f5aa-cebe-d7c1b39671e7/java.io.tmpdir in system properties and HBase conf 2024-11-18T05:18:54,711 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting dfs.journalnode.edits.dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/e1a8447b-7280-f5aa-cebe-d7c1b39671e7/dfs.journalnode.edits.dir in system properties and HBase conf 2024-11-18T05:18:54,711 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting dfs.provided.aliasmap.inmemory.leveldb.dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/e1a8447b-7280-f5aa-cebe-d7c1b39671e7/dfs.provided.aliasmap.inmemory.leveldb.dir in system properties and HBase conf 2024-11-18T05:18:54,712 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting fs.s3a.committer.staging.tmp.path to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/e1a8447b-7280-f5aa-cebe-d7c1b39671e7/fs.s3a.committer.staging.tmp.path in system properties and HBase conf 2024-11-18T05:18:55,793 WARN [Time-limited test {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-namenode.properties,hadoop-metrics2.properties 2024-11-18T05:18:55,914 INFO [Time-limited test {}] log.Log(170): Logging initialized @3251ms to org.eclipse.jetty.util.log.Slf4jLog 2024-11-18T05:18:56,010 WARN [Time-limited test {}] server.AuthenticationFilter(240): Unable to initialize FileSignerSecretProvider, falling back to use random secrets. Reason: Could not read signature secret file: /home/jenkins/hadoop-http-auth-signature-secret 2024-11-18T05:18:56,117 INFO [Time-limited test {}] server.Server(375): jetty-9.4.53.v20231009; built: 2023-10-09T12:29:09.265Z; git: 27bde00a0b95a1d5bbee0eae7984f891d2d0f8c9; jvm 17.0.11+9 2024-11-18T05:18:56,183 INFO [Time-limited test {}] session.DefaultSessionIdManager(334): DefaultSessionIdManager workerName=node0 2024-11-18T05:18:56,184 INFO [Time-limited test {}] session.DefaultSessionIdManager(339): No SessionScavenger set, using defaults 2024-11-18T05:18:56,186 INFO [Time-limited test {}] session.HouseKeeper(132): node0 Scavenging every 600000ms 2024-11-18T05:18:56,214 WARN [Time-limited test {}] server.AuthenticationFilter(240): Unable to initialize FileSignerSecretProvider, falling back to use random secrets. Reason: Could not read signature secret file: /home/jenkins/hadoop-http-auth-signature-secret 2024-11-18T05:18:56,217 INFO [Time-limited test {}] handler.ContextHandler(921): Started o.e.j.s.ServletContextHandler@842d13f{logs,/logs,file:///home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/e1a8447b-7280-f5aa-cebe-d7c1b39671e7/hadoop.log.dir/,AVAILABLE} 2024-11-18T05:18:56,218 INFO [Time-limited test {}] handler.ContextHandler(921): Started o.e.j.s.ServletContextHandler@201ce359{static,/static,jar:file:/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/local-repository/org/apache/hadoop/hadoop-hdfs/3.4.1/hadoop-hdfs-3.4.1-tests.jar!/webapps/static,AVAILABLE} 2024-11-18T05:18:56,436 INFO [Time-limited test {}] handler.ContextHandler(921): Started o.e.j.w.WebAppContext@2490b214{hdfs,/,file:///home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/e1a8447b-7280-f5aa-cebe-d7c1b39671e7/java.io.tmpdir/jetty-localhost-38479-hadoop-hdfs-3_4_1-tests_jar-_-any-11512389107071374011/webapp/,AVAILABLE}{jar:file:/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/local-repository/org/apache/hadoop/hadoop-hdfs/3.4.1/hadoop-hdfs-3.4.1-tests.jar!/webapps/hdfs} 2024-11-18T05:18:56,446 INFO [Time-limited test {}] server.AbstractConnector(333): Started ServerConnector@1f7e2804{HTTP/1.1, (http/1.1)}{localhost:38479} 2024-11-18T05:18:56,447 INFO [Time-limited test {}] server.Server(415): Started @3785ms 2024-11-18T05:18:56,815 WARN [Time-limited test {}] server.AuthenticationFilter(240): Unable to initialize FileSignerSecretProvider, falling back to use random secrets. Reason: Could not read signature secret file: /home/jenkins/hadoop-http-auth-signature-secret 2024-11-18T05:18:56,821 INFO [Time-limited test {}] server.Server(375): jetty-9.4.53.v20231009; built: 2023-10-09T12:29:09.265Z; git: 27bde00a0b95a1d5bbee0eae7984f891d2d0f8c9; jvm 17.0.11+9 2024-11-18T05:18:56,822 INFO [Time-limited test {}] session.DefaultSessionIdManager(334): DefaultSessionIdManager workerName=node0 2024-11-18T05:18:56,822 INFO [Time-limited test {}] session.DefaultSessionIdManager(339): No SessionScavenger set, using defaults 2024-11-18T05:18:56,822 INFO [Time-limited test {}] session.HouseKeeper(132): node0 Scavenging every 660000ms 2024-11-18T05:18:56,823 INFO [Time-limited test {}] handler.ContextHandler(921): Started o.e.j.s.ServletContextHandler@5854846b{logs,/logs,file:///home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/e1a8447b-7280-f5aa-cebe-d7c1b39671e7/hadoop.log.dir/,AVAILABLE} 2024-11-18T05:18:56,824 INFO [Time-limited test {}] handler.ContextHandler(921): Started o.e.j.s.ServletContextHandler@1a2745b0{static,/static,jar:file:/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/local-repository/org/apache/hadoop/hadoop-hdfs/3.4.1/hadoop-hdfs-3.4.1-tests.jar!/webapps/static,AVAILABLE} 2024-11-18T05:18:56,945 INFO [Time-limited test {}] handler.ContextHandler(921): Started o.e.j.w.WebAppContext@7d75efc4{datanode,/,file:///home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/e1a8447b-7280-f5aa-cebe-d7c1b39671e7/java.io.tmpdir/jetty-localhost-35063-hadoop-hdfs-3_4_1-tests_jar-_-any-18351200718336839937/webapp/,AVAILABLE}{jar:file:/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/local-repository/org/apache/hadoop/hadoop-hdfs/3.4.1/hadoop-hdfs-3.4.1-tests.jar!/webapps/datanode} 2024-11-18T05:18:56,945 INFO [Time-limited test {}] server.AbstractConnector(333): Started ServerConnector@723ec49{HTTP/1.1, (http/1.1)}{localhost:35063} 2024-11-18T05:18:56,946 INFO [Time-limited test {}] server.Server(415): Started @4284ms 2024-11-18T05:18:57,002 WARN [Time-limited test {}] web.RestCsrfPreventionFilterHandler(75): Got null for restCsrfPreventionFilter - will not do any filtering. 2024-11-18T05:18:57,487 WARN [Thread-73 {}] impl.BlockPoolSlice(347): dfsUsed file missing in /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/e1a8447b-7280-f5aa-cebe-d7c1b39671e7/cluster_b7a7248c-30f6-7402-42f2-d4751190cb92/dfs/data/data2/current/BP-1100534618-172.17.0.2-1731907135498/current, will proceed with Du for space computation calculation, 2024-11-18T05:18:57,487 WARN [Thread-72 {}] impl.BlockPoolSlice(347): dfsUsed file missing in /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/e1a8447b-7280-f5aa-cebe-d7c1b39671e7/cluster_b7a7248c-30f6-7402-42f2-d4751190cb92/dfs/data/data1/current/BP-1100534618-172.17.0.2-1731907135498/current, will proceed with Du for space computation calculation, 2024-11-18T05:18:57,521 WARN [Thread-58 {}] datanode.DirectoryScanner(302): dfs.datanode.directoryscan.throttle.limit.ms.per.sec set to value above 1000 ms/sec. Assuming default value of -1 2024-11-18T05:18:57,572 INFO [Block report processor {}] blockmanagement.BlockManager(2940): BLOCK* processReport 0x7a16aa1df264a919 with lease ID 0xa0cc160ed7ef6226: Processing first storage report for DS-564787d6-4f9e-4ae8-8ae2-11502196172f from datanode DatanodeRegistration(127.0.0.1:38965, datanodeUuid=e1f73d61-a7b2-44a2-be83-c71cb05bbbbe, infoPort=45257, infoSecurePort=0, ipcPort=38907, storageInfo=lv=-57;cid=testClusterID;nsid=1144495474;c=1731907135498) 2024-11-18T05:18:57,573 INFO [Block report processor {}] blockmanagement.BlockManager(2972): BLOCK* processReport 0x7a16aa1df264a919 with lease ID 0xa0cc160ed7ef6226: from storage DS-564787d6-4f9e-4ae8-8ae2-11502196172f node DatanodeRegistration(127.0.0.1:38965, datanodeUuid=e1f73d61-a7b2-44a2-be83-c71cb05bbbbe, infoPort=45257, infoSecurePort=0, ipcPort=38907, storageInfo=lv=-57;cid=testClusterID;nsid=1144495474;c=1731907135498), blocks: 0, hasStaleStorage: true, processing time: 2 msecs, invalidatedBlocks: 0 2024-11-18T05:18:57,573 INFO [Block report processor {}] blockmanagement.BlockManager(2940): BLOCK* processReport 0x7a16aa1df264a919 with lease ID 0xa0cc160ed7ef6226: Processing first storage report for DS-261e564e-63de-4cab-b12a-7c239b32298b from datanode DatanodeRegistration(127.0.0.1:38965, datanodeUuid=e1f73d61-a7b2-44a2-be83-c71cb05bbbbe, infoPort=45257, infoSecurePort=0, ipcPort=38907, storageInfo=lv=-57;cid=testClusterID;nsid=1144495474;c=1731907135498) 2024-11-18T05:18:57,573 INFO [Block report processor {}] blockmanagement.BlockManager(2972): BLOCK* processReport 0x7a16aa1df264a919 with lease ID 0xa0cc160ed7ef6226: from storage DS-261e564e-63de-4cab-b12a-7c239b32298b node DatanodeRegistration(127.0.0.1:38965, datanodeUuid=e1f73d61-a7b2-44a2-be83-c71cb05bbbbe, infoPort=45257, infoSecurePort=0, ipcPort=38907, storageInfo=lv=-57;cid=testClusterID;nsid=1144495474;c=1731907135498), blocks: 0, hasStaleStorage: false, processing time: 0 msecs, invalidatedBlocks: 0 2024-11-18T05:18:57,662 DEBUG [Time-limited test {}] hbase.HBaseTestingUtility(703): Setting hbase.rootdir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/e1a8447b-7280-f5aa-cebe-d7c1b39671e7 2024-11-18T05:18:57,734 INFO [Time-limited test {}] zookeeper.MiniZooKeeperCluster(259): Started connectionTimeout=30000, dir=/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/e1a8447b-7280-f5aa-cebe-d7c1b39671e7/cluster_b7a7248c-30f6-7402-42f2-d4751190cb92/zookeeper_0, clientPort=61937, secureClientPort=-1, dataDir=/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/e1a8447b-7280-f5aa-cebe-d7c1b39671e7/cluster_b7a7248c-30f6-7402-42f2-d4751190cb92/zookeeper_0/version-2, dataDirSize=457 dataLogDir=/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/e1a8447b-7280-f5aa-cebe-d7c1b39671e7/cluster_b7a7248c-30f6-7402-42f2-d4751190cb92/zookeeper_0/version-2, dataLogSize=457 tickTime=2000, maxClientCnxns=300, minSessionTimeout=4000, maxSessionTimeout=40000, clientPortListenBacklog=-1, serverId=0 2024-11-18T05:18:57,743 INFO [Time-limited test {}] zookeeper.MiniZooKeeperCluster(284): Started MiniZooKeeperCluster and ran 'stat' on client port=61937 2024-11-18T05:18:57,753 INFO [Time-limited test {}] fs.HFileSystem(339): Added intercepting call to namenode#getBlockLocations so can do block reordering using class org.apache.hadoop.hbase.fs.HFileSystem$ReorderWALBlocks 2024-11-18T05:18:57,756 INFO [Time-limited test {}] fs.HFileSystem(339): Added intercepting call to namenode#getBlockLocations so can do block reordering using class org.apache.hadoop.hbase.fs.HFileSystem$ReorderWALBlocks 2024-11-18T05:18:57,972 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38965 is added to blk_1073741825_1001 (size=7) 2024-11-18T05:18:58,381 INFO [Time-limited test {}] util.FSUtils(490): Created version file at hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc with version=8 2024-11-18T05:18:58,381 INFO [Time-limited test {}] hbase.HBaseTestingUtility(1460): Setting hbase.fs.tmp.dir to hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/hbase-staging 2024-11-18T05:18:58,509 DEBUG [Time-limited test {}] channel.MultithreadEventLoopGroup(44): -Dio.netty.eventLoopThreads: 16 2024-11-18T05:18:58,777 INFO [Time-limited test {}] client.ConnectionUtils(129): master/7cf745f7364a:0 server-side Connection retries=6 2024-11-18T05:18:58,798 INFO [Time-limited test {}] ipc.RpcExecutor(188): Instantiated default.FPBQ.Fifo with queueClass=class java.util.concurrent.LinkedBlockingQueue; numCallQueues=1, maxQueueLength=30, handlerCount=3 2024-11-18T05:18:58,798 INFO [Time-limited test {}] ipc.RpcExecutor(188): Instantiated priority.RWQ.Fifo with queueClass=class java.util.concurrent.LinkedBlockingQueue; numCallQueues=2, maxQueueLength=30, handlerCount=3 2024-11-18T05:18:58,799 INFO [Time-limited test {}] ipc.RWQueueRpcExecutor(113): priority.RWQ.Fifo writeQueues=1 writeHandlers=1 readQueues=1 readHandlers=2 scanQueues=0 scanHandlers=0 2024-11-18T05:18:58,799 INFO [Time-limited test {}] ipc.RpcExecutor(188): Instantiated replication.FPBQ.Fifo with queueClass=class java.util.concurrent.LinkedBlockingQueue; numCallQueues=1, maxQueueLength=30, handlerCount=3 2024-11-18T05:18:58,799 INFO [Time-limited test {}] ipc.RpcExecutor(188): Instantiated metaPriority.FPBQ.Fifo with queueClass=class java.util.concurrent.LinkedBlockingQueue; numCallQueues=1, maxQueueLength=30, handlerCount=1 2024-11-18T05:18:58,956 INFO [Time-limited test {}] ipc.RpcServerFactory(64): Creating org.apache.hadoop.hbase.ipc.NettyRpcServer hosting hbase.pb.MasterService, hbase.pb.RegionServerStatusService, hbase.pb.LockService, hbase.pb.HbckService, hbase.pb.ClientMetaService, hbase.pb.ClientService, hbase.pb.AdminService, hbase.pb.ClientMetaService, hbase.pb.BootstrapNodeService 2024-11-18T05:18:59,014 INFO [Time-limited test {}] metrics.MetricRegistriesLoader(60): Loaded MetricRegistries class org.apache.hadoop.hbase.metrics.impl.MetricRegistriesImpl 2024-11-18T05:18:59,023 DEBUG [Time-limited test {}] util.ClassSize(228): Using Unsafe to estimate memory layout 2024-11-18T05:18:59,026 INFO [Time-limited test {}] ipc.NettyRpcServer(315): Using org.apache.hbase.thirdparty.io.netty.buffer.PooledByteBufAllocator for buffer allocation 2024-11-18T05:18:59,053 DEBUG [Time-limited test {}] channel.DefaultChannelId(84): -Dio.netty.processId: 20145 (auto-detected) 2024-11-18T05:18:59,054 DEBUG [Time-limited test {}] channel.DefaultChannelId(106): -Dio.netty.machineId: 02:42:ac:ff:fe:11:00:02 (auto-detected) 2024-11-18T05:18:59,072 INFO [Time-limited test {}] ipc.NettyRpcServer(197): Bind to /172.17.0.2:39359 2024-11-18T05:18:59,080 INFO [Time-limited test {}] fs.HFileSystem(339): Added intercepting call to namenode#getBlockLocations so can do block reordering using class org.apache.hadoop.hbase.fs.HFileSystem$ReorderWALBlocks 2024-11-18T05:18:59,082 INFO [Time-limited test {}] fs.HFileSystem(339): Added intercepting call to namenode#getBlockLocations so can do block reordering using class org.apache.hadoop.hbase.fs.HFileSystem$ReorderWALBlocks 2024-11-18T05:18:59,099 INFO [Time-limited test {}] zookeeper.RecoverableZooKeeper(138): Process identifier=master:39359 connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:18:59,131 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:393590x0, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:18:59,134 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): master:39359-0x1000911699b0000 connected 2024-11-18T05:18:59,167 DEBUG [Time-limited test {}] zookeeper.ZKUtil(113): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Set watcher on znode that does not yet exist, /hbase/master 2024-11-18T05:18:59,171 DEBUG [Time-limited test {}] zookeeper.ZKUtil(113): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Set watcher on znode that does not yet exist, /hbase/running 2024-11-18T05:18:59,174 DEBUG [Time-limited test {}] zookeeper.ZKUtil(113): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Set watcher on znode that does not yet exist, /hbase/acl 2024-11-18T05:18:59,178 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=3 with threadPrefix=default.FPBQ.Fifo, numCallQueues=1, port=39359 2024-11-18T05:18:59,180 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=1 with threadPrefix=priority.RWQ.Fifo.write, numCallQueues=1, port=39359 2024-11-18T05:18:59,180 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=3 with threadPrefix=priority.RWQ.Fifo.read, numCallQueues=1, port=39359 2024-11-18T05:18:59,183 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=3 with threadPrefix=replication.FPBQ.Fifo, numCallQueues=1, port=39359 2024-11-18T05:18:59,183 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=1 with threadPrefix=metaPriority.FPBQ.Fifo, numCallQueues=1, port=39359 2024-11-18T05:18:59,190 INFO [Time-limited test {}] master.HMaster(488): hbase.rootdir=hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc, hbase.cluster.distributed=false 2024-11-18T05:18:59,253 INFO [Time-limited test {}] client.ConnectionUtils(129): regionserver/7cf745f7364a:0 server-side Connection retries=6 2024-11-18T05:18:59,253 INFO [Time-limited test {}] ipc.RpcExecutor(188): Instantiated default.FPBQ.Fifo with queueClass=class java.util.concurrent.LinkedBlockingQueue; numCallQueues=1, maxQueueLength=30, handlerCount=3 2024-11-18T05:18:59,253 INFO [Time-limited test {}] ipc.RpcExecutor(188): Instantiated priority.RWQ.Fifo with queueClass=class java.util.concurrent.LinkedBlockingQueue; numCallQueues=2, maxQueueLength=30, handlerCount=3 2024-11-18T05:18:59,253 INFO [Time-limited test {}] ipc.RWQueueRpcExecutor(113): priority.RWQ.Fifo writeQueues=1 writeHandlers=1 readQueues=1 readHandlers=2 scanQueues=0 scanHandlers=0 2024-11-18T05:18:59,253 INFO [Time-limited test {}] ipc.RpcExecutor(188): Instantiated replication.FPBQ.Fifo with queueClass=class java.util.concurrent.LinkedBlockingQueue; numCallQueues=1, maxQueueLength=30, handlerCount=3 2024-11-18T05:18:59,254 INFO [Time-limited test {}] ipc.RpcExecutor(188): Instantiated metaPriority.FPBQ.Fifo with queueClass=class java.util.concurrent.LinkedBlockingQueue; numCallQueues=1, maxQueueLength=30, handlerCount=1 2024-11-18T05:18:59,256 INFO [Time-limited test {}] ipc.RpcServerFactory(64): Creating org.apache.hadoop.hbase.ipc.NettyRpcServer hosting hbase.pb.ClientService, hbase.pb.AdminService, hbase.pb.ClientMetaService, hbase.pb.BootstrapNodeService 2024-11-18T05:18:59,258 INFO [Time-limited test {}] ipc.NettyRpcServer(315): Using org.apache.hbase.thirdparty.io.netty.buffer.PooledByteBufAllocator for buffer allocation 2024-11-18T05:18:59,258 INFO [Time-limited test {}] ipc.NettyRpcServer(197): Bind to /172.17.0.2:32867 2024-11-18T05:18:59,260 INFO [Time-limited test {}] hfile.BlockCacheFactory(123): Allocating BlockCache size=880 MB, blockSize=64 KB 2024-11-18T05:18:59,265 DEBUG [Time-limited test {}] mob.MobFileCache(124): MobFileCache enabled with cacheSize=1000, evictPeriods=3600sec, evictRemainRatio=0.5 2024-11-18T05:18:59,266 INFO [Time-limited test {}] fs.HFileSystem(339): Added intercepting call to namenode#getBlockLocations so can do block reordering using class org.apache.hadoop.hbase.fs.HFileSystem$ReorderWALBlocks 2024-11-18T05:18:59,270 INFO [Time-limited test {}] fs.HFileSystem(339): Added intercepting call to namenode#getBlockLocations so can do block reordering using class org.apache.hadoop.hbase.fs.HFileSystem$ReorderWALBlocks 2024-11-18T05:18:59,275 INFO [Time-limited test {}] zookeeper.RecoverableZooKeeper(138): Process identifier=regionserver:32867 connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:18:59,279 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:328670x0, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:18:59,279 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): regionserver:32867-0x1000911699b0001 connected 2024-11-18T05:18:59,280 DEBUG [Time-limited test {}] zookeeper.ZKUtil(113): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Set watcher on znode that does not yet exist, /hbase/master 2024-11-18T05:18:59,282 DEBUG [Time-limited test {}] zookeeper.ZKUtil(113): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Set watcher on znode that does not yet exist, /hbase/running 2024-11-18T05:18:59,283 DEBUG [Time-limited test {}] zookeeper.ZKUtil(113): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Set watcher on znode that does not yet exist, /hbase/acl 2024-11-18T05:18:59,285 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=3 with threadPrefix=default.FPBQ.Fifo, numCallQueues=1, port=32867 2024-11-18T05:18:59,285 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=1 with threadPrefix=priority.RWQ.Fifo.write, numCallQueues=1, port=32867 2024-11-18T05:18:59,288 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=3 with threadPrefix=priority.RWQ.Fifo.read, numCallQueues=1, port=32867 2024-11-18T05:18:59,288 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=3 with threadPrefix=replication.FPBQ.Fifo, numCallQueues=1, port=32867 2024-11-18T05:18:59,289 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=1 with threadPrefix=metaPriority.FPBQ.Fifo, numCallQueues=1, port=32867 2024-11-18T05:18:59,291 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] master.HMaster(2445): Adding backup master ZNode /hbase/backup-masters/7cf745f7364a,39359,1731907138502 2024-11-18T05:18:59,297 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/backup-masters 2024-11-18T05:18:59,297 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/backup-masters 2024-11-18T05:18:59,299 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] zookeeper.ZKUtil(111): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Set watcher on existing znode=/hbase/backup-masters/7cf745f7364a,39359,1731907138502 2024-11-18T05:18:59,308 DEBUG [M:0;7cf745f7364a:39359 {}] regionserver.ShutdownHook(81): Installed shutdown hook thread: Shutdownhook:M:0;7cf745f7364a:39359 2024-11-18T05:18:59,321 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeCreated, state=SyncConnected, path=/hbase/master 2024-11-18T05:18:59,321 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeCreated, state=SyncConnected, path=/hbase/master 2024-11-18T05:18:59,321 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-11-18T05:18:59,321 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-11-18T05:18:59,322 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] zookeeper.ZKUtil(111): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Set watcher on existing znode=/hbase/master 2024-11-18T05:18:59,323 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKUtil(111): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Set watcher on existing znode=/hbase/master 2024-11-18T05:18:59,323 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] master.ActiveMasterManager(245): Deleting ZNode for /hbase/backup-masters/7cf745f7364a,39359,1731907138502 from backup master directory 2024-11-18T05:18:59,326 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/backup-masters/7cf745f7364a,39359,1731907138502 2024-11-18T05:18:59,326 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/backup-masters 2024-11-18T05:18:59,326 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/backup-masters 2024-11-18T05:18:59,327 WARN [master/7cf745f7364a:0:becomeActiveMaster {}] hbase.ZNodeClearer(69): Environment variable HBASE_ZNODE_FILE not set; znodes will not be cleared on crash by start scripts (Longer MTTR!) 2024-11-18T05:18:59,327 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] master.ActiveMasterManager(255): Registered as active master=7cf745f7364a,39359,1731907138502 2024-11-18T05:18:59,329 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] regionserver.ChunkCreator(488): Allocating data MemStoreChunkPool with chunk size 2 MB, max count 396, initial count 0 2024-11-18T05:18:59,330 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] regionserver.ChunkCreator(488): Allocating index MemStoreChunkPool with chunk size 204.80 KB, max count 440, initial count 0 2024-11-18T05:18:59,394 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38965 is added to blk_1073741826_1002 (size=42) 2024-11-18T05:18:59,798 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] util.FSUtils(639): Created cluster ID file at hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/hbase.id with ID: 447e98b2-1824-4bc5-9f42-421c6abc30fb 2024-11-18T05:18:59,837 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] fs.HFileSystem(339): Added intercepting call to namenode#getBlockLocations so can do block reordering using class org.apache.hadoop.hbase.fs.HFileSystem$ReorderWALBlocks 2024-11-18T05:18:59,863 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-11-18T05:18:59,863 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-11-18T05:18:59,876 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38965 is added to blk_1073741827_1003 (size=196) 2024-11-18T05:19:00,293 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] region.MasterRegion(372): Create or load local region for table 'master:store', {TABLE_ATTRIBUTES => {METADATA => {'hbase.store.file-tracker.impl' => 'DEFAULT'}}}, {NAME => 'info', INDEX_BLOCK_ENCODING => 'NONE', VERSIONS => '3', KEEP_DELETED_CELLS => 'FALSE', DATA_BLOCK_ENCODING => 'ROW_INDEX_V1', TTL => 'FOREVER', MIN_VERSIONS => '0', REPLICATION_SCOPE => '0', BLOOMFILTER => 'ROWCOL', IN_MEMORY => 'true', COMPRESSION => 'NONE', BLOCKCACHE => 'true', BLOCKSIZE => '8192 B (8KB)'}, {NAME => 'proc', INDEX_BLOCK_ENCODING => 'NONE', VERSIONS => '1', KEEP_DELETED_CELLS => 'FALSE', DATA_BLOCK_ENCODING => 'NONE', TTL => 'FOREVER', MIN_VERSIONS => '0', REPLICATION_SCOPE => '0', BLOOMFILTER => 'ROW', IN_MEMORY => 'false', COMPRESSION => 'NONE', BLOCKCACHE => 'true', BLOCKSIZE => '65536 B (64KB)'}, {NAME => 'rs', INDEX_BLOCK_ENCODING => 'NONE', VERSIONS => '1', KEEP_DELETED_CELLS => 'FALSE', DATA_BLOCK_ENCODING => 'NONE', TTL => 'FOREVER', MIN_VERSIONS => '0', REPLICATION_SCOPE => '0', BLOOMFILTER => 'ROW', IN_MEMORY => 'false', COMPRESSION => 'NONE', BLOCKCACHE => 'true', BLOCKSIZE => '65536 B (64KB)'}, {NAME => 'state', INDEX_BLOCK_ENCODING => 'NONE', VERSIONS => '1', KEEP_DELETED_CELLS => 'FALSE', DATA_BLOCK_ENCODING => 'NONE', TTL => 'FOREVER', MIN_VERSIONS => '0', REPLICATION_SCOPE => '0', BLOOMFILTER => 'ROW', IN_MEMORY => 'false', COMPRESSION => 'NONE', BLOCKCACHE => 'true', BLOCKSIZE => '65536 B (64KB)'} 2024-11-18T05:19:00,296 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] region.MasterRegionFlusherAndCompactor(132): Injected flushSize=134217728, flushPerChanges=1000000, flushIntervalMs=900000 2024-11-18T05:19:00,313 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] asyncfs.FanOutOneBlockAsyncDFSOutputSaslHelper(244): No decryptEncryptedDataEncryptionKey method in DFSClient, should be hadoop version with HDFS-12396 java.lang.NoSuchMethodException: org.apache.hadoop.hdfs.DFSClient.decryptEncryptedDataEncryptionKey(org.apache.hadoop.fs.FileEncryptionInfo) at java.lang.Class.getDeclaredMethod(Class.java:2675) ~[?:?] at org.apache.hadoop.hbase.io.asyncfs.FanOutOneBlockAsyncDFSOutputSaslHelper.createTransparentCryptoHelperWithoutHDFS12396(FanOutOneBlockAsyncDFSOutputSaslHelper.java:183) ~[hbase-asyncfs-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.io.asyncfs.FanOutOneBlockAsyncDFSOutputSaslHelper.createTransparentCryptoHelper(FanOutOneBlockAsyncDFSOutputSaslHelper.java:242) ~[hbase-asyncfs-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.io.asyncfs.FanOutOneBlockAsyncDFSOutputSaslHelper.(FanOutOneBlockAsyncDFSOutputSaslHelper.java:253) ~[hbase-asyncfs-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at java.lang.Class.forName0(Native Method) ~[?:?] at java.lang.Class.forName(Class.java:375) ~[?:?] at org.apache.hadoop.hbase.wal.AsyncFSWALProvider.load(AsyncFSWALProvider.java:147) ~[classes/:?] at org.apache.hadoop.hbase.wal.WALFactory.getProviderClass(WALFactory.java:160) ~[classes/:?] at org.apache.hadoop.hbase.wal.WALFactory.getProvider(WALFactory.java:200) ~[classes/:?] at org.apache.hadoop.hbase.wal.WALFactory.(WALFactory.java:232) ~[classes/:?] at org.apache.hadoop.hbase.wal.WALFactory.(WALFactory.java:207) ~[classes/:?] at org.apache.hadoop.hbase.master.region.MasterRegion.create(MasterRegion.java:402) ~[classes/:?] at org.apache.hadoop.hbase.master.region.MasterRegionFactory.create(MasterRegionFactory.java:135) ~[classes/:?] at org.apache.hadoop.hbase.master.HMaster.finishActiveMasterInitialization(HMaster.java:973) ~[classes/:?] at org.apache.hadoop.hbase.master.HMaster.startActiveMasterManager(HMaster.java:2470) ~[classes/:?] at org.apache.hadoop.hbase.master.HMaster.lambda$run$0(HMaster.java:590) ~[classes/:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:187) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:177) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.HMaster.lambda$run$1(HMaster.java:587) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:00,317 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] wal.WALFactory(183): Instantiating WALProvider of type class org.apache.hadoop.hbase.wal.AsyncFSWALProvider 2024-11-18T05:19:00,346 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38965 is added to blk_1073741828_1004 (size=1189) 2024-11-18T05:19:00,765 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] regionserver.HRegion(7124): Creating {ENCODED => 1595e783b53d99cd5eef43b6debb2682, NAME => 'master:store,,1.1595e783b53d99cd5eef43b6debb2682.', STARTKEY => '', ENDKEY => ''}, tableDescriptor='master:store', {TABLE_ATTRIBUTES => {METADATA => {'hbase.store.file-tracker.impl' => 'DEFAULT'}}}, {NAME => 'info', INDEX_BLOCK_ENCODING => 'NONE', VERSIONS => '3', KEEP_DELETED_CELLS => 'FALSE', DATA_BLOCK_ENCODING => 'ROW_INDEX_V1', TTL => 'FOREVER', MIN_VERSIONS => '0', REPLICATION_SCOPE => '0', BLOOMFILTER => 'ROWCOL', IN_MEMORY => 'true', COMPRESSION => 'NONE', BLOCKCACHE => 'true', BLOCKSIZE => '8192 B (8KB)'}, {NAME => 'proc', INDEX_BLOCK_ENCODING => 'NONE', VERSIONS => '1', KEEP_DELETED_CELLS => 'FALSE', DATA_BLOCK_ENCODING => 'NONE', TTL => 'FOREVER', MIN_VERSIONS => '0', REPLICATION_SCOPE => '0', BLOOMFILTER => 'ROW', IN_MEMORY => 'false', COMPRESSION => 'NONE', BLOCKCACHE => 'true', BLOCKSIZE => '65536 B (64KB)'}, {NAME => 'rs', INDEX_BLOCK_ENCODING => 'NONE', VERSIONS => '1', KEEP_DELETED_CELLS => 'FALSE', DATA_BLOCK_ENCODING => 'NONE', TTL => 'FOREVER', MIN_VERSIONS => '0', REPLICATION_SCOPE => '0', BLOOMFILTER => 'ROW', IN_MEMORY => 'false', COMPRESSION => 'NONE', BLOCKCACHE => 'true', BLOCKSIZE => '65536 B (64KB)'}, {NAME => 'state', INDEX_BLOCK_ENCODING => 'NONE', VERSIONS => '1', KEEP_DELETED_CELLS => 'FALSE', DATA_BLOCK_ENCODING => 'NONE', TTL => 'FOREVER', MIN_VERSIONS => '0', REPLICATION_SCOPE => '0', BLOOMFILTER => 'ROW', IN_MEMORY => 'false', COMPRESSION => 'NONE', BLOCKCACHE => 'true', BLOCKSIZE => '65536 B (64KB)'}, under table dir hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/MasterData/data/master/store 2024-11-18T05:19:00,779 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38965 is added to blk_1073741829_1005 (size=34) 2024-11-18T05:19:01,186 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] throttle.StoreHotnessProtector(112): StoreHotnessProtector is disabled. Set hbase.region.store.parallel.put.limit > 0 to enable, which may help mitigate load under heavy write pressure. 2024-11-18T05:19:01,186 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] regionserver.HRegion(894): Instantiated master:store,,1.1595e783b53d99cd5eef43b6debb2682.; StoreHotnessProtector, parallelPutToStoreThreadLimit=0 ; minColumnNum=100 ; preparePutThreadLimit=0 ; hotProtect now disable 2024-11-18T05:19:01,187 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] regionserver.HRegion(1681): Closing 1595e783b53d99cd5eef43b6debb2682, disabling compactions & flushes 2024-11-18T05:19:01,187 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] regionserver.HRegion(1703): Closing region master:store,,1.1595e783b53d99cd5eef43b6debb2682. 2024-11-18T05:19:01,187 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] regionserver.HRegion(1724): Waiting without time limit for close lock on master:store,,1.1595e783b53d99cd5eef43b6debb2682. 2024-11-18T05:19:01,187 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] regionserver.HRegion(1791): Acquired close lock on master:store,,1.1595e783b53d99cd5eef43b6debb2682. after waiting 0 ms 2024-11-18T05:19:01,188 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] regionserver.HRegion(1801): Updates disabled for region master:store,,1.1595e783b53d99cd5eef43b6debb2682. 2024-11-18T05:19:01,188 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] regionserver.HRegion(1922): Closed master:store,,1.1595e783b53d99cd5eef43b6debb2682. 2024-11-18T05:19:01,188 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] regionserver.HRegion(1635): Region close journal for 1595e783b53d99cd5eef43b6debb2682: 2024-11-18T05:19:01,190 WARN [master/7cf745f7364a:0:becomeActiveMaster {}] region.MasterRegion(249): failed to clean up initializing flag: hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/MasterData/data/master/store/.initializing 2024-11-18T05:19:01,190 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] region.MasterRegion(219): WALDir=hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/MasterData/WALs/7cf745f7364a,39359,1731907138502 2024-11-18T05:19:01,197 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] monitor.StreamSlowMonitor(122): New stream slow monitor defaultMonitorName 2024-11-18T05:19:01,208 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] wal.AbstractFSWAL(500): WAL configuration: blocksize=256 MB, rollsize=128 MB, prefix=7cf745f7364a%2C39359%2C1731907138502, suffix=, logDir=hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/MasterData/WALs/7cf745f7364a,39359,1731907138502, archiveDir=hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/MasterData/oldWALs, maxLogs=10 2024-11-18T05:19:01,233 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] asyncfs.FanOutOneBlockAsyncDFSOutputHelper(617): When create output stream for /user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/MasterData/WALs/7cf745f7364a,39359,1731907138502/7cf745f7364a%2C39359%2C1731907138502.1731907141214, exclude list is [], retry=0 2024-11-18T05:19:01,252 DEBUG [RS-EventLoopGroup-3-2 {}] asyncfs.FanOutOneBlockAsyncDFSOutputSaslHelper(816): SASL client skipping handshake in unsecured configuration for addr = 127.0.0.1/127.0.0.1, datanodeId = DatanodeInfoWithStorage[127.0.0.1:38965,DS-564787d6-4f9e-4ae8-8ae2-11502196172f,DISK] 2024-11-18T05:19:01,256 DEBUG [RS-EventLoopGroup-3-2 {}] asyncfs.ProtobufDecoder(117): Hadoop 3.3 and above shades protobuf. 2024-11-18T05:19:01,298 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] wal.AbstractFSWAL(841): New WAL /user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/MasterData/WALs/7cf745f7364a,39359,1731907138502/7cf745f7364a%2C39359%2C1731907138502.1731907141214 2024-11-18T05:19:01,298 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] wal.AbstractFSWAL(925): Create new AsyncFSWAL writer with pipeline: [(127.0.0.1/127.0.0.1:45257:45257)] 2024-11-18T05:19:01,299 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] regionserver.HRegion(7285): Opening region: {ENCODED => 1595e783b53d99cd5eef43b6debb2682, NAME => 'master:store,,1.1595e783b53d99cd5eef43b6debb2682.', STARTKEY => '', ENDKEY => ''} 2024-11-18T05:19:01,300 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] regionserver.HRegion(894): Instantiated master:store,,1.1595e783b53d99cd5eef43b6debb2682.; StoreHotnessProtector, parallelPutToStoreThreadLimit=0 ; minColumnNum=100 ; preparePutThreadLimit=0 ; hotProtect now disable 2024-11-18T05:19:01,304 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] regionserver.HRegion(7327): checking encryption for 1595e783b53d99cd5eef43b6debb2682 2024-11-18T05:19:01,305 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] regionserver.HRegion(7330): checking classloading for 1595e783b53d99cd5eef43b6debb2682 2024-11-18T05:19:01,349 INFO [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] regionserver.HStore(400): Created cacheConfig: cacheDataOnRead=true, cacheDataOnWrite=false, cacheIndexesOnWrite=false, cacheBloomsOnWrite=false, cacheEvictOnClose=false, cacheDataCompressed=false, prefetchOnOpen=false, for column family info of region 1595e783b53d99cd5eef43b6debb2682 2024-11-18T05:19:01,380 INFO [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] compactions.CompactionConfiguration(181): size [minCompactSize:128 MB, maxCompactSize:8.00 EB, offPeakMaxCompactSize:8.00 EB); files [minFilesToCompact:3, maxFilesToCompact:10); ratio 1.200000; off-peak ratio 5.000000; throttle point 2684354560; major period 604800000, major jitter 0.500000, min locality to compact 0.000000; tiered compaction: max_age 9223372036854775807, incoming window min 6, compaction policy for tiered window org.apache.hadoop.hbase.regionserver.compactions.ExploringCompactionPolicy, single output for minor true, compaction window factory org.apache.hadoop.hbase.regionserver.compactions.ExponentialCompactionWindowFactory, region 1595e783b53d99cd5eef43b6debb2682 columnFamilyName info 2024-11-18T05:19:01,385 DEBUG [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-11-18T05:19:01,387 INFO [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] regionserver.HStore(327): Store=1595e783b53d99cd5eef43b6debb2682/info, memstore type=DefaultMemStore, storagePolicy=NONE, verifyBulkLoads=false, parallelPutCountPrintThreshold=50, encoding=ROW_INDEX_V1, compression=NONE 2024-11-18T05:19:01,388 INFO [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] regionserver.HStore(400): Created cacheConfig: cacheDataOnRead=true, cacheDataOnWrite=false, cacheIndexesOnWrite=false, cacheBloomsOnWrite=false, cacheEvictOnClose=false, cacheDataCompressed=false, prefetchOnOpen=false, for column family proc of region 1595e783b53d99cd5eef43b6debb2682 2024-11-18T05:19:01,391 INFO [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] compactions.CompactionConfiguration(181): size [minCompactSize:128 MB, maxCompactSize:8.00 EB, offPeakMaxCompactSize:8.00 EB); files [minFilesToCompact:3, maxFilesToCompact:10); ratio 1.200000; off-peak ratio 5.000000; throttle point 2684354560; major period 604800000, major jitter 0.500000, min locality to compact 0.000000; tiered compaction: max_age 9223372036854775807, incoming window min 6, compaction policy for tiered window org.apache.hadoop.hbase.regionserver.compactions.ExploringCompactionPolicy, single output for minor true, compaction window factory org.apache.hadoop.hbase.regionserver.compactions.ExponentialCompactionWindowFactory, region 1595e783b53d99cd5eef43b6debb2682 columnFamilyName proc 2024-11-18T05:19:01,392 DEBUG [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-11-18T05:19:01,393 INFO [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] regionserver.HStore(327): Store=1595e783b53d99cd5eef43b6debb2682/proc, memstore type=DefaultMemStore, storagePolicy=NONE, verifyBulkLoads=false, parallelPutCountPrintThreshold=50, encoding=NONE, compression=NONE 2024-11-18T05:19:01,393 INFO [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] regionserver.HStore(400): Created cacheConfig: cacheDataOnRead=true, cacheDataOnWrite=false, cacheIndexesOnWrite=false, cacheBloomsOnWrite=false, cacheEvictOnClose=false, cacheDataCompressed=false, prefetchOnOpen=false, for column family rs of region 1595e783b53d99cd5eef43b6debb2682 2024-11-18T05:19:01,395 INFO [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] compactions.CompactionConfiguration(181): size [minCompactSize:128 MB, maxCompactSize:8.00 EB, offPeakMaxCompactSize:8.00 EB); files [minFilesToCompact:3, maxFilesToCompact:10); ratio 1.200000; off-peak ratio 5.000000; throttle point 2684354560; major period 604800000, major jitter 0.500000, min locality to compact 0.000000; tiered compaction: max_age 9223372036854775807, incoming window min 6, compaction policy for tiered window org.apache.hadoop.hbase.regionserver.compactions.ExploringCompactionPolicy, single output for minor true, compaction window factory org.apache.hadoop.hbase.regionserver.compactions.ExponentialCompactionWindowFactory, region 1595e783b53d99cd5eef43b6debb2682 columnFamilyName rs 2024-11-18T05:19:01,396 DEBUG [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-11-18T05:19:01,397 INFO [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] regionserver.HStore(327): Store=1595e783b53d99cd5eef43b6debb2682/rs, memstore type=DefaultMemStore, storagePolicy=NONE, verifyBulkLoads=false, parallelPutCountPrintThreshold=50, encoding=NONE, compression=NONE 2024-11-18T05:19:01,397 INFO [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] regionserver.HStore(400): Created cacheConfig: cacheDataOnRead=true, cacheDataOnWrite=false, cacheIndexesOnWrite=false, cacheBloomsOnWrite=false, cacheEvictOnClose=false, cacheDataCompressed=false, prefetchOnOpen=false, for column family state of region 1595e783b53d99cd5eef43b6debb2682 2024-11-18T05:19:01,400 INFO [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] compactions.CompactionConfiguration(181): size [minCompactSize:128 MB, maxCompactSize:8.00 EB, offPeakMaxCompactSize:8.00 EB); files [minFilesToCompact:3, maxFilesToCompact:10); ratio 1.200000; off-peak ratio 5.000000; throttle point 2684354560; major period 604800000, major jitter 0.500000, min locality to compact 0.000000; tiered compaction: max_age 9223372036854775807, incoming window min 6, compaction policy for tiered window org.apache.hadoop.hbase.regionserver.compactions.ExploringCompactionPolicy, single output for minor true, compaction window factory org.apache.hadoop.hbase.regionserver.compactions.ExponentialCompactionWindowFactory, region 1595e783b53d99cd5eef43b6debb2682 columnFamilyName state 2024-11-18T05:19:01,400 DEBUG [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-11-18T05:19:01,401 INFO [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] regionserver.HStore(327): Store=1595e783b53d99cd5eef43b6debb2682/state, memstore type=DefaultMemStore, storagePolicy=NONE, verifyBulkLoads=false, parallelPutCountPrintThreshold=50, encoding=NONE, compression=NONE 2024-11-18T05:19:01,404 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] regionserver.HRegion(5301): Found 0 recovered edits file(s) under hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682 2024-11-18T05:19:01,405 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] regionserver.HRegion(5301): Found 0 recovered edits file(s) under hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682 2024-11-18T05:19:01,413 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] regionserver.FlushLargeStoresPolicy(65): No hbase.hregion.percolumnfamilyflush.size.lower.bound set in table master:store descriptor;using region.getMemStoreFlushHeapSize/# of families (32.0 M)) instead. 2024-11-18T05:19:01,417 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] regionserver.HRegion(1085): writing seq id for 1595e783b53d99cd5eef43b6debb2682 2024-11-18T05:19:01,422 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] wal.WALSplitUtil(409): Wrote file=hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/recovered.edits/1.seqid, newMaxSeqId=1, maxSeqId=-1 2024-11-18T05:19:01,422 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] regionserver.HRegion(1102): Opened 1595e783b53d99cd5eef43b6debb2682; next sequenceid=2; SteppingSplitPolicysuper{IncreasingToUpperBoundRegionSplitPolicy{initialSize=268435456, ConstantSizeRegionSplitPolicy{desiredMaxFileSize=66600387, jitterRate=-0.007576897740364075}}}, FlushLargeStoresPolicy{flushSizeLowerBound=33554432} 2024-11-18T05:19:01,427 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] regionserver.HRegion(1001): Region open journal for 1595e783b53d99cd5eef43b6debb2682: 2024-11-18T05:19:01,428 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] region.MasterRegionFlusherAndCompactor(122): Constructor flushSize=134217728, flushPerChanges=1000000, flushIntervalMs=900000, compactMin=4 2024-11-18T05:19:01,456 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodec@6be08398, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-11-18T05:19:01,490 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] master.HMaster(882): No meta location available on zookeeper, skip migrating... 2024-11-18T05:19:01,502 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] region.RegionProcedureStore(104): Starting the Region Procedure Store, number threads=5 2024-11-18T05:19:01,502 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] procedure2.ProcedureExecutor(633): Starting 5 core workers (bigger of cpus/4 or 16) with max (burst) worker count=50 2024-11-18T05:19:01,505 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] region.RegionProcedureStore(255): Starting Region Procedure Store lease recovery... 2024-11-18T05:19:01,506 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] procedure2.ProcedureExecutor(653): Recovered RegionProcedureStore lease in 1 msec 2024-11-18T05:19:01,512 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] procedure2.ProcedureExecutor(667): Loaded RegionProcedureStore in 5 msec 2024-11-18T05:19:01,512 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] procedure2.RemoteProcedureDispatcher(96): Instantiated, coreThreads=3 (allowCoreThreadTimeOut=true), queueMaxSize=32, operationDelay=150 2024-11-18T05:19:01,536 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] master.RegionServerTracker(127): Upgrading RegionServerTracker to active master mode; 0 have existingServerCrashProcedures, 0 possibly 'live' servers, and 0 'splitting'. 2024-11-18T05:19:01,548 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] zookeeper.ZKUtil(444): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Unable to get data of znode /hbase/balancer because node does not exist (not necessarily an error) 2024-11-18T05:19:01,551 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] zookeeper.RecoverableZooKeeper(215): Node /hbase/balancer already deleted, retry=false 2024-11-18T05:19:01,553 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] normalizer.SimpleRegionNormalizer(163): Updated configuration for key 'hbase.normalizer.merge.min_region_size.mb' from 0 to 1 2024-11-18T05:19:01,554 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] zookeeper.ZKUtil(444): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Unable to get data of znode /hbase/normalizer because node does not exist (not necessarily an error) 2024-11-18T05:19:01,556 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] zookeeper.RecoverableZooKeeper(215): Node /hbase/normalizer already deleted, retry=false 2024-11-18T05:19:01,558 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] normalizer.RegionNormalizerWorker(137): Normalizer rate limit set to unlimited 2024-11-18T05:19:01,561 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] zookeeper.ZKUtil(444): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Unable to get data of znode /hbase/switch/split because node does not exist (not necessarily an error) 2024-11-18T05:19:01,562 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] zookeeper.RecoverableZooKeeper(215): Node /hbase/switch/split already deleted, retry=false 2024-11-18T05:19:01,563 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] zookeeper.ZKUtil(444): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Unable to get data of znode /hbase/switch/merge because node does not exist (not necessarily an error) 2024-11-18T05:19:01,565 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] zookeeper.RecoverableZooKeeper(215): Node /hbase/switch/merge already deleted, retry=false 2024-11-18T05:19:01,574 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] zookeeper.ZKUtil(444): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Unable to get data of znode /hbase/snapshot-cleanup because node does not exist (not necessarily an error) 2024-11-18T05:19:01,575 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] zookeeper.RecoverableZooKeeper(215): Node /hbase/snapshot-cleanup already deleted, retry=false 2024-11-18T05:19:01,580 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeCreated, state=SyncConnected, path=/hbase/running 2024-11-18T05:19:01,580 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeCreated, state=SyncConnected, path=/hbase/running 2024-11-18T05:19:01,580 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-11-18T05:19:01,580 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-11-18T05:19:01,581 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] master.HMaster(826): Active/primary master=7cf745f7364a,39359,1731907138502, sessionid=0x1000911699b0000, setting cluster-up flag (Was=false) 2024-11-18T05:19:01,593 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-11-18T05:19:01,593 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-11-18T05:19:01,598 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] procedure.ZKProcedureUtil(251): Clearing all znodes /hbase/flush-table-proc/acquired, /hbase/flush-table-proc/reached, /hbase/flush-table-proc/abort 2024-11-18T05:19:01,599 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] procedure.ZKProcedureCoordinator(245): Starting controller for procedure member=7cf745f7364a,39359,1731907138502 2024-11-18T05:19:01,604 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-11-18T05:19:01,604 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-11-18T05:19:01,609 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] procedure.ZKProcedureUtil(251): Clearing all znodes /hbase/online-snapshot/acquired, /hbase/online-snapshot/reached, /hbase/online-snapshot/abort 2024-11-18T05:19:01,611 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] procedure.ZKProcedureCoordinator(245): Starting controller for procedure member=7cf745f7364a,39359,1731907138502 2024-11-18T05:19:01,696 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] procedure2.ProcedureExecutor(1098): Stored pid=1, state=RUNNABLE:INIT_META_WRITE_FS_LAYOUT; InitMetaProcedure table=hbase:meta 2024-11-18T05:19:01,702 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] balancer.BaseLoadBalancer(575): slop=0.2 2024-11-18T05:19:01,705 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] balancer.StochasticLoadBalancer(294): Loaded config; maxSteps=1000000, runMaxSteps=false, stepsPerRegion=800, maxRunningTime=30000, isByTable=false, CostFunctions=[RegionCountSkewCostFunction, PrimaryRegionCountSkewCostFunction, MoveCostFunction, ServerLocalityCostFunction, RackLocalityCostFunction, TableSkewCostFunction, RegionReplicaHostCostFunction, RegionReplicaRackCostFunction, ReadRequestCostFunction, WriteRequestCostFunction, MemStoreSizeCostFunction, StoreFileCostFunction] , sum of multiplier of cost functions = 0.0 etc. 2024-11-18T05:19:01,705 DEBUG [RS:0;7cf745f7364a:32867 {}] regionserver.ShutdownHook(81): Installed shutdown hook thread: Shutdownhook:RS:0;7cf745f7364a:32867 2024-11-18T05:19:01,706 INFO [RS:0;7cf745f7364a:32867 {}] regionserver.HRegionServer(1008): ClusterId : 447e98b2-1824-4bc5-9f42-421c6abc30fb 2024-11-18T05:19:01,709 DEBUG [RS:0;7cf745f7364a:32867 {}] procedure.RegionServerProcedureManagerHost(43): Procedure flush-table-proc initializing 2024-11-18T05:19:01,711 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] balancer.RegionLocationFinder(146): Skipping locality-based refresh due to oldStatus=null, newStatus=Master: 7cf745f7364a,39359,1731907138502 Number of backup masters: 0 Number of live region servers: 0 Number of dead region servers: 0 Number of unknown region servers: 0 Average load: 0.0 Number of requests: 0 Number of regions: 0 Number of regions in transition: 0 2024-11-18T05:19:01,714 DEBUG [RS:0;7cf745f7364a:32867 {}] procedure.RegionServerProcedureManagerHost(45): Procedure flush-table-proc initialized 2024-11-18T05:19:01,714 DEBUG [RS:0;7cf745f7364a:32867 {}] procedure.RegionServerProcedureManagerHost(43): Procedure online-snapshot initializing 2024-11-18T05:19:01,714 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] executor.ExecutorService(95): Starting executor service name=MASTER_OPEN_REGION-master/7cf745f7364a:0, corePoolSize=5, maxPoolSize=5 2024-11-18T05:19:01,715 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] executor.ExecutorService(95): Starting executor service name=MASTER_CLOSE_REGION-master/7cf745f7364a:0, corePoolSize=5, maxPoolSize=5 2024-11-18T05:19:01,715 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] executor.ExecutorService(95): Starting executor service name=MASTER_SERVER_OPERATIONS-master/7cf745f7364a:0, corePoolSize=5, maxPoolSize=5 2024-11-18T05:19:01,715 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] executor.ExecutorService(95): Starting executor service name=MASTER_META_SERVER_OPERATIONS-master/7cf745f7364a:0, corePoolSize=5, maxPoolSize=5 2024-11-18T05:19:01,715 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] executor.ExecutorService(95): Starting executor service name=M_LOG_REPLAY_OPS-master/7cf745f7364a:0, corePoolSize=10, maxPoolSize=10 2024-11-18T05:19:01,715 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] executor.ExecutorService(95): Starting executor service name=MASTER_SNAPSHOT_OPERATIONS-master/7cf745f7364a:0, corePoolSize=1, maxPoolSize=1 2024-11-18T05:19:01,715 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] executor.ExecutorService(95): Starting executor service name=MASTER_MERGE_OPERATIONS-master/7cf745f7364a:0, corePoolSize=2, maxPoolSize=2 2024-11-18T05:19:01,716 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] executor.ExecutorService(95): Starting executor service name=MASTER_TABLE_OPERATIONS-master/7cf745f7364a:0, corePoolSize=1, maxPoolSize=1 2024-11-18T05:19:01,717 DEBUG [RS:0;7cf745f7364a:32867 {}] procedure.RegionServerProcedureManagerHost(45): Procedure online-snapshot initialized 2024-11-18T05:19:01,717 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] procedure2.TimeoutExecutorThread(81): ADDED pid=-1, state=WAITING_TIMEOUT; org.apache.hadoop.hbase.procedure2.CompletedProcedureCleaner; timeout=30000, timestamp=1731907171717 2024-11-18T05:19:01,717 DEBUG [RS:0;7cf745f7364a:32867 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodec@1d2056ae, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-11-18T05:19:01,718 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] cleaner.DirScanPool(74): log_cleaner Cleaner pool size is 1 2024-11-18T05:19:01,719 DEBUG [RS:0;7cf745f7364a:32867 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodec@416e45f1, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=7cf745f7364a/172.17.0.2:0 2024-11-18T05:19:01,719 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] cleaner.CleanerChore(192): Initialize cleaner=org.apache.hadoop.hbase.master.cleaner.TimeToLiveLogCleaner 2024-11-18T05:19:01,721 DEBUG [PEWorker-1 {}] procedure.InitMetaProcedure(96): Execute pid=1, state=RUNNABLE:INIT_META_WRITE_FS_LAYOUT, locked=true; InitMetaProcedure table=hbase:meta 2024-11-18T05:19:01,722 INFO [PEWorker-1 {}] procedure.InitMetaProcedure(75): BOOTSTRAP: creating hbase:meta region 2024-11-18T05:19:01,723 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] cleaner.CleanerChore(192): Initialize cleaner=org.apache.hadoop.hbase.replication.master.ReplicationLogCleaner 2024-11-18T05:19:01,723 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] cleaner.CleanerChore(192): Initialize cleaner=org.apache.hadoop.hbase.master.cleaner.TimeToLiveMasterLocalStoreWALCleaner 2024-11-18T05:19:01,723 INFO [RS:0;7cf745f7364a:32867 {}] regionserver.RegionServerCoprocessorHost(67): System coprocessor loading is enabled 2024-11-18T05:19:01,723 INFO [RS:0;7cf745f7364a:32867 {}] regionserver.RegionServerCoprocessorHost(68): Table coprocessor loading is enabled 2024-11-18T05:19:01,723 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] cleaner.CleanerChore(192): Initialize cleaner=org.apache.hadoop.hbase.master.cleaner.TimeToLiveProcedureWALCleaner 2024-11-18T05:19:01,723 DEBUG [RS:0;7cf745f7364a:32867 {}] regionserver.HRegionServer(1090): About to register with Master. 2024-11-18T05:19:01,723 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] cleaner.LogCleaner(148): Creating 1 old WALs cleaner threads 2024-11-18T05:19:01,724 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=LogsCleaner, period=600000, unit=MILLISECONDS is enabled. 2024-11-18T05:19:01,726 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] cleaner.DirScanPool(74): hfile_cleaner Cleaner pool size is 2 2024-11-18T05:19:01,727 DEBUG [PEWorker-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-11-18T05:19:01,727 INFO [RS:0;7cf745f7364a:32867 {}] regionserver.HRegionServer(3073): reportForDuty to master=7cf745f7364a,39359,1731907138502 with isa=7cf745f7364a/172.17.0.2:32867, startcode=1731907139252 2024-11-18T05:19:01,727 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] cleaner.CleanerChore(192): Initialize cleaner=org.apache.hadoop.hbase.master.cleaner.TimeToLiveMasterLocalStoreHFileCleaner 2024-11-18T05:19:01,727 INFO [PEWorker-1 {}] util.FSTableDescriptors(133): Creating new hbase:meta table descriptor 'hbase:meta', {TABLE_ATTRIBUTES => {IS_META => 'true', coprocessor$1 => '|org.apache.hadoop.hbase.coprocessor.MultiRowMutationEndpoint|536870911|', METADATA => {'hbase.store.file-tracker.impl' => 'DEFAULT'}}}, {NAME => 'info', INDEX_BLOCK_ENCODING => 'NONE', VERSIONS => '3', KEEP_DELETED_CELLS => 'FALSE', DATA_BLOCK_ENCODING => 'ROW_INDEX_V1', TTL => 'FOREVER', MIN_VERSIONS => '0', REPLICATION_SCOPE => '0', BLOOMFILTER => 'ROWCOL', IN_MEMORY => 'true', COMPRESSION => 'NONE', BLOCKCACHE => 'true', BLOCKSIZE => '8192 B (8KB)'}, {NAME => 'rep_barrier', INDEX_BLOCK_ENCODING => 'NONE', VERSIONS => '2147483647', KEEP_DELETED_CELLS => 'FALSE', DATA_BLOCK_ENCODING => 'ROW_INDEX_V1', TTL => 'FOREVER', MIN_VERSIONS => '0', REPLICATION_SCOPE => '0', BLOOMFILTER => 'ROWCOL', IN_MEMORY => 'true', COMPRESSION => 'NONE', BLOCKCACHE => 'true', BLOCKSIZE => '65536 B (64KB)'}, {NAME => 'table', INDEX_BLOCK_ENCODING => 'NONE', VERSIONS => '3', KEEP_DELETED_CELLS => 'FALSE', DATA_BLOCK_ENCODING => 'ROW_INDEX_V1', TTL => 'FOREVER', MIN_VERSIONS => '0', REPLICATION_SCOPE => '0', BLOOMFILTER => 'ROWCOL', IN_MEMORY => 'true', COMPRESSION => 'NONE', BLOCKCACHE => 'true', BLOCKSIZE => '8192 B (8KB)'} 2024-11-18T05:19:01,727 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] cleaner.CleanerChore(192): Initialize cleaner=org.apache.hadoop.hbase.master.cleaner.HFileLinkCleaner 2024-11-18T05:19:01,729 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] cleaner.CleanerChore(192): Initialize cleaner=org.apache.hadoop.hbase.master.snapshot.SnapshotHFileCleaner 2024-11-18T05:19:01,730 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] cleaner.CleanerChore(192): Initialize cleaner=org.apache.hadoop.hbase.master.cleaner.TimeToLiveHFileCleaner 2024-11-18T05:19:01,731 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] cleaner.HFileCleaner(260): Starting for large file=Thread[master/7cf745f7364a:0:becomeActiveMaster-HFileCleaner.large.0-1731907141731,5,FailOnTimeoutGroup] 2024-11-18T05:19:01,732 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] cleaner.HFileCleaner(275): Starting for small files=Thread[master/7cf745f7364a:0:becomeActiveMaster-HFileCleaner.small.0-1731907141731,5,FailOnTimeoutGroup] 2024-11-18T05:19:01,732 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=HFileCleaner, period=600000, unit=MILLISECONDS is enabled. 2024-11-18T05:19:01,732 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] master.HMaster(1680): Reopening regions with very high storeFileRefCount is disabled. Provide threshold value > 0 for hbase.regions.recovery.store.file.ref.count to enable it. 2024-11-18T05:19:01,733 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=ReplicationBarrierCleaner, period=43200000, unit=MILLISECONDS is enabled. 2024-11-18T05:19:01,733 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=SnapshotCleaner, period=1800000, unit=MILLISECONDS is enabled. 2024-11-18T05:19:01,737 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38965 is added to blk_1073741831_1007 (size=1039) 2024-11-18T05:19:01,742 DEBUG [RS:0;7cf745f7364a:32867 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=RegionServerStatusService, sasl=false 2024-11-18T05:19:01,775 INFO [RS-EventLoopGroup-1-2 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.2:41989, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins.hfs.0 (auth:SIMPLE), service=RegionServerStatusService 2024-11-18T05:19:01,781 INFO [RpcServer.priority.RWQ.Fifo.write.handler=0,queue=0,port=39359 {}] master.ServerManager(332): Checking decommissioned status of RegionServer 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:01,783 INFO [RpcServer.priority.RWQ.Fifo.write.handler=0,queue=0,port=39359 {}] master.ServerManager(486): Registering regionserver=7cf745f7364a,32867,1731907139252 2024-11-18T05:19:01,797 DEBUG [RS:0;7cf745f7364a:32867 {}] regionserver.HRegionServer(1725): Config from master: hbase.rootdir=hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc 2024-11-18T05:19:01,797 DEBUG [RS:0;7cf745f7364a:32867 {}] regionserver.HRegionServer(1725): Config from master: fs.defaultFS=hdfs://localhost:37393 2024-11-18T05:19:01,797 DEBUG [RS:0;7cf745f7364a:32867 {}] regionserver.HRegionServer(1725): Config from master: hbase.master.info.port=-1 2024-11-18T05:19:01,802 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/rs 2024-11-18T05:19:01,802 DEBUG [RS:0;7cf745f7364a:32867 {}] zookeeper.ZKUtil(111): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Set watcher on existing znode=/hbase/rs/7cf745f7364a,32867,1731907139252 2024-11-18T05:19:01,802 WARN [RS:0;7cf745f7364a:32867 {}] hbase.ZNodeClearer(69): Environment variable HBASE_ZNODE_FILE not set; znodes will not be cleared on crash by start scripts (Longer MTTR!) 2024-11-18T05:19:01,803 INFO [RS:0;7cf745f7364a:32867 {}] wal.WALFactory(183): Instantiating WALProvider of type class org.apache.hadoop.hbase.wal.AsyncFSWALProvider 2024-11-18T05:19:01,803 DEBUG [RS:0;7cf745f7364a:32867 {}] regionserver.HRegionServer(2100): logDir=hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/WALs/7cf745f7364a,32867,1731907139252 2024-11-18T05:19:01,804 INFO [RegionServerTracker-0 {}] master.RegionServerTracker(179): RegionServer ephemeral node created, adding [7cf745f7364a,32867,1731907139252] 2024-11-18T05:19:01,816 DEBUG [RS:0;7cf745f7364a:32867 {}] regionserver.Replication(140): Replication stats-in-log period=300 seconds 2024-11-18T05:19:01,828 INFO [RS:0;7cf745f7364a:32867 {}] regionserver.MetricsRegionServerWrapperImpl(120): Computing regionserver metrics every 5000 milliseconds 2024-11-18T05:19:01,841 INFO [RS:0;7cf745f7364a:32867 {}] regionserver.MemStoreFlusher(130): globalMemStoreLimit=880 M, globalMemStoreLimitLowMark=836 M, Offheap=false 2024-11-18T05:19:01,844 INFO [RS:0;7cf745f7364a:32867 {}] throttle.PressureAwareCompactionThroughputController(131): Compaction throughput configurations, higher bound: 100.00 MB/second, lower bound 50.00 MB/second, off peak: unlimited, tuning period: 60000 ms 2024-11-18T05:19:01,844 INFO [RS:0;7cf745f7364a:32867 {}] hbase.ChoreService(168): Chore ScheduledChore name=CompactionThroughputTuner, period=60000, unit=MILLISECONDS is enabled. 2024-11-18T05:19:01,845 INFO [RS:0;7cf745f7364a:32867 {}] regionserver.HRegionServer$CompactionChecker(1988): CompactionChecker runs every PT1S 2024-11-18T05:19:01,852 INFO [RS:0;7cf745f7364a:32867 {}] hbase.ChoreService(168): Chore ScheduledChore name=CompactedHFilesCleaner, period=120000, unit=MILLISECONDS is enabled. 2024-11-18T05:19:01,852 DEBUG [RS:0;7cf745f7364a:32867 {}] executor.ExecutorService(95): Starting executor service name=RS_OPEN_REGION-regionserver/7cf745f7364a:0, corePoolSize=1, maxPoolSize=1 2024-11-18T05:19:01,852 DEBUG [RS:0;7cf745f7364a:32867 {}] executor.ExecutorService(95): Starting executor service name=RS_OPEN_META-regionserver/7cf745f7364a:0, corePoolSize=1, maxPoolSize=1 2024-11-18T05:19:01,852 DEBUG [RS:0;7cf745f7364a:32867 {}] executor.ExecutorService(95): Starting executor service name=RS_OPEN_PRIORITY_REGION-regionserver/7cf745f7364a:0, corePoolSize=1, maxPoolSize=1 2024-11-18T05:19:01,852 DEBUG [RS:0;7cf745f7364a:32867 {}] executor.ExecutorService(95): Starting executor service name=RS_CLOSE_REGION-regionserver/7cf745f7364a:0, corePoolSize=1, maxPoolSize=1 2024-11-18T05:19:01,853 DEBUG [RS:0;7cf745f7364a:32867 {}] executor.ExecutorService(95): Starting executor service name=RS_CLOSE_META-regionserver/7cf745f7364a:0, corePoolSize=1, maxPoolSize=1 2024-11-18T05:19:01,853 DEBUG [RS:0;7cf745f7364a:32867 {}] executor.ExecutorService(95): Starting executor service name=RS_LOG_REPLAY_OPS-regionserver/7cf745f7364a:0, corePoolSize=2, maxPoolSize=2 2024-11-18T05:19:01,853 DEBUG [RS:0;7cf745f7364a:32867 {}] executor.ExecutorService(95): Starting executor service name=RS_COMPACTED_FILES_DISCHARGER-regionserver/7cf745f7364a:0, corePoolSize=1, maxPoolSize=1 2024-11-18T05:19:01,853 DEBUG [RS:0;7cf745f7364a:32867 {}] executor.ExecutorService(95): Starting executor service name=RS_REGION_REPLICA_FLUSH_OPS-regionserver/7cf745f7364a:0, corePoolSize=1, maxPoolSize=1 2024-11-18T05:19:01,853 DEBUG [RS:0;7cf745f7364a:32867 {}] executor.ExecutorService(95): Starting executor service name=RS_REFRESH_PEER-regionserver/7cf745f7364a:0, corePoolSize=1, maxPoolSize=1 2024-11-18T05:19:01,853 DEBUG [RS:0;7cf745f7364a:32867 {}] executor.ExecutorService(95): Starting executor service name=RS_SWITCH_RPC_THROTTLE-regionserver/7cf745f7364a:0, corePoolSize=1, maxPoolSize=1 2024-11-18T05:19:01,853 DEBUG [RS:0;7cf745f7364a:32867 {}] executor.ExecutorService(95): Starting executor service name=RS_CLAIM_REPLICATION_QUEUE-regionserver/7cf745f7364a:0, corePoolSize=1, maxPoolSize=1 2024-11-18T05:19:01,854 DEBUG [RS:0;7cf745f7364a:32867 {}] executor.ExecutorService(95): Starting executor service name=RS_SNAPSHOT_OPERATIONS-regionserver/7cf745f7364a:0, corePoolSize=3, maxPoolSize=3 2024-11-18T05:19:01,854 DEBUG [RS:0;7cf745f7364a:32867 {}] executor.ExecutorService(95): Starting executor service name=RS_FLUSH_OPERATIONS-regionserver/7cf745f7364a:0, corePoolSize=3, maxPoolSize=3 2024-11-18T05:19:01,855 INFO [RS:0;7cf745f7364a:32867 {}] hbase.ChoreService(168): Chore ScheduledChore name=CompactionChecker, period=1000, unit=MILLISECONDS is enabled. 2024-11-18T05:19:01,856 INFO [RS:0;7cf745f7364a:32867 {}] hbase.ChoreService(168): Chore ScheduledChore name=MemstoreFlusherChore, period=1000, unit=MILLISECONDS is enabled. 2024-11-18T05:19:01,856 INFO [RS:0;7cf745f7364a:32867 {}] hbase.ChoreService(168): Chore ScheduledChore name=nonceCleaner, period=360000, unit=MILLISECONDS is enabled. 2024-11-18T05:19:01,856 INFO [RS:0;7cf745f7364a:32867 {}] hbase.ChoreService(168): Chore ScheduledChore name=BrokenStoreFileCleaner, period=21600000, unit=MILLISECONDS is enabled. 2024-11-18T05:19:01,856 INFO [RS:0;7cf745f7364a:32867 {}] hbase.ChoreService(168): Chore ScheduledChore name=7cf745f7364a,32867,1731907139252-MobFileCleanerChore, period=86400, unit=SECONDS is enabled. 2024-11-18T05:19:01,876 INFO [RS:0;7cf745f7364a:32867 {}] regionserver.HeapMemoryManager(209): Starting, tuneOn=false 2024-11-18T05:19:01,877 INFO [RS:0;7cf745f7364a:32867 {}] hbase.ChoreService(168): Chore ScheduledChore name=7cf745f7364a,32867,1731907139252-HeapMemoryTunerChore, period=60000, unit=MILLISECONDS is enabled. 2024-11-18T05:19:01,897 INFO [RS:0;7cf745f7364a:32867 {}] regionserver.Replication(204): 7cf745f7364a,32867,1731907139252 started 2024-11-18T05:19:01,897 INFO [RS:0;7cf745f7364a:32867 {}] regionserver.HRegionServer(1767): Serving as 7cf745f7364a,32867,1731907139252, RpcServer on 7cf745f7364a/172.17.0.2:32867, sessionid=0x1000911699b0001 2024-11-18T05:19:01,898 DEBUG [RS:0;7cf745f7364a:32867 {}] procedure.RegionServerProcedureManagerHost(51): Procedure flush-table-proc starting 2024-11-18T05:19:01,898 DEBUG [RS:0;7cf745f7364a:32867 {}] flush.RegionServerFlushTableProcedureManager(108): Start region server flush procedure manager 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:01,898 DEBUG [RS:0;7cf745f7364a:32867 {}] procedure.ZKProcedureMemberRpcs(357): Starting procedure member '7cf745f7364a,32867,1731907139252' 2024-11-18T05:19:01,898 DEBUG [RS:0;7cf745f7364a:32867 {}] procedure.ZKProcedureMemberRpcs(134): Checking for aborted procedures on node: '/hbase/flush-table-proc/abort' 2024-11-18T05:19:01,899 DEBUG [RS:0;7cf745f7364a:32867 {}] procedure.ZKProcedureMemberRpcs(154): Looking for new procedures under znode:'/hbase/flush-table-proc/acquired' 2024-11-18T05:19:01,900 DEBUG [RS:0;7cf745f7364a:32867 {}] procedure.RegionServerProcedureManagerHost(53): Procedure flush-table-proc started 2024-11-18T05:19:01,900 DEBUG [RS:0;7cf745f7364a:32867 {}] procedure.RegionServerProcedureManagerHost(51): Procedure online-snapshot starting 2024-11-18T05:19:01,900 DEBUG [RS:0;7cf745f7364a:32867 {}] snapshot.RegionServerSnapshotManager(126): Start Snapshot Manager 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:01,900 DEBUG [RS:0;7cf745f7364a:32867 {}] procedure.ZKProcedureMemberRpcs(357): Starting procedure member '7cf745f7364a,32867,1731907139252' 2024-11-18T05:19:01,900 DEBUG [RS:0;7cf745f7364a:32867 {}] procedure.ZKProcedureMemberRpcs(134): Checking for aborted procedures on node: '/hbase/online-snapshot/abort' 2024-11-18T05:19:01,901 DEBUG [RS:0;7cf745f7364a:32867 {}] procedure.ZKProcedureMemberRpcs(154): Looking for new procedures under znode:'/hbase/online-snapshot/acquired' 2024-11-18T05:19:01,901 DEBUG [RS:0;7cf745f7364a:32867 {}] procedure.RegionServerProcedureManagerHost(53): Procedure online-snapshot started 2024-11-18T05:19:01,901 INFO [RS:0;7cf745f7364a:32867 {}] quotas.RegionServerRpcQuotaManager(64): Quota support disabled 2024-11-18T05:19:01,901 INFO [RS:0;7cf745f7364a:32867 {}] quotas.RegionServerSpaceQuotaManager(80): Quota support disabled, not starting space quota manager. 2024-11-18T05:19:02,007 INFO [RS:0;7cf745f7364a:32867 {}] monitor.StreamSlowMonitor(122): New stream slow monitor defaultMonitorName 2024-11-18T05:19:02,010 INFO [RS:0;7cf745f7364a:32867 {}] wal.AbstractFSWAL(500): WAL configuration: blocksize=256 MB, rollsize=128 MB, prefix=7cf745f7364a%2C32867%2C1731907139252, suffix=, logDir=hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/WALs/7cf745f7364a,32867,1731907139252, archiveDir=hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/oldWALs, maxLogs=32 2024-11-18T05:19:02,027 DEBUG [RS:0;7cf745f7364a:32867 {}] asyncfs.FanOutOneBlockAsyncDFSOutputHelper(617): When create output stream for /user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/WALs/7cf745f7364a,32867,1731907139252/7cf745f7364a%2C32867%2C1731907139252.1731907142013, exclude list is [], retry=0 2024-11-18T05:19:02,032 DEBUG [RS-EventLoopGroup-3-2 {}] asyncfs.FanOutOneBlockAsyncDFSOutputSaslHelper(816): SASL client skipping handshake in unsecured configuration for addr = 127.0.0.1/127.0.0.1, datanodeId = DatanodeInfoWithStorage[127.0.0.1:38965,DS-564787d6-4f9e-4ae8-8ae2-11502196172f,DISK] 2024-11-18T05:19:02,035 INFO [RS:0;7cf745f7364a:32867 {}] wal.AbstractFSWAL(841): New WAL /user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/WALs/7cf745f7364a,32867,1731907139252/7cf745f7364a%2C32867%2C1731907139252.1731907142013 2024-11-18T05:19:02,036 DEBUG [RS:0;7cf745f7364a:32867 {}] wal.AbstractFSWAL(925): Create new AsyncFSWAL writer with pipeline: [(127.0.0.1/127.0.0.1:45257:45257)] 2024-11-18T05:19:02,140 INFO [PEWorker-1 {}] util.FSTableDescriptors(140): Updated hbase:meta table descriptor to hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/data/hbase/meta/.tabledesc/.tableinfo.0000000001.1039 2024-11-18T05:19:02,140 INFO [PEWorker-1 {}] regionserver.HRegion(7106): creating {ENCODED => 1588230740, NAME => 'hbase:meta,,1', STARTKEY => '', ENDKEY => ''}, tableDescriptor='hbase:meta', {TABLE_ATTRIBUTES => {IS_META => 'true', coprocessor$1 => '|org.apache.hadoop.hbase.coprocessor.MultiRowMutationEndpoint|536870911|', METADATA => {'hbase.store.file-tracker.impl' => 'DEFAULT'}}}, {NAME => 'info', INDEX_BLOCK_ENCODING => 'NONE', VERSIONS => '3', KEEP_DELETED_CELLS => 'FALSE', DATA_BLOCK_ENCODING => 'ROW_INDEX_V1', TTL => 'FOREVER', MIN_VERSIONS => '0', REPLICATION_SCOPE => '0', BLOOMFILTER => 'ROWCOL', IN_MEMORY => 'true', COMPRESSION => 'NONE', BLOCKCACHE => 'true', BLOCKSIZE => '8192 B (8KB)'}, {NAME => 'rep_barrier', INDEX_BLOCK_ENCODING => 'NONE', VERSIONS => '2147483647', KEEP_DELETED_CELLS => 'FALSE', DATA_BLOCK_ENCODING => 'ROW_INDEX_V1', TTL => 'FOREVER', MIN_VERSIONS => '0', REPLICATION_SCOPE => '0', BLOOMFILTER => 'ROWCOL', IN_MEMORY => 'true', COMPRESSION => 'NONE', BLOCKCACHE => 'true', BLOCKSIZE => '65536 B (64KB)'}, {NAME => 'table', INDEX_BLOCK_ENCODING => 'NONE', VERSIONS => '3', KEEP_DELETED_CELLS => 'FALSE', DATA_BLOCK_ENCODING => 'ROW_INDEX_V1', TTL => 'FOREVER', MIN_VERSIONS => '0', REPLICATION_SCOPE => '0', BLOOMFILTER => 'ROWCOL', IN_MEMORY => 'true', COMPRESSION => 'NONE', BLOCKCACHE => 'true', BLOCKSIZE => '8192 B (8KB)'}, regionDir=hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc 2024-11-18T05:19:02,149 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38965 is added to blk_1073741833_1009 (size=32) 2024-11-18T05:19:02,552 DEBUG [PEWorker-1 {}] regionserver.HRegion(894): Instantiated hbase:meta,,1.1588230740; StoreHotnessProtector, parallelPutToStoreThreadLimit=0 ; minColumnNum=100 ; preparePutThreadLimit=0 ; hotProtect now disable 2024-11-18T05:19:02,554 INFO [StoreOpener-1588230740-1 {}] regionserver.HStore(400): Created cacheConfig: cacheDataOnRead=true, cacheDataOnWrite=false, cacheIndexesOnWrite=false, cacheBloomsOnWrite=false, cacheEvictOnClose=false, cacheDataCompressed=false, prefetchOnOpen=false, for column family info of region 1588230740 2024-11-18T05:19:02,557 INFO [StoreOpener-1588230740-1 {}] compactions.CompactionConfiguration(181): size [minCompactSize:128 MB, maxCompactSize:8.00 EB, offPeakMaxCompactSize:8.00 EB); files [minFilesToCompact:3, maxFilesToCompact:10); ratio 1.200000; off-peak ratio 5.000000; throttle point 2684354560; major period 604800000, major jitter 0.500000, min locality to compact 0.000000; tiered compaction: max_age 9223372036854775807, incoming window min 6, compaction policy for tiered window org.apache.hadoop.hbase.regionserver.compactions.ExploringCompactionPolicy, single output for minor true, compaction window factory org.apache.hadoop.hbase.regionserver.compactions.ExponentialCompactionWindowFactory, region 1588230740 columnFamilyName info 2024-11-18T05:19:02,557 DEBUG [StoreOpener-1588230740-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-11-18T05:19:02,558 INFO [StoreOpener-1588230740-1 {}] regionserver.HStore(327): Store=1588230740/info, memstore type=DefaultMemStore, storagePolicy=NONE, verifyBulkLoads=false, parallelPutCountPrintThreshold=50, encoding=ROW_INDEX_V1, compression=NONE 2024-11-18T05:19:02,558 INFO [StoreOpener-1588230740-1 {}] regionserver.HStore(400): Created cacheConfig: cacheDataOnRead=true, cacheDataOnWrite=false, cacheIndexesOnWrite=false, cacheBloomsOnWrite=false, cacheEvictOnClose=false, cacheDataCompressed=false, prefetchOnOpen=false, for column family rep_barrier of region 1588230740 2024-11-18T05:19:02,560 INFO [StoreOpener-1588230740-1 {}] compactions.CompactionConfiguration(181): size [minCompactSize:128 MB, maxCompactSize:8.00 EB, offPeakMaxCompactSize:8.00 EB); files [minFilesToCompact:3, maxFilesToCompact:10); ratio 1.200000; off-peak ratio 5.000000; throttle point 2684354560; major period 604800000, major jitter 0.500000, min locality to compact 0.000000; tiered compaction: max_age 9223372036854775807, incoming window min 6, compaction policy for tiered window org.apache.hadoop.hbase.regionserver.compactions.ExploringCompactionPolicy, single output for minor true, compaction window factory org.apache.hadoop.hbase.regionserver.compactions.ExponentialCompactionWindowFactory, region 1588230740 columnFamilyName rep_barrier 2024-11-18T05:19:02,560 DEBUG [StoreOpener-1588230740-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-11-18T05:19:02,561 INFO [StoreOpener-1588230740-1 {}] regionserver.HStore(327): Store=1588230740/rep_barrier, memstore type=DefaultMemStore, storagePolicy=NONE, verifyBulkLoads=false, parallelPutCountPrintThreshold=50, encoding=ROW_INDEX_V1, compression=NONE 2024-11-18T05:19:02,561 INFO [StoreOpener-1588230740-1 {}] regionserver.HStore(400): Created cacheConfig: cacheDataOnRead=true, cacheDataOnWrite=false, cacheIndexesOnWrite=false, cacheBloomsOnWrite=false, cacheEvictOnClose=false, cacheDataCompressed=false, prefetchOnOpen=false, for column family table of region 1588230740 2024-11-18T05:19:02,563 INFO [StoreOpener-1588230740-1 {}] compactions.CompactionConfiguration(181): size [minCompactSize:128 MB, maxCompactSize:8.00 EB, offPeakMaxCompactSize:8.00 EB); files [minFilesToCompact:3, maxFilesToCompact:10); ratio 1.200000; off-peak ratio 5.000000; throttle point 2684354560; major period 604800000, major jitter 0.500000, min locality to compact 0.000000; tiered compaction: max_age 9223372036854775807, incoming window min 6, compaction policy for tiered window org.apache.hadoop.hbase.regionserver.compactions.ExploringCompactionPolicy, single output for minor true, compaction window factory org.apache.hadoop.hbase.regionserver.compactions.ExponentialCompactionWindowFactory, region 1588230740 columnFamilyName table 2024-11-18T05:19:02,564 DEBUG [StoreOpener-1588230740-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-11-18T05:19:02,564 INFO [StoreOpener-1588230740-1 {}] regionserver.HStore(327): Store=1588230740/table, memstore type=DefaultMemStore, storagePolicy=NONE, verifyBulkLoads=false, parallelPutCountPrintThreshold=50, encoding=ROW_INDEX_V1, compression=NONE 2024-11-18T05:19:02,566 DEBUG [PEWorker-1 {}] regionserver.HRegion(5301): Found 0 recovered edits file(s) under hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/data/hbase/meta/1588230740 2024-11-18T05:19:02,567 DEBUG [PEWorker-1 {}] regionserver.HRegion(5301): Found 0 recovered edits file(s) under hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/data/hbase/meta/1588230740 2024-11-18T05:19:02,570 DEBUG [PEWorker-1 {}] regionserver.FlushLargeStoresPolicy(65): No hbase.hregion.percolumnfamilyflush.size.lower.bound set in table hbase:meta descriptor;using region.getMemStoreFlushHeapSize/# of families (42.7 M)) instead. 2024-11-18T05:19:02,572 DEBUG [PEWorker-1 {}] regionserver.HRegion(1085): writing seq id for 1588230740 2024-11-18T05:19:02,576 DEBUG [PEWorker-1 {}] wal.WALSplitUtil(409): Wrote file=hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/data/hbase/meta/1588230740/recovered.edits/1.seqid, newMaxSeqId=1, maxSeqId=-1 2024-11-18T05:19:02,577 INFO [PEWorker-1 {}] regionserver.HRegion(1102): Opened 1588230740; next sequenceid=2; SteppingSplitPolicysuper{IncreasingToUpperBoundRegionSplitPolicy{initialSize=268435456, ConstantSizeRegionSplitPolicy{desiredMaxFileSize=66395884, jitterRate=-0.010624229907989502}}}, FlushLargeStoresPolicy{flushSizeLowerBound=44739242} 2024-11-18T05:19:02,579 DEBUG [PEWorker-1 {}] regionserver.HRegion(1001): Region open journal for 1588230740: 2024-11-18T05:19:02,579 DEBUG [PEWorker-1 {}] regionserver.HRegion(1681): Closing 1588230740, disabling compactions & flushes 2024-11-18T05:19:02,579 INFO [PEWorker-1 {}] regionserver.HRegion(1703): Closing region hbase:meta,,1.1588230740 2024-11-18T05:19:02,579 DEBUG [PEWorker-1 {}] regionserver.HRegion(1724): Waiting without time limit for close lock on hbase:meta,,1.1588230740 2024-11-18T05:19:02,579 DEBUG [PEWorker-1 {}] regionserver.HRegion(1791): Acquired close lock on hbase:meta,,1.1588230740 after waiting 0 ms 2024-11-18T05:19:02,579 DEBUG [PEWorker-1 {}] regionserver.HRegion(1801): Updates disabled for region hbase:meta,,1.1588230740 2024-11-18T05:19:02,580 INFO [PEWorker-1 {}] regionserver.HRegion(1922): Closed hbase:meta,,1.1588230740 2024-11-18T05:19:02,581 DEBUG [PEWorker-1 {}] regionserver.HRegion(1635): Region close journal for 1588230740: 2024-11-18T05:19:02,583 DEBUG [PEWorker-1 {}] procedure.InitMetaProcedure(96): Execute pid=1, state=RUNNABLE:INIT_META_ASSIGN_META, locked=true; InitMetaProcedure table=hbase:meta 2024-11-18T05:19:02,583 INFO [PEWorker-1 {}] procedure.InitMetaProcedure(107): Going to assign meta 2024-11-18T05:19:02,589 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=2, ppid=1, state=RUNNABLE:REGION_STATE_TRANSITION_GET_ASSIGN_CANDIDATE; TransitRegionStateProcedure table=hbase:meta, region=1588230740, ASSIGN}] 2024-11-18T05:19:02,597 INFO [PEWorker-5 {}] procedure.MasterProcedureScheduler(786): Took xlock for pid=2, ppid=1, state=RUNNABLE:REGION_STATE_TRANSITION_GET_ASSIGN_CANDIDATE; TransitRegionStateProcedure table=hbase:meta, region=1588230740, ASSIGN 2024-11-18T05:19:02,600 INFO [PEWorker-5 {}] assignment.TransitRegionStateProcedure(264): Starting pid=2, ppid=1, state=RUNNABLE:REGION_STATE_TRANSITION_GET_ASSIGN_CANDIDATE, locked=true; TransitRegionStateProcedure table=hbase:meta, region=1588230740, ASSIGN; state=OFFLINE, location=null; forceNewPlan=false, retain=false 2024-11-18T05:19:02,751 DEBUG [7cf745f7364a:39359 {}] assignment.AssignmentManager(2444): Processing assignQueue; systemServersCount=1, allServersCount=1 2024-11-18T05:19:02,756 INFO [PEWorker-2 {}] assignment.RegionStateStore(202): pid=2 updating hbase:meta row=1588230740, regionState=OPENING, regionLocation=7cf745f7364a,32867,1731907139252 2024-11-18T05:19:02,761 INFO [PEWorker-2 {}] zookeeper.MetaTableLocator(171): Setting hbase:meta replicaId=0 location in ZooKeeper as 7cf745f7364a,32867,1731907139252, state=OPENING 2024-11-18T05:19:02,766 DEBUG [PEWorker-2 {}] zookeeper.MetaTableLocator(183): hbase:meta region location doesn't exist, create it 2024-11-18T05:19:02,768 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-11-18T05:19:02,768 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-11-18T05:19:02,769 DEBUG [zk-event-processor-pool-0 {}] hbase.MetaRegionLocationCache(167): Updating meta znode for path /hbase/meta-region-server: CHANGED 2024-11-18T05:19:02,769 DEBUG [zk-event-processor-pool-0 {}] hbase.MetaRegionLocationCache(167): Updating meta znode for path /hbase/meta-region-server: CHANGED 2024-11-18T05:19:02,770 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=3, ppid=2, state=RUNNABLE; OpenRegionProcedure 1588230740, server=7cf745f7364a,32867,1731907139252}] 2024-11-18T05:19:02,944 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:02,946 DEBUG [RSProcedureDispatcher-pool-0 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=AdminService, sasl=false 2024-11-18T05:19:02,949 INFO [RS-EventLoopGroup-3-3 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.2:60206, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=AdminService 2024-11-18T05:19:02,959 INFO [RS_OPEN_META-regionserver/7cf745f7364a:0-0 {event_type=M_RS_OPEN_META, pid=3}] handler.AssignRegionHandler(135): Open hbase:meta,,1.1588230740 2024-11-18T05:19:02,959 INFO [RS_OPEN_META-regionserver/7cf745f7364a:0-0 {event_type=M_RS_OPEN_META, pid=3}] wal.WALFactory(183): Instantiating WALProvider of type class org.apache.hadoop.hbase.wal.AsyncFSWALProvider 2024-11-18T05:19:02,959 INFO [RS_OPEN_META-regionserver/7cf745f7364a:0-0 {event_type=M_RS_OPEN_META, pid=3}] monitor.StreamSlowMonitor(122): New stream slow monitor .meta 2024-11-18T05:19:02,962 INFO [RS_OPEN_META-regionserver/7cf745f7364a:0-0 {event_type=M_RS_OPEN_META, pid=3}] wal.AbstractFSWAL(500): WAL configuration: blocksize=256 MB, rollsize=128 MB, prefix=7cf745f7364a%2C32867%2C1731907139252.meta, suffix=.meta, logDir=hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/WALs/7cf745f7364a,32867,1731907139252, archiveDir=hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/oldWALs, maxLogs=32 2024-11-18T05:19:02,979 DEBUG [RS_OPEN_META-regionserver/7cf745f7364a:0-0 {event_type=M_RS_OPEN_META, pid=3}] asyncfs.FanOutOneBlockAsyncDFSOutputHelper(617): When create output stream for /user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/WALs/7cf745f7364a,32867,1731907139252/7cf745f7364a%2C32867%2C1731907139252.meta.1731907142964.meta, exclude list is [], retry=0 2024-11-18T05:19:02,982 DEBUG [RS-EventLoopGroup-3-1 {}] asyncfs.FanOutOneBlockAsyncDFSOutputSaslHelper(816): SASL client skipping handshake in unsecured configuration for addr = 127.0.0.1/127.0.0.1, datanodeId = DatanodeInfoWithStorage[127.0.0.1:38965,DS-564787d6-4f9e-4ae8-8ae2-11502196172f,DISK] 2024-11-18T05:19:02,985 INFO [RS_OPEN_META-regionserver/7cf745f7364a:0-0 {event_type=M_RS_OPEN_META, pid=3}] wal.AbstractFSWAL(841): New WAL /user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/WALs/7cf745f7364a,32867,1731907139252/7cf745f7364a%2C32867%2C1731907139252.meta.1731907142964.meta 2024-11-18T05:19:02,986 DEBUG [RS_OPEN_META-regionserver/7cf745f7364a:0-0 {event_type=M_RS_OPEN_META, pid=3}] wal.AbstractFSWAL(925): Create new AsyncFSWAL writer with pipeline: [(127.0.0.1/127.0.0.1:45257:45257)] 2024-11-18T05:19:02,986 DEBUG [RS_OPEN_META-regionserver/7cf745f7364a:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(7285): Opening region: {ENCODED => 1588230740, NAME => 'hbase:meta,,1', STARTKEY => '', ENDKEY => ''} 2024-11-18T05:19:02,987 DEBUG [RS_OPEN_META-regionserver/7cf745f7364a:0-0 {event_type=M_RS_OPEN_META, pid=3}] coprocessor.CoprocessorHost(215): Loading coprocessor class org.apache.hadoop.hbase.coprocessor.MultiRowMutationEndpoint with path null and priority 536870911 2024-11-18T05:19:03,047 DEBUG [RS_OPEN_META-regionserver/7cf745f7364a:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(7999): Registered coprocessor service: region=hbase:meta,,1 service=MultiRowMutationService 2024-11-18T05:19:03,051 INFO [RS_OPEN_META-regionserver/7cf745f7364a:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.RegionCoprocessorHost(436): Loaded coprocessor org.apache.hadoop.hbase.coprocessor.MultiRowMutationEndpoint from HTD of hbase:meta successfully. 2024-11-18T05:19:03,056 DEBUG [RS_OPEN_META-regionserver/7cf745f7364a:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.MetricsRegionSourceImpl(79): Creating new MetricsRegionSourceImpl for table meta 1588230740 2024-11-18T05:19:03,056 DEBUG [RS_OPEN_META-regionserver/7cf745f7364a:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(894): Instantiated hbase:meta,,1.1588230740; StoreHotnessProtector, parallelPutToStoreThreadLimit=0 ; minColumnNum=100 ; preparePutThreadLimit=0 ; hotProtect now disable 2024-11-18T05:19:03,056 DEBUG [RS_OPEN_META-regionserver/7cf745f7364a:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(7327): checking encryption for 1588230740 2024-11-18T05:19:03,056 DEBUG [RS_OPEN_META-regionserver/7cf745f7364a:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(7330): checking classloading for 1588230740 2024-11-18T05:19:03,059 INFO [StoreOpener-1588230740-1 {}] regionserver.HStore(400): Created cacheConfig: cacheDataOnRead=true, cacheDataOnWrite=false, cacheIndexesOnWrite=false, cacheBloomsOnWrite=false, cacheEvictOnClose=false, cacheDataCompressed=false, prefetchOnOpen=false, for column family info of region 1588230740 2024-11-18T05:19:03,061 INFO [StoreOpener-1588230740-1 {}] compactions.CompactionConfiguration(181): size [minCompactSize:128 MB, maxCompactSize:8.00 EB, offPeakMaxCompactSize:8.00 EB); files [minFilesToCompact:3, maxFilesToCompact:10); ratio 1.200000; off-peak ratio 5.000000; throttle point 2684354560; major period 604800000, major jitter 0.500000, min locality to compact 0.000000; tiered compaction: max_age 9223372036854775807, incoming window min 6, compaction policy for tiered window org.apache.hadoop.hbase.regionserver.compactions.ExploringCompactionPolicy, single output for minor true, compaction window factory org.apache.hadoop.hbase.regionserver.compactions.ExponentialCompactionWindowFactory, region 1588230740 columnFamilyName info 2024-11-18T05:19:03,061 DEBUG [StoreOpener-1588230740-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-11-18T05:19:03,062 INFO [StoreOpener-1588230740-1 {}] regionserver.HStore(327): Store=1588230740/info, memstore type=DefaultMemStore, storagePolicy=NONE, verifyBulkLoads=false, parallelPutCountPrintThreshold=50, encoding=ROW_INDEX_V1, compression=NONE 2024-11-18T05:19:03,062 INFO [StoreOpener-1588230740-1 {}] regionserver.HStore(400): Created cacheConfig: cacheDataOnRead=true, cacheDataOnWrite=false, cacheIndexesOnWrite=false, cacheBloomsOnWrite=false, cacheEvictOnClose=false, cacheDataCompressed=false, prefetchOnOpen=false, for column family rep_barrier of region 1588230740 2024-11-18T05:19:03,063 INFO [StoreOpener-1588230740-1 {}] compactions.CompactionConfiguration(181): size [minCompactSize:128 MB, maxCompactSize:8.00 EB, offPeakMaxCompactSize:8.00 EB); files [minFilesToCompact:3, maxFilesToCompact:10); ratio 1.200000; off-peak ratio 5.000000; throttle point 2684354560; major period 604800000, major jitter 0.500000, min locality to compact 0.000000; tiered compaction: max_age 9223372036854775807, incoming window min 6, compaction policy for tiered window org.apache.hadoop.hbase.regionserver.compactions.ExploringCompactionPolicy, single output for minor true, compaction window factory org.apache.hadoop.hbase.regionserver.compactions.ExponentialCompactionWindowFactory, region 1588230740 columnFamilyName rep_barrier 2024-11-18T05:19:03,063 DEBUG [StoreOpener-1588230740-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-11-18T05:19:03,064 INFO [StoreOpener-1588230740-1 {}] regionserver.HStore(327): Store=1588230740/rep_barrier, memstore type=DefaultMemStore, storagePolicy=NONE, verifyBulkLoads=false, parallelPutCountPrintThreshold=50, encoding=ROW_INDEX_V1, compression=NONE 2024-11-18T05:19:03,064 INFO [StoreOpener-1588230740-1 {}] regionserver.HStore(400): Created cacheConfig: cacheDataOnRead=true, cacheDataOnWrite=false, cacheIndexesOnWrite=false, cacheBloomsOnWrite=false, cacheEvictOnClose=false, cacheDataCompressed=false, prefetchOnOpen=false, for column family table of region 1588230740 2024-11-18T05:19:03,065 INFO [StoreOpener-1588230740-1 {}] compactions.CompactionConfiguration(181): size [minCompactSize:128 MB, maxCompactSize:8.00 EB, offPeakMaxCompactSize:8.00 EB); files [minFilesToCompact:3, maxFilesToCompact:10); ratio 1.200000; off-peak ratio 5.000000; throttle point 2684354560; major period 604800000, major jitter 0.500000, min locality to compact 0.000000; tiered compaction: max_age 9223372036854775807, incoming window min 6, compaction policy for tiered window org.apache.hadoop.hbase.regionserver.compactions.ExploringCompactionPolicy, single output for minor true, compaction window factory org.apache.hadoop.hbase.regionserver.compactions.ExponentialCompactionWindowFactory, region 1588230740 columnFamilyName table 2024-11-18T05:19:03,066 DEBUG [StoreOpener-1588230740-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-11-18T05:19:03,066 INFO [StoreOpener-1588230740-1 {}] regionserver.HStore(327): Store=1588230740/table, memstore type=DefaultMemStore, storagePolicy=NONE, verifyBulkLoads=false, parallelPutCountPrintThreshold=50, encoding=ROW_INDEX_V1, compression=NONE 2024-11-18T05:19:03,067 DEBUG [RS_OPEN_META-regionserver/7cf745f7364a:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(5301): Found 0 recovered edits file(s) under hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/data/hbase/meta/1588230740 2024-11-18T05:19:03,070 DEBUG [RS_OPEN_META-regionserver/7cf745f7364a:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(5301): Found 0 recovered edits file(s) under hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/data/hbase/meta/1588230740 2024-11-18T05:19:03,072 DEBUG [RS_OPEN_META-regionserver/7cf745f7364a:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.FlushLargeStoresPolicy(65): No hbase.hregion.percolumnfamilyflush.size.lower.bound set in table hbase:meta descriptor;using region.getMemStoreFlushHeapSize/# of families (42.7 M)) instead. 2024-11-18T05:19:03,074 DEBUG [RS_OPEN_META-regionserver/7cf745f7364a:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(1085): writing seq id for 1588230740 2024-11-18T05:19:03,076 INFO [RS_OPEN_META-regionserver/7cf745f7364a:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(1102): Opened 1588230740; next sequenceid=2; SteppingSplitPolicysuper{IncreasingToUpperBoundRegionSplitPolicy{initialSize=268435456, ConstantSizeRegionSplitPolicy{desiredMaxFileSize=67482057, jitterRate=0.005561009049415588}}}, FlushLargeStoresPolicy{flushSizeLowerBound=44739242} 2024-11-18T05:19:03,077 DEBUG [RS_OPEN_META-regionserver/7cf745f7364a:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(1001): Region open journal for 1588230740: 2024-11-18T05:19:03,084 INFO [RS_OPEN_META-regionserver/7cf745f7364a:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegionServer(2601): Post open deploy tasks for hbase:meta,,1.1588230740, pid=3, masterSystemTime=1731907142938 2024-11-18T05:19:03,095 DEBUG [RS_OPEN_META-regionserver/7cf745f7364a:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegionServer(2628): Finished post open deploy task for hbase:meta,,1.1588230740 2024-11-18T05:19:03,095 INFO [RS_OPEN_META-regionserver/7cf745f7364a:0-0 {event_type=M_RS_OPEN_META, pid=3}] handler.AssignRegionHandler(164): Opened hbase:meta,,1.1588230740 2024-11-18T05:19:03,096 INFO [PEWorker-4 {}] assignment.RegionStateStore(202): pid=2 updating hbase:meta row=1588230740, regionState=OPEN, openSeqNum=2, regionLocation=7cf745f7364a,32867,1731907139252 2024-11-18T05:19:03,098 INFO [PEWorker-4 {}] zookeeper.MetaTableLocator(171): Setting hbase:meta replicaId=0 location in ZooKeeper as 7cf745f7364a,32867,1731907139252, state=OPEN 2024-11-18T05:19:03,102 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDataChanged, state=SyncConnected, path=/hbase/meta-region-server 2024-11-18T05:19:03,102 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDataChanged, state=SyncConnected, path=/hbase/meta-region-server 2024-11-18T05:19:03,103 DEBUG [zk-event-processor-pool-0 {}] hbase.MetaRegionLocationCache(167): Updating meta znode for path /hbase/meta-region-server: CHANGED 2024-11-18T05:19:03,103 DEBUG [zk-event-processor-pool-0 {}] hbase.MetaRegionLocationCache(167): Updating meta znode for path /hbase/meta-region-server: CHANGED 2024-11-18T05:19:03,107 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=3, resume processing ppid=2 2024-11-18T05:19:03,107 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=3, ppid=2, state=SUCCESS; OpenRegionProcedure 1588230740, server=7cf745f7364a,32867,1731907139252 in 332 msec 2024-11-18T05:19:03,113 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=2, resume processing ppid=1 2024-11-18T05:19:03,113 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=2, ppid=1, state=SUCCESS; TransitRegionStateProcedure table=hbase:meta, region=1588230740, ASSIGN in 520 msec 2024-11-18T05:19:03,118 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=1, state=SUCCESS; InitMetaProcedure table=hbase:meta in 1.4720 sec 2024-11-18T05:19:03,118 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] master.HMaster(1088): Wait for region servers to report in: status=status unset, state=RUNNING, startTime=1731907143118, completionTime=-1 2024-11-18T05:19:03,118 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] master.ServerManager(907): Finished waiting on RegionServer count=1; waited=0ms, expected min=1 server(s), max=1 server(s), master is running 2024-11-18T05:19:03,119 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] assignment.AssignmentManager(1747): Joining cluster... 2024-11-18T05:19:03,155 DEBUG [hconnection-0x6d9680e7-shared-pool-0 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=ClientService, sasl=false 2024-11-18T05:19:03,158 INFO [RS-EventLoopGroup-3-2 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.2:60210, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=ClientService 2024-11-18T05:19:03,167 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] assignment.AssignmentManager(1759): Number of RegionServers=1 2024-11-18T05:19:03,167 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] procedure2.TimeoutExecutorThread(81): ADDED pid=-1, state=WAITING_TIMEOUT; org.apache.hadoop.hbase.master.assignment.AssignmentManager$RegionInTransitionChore; timeout=60000, timestamp=1731907203167 2024-11-18T05:19:03,168 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] procedure2.TimeoutExecutorThread(81): ADDED pid=-1, state=WAITING_TIMEOUT; org.apache.hadoop.hbase.master.assignment.AssignmentManager$DeadServerMetricRegionChore; timeout=120000, timestamp=1731907263168 2024-11-18T05:19:03,168 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] assignment.AssignmentManager(1766): Joined the cluster in 48 msec 2024-11-18T05:19:03,190 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=7cf745f7364a,39359,1731907138502-ClusterStatusChore, period=60000, unit=MILLISECONDS is enabled. 2024-11-18T05:19:03,191 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=7cf745f7364a,39359,1731907138502-BalancerChore, period=300000, unit=MILLISECONDS is enabled. 2024-11-18T05:19:03,191 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=7cf745f7364a,39359,1731907138502-RegionNormalizerChore, period=300000, unit=MILLISECONDS is enabled. 2024-11-18T05:19:03,192 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=CatalogJanitor-7cf745f7364a:39359, period=300000, unit=MILLISECONDS is enabled. 2024-11-18T05:19:03,193 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=HbckChore-, period=3600000, unit=MILLISECONDS is enabled. 2024-11-18T05:19:03,198 DEBUG [master/7cf745f7364a:0.Chore.1 {}] janitor.CatalogJanitor(179): 2024-11-18T05:19:03,201 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] master.TableNamespaceManager(92): Namespace table not found. Creating... 2024-11-18T05:19:03,202 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] master.HMaster(2425): Client=null/null create 'hbase:namespace', {NAME => 'info', INDEX_BLOCK_ENCODING => 'NONE', VERSIONS => '10', KEEP_DELETED_CELLS => 'FALSE', DATA_BLOCK_ENCODING => 'NONE', TTL => 'FOREVER', MIN_VERSIONS => '0', REPLICATION_SCOPE => '0', BLOOMFILTER => 'ROW', IN_MEMORY => 'true', COMPRESSION => 'NONE', BLOCKCACHE => 'true', BLOCKSIZE => '8192 B (8KB)'} 2024-11-18T05:19:03,208 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] procedure2.ProcedureExecutor(1098): Stored pid=4, state=RUNNABLE:CREATE_TABLE_PRE_OPERATION; CreateTableProcedure table=hbase:namespace 2024-11-18T05:19:03,211 INFO [PEWorker-2 {}] procedure.CreateTableProcedure(89): pid=4, state=RUNNABLE:CREATE_TABLE_PRE_OPERATION, locked=true; CreateTableProcedure table=hbase:namespace execute state=CREATE_TABLE_PRE_OPERATION 2024-11-18T05:19:03,212 DEBUG [PEWorker-2 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-11-18T05:19:03,214 INFO [PEWorker-2 {}] procedure.CreateTableProcedure(89): pid=4, state=RUNNABLE:CREATE_TABLE_WRITE_FS_LAYOUT, locked=true; CreateTableProcedure table=hbase:namespace execute state=CREATE_TABLE_WRITE_FS_LAYOUT 2024-11-18T05:19:03,224 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38965 is added to blk_1073741835_1011 (size=358) 2024-11-18T05:19:03,628 INFO [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(7106): creating {ENCODED => fc40d990d84dd61268a80bc76a9a24b6, NAME => 'hbase:namespace,,1731907143201.fc40d990d84dd61268a80bc76a9a24b6.', STARTKEY => '', ENDKEY => ''}, tableDescriptor='hbase:namespace', {TABLE_ATTRIBUTES => {METADATA => {'hbase.store.file-tracker.impl' => 'DEFAULT'}}}, {NAME => 'info', INDEX_BLOCK_ENCODING => 'NONE', VERSIONS => '10', KEEP_DELETED_CELLS => 'FALSE', DATA_BLOCK_ENCODING => 'NONE', TTL => 'FOREVER', MIN_VERSIONS => '0', REPLICATION_SCOPE => '0', BLOOMFILTER => 'ROW', IN_MEMORY => 'true', COMPRESSION => 'NONE', BLOCKCACHE => 'true', BLOCKSIZE => '8192 B (8KB)'}, regionDir=hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc 2024-11-18T05:19:03,637 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38965 is added to blk_1073741836_1012 (size=42) 2024-11-18T05:19:04,038 DEBUG [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(894): Instantiated hbase:namespace,,1731907143201.fc40d990d84dd61268a80bc76a9a24b6.; StoreHotnessProtector, parallelPutToStoreThreadLimit=0 ; minColumnNum=100 ; preparePutThreadLimit=0 ; hotProtect now disable 2024-11-18T05:19:04,039 DEBUG [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(1681): Closing fc40d990d84dd61268a80bc76a9a24b6, disabling compactions & flushes 2024-11-18T05:19:04,039 INFO [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(1703): Closing region hbase:namespace,,1731907143201.fc40d990d84dd61268a80bc76a9a24b6. 2024-11-18T05:19:04,039 DEBUG [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(1724): Waiting without time limit for close lock on hbase:namespace,,1731907143201.fc40d990d84dd61268a80bc76a9a24b6. 2024-11-18T05:19:04,039 DEBUG [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(1791): Acquired close lock on hbase:namespace,,1731907143201.fc40d990d84dd61268a80bc76a9a24b6. after waiting 0 ms 2024-11-18T05:19:04,039 DEBUG [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(1801): Updates disabled for region hbase:namespace,,1731907143201.fc40d990d84dd61268a80bc76a9a24b6. 2024-11-18T05:19:04,039 INFO [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(1922): Closed hbase:namespace,,1731907143201.fc40d990d84dd61268a80bc76a9a24b6. 2024-11-18T05:19:04,039 DEBUG [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(1635): Region close journal for fc40d990d84dd61268a80bc76a9a24b6: 2024-11-18T05:19:04,042 INFO [PEWorker-2 {}] procedure.CreateTableProcedure(89): pid=4, state=RUNNABLE:CREATE_TABLE_ADD_TO_META, locked=true; CreateTableProcedure table=hbase:namespace execute state=CREATE_TABLE_ADD_TO_META 2024-11-18T05:19:04,050 DEBUG [PEWorker-2 {}] hbase.MetaTableAccessor(2113): Put {"totalColumns":2,"row":"hbase:namespace,,1731907143201.fc40d990d84dd61268a80bc76a9a24b6.","families":{"info":[{"qualifier":"regioninfo","vlen":41,"tag":[],"timestamp":"1731907144044"},{"qualifier":"state","vlen":6,"tag":[],"timestamp":"1731907144044"}]},"ts":"1731907144044"} 2024-11-18T05:19:04,078 INFO [PEWorker-2 {}] hbase.MetaTableAccessor(1516): Added 1 regions to meta. 2024-11-18T05:19:04,080 INFO [PEWorker-2 {}] procedure.CreateTableProcedure(89): pid=4, state=RUNNABLE:CREATE_TABLE_ASSIGN_REGIONS, locked=true; CreateTableProcedure table=hbase:namespace execute state=CREATE_TABLE_ASSIGN_REGIONS 2024-11-18T05:19:04,083 DEBUG [PEWorker-2 {}] hbase.MetaTableAccessor(2113): Put {"totalColumns":1,"row":"hbase:namespace","families":{"table":[{"qualifier":"state","vlen":2,"tag":[],"timestamp":"1731907144081"}]},"ts":"1731907144081"} 2024-11-18T05:19:04,088 INFO [PEWorker-2 {}] hbase.MetaTableAccessor(1655): Updated tableName=hbase:namespace, state=ENABLING in hbase:meta 2024-11-18T05:19:04,094 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=5, ppid=4, state=RUNNABLE:REGION_STATE_TRANSITION_GET_ASSIGN_CANDIDATE; TransitRegionStateProcedure table=hbase:namespace, region=fc40d990d84dd61268a80bc76a9a24b6, ASSIGN}] 2024-11-18T05:19:04,096 INFO [PEWorker-3 {}] procedure.MasterProcedureScheduler(786): Took xlock for pid=5, ppid=4, state=RUNNABLE:REGION_STATE_TRANSITION_GET_ASSIGN_CANDIDATE; TransitRegionStateProcedure table=hbase:namespace, region=fc40d990d84dd61268a80bc76a9a24b6, ASSIGN 2024-11-18T05:19:04,098 INFO [PEWorker-3 {}] assignment.TransitRegionStateProcedure(264): Starting pid=5, ppid=4, state=RUNNABLE:REGION_STATE_TRANSITION_GET_ASSIGN_CANDIDATE, locked=true; TransitRegionStateProcedure table=hbase:namespace, region=fc40d990d84dd61268a80bc76a9a24b6, ASSIGN; state=OFFLINE, location=7cf745f7364a,32867,1731907139252; forceNewPlan=false, retain=false 2024-11-18T05:19:04,249 INFO [PEWorker-4 {}] assignment.RegionStateStore(202): pid=5 updating hbase:meta row=fc40d990d84dd61268a80bc76a9a24b6, regionState=OPENING, regionLocation=7cf745f7364a,32867,1731907139252 2024-11-18T05:19:04,253 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=6, ppid=5, state=RUNNABLE; OpenRegionProcedure fc40d990d84dd61268a80bc76a9a24b6, server=7cf745f7364a,32867,1731907139252}] 2024-11-18T05:19:04,407 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:04,414 INFO [RS_OPEN_PRIORITY_REGION-regionserver/7cf745f7364a:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] handler.AssignRegionHandler(135): Open hbase:namespace,,1731907143201.fc40d990d84dd61268a80bc76a9a24b6. 2024-11-18T05:19:04,414 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/7cf745f7364a:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(7285): Opening region: {ENCODED => fc40d990d84dd61268a80bc76a9a24b6, NAME => 'hbase:namespace,,1731907143201.fc40d990d84dd61268a80bc76a9a24b6.', STARTKEY => '', ENDKEY => ''} 2024-11-18T05:19:04,414 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/7cf745f7364a:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.MetricsRegionSourceImpl(79): Creating new MetricsRegionSourceImpl for table namespace fc40d990d84dd61268a80bc76a9a24b6 2024-11-18T05:19:04,414 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/7cf745f7364a:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(894): Instantiated hbase:namespace,,1731907143201.fc40d990d84dd61268a80bc76a9a24b6.; StoreHotnessProtector, parallelPutToStoreThreadLimit=0 ; minColumnNum=100 ; preparePutThreadLimit=0 ; hotProtect now disable 2024-11-18T05:19:04,415 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/7cf745f7364a:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(7327): checking encryption for fc40d990d84dd61268a80bc76a9a24b6 2024-11-18T05:19:04,415 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/7cf745f7364a:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(7330): checking classloading for fc40d990d84dd61268a80bc76a9a24b6 2024-11-18T05:19:04,417 INFO [StoreOpener-fc40d990d84dd61268a80bc76a9a24b6-1 {}] regionserver.HStore(400): Created cacheConfig: cacheDataOnRead=true, cacheDataOnWrite=false, cacheIndexesOnWrite=false, cacheBloomsOnWrite=false, cacheEvictOnClose=false, cacheDataCompressed=false, prefetchOnOpen=false, for column family info of region fc40d990d84dd61268a80bc76a9a24b6 2024-11-18T05:19:04,420 INFO [StoreOpener-fc40d990d84dd61268a80bc76a9a24b6-1 {}] compactions.CompactionConfiguration(181): size [minCompactSize:128 MB, maxCompactSize:8.00 EB, offPeakMaxCompactSize:8.00 EB); files [minFilesToCompact:3, maxFilesToCompact:10); ratio 1.200000; off-peak ratio 5.000000; throttle point 2684354560; major period 604800000, major jitter 0.500000, min locality to compact 0.000000; tiered compaction: max_age 9223372036854775807, incoming window min 6, compaction policy for tiered window org.apache.hadoop.hbase.regionserver.compactions.ExploringCompactionPolicy, single output for minor true, compaction window factory org.apache.hadoop.hbase.regionserver.compactions.ExponentialCompactionWindowFactory, region fc40d990d84dd61268a80bc76a9a24b6 columnFamilyName info 2024-11-18T05:19:04,421 DEBUG [StoreOpener-fc40d990d84dd61268a80bc76a9a24b6-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-11-18T05:19:04,421 INFO [StoreOpener-fc40d990d84dd61268a80bc76a9a24b6-1 {}] regionserver.HStore(327): Store=fc40d990d84dd61268a80bc76a9a24b6/info, memstore type=DefaultMemStore, storagePolicy=NONE, verifyBulkLoads=false, parallelPutCountPrintThreshold=50, encoding=NONE, compression=NONE 2024-11-18T05:19:04,423 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/7cf745f7364a:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(5301): Found 0 recovered edits file(s) under hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/data/hbase/namespace/fc40d990d84dd61268a80bc76a9a24b6 2024-11-18T05:19:04,424 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/7cf745f7364a:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(5301): Found 0 recovered edits file(s) under hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/data/hbase/namespace/fc40d990d84dd61268a80bc76a9a24b6 2024-11-18T05:19:04,428 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/7cf745f7364a:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(1085): writing seq id for fc40d990d84dd61268a80bc76a9a24b6 2024-11-18T05:19:04,432 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/7cf745f7364a:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] wal.WALSplitUtil(409): Wrote file=hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/data/hbase/namespace/fc40d990d84dd61268a80bc76a9a24b6/recovered.edits/1.seqid, newMaxSeqId=1, maxSeqId=-1 2024-11-18T05:19:04,433 INFO [RS_OPEN_PRIORITY_REGION-regionserver/7cf745f7364a:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(1102): Opened fc40d990d84dd61268a80bc76a9a24b6; next sequenceid=2; SteppingSplitPolicysuper{IncreasingToUpperBoundRegionSplitPolicy{initialSize=268435456, ConstantSizeRegionSplitPolicy{desiredMaxFileSize=64604231, jitterRate=-0.03732194006443024}}}, FlushLargeStoresPolicy{flushSizeLowerBound=-1} 2024-11-18T05:19:04,434 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/7cf745f7364a:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(1001): Region open journal for fc40d990d84dd61268a80bc76a9a24b6: 2024-11-18T05:19:04,437 INFO [RS_OPEN_PRIORITY_REGION-regionserver/7cf745f7364a:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegionServer(2601): Post open deploy tasks for hbase:namespace,,1731907143201.fc40d990d84dd61268a80bc76a9a24b6., pid=6, masterSystemTime=1731907144407 2024-11-18T05:19:04,442 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/7cf745f7364a:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegionServer(2628): Finished post open deploy task for hbase:namespace,,1731907143201.fc40d990d84dd61268a80bc76a9a24b6. 2024-11-18T05:19:04,442 INFO [RS_OPEN_PRIORITY_REGION-regionserver/7cf745f7364a:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] handler.AssignRegionHandler(164): Opened hbase:namespace,,1731907143201.fc40d990d84dd61268a80bc76a9a24b6. 2024-11-18T05:19:04,444 INFO [PEWorker-5 {}] assignment.RegionStateStore(202): pid=5 updating hbase:meta row=fc40d990d84dd61268a80bc76a9a24b6, regionState=OPEN, openSeqNum=2, regionLocation=7cf745f7364a,32867,1731907139252 2024-11-18T05:19:04,468 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=6, resume processing ppid=5 2024-11-18T05:19:04,470 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=6, ppid=5, state=SUCCESS; OpenRegionProcedure fc40d990d84dd61268a80bc76a9a24b6, server=7cf745f7364a,32867,1731907139252 in 196 msec 2024-11-18T05:19:04,474 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=5, resume processing ppid=4 2024-11-18T05:19:04,474 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=5, ppid=4, state=SUCCESS; TransitRegionStateProcedure table=hbase:namespace, region=fc40d990d84dd61268a80bc76a9a24b6, ASSIGN in 375 msec 2024-11-18T05:19:04,476 INFO [PEWorker-2 {}] procedure.CreateTableProcedure(89): pid=4, state=RUNNABLE:CREATE_TABLE_UPDATE_DESC_CACHE, locked=true; CreateTableProcedure table=hbase:namespace execute state=CREATE_TABLE_UPDATE_DESC_CACHE 2024-11-18T05:19:04,476 DEBUG [PEWorker-2 {}] hbase.MetaTableAccessor(2113): Put {"totalColumns":1,"row":"hbase:namespace","families":{"table":[{"qualifier":"state","vlen":2,"tag":[],"timestamp":"1731907144476"}]},"ts":"1731907144476"} 2024-11-18T05:19:04,480 INFO [PEWorker-2 {}] hbase.MetaTableAccessor(1655): Updated tableName=hbase:namespace, state=ENABLED in hbase:meta 2024-11-18T05:19:04,486 INFO [PEWorker-2 {}] procedure.CreateTableProcedure(89): pid=4, state=RUNNABLE:CREATE_TABLE_POST_OPERATION, locked=true; CreateTableProcedure table=hbase:namespace execute state=CREATE_TABLE_POST_OPERATION 2024-11-18T05:19:04,490 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=4, state=SUCCESS; CreateTableProcedure table=hbase:namespace in 1.2830 sec 2024-11-18T05:19:04,513 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] zookeeper.ZKUtil(113): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Set watcher on znode that does not yet exist, /hbase/namespace 2024-11-18T05:19:04,516 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-11-18T05:19:04,516 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeCreated, state=SyncConnected, path=/hbase/namespace 2024-11-18T05:19:04,516 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-11-18T05:19:04,569 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] procedure2.ProcedureExecutor(1098): Stored pid=7, state=RUNNABLE:CREATE_NAMESPACE_PREPARE; CreateNamespaceProcedure, namespace=default 2024-11-18T05:19:04,592 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/namespace 2024-11-18T05:19:04,608 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=7, state=SUCCESS; CreateNamespaceProcedure, namespace=default in 38 msec 2024-11-18T05:19:04,617 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] procedure2.ProcedureExecutor(1098): Stored pid=8, state=RUNNABLE:CREATE_NAMESPACE_PREPARE; CreateNamespaceProcedure, namespace=hbase 2024-11-18T05:19:04,632 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/namespace 2024-11-18T05:19:04,638 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=8, state=SUCCESS; CreateNamespaceProcedure, namespace=hbase in 20 msec 2024-11-18T05:19:04,654 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDataChanged, state=SyncConnected, path=/hbase/namespace/default 2024-11-18T05:19:04,657 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDataChanged, state=SyncConnected, path=/hbase/namespace/hbase 2024-11-18T05:19:04,658 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] master.HMaster(1218): Master has completed initialization 5.331sec 2024-11-18T05:19:04,659 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] quotas.MasterQuotaManager(97): Quota support disabled 2024-11-18T05:19:04,661 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] slowlog.SlowLogMasterService(57): Slow/Large requests logging to system table hbase:slowlog is disabled. Quitting. 2024-11-18T05:19:04,662 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] waleventtracker.WALEventTrackerTableCreator(75): wal event tracker requests logging to table REPLICATION.WALEVENTTRACKER is disabled. Quitting. 2024-11-18T05:19:04,662 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] master.ReplicationSinkTrackerTableCreator(90): replication sink tracker requests logging to table REPLICATION.SINK_TRACKER is disabled. Quitting. 2024-11-18T05:19:04,663 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] zookeeper.ZKWatcher(271): not a secure deployment, proceeding 2024-11-18T05:19:04,663 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=7cf745f7364a,39359,1731907138502-MobFileCleanerChore, period=86400, unit=SECONDS is enabled. 2024-11-18T05:19:04,664 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=7cf745f7364a,39359,1731907138502-MobFileCompactionChore, period=604800, unit=SECONDS is enabled. 2024-11-18T05:19:04,672 DEBUG [master/7cf745f7364a:0:becomeActiveMaster {}] master.HMaster(1321): Balancer post startup initialization complete, took 0 seconds 2024-11-18T05:19:04,673 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=RollingUpgradeChore, period=10, unit=SECONDS is enabled. 2024-11-18T05:19:04,674 INFO [master/7cf745f7364a:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=7cf745f7364a,39359,1731907138502-OldWALsDirSizeChore, period=300000, unit=MILLISECONDS is enabled. 2024-11-18T05:19:04,712 DEBUG [Time-limited test {}] zookeeper.ReadOnlyZKClient(149): Connect 0x7502c059 to 127.0.0.1:61937 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@6ea82e8f 2024-11-18T05:19:04,713 WARN [Time-limited test {}] client.ZKConnectionRegistry(90): ZKConnectionRegistry is deprecated. See https://hbase.apache.org/book.html#client.rpcconnectionregistry 2024-11-18T05:19:04,735 DEBUG [Time-limited test {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodec@707adb81, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-11-18T05:19:04,739 DEBUG [Time-limited test {}] nio.NioEventLoop(110): -Dio.netty.noKeySetOptimization: false 2024-11-18T05:19:04,739 DEBUG [Time-limited test {}] nio.NioEventLoop(111): -Dio.netty.selectorAutoRebuildThreshold: 512 2024-11-18T05:19:04,751 DEBUG [hconnection-0x3e1871-shared-pool-0 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=ClientService, sasl=false 2024-11-18T05:19:04,763 INFO [RS-EventLoopGroup-3-1 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.2:60222, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=ClientService 2024-11-18T05:19:04,776 INFO [Time-limited test {}] hbase.HBaseTestingUtility(1199): Minicluster is up; activeMaster=7cf745f7364a,39359,1731907138502 2024-11-18T05:19:04,779 DEBUG [Time-limited test {}] zookeeper.ReadOnlyZKClient(149): Connect 0x57d89e0d to 127.0.0.1:61937 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@7d7b22aa 2024-11-18T05:19:04,798 DEBUG [ReadOnlyZKClient-127.0.0.1:61937@0x57d89e0d {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodec@3b1ff493, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-11-18T05:19:04,826 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testRemovePeerTableCFs[0] Thread=222, OpenFileDescriptor=448, MaxFileDescriptor=1048576, SystemLoadAverage=400, ProcessCount=11, AvailableMemoryMB=12123 2024-11-18T05:19:04,904 DEBUG [Time-limited test {}] client.ConnectionUtils(573): Start fetching master stub from registry 2024-11-18T05:19:04,915 DEBUG [ReadOnlyZKClient-127.0.0.1:61937@0x57d89e0d {}] client.AsyncConnectionImpl(310): The fetched master address is 7cf745f7364a,39359,1731907138502 2024-11-18T05:19:04,918 DEBUG [ReadOnlyZKClient-127.0.0.1:61937@0x57d89e0d {}] client.ConnectionUtils(581): The fetched master stub is org.apache.hadoop.hbase.shaded.protobuf.generated.MasterProtos$MasterService$Stub@3310d9de 2024-11-18T05:19:04,920 DEBUG [ReadOnlyZKClient-127.0.0.1:61937@0x57d89e0d {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=MasterService, sasl=false 2024-11-18T05:19:04,924 INFO [RS-EventLoopGroup-1-3 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.2:35970, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=MasterService 2024-11-18T05:19:04,925 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-11-18T05:19:04,934 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=9, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-11-18T05:19:04,945 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=9 2024-11-18T05:19:04,960 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:04,962 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:04,965 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id0x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:04,968 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0004 connected 2024-11-18T05:19:05,054 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=9 2024-11-18T05:19:05,072 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0004, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:05,081 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-11-18T05:19:05,081 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-11-18T05:19:05,093 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=10, ppid=9, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:05,258 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:05,260 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=10 2024-11-18T05:19:05,262 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=10}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-11-18T05:19:05,263 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=9 2024-11-18T05:19:05,284 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=10}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:05,308 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=10}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-11-18T05:19:05,323 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=10}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=10 2024-11-18T05:19:05,325 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=10 2024-11-18T05:19:05,331 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:05,335 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=10, resume processing ppid=9 2024-11-18T05:19:05,335 INFO [PEWorker-4 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-11-18T05:19:05,335 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=10, ppid=9, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 238 msec 2024-11-18T05:19:05,338 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=9, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 408 msec 2024-11-18T05:19:05,373 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x6e0a8d0f to 127.0.0.1:61937 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@48202db0 2024-11-18T05:19:05,378 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-11-18T05:19:05,380 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-11-18T05:19:05,381 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@5cc77199, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-11-18T05:19:05,383 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:05,388 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:05,388 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1000911699b0006 connected 2024-11-18T05:19:05,389 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-11-18T05:19:05,574 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=9 2024-11-18T05:19:05,575 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-11-18T05:19:05,579 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-11-18T05:19:05,585 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=11, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-11-18T05:19:05,587 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=11 2024-11-18T05:19:05,611 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:05,612 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:05,615 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id0x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:05,616 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0007 connected 2024-11-18T05:19:05,694 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=11 2024-11-18T05:19:05,718 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0007, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:05,725 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=12, ppid=11, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:05,878 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:05,879 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=12 2024-11-18T05:19:05,879 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=12}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-11-18T05:19:05,882 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=12}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-11-18T05:19:05,883 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=12}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-11-18T05:19:05,883 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-11-18T05:19:05,883 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1000911699b0006, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:05,883 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1000911699b0006, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:05,903 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=11 2024-11-18T05:19:05,986 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1000911699b0006, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:05,987 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=12}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x6e0a8d0f to 127.0.0.1:61937 2024-11-18T05:19:05,987 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=12}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-11-18T05:19:06,005 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=12}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-11-18T05:19:06,006 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=12}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-11-18T05:19:06,006 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=12}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=12 2024-11-18T05:19:06,007 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=12 2024-11-18T05:19:06,011 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:06,015 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=12, resume processing ppid=11 2024-11-18T05:19:06,015 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=12, ppid=11, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 286 msec 2024-11-18T05:19:06,015 INFO [PEWorker-2 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-11-18T05:19:06,018 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=11, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 435 msec 2024-11-18T05:19:06,052 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x00574d43 to 127.0.0.1:61937 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@78d7f1f4 2024-11-18T05:19:06,056 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-11-18T05:19:06,056 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-11-18T05:19:06,057 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@5ee93e5a, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-11-18T05:19:06,059 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:06,075 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:06,076 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-11-18T05:19:06,077 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1000911699b0009 connected 2024-11-18T05:19:06,213 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=11 2024-11-18T05:19:06,214 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-11-18T05:19:06,218 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:06,220 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:06,221 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:06,223 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst2=[cf1], testRemovePeerTableCFst1=null},bandwidth=0,serial=false 2024-11-18T05:19:06,226 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=13, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-11-18T05:19:06,228 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=13 2024-11-18T05:19:06,251 INFO [PEWorker-4 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:06,253 INFO [PEWorker-4 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:06,256 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id0x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:06,257 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b000a connected 2024-11-18T05:19:06,343 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=13 2024-11-18T05:19:06,359 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b000a, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:06,367 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=14, ppid=13, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:06,520 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:06,521 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=14 2024-11-18T05:19:06,521 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=14}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-11-18T05:19:06,523 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=14}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-11-18T05:19:06,523 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=14}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-11-18T05:19:06,523 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-11-18T05:19:06,524 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1000911699b0009, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:06,524 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1000911699b0009, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:06,554 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=13 2024-11-18T05:19:06,626 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1000911699b0009, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:06,627 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=14}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x00574d43 to 127.0.0.1:61937 2024-11-18T05:19:06,627 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=14}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-11-18T05:19:06,651 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=14}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-11-18T05:19:06,651 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=14}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-11-18T05:19:06,651 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=14}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=14 2024-11-18T05:19:06,652 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=14 2024-11-18T05:19:06,656 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:06,663 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=14, resume processing ppid=13 2024-11-18T05:19:06,663 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=14, ppid=13, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 289 msec 2024-11-18T05:19:06,663 INFO [PEWorker-5 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst2=[cf1], testRemovePeerTableCFst1=null},bandwidth=0,serial=false 2024-11-18T05:19:06,666 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=13, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 440 msec 2024-11-18T05:19:06,695 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x2d6168cd to 127.0.0.1:61937 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@44dbed4f 2024-11-18T05:19:06,699 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-11-18T05:19:06,700 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-11-18T05:19:06,700 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@527d1b2f, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-11-18T05:19:06,702 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:06,704 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:06,705 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-11-18T05:19:06,712 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1000911699b000c connected 2024-11-18T05:19:06,864 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=13 2024-11-18T05:19:06,865 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-11-18T05:19:06,866 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:06,868 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:06,869 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:06,871 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:06,872 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst2=[cf1]},bandwidth=0,serial=false 2024-11-18T05:19:06,874 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=15, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-11-18T05:19:06,877 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=15 2024-11-18T05:19:06,895 INFO [PEWorker-2 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:06,896 INFO [PEWorker-2 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:06,902 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id0x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:06,903 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b000d connected 2024-11-18T05:19:06,983 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=15 2024-11-18T05:19:07,005 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b000d, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:07,011 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=16, ppid=15, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:07,165 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:07,166 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=16 2024-11-18T05:19:07,166 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=16}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-11-18T05:19:07,168 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=16}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-11-18T05:19:07,168 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=16}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-11-18T05:19:07,168 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-11-18T05:19:07,168 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1000911699b000c, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:07,169 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1000911699b000c, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:07,194 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=15 2024-11-18T05:19:07,271 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1000911699b000c, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:07,271 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=16}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x2d6168cd to 127.0.0.1:61937 2024-11-18T05:19:07,272 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=16}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-11-18T05:19:07,290 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=16}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-11-18T05:19:07,290 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=16}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-11-18T05:19:07,290 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=16}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=16 2024-11-18T05:19:07,291 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=16 2024-11-18T05:19:07,295 INFO [PEWorker-1 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:07,300 INFO [PEWorker-3 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst2=[cf1]},bandwidth=0,serial=false 2024-11-18T05:19:07,300 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=16, resume processing ppid=15 2024-11-18T05:19:07,300 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=16, ppid=15, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 284 msec 2024-11-18T05:19:07,303 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=15, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 427 msec 2024-11-18T05:19:07,324 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x3225c6f1 to 127.0.0.1:61937 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@a4372f2 2024-11-18T05:19:07,328 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-11-18T05:19:07,328 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-11-18T05:19:07,328 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@579d451, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-11-18T05:19:07,330 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:07,332 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:07,333 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-11-18T05:19:07,333 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1000911699b000f connected 2024-11-18T05:19:07,503 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=15 2024-11-18T05:19:07,504 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-11-18T05:19:07,504 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:07,506 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:07,507 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:07,508 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-11-18T05:19:07,510 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=17, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-11-18T05:19:07,512 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=17 2024-11-18T05:19:07,535 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:07,536 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:07,539 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id0x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:07,540 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0010 connected 2024-11-18T05:19:07,623 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=17 2024-11-18T05:19:07,642 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0010, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:07,647 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=18, ppid=17, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:07,801 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:07,802 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=18 2024-11-18T05:19:07,802 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=18}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-11-18T05:19:07,804 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=18}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-11-18T05:19:07,804 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=18}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-11-18T05:19:07,804 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-11-18T05:19:07,804 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1000911699b000f, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:07,804 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1000911699b000f, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:07,821 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsTableSourceImpl(133): Creating new MetricsTableSourceImpl for table 'hbase:meta' 2024-11-18T05:19:07,823 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsTableSourceImpl(133): Creating new MetricsTableSourceImpl for table 'hbase:namespace' 2024-11-18T05:19:07,833 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=17 2024-11-18T05:19:07,908 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1000911699b000f, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:07,908 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=18}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x3225c6f1 to 127.0.0.1:61937 2024-11-18T05:19:07,909 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=18}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-11-18T05:19:07,948 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=18}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-11-18T05:19:07,948 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=18}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-11-18T05:19:07,948 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=18}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=18 2024-11-18T05:19:07,950 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=18 2024-11-18T05:19:07,954 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:07,958 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=18, resume processing ppid=17 2024-11-18T05:19:07,958 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=18, ppid=17, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 307 msec 2024-11-18T05:19:07,958 INFO [PEWorker-2 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-11-18T05:19:07,961 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=17, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 450 msec 2024-11-18T05:19:07,996 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x62baa526 to 127.0.0.1:61937 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@29b9f159 2024-11-18T05:19:08,021 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-11-18T05:19:08,021 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-11-18T05:19:08,022 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@33190185, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-11-18T05:19:08,024 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:08,027 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:08,028 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-11-18T05:19:08,029 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1000911699b0012 connected 2024-11-18T05:19:08,144 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=17 2024-11-18T05:19:08,144 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-11-18T05:19:08,145 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:08,146 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:08,148 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst4=null},bandwidth=0,serial=false 2024-11-18T05:19:08,149 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=19, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-11-18T05:19:08,151 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=19 2024-11-18T05:19:08,170 INFO [PEWorker-3 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:08,171 INFO [PEWorker-3 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:08,174 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id0x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:08,174 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0013 connected 2024-11-18T05:19:08,254 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=19 2024-11-18T05:19:08,276 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0013, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:08,281 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=20, ppid=19, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:08,434 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:08,435 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=20 2024-11-18T05:19:08,435 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=20}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-11-18T05:19:08,437 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=20}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-11-18T05:19:08,437 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=20}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-11-18T05:19:08,437 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-11-18T05:19:08,438 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1000911699b0012, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:08,438 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1000911699b0012, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:08,463 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=19 2024-11-18T05:19:08,541 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1000911699b0012, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:08,541 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=20}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x62baa526 to 127.0.0.1:61937 2024-11-18T05:19:08,541 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=20}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-11-18T05:19:08,565 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=20}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-11-18T05:19:08,566 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=20}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-11-18T05:19:08,566 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=20}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=20 2024-11-18T05:19:08,567 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=20 2024-11-18T05:19:08,568 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-11-18T05:19:08,573 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:08,577 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=20, resume processing ppid=19 2024-11-18T05:19:08,577 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=20, ppid=19, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 292 msec 2024-11-18T05:19:08,577 INFO [PEWorker-4 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst4=null},bandwidth=0,serial=false 2024-11-18T05:19:08,579 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=19, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 429 msec 2024-11-18T05:19:08,604 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x64897f8a to 127.0.0.1:61937 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@2a4c6aca 2024-11-18T05:19:08,618 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-11-18T05:19:08,618 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-11-18T05:19:08,618 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@1380e2d0, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-11-18T05:19:08,621 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:08,625 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:08,626 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-11-18T05:19:08,626 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1000911699b0015 connected 2024-11-18T05:19:08,774 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=19 2024-11-18T05:19:08,774 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-11-18T05:19:08,775 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:08,776 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-11-18T05:19:08,778 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=21, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-11-18T05:19:08,779 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=21 2024-11-18T05:19:08,803 INFO [PEWorker-2 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:08,804 INFO [PEWorker-2 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:08,807 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id0x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:08,807 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0016 connected 2024-11-18T05:19:08,883 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=21 2024-11-18T05:19:08,909 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0016, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:08,915 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=22, ppid=21, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:09,011 DEBUG [HBase-Metrics2-1 {}] impl.GlobalMetricRegistriesAdapter(131): Registering adapter for the MetricRegistry: RegionServer,sub=TableRequests_Namespace_hbase_table_meta 2024-11-18T05:19:09,012 INFO [HBase-Metrics2-1 {}] impl.GlobalMetricRegistriesAdapter(135): Registering RegionServer,sub=TableRequests_Namespace_hbase_table_meta Metrics about Tables on a single HBase RegionServer 2024-11-18T05:19:09,015 DEBUG [HBase-Metrics2-1 {}] impl.GlobalMetricRegistriesAdapter(131): Registering adapter for the MetricRegistry: RegionServer,sub=TableRequests_Namespace_hbase_table_namespace 2024-11-18T05:19:09,016 INFO [HBase-Metrics2-1 {}] impl.GlobalMetricRegistriesAdapter(135): Registering RegionServer,sub=TableRequests_Namespace_hbase_table_namespace Metrics about Tables on a single HBase RegionServer 2024-11-18T05:19:09,017 DEBUG [HBase-Metrics2-1 {}] impl.GlobalMetricRegistriesAdapter(131): Registering adapter for the MetricRegistry: RegionServer,sub=Coprocessor.Region.CP_org.apache.hadoop.hbase.coprocessor.MultiRowMutationEndpoint 2024-11-18T05:19:09,017 INFO [HBase-Metrics2-1 {}] impl.GlobalMetricRegistriesAdapter(135): Registering RegionServer,sub=Coprocessor.Region.CP_org.apache.hadoop.hbase.coprocessor.MultiRowMutationEndpoint Metrics about HBase RegionObservers 2024-11-18T05:19:09,018 DEBUG [HBase-Metrics2-1 {}] impl.GlobalMetricRegistriesAdapter(131): Registering adapter for the MetricRegistry: RegionServer,sub=TableRequests_Namespace_master_table_store 2024-11-18T05:19:09,018 INFO [HBase-Metrics2-1 {}] impl.GlobalMetricRegistriesAdapter(135): Registering RegionServer,sub=TableRequests_Namespace_master_table_store Metrics about Tables on a single HBase RegionServer 2024-11-18T05:19:09,068 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:09,068 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=22 2024-11-18T05:19:09,069 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=22}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-11-18T05:19:09,070 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=22}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-11-18T05:19:09,070 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=22}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-11-18T05:19:09,071 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-11-18T05:19:09,071 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1000911699b0015, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:09,071 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1000911699b0015, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:09,093 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=21 2024-11-18T05:19:09,173 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1000911699b0015, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:09,174 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=22}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x64897f8a to 127.0.0.1:61937 2024-11-18T05:19:09,174 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=22}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-11-18T05:19:09,194 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=22}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-11-18T05:19:09,194 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=22}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-11-18T05:19:09,195 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=22}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=22 2024-11-18T05:19:09,196 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=22 2024-11-18T05:19:09,201 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:09,205 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=22, resume processing ppid=21 2024-11-18T05:19:09,205 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=22, ppid=21, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 286 msec 2024-11-18T05:19:09,205 INFO [PEWorker-5 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-11-18T05:19:09,208 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=21, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 429 msec 2024-11-18T05:19:09,232 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x360623c4 to 127.0.0.1:61937 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@ab48e89 2024-11-18T05:19:09,247 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-11-18T05:19:09,248 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-11-18T05:19:09,248 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@665143b3, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-11-18T05:19:09,250 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:09,267 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:09,267 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-11-18T05:19:09,268 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1000911699b0018 connected 2024-11-18T05:19:09,403 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=21 2024-11-18T05:19:09,404 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-11-18T05:19:09,404 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:09,408 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-11-18T05:19:09,408 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-11-18T05:19:09,412 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=24, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-11-18T05:19:09,412 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=23, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-11-18T05:19:09,414 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-11-18T05:19:09,415 DEBUG [PEWorker-2 {}] procedure.MasterProcedureScheduler(583): PEER '1', shared lock count=0, exclusively locked by procId=23 2024-11-18T05:19:09,415 DEBUG [PEWorker-2 {}] procedure2.ProcedureExecutor(1470): LOCK_EVENT_WAIT pid=24, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-11-18T05:19:09,415 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=24 2024-11-18T05:19:09,417 DEBUG [PEWorker-4 {}] zookeeper.ZKUtil(111): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-11-18T05:19:09,420 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-11-18T05:19:09,420 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-11-18T05:19:09,420 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-11-18T05:19:09,422 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=25, ppid=23, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:09,523 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-11-18T05:19:09,523 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=24 2024-11-18T05:19:09,575 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:09,575 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=25 2024-11-18T05:19:09,576 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=25}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-11-18T05:19:09,576 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=25}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-11-18T05:19:09,576 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=25}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-11-18T05:19:09,576 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-11-18T05:19:09,576 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1000911699b0018, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:09,576 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1000911699b0018, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:09,679 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1000911699b0018, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:09,679 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=25}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x360623c4 to 127.0.0.1:61937 2024-11-18T05:19:09,679 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=25}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-11-18T05:19:09,679 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=25}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-11-18T05:19:09,682 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=25}] zookeeper.ZKUtil(111): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/1/7cf745f7364a%2C32867%2C1731907139252.1731907142013 2024-11-18T05:19:09,685 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/1/7cf745f7364a%2C32867%2C1731907139252.1731907142013 2024-11-18T05:19:09,685 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/1 2024-11-18T05:19:09,685 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/1 2024-11-18T05:19:09,685 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=25}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-11-18T05:19:09,686 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=25}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=25 2024-11-18T05:19:09,686 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=25 2024-11-18T05:19:09,690 INFO [PEWorker-1 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:09,693 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=25, resume processing ppid=23 2024-11-18T05:19:09,693 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=25, ppid=23, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 268 msec 2024-11-18T05:19:09,697 DEBUG [PEWorker-1 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-11-18T05:19:09,697 INFO [PEWorker-1 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-11-18T05:19:09,700 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=23, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 288 msec 2024-11-18T05:19:09,701 WARN [PEWorker-2 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-11-18T05:19:09,709 ERROR [PEWorker-2 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=24, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-11-18T05:19:09,711 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=24, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=301 msec 2024-11-18T05:19:09,711 WARN [PEWorker-2 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-11-18T05:19:09,734 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-11-18T05:19:09,734 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=24 2024-11-18T05:19:09,734 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-11-18T05:19:09,735 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-11-18T05:19:09,736 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-11-18T05:19:09,737 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=26, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-11-18T05:19:09,738 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=26 2024-11-18T05:19:09,738 WARN [PEWorker-4 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-11-18T05:19:09,739 ERROR [PEWorker-4 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=26, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-11-18T05:19:09,741 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=26, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=4 msec 2024-11-18T05:19:09,741 WARN [PEWorker-4 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-11-18T05:19:09,843 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=26 2024-11-18T05:19:09,844 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-11-18T05:19:09,845 INFO [Time-limited test {}] zookeeper.RecoverableZooKeeper(138): Process identifier=testing utility connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:09,849 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): testing utility0x0, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:09,849 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): testing utility-0x1000911699b0019 connected 2024-11-18T05:19:09,884 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testRemovePeerTableCFs[0] Thread=223 (was 222) Potentially hanging thread: RSProcedureDispatcher-pool-2 java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.poll(LinkedBlockingQueue.java:460) java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1061) java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) java.base@17.0.11/java.lang.Thread.run(Thread.java:840) Potentially hanging thread: RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) java.base@17.0.11/java.lang.Thread.run(Thread.java:840) Potentially hanging thread: Timer for 'HBase' metrics system java.base@17.0.11/java.lang.Object.wait(Native Method) java.base@17.0.11/java.util.TimerThread.mainLoop(Timer.java:563) java.base@17.0.11/java.util.TimerThread.run(Timer.java:516) Potentially hanging thread: ForkJoinPool.commonPool-worker-1 java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkUntil(LockSupport.java:410) java.base@17.0.11/java.util.concurrent.ForkJoinPool.awaitWork(ForkJoinPool.java:1726) java.base@17.0.11/java.util.concurrent.ForkJoinPool.runWorker(ForkJoinPool.java:1623) java.base@17.0.11/java.util.concurrent.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:165) Potentially hanging thread: RS-EventLoopGroup-1-3 app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait(Native Method) app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait(Native.java:220) app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait(Native.java:213) app//org.apache.hbase.thirdparty.io.netty.channel.epoll.EpollEventLoop.epollWaitNoTimerChange(EpollEventLoop.java:308) app//org.apache.hbase.thirdparty.io.netty.channel.epoll.EpollEventLoop.run(EpollEventLoop.java:365) app//org.apache.hbase.thirdparty.io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:997) app//org.apache.hbase.thirdparty.io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74) app//org.apache.hbase.thirdparty.io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) java.base@17.0.11/java.lang.Thread.run(Thread.java:840) Potentially hanging thread: RPCClient-NioEventLoopGroup-4-2 java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:141) app//org.apache.hbase.thirdparty.io.netty.channel.nio.SelectedSelectionKeySetSelector.select(SelectedSelectionKeySetSelector.java:62) app//org.apache.hbase.thirdparty.io.netty.channel.nio.NioEventLoop.select(NioEventLoop.java:883) app//org.apache.hbase.thirdparty.io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:526) app//org.apache.hbase.thirdparty.io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:997) app//org.apache.hbase.thirdparty.io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74) app//org.apache.hbase.thirdparty.io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) java.base@17.0.11/java.lang.Thread.run(Thread.java:840) - Thread LEAK? -, OpenFileDescriptor=452 (was 448) - OpenFileDescriptor LEAK? -, MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=392 (was 400), ProcessCount=11 (was 11), AvailableMemoryMB=12056 (was 12123) 2024-11-18T05:19:09,895 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testNamespacesAndTableCfsConfigConflict[0] Thread=223, OpenFileDescriptor=452, MaxFileDescriptor=1048576, SystemLoadAverage=392, ProcessCount=11, AvailableMemoryMB=12056 2024-11-18T05:19:09,896 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-11-18T05:19:09,898 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=27, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-11-18T05:19:09,899 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=27 2024-11-18T05:19:09,922 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:09,924 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:09,936 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id0x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:09,937 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b001a connected 2024-11-18T05:19:10,003 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=27 2024-11-18T05:19:10,038 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b001a, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:10,051 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=28, ppid=27, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:10,205 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:10,206 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=28 2024-11-18T05:19:10,206 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=28}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-11-18T05:19:10,213 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=27 2024-11-18T05:19:10,226 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=28}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:10,243 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=28}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-11-18T05:19:10,252 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=28}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=28 2024-11-18T05:19:10,252 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=28 2024-11-18T05:19:10,256 INFO [PEWorker-1 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:10,259 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=28, resume processing ppid=27 2024-11-18T05:19:10,259 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=28, ppid=27, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 205 msec 2024-11-18T05:19:10,259 INFO [PEWorker-1 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-11-18T05:19:10,262 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=27, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 363 msec 2024-11-18T05:19:10,290 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x237b2dd9 to 127.0.0.1:61937 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@3098f115 2024-11-18T05:19:10,294 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-11-18T05:19:10,295 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-11-18T05:19:10,295 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@46c5b6c7, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-11-18T05:19:10,296 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:10,299 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:10,299 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1000911699b001c connected 2024-11-18T05:19:10,299 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-11-18T05:19:10,523 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=27 2024-11-18T05:19:10,524 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-11-18T05:19:10,525 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-11-18T05:19:10,526 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=29, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-11-18T05:19:10,528 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=29 2024-11-18T05:19:10,545 INFO [PEWorker-4 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:10,546 INFO [PEWorker-4 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:10,549 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id0x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:10,549 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b001d connected 2024-11-18T05:19:10,633 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=29 2024-11-18T05:19:10,651 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b001d, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:10,656 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=30, ppid=29, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:10,809 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:10,810 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=30 2024-11-18T05:19:10,810 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=30}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-11-18T05:19:10,812 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=30}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-11-18T05:19:10,812 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=30}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-11-18T05:19:10,812 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-11-18T05:19:10,812 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1000911699b001c, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:10,813 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1000911699b001c, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:10,843 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=29 2024-11-18T05:19:10,915 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1000911699b001c, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:10,915 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=30}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x237b2dd9 to 127.0.0.1:61937 2024-11-18T05:19:10,915 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=30}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-11-18T05:19:10,931 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=30}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-11-18T05:19:10,932 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=30}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-11-18T05:19:10,932 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=30}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=30 2024-11-18T05:19:10,933 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=30 2024-11-18T05:19:10,936 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:10,939 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=30, resume processing ppid=29 2024-11-18T05:19:10,939 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=30, ppid=29, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 280 msec 2024-11-18T05:19:10,939 INFO [PEWorker-3 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-11-18T05:19:10,942 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=29, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 415 msec 2024-11-18T05:19:10,966 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x0f21ace1 to 127.0.0.1:61937 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@5c2894c2 2024-11-18T05:19:10,970 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-11-18T05:19:10,970 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-11-18T05:19:10,971 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@4f3f18b1, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-11-18T05:19:10,972 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:10,974 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:10,975 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-11-18T05:19:10,975 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1000911699b001f connected 2024-11-18T05:19:11,153 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=29 2024-11-18T05:19:11,154 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-11-18T05:19:11,155 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:11,157 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns1],bandwidth=0,serial=false 2024-11-18T05:19:11,160 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=31, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-11-18T05:19:11,161 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=31 2024-11-18T05:19:11,179 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:11,179 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:11,182 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id0x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:11,183 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0020 connected 2024-11-18T05:19:11,274 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=31 2024-11-18T05:19:11,284 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0020, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:11,289 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=32, ppid=31, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:11,442 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:11,443 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=32 2024-11-18T05:19:11,443 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=32}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-11-18T05:19:11,444 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=32}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-11-18T05:19:11,444 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=32}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-11-18T05:19:11,444 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-11-18T05:19:11,444 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1000911699b001f, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:11,445 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1000911699b001f, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:11,484 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=31 2024-11-18T05:19:11,547 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1000911699b001f, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:11,547 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=32}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x0f21ace1 to 127.0.0.1:61937 2024-11-18T05:19:11,547 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=32}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-11-18T05:19:11,570 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=32}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-11-18T05:19:11,571 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=32}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-11-18T05:19:11,572 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=32}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=32 2024-11-18T05:19:11,573 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=32 2024-11-18T05:19:11,576 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:11,581 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=32, resume processing ppid=31 2024-11-18T05:19:11,582 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=32, ppid=31, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 288 msec 2024-11-18T05:19:11,582 INFO [PEWorker-2 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns1],bandwidth=0,serial=false 2024-11-18T05:19:11,585 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=31, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 425 msec 2024-11-18T05:19:11,628 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x7d32b564 to 127.0.0.1:61937 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@3fe98780 2024-11-18T05:19:11,633 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-11-18T05:19:11,633 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-11-18T05:19:11,634 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@5988905e, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-11-18T05:19:11,635 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:11,638 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:11,638 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-11-18T05:19:11,638 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1000911699b0022 connected 2024-11-18T05:19:11,793 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=31 2024-11-18T05:19:11,794 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-11-18T05:19:11,794 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:11,796 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns1],tableCFs={ns1:testNamespacesAndTableCfsConfigConflict1=null},bandwidth=0,serial=false 2024-11-18T05:19:11,798 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=33, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-11-18T05:19:11,798 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=33 2024-11-18T05:19:11,822 INFO [PEWorker-3 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:11,823 INFO [PEWorker-3 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:11,825 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id0x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:11,826 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0023 connected 2024-11-18T05:19:11,903 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=33 2024-11-18T05:19:11,927 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0023, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:11,928 WARN [PEWorker-3 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.DoNotRetryIOException: Table-cfs ns1:testNamespacesAndTableCfsConfigConflict1 is conflict with namespaces ns1 in peer config at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkNamespacesAndTableCfsConfigConflict(ReplicationPeerManager.java:369) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerConfig(ReplicationPeerManager.java:331) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preUpdatePeerConfig(ReplicationPeerManager.java:161) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure.prePeerModification(UpdatePeerConfigProcedure.java:176) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-11-18T05:19:11,930 ERROR [PEWorker-3 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=33, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.DoNotRetryIOException via master-update_config-peer:org.apache.hadoop.hbase.DoNotRetryIOException: Table-cfs ns1:testNamespacesAndTableCfsConfigConflict1 is conflict with namespaces ns1 in peer config; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.DoNotRetryIOException: Table-cfs ns1:testNamespacesAndTableCfsConfigConflict1 is conflict with namespaces ns1 in peer config at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.DoNotRetryIOException: Table-cfs ns1:testNamespacesAndTableCfsConfigConflict1 is conflict with namespaces ns1 in peer config at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkNamespacesAndTableCfsConfigConflict(ReplicationPeerManager.java:369) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerConfig(ReplicationPeerManager.java:331) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preUpdatePeerConfig(ReplicationPeerManager.java:161) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure.prePeerModification(UpdatePeerConfigProcedure.java:176) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-11-18T05:19:11,931 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=33, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.DoNotRetryIOException via master-update_config-peer:org.apache.hadoop.hbase.DoNotRetryIOException: Table-cfs ns1:testNamespacesAndTableCfsConfigConflict1 is conflict with namespaces ns1 in peer config; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure exec-time=134 msec 2024-11-18T05:19:11,931 WARN [PEWorker-3 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-11-18T05:19:12,114 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=33 2024-11-18T05:19:12,115 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 failed with Table-cfs ns1:testNamespacesAndTableCfsConfigConflict1 is conflict with namespaces ns1 in peer config 2024-11-18T05:19:12,116 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:12,117 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns1],tableCFs={ns2:testNamespacesAndTableCfsConfigConflict2=null},bandwidth=0,serial=false 2024-11-18T05:19:12,119 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=34, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-11-18T05:19:12,119 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=34 2024-11-18T05:19:12,143 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:12,144 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:12,147 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id0x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:12,148 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0024 connected 2024-11-18T05:19:12,224 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=34 2024-11-18T05:19:12,249 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0024, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:12,255 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=35, ppid=34, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:12,409 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:12,410 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=35 2024-11-18T05:19:12,410 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=35}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-11-18T05:19:12,411 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=35}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-11-18T05:19:12,411 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=35}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-11-18T05:19:12,412 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-11-18T05:19:12,412 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1000911699b0022, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:12,412 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1000911699b0022, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:12,433 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=34 2024-11-18T05:19:12,514 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1000911699b0022, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:12,514 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=35}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x7d32b564 to 127.0.0.1:61937 2024-11-18T05:19:12,514 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=35}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-11-18T05:19:12,537 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=35}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-11-18T05:19:12,537 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=35}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-11-18T05:19:12,538 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=35}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=35 2024-11-18T05:19:12,539 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=35 2024-11-18T05:19:12,543 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:12,546 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=35, resume processing ppid=34 2024-11-18T05:19:12,546 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=35, ppid=34, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 288 msec 2024-11-18T05:19:12,546 INFO [PEWorker-2 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns1],tableCFs={ns2:testNamespacesAndTableCfsConfigConflict2=null},bandwidth=0,serial=false 2024-11-18T05:19:12,548 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=34, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 429 msec 2024-11-18T05:19:12,581 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x60114f58 to 127.0.0.1:61937 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@4a1facc7 2024-11-18T05:19:12,585 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-11-18T05:19:12,585 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-11-18T05:19:12,586 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@675b2149, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-11-18T05:19:12,587 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:12,589 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:12,589 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-11-18T05:19:12,591 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1000911699b0026 connected 2024-11-18T05:19:12,743 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=34 2024-11-18T05:19:12,743 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-11-18T05:19:12,744 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:12,745 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns2],tableCFs={ns2:testNamespacesAndTableCfsConfigConflict2=null},bandwidth=0,serial=false 2024-11-18T05:19:12,746 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=36, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-11-18T05:19:12,747 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=36 2024-11-18T05:19:12,771 INFO [PEWorker-3 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:12,772 INFO [PEWorker-3 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:12,774 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id0x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:12,775 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0027 connected 2024-11-18T05:19:12,854 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=36 2024-11-18T05:19:12,877 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0027, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:12,877 WARN [PEWorker-3 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.DoNotRetryIOException: Table-cfs ns2:testNamespacesAndTableCfsConfigConflict2 is conflict with namespaces ns2 in peer config at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkNamespacesAndTableCfsConfigConflict(ReplicationPeerManager.java:369) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerConfig(ReplicationPeerManager.java:331) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preUpdatePeerConfig(ReplicationPeerManager.java:161) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure.prePeerModification(UpdatePeerConfigProcedure.java:176) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-11-18T05:19:12,879 ERROR [PEWorker-3 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=36, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.DoNotRetryIOException via master-update_config-peer:org.apache.hadoop.hbase.DoNotRetryIOException: Table-cfs ns2:testNamespacesAndTableCfsConfigConflict2 is conflict with namespaces ns2 in peer config; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.DoNotRetryIOException: Table-cfs ns2:testNamespacesAndTableCfsConfigConflict2 is conflict with namespaces ns2 in peer config at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.DoNotRetryIOException: Table-cfs ns2:testNamespacesAndTableCfsConfigConflict2 is conflict with namespaces ns2 in peer config at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkNamespacesAndTableCfsConfigConflict(ReplicationPeerManager.java:369) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerConfig(ReplicationPeerManager.java:331) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preUpdatePeerConfig(ReplicationPeerManager.java:161) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure.prePeerModification(UpdatePeerConfigProcedure.java:176) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-11-18T05:19:12,881 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=36, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.DoNotRetryIOException via master-update_config-peer:org.apache.hadoop.hbase.DoNotRetryIOException: Table-cfs ns2:testNamespacesAndTableCfsConfigConflict2 is conflict with namespaces ns2 in peer config; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure exec-time=134 msec 2024-11-18T05:19:12,881 WARN [PEWorker-3 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-11-18T05:19:13,063 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=36 2024-11-18T05:19:13,064 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 failed with Table-cfs ns2:testNamespacesAndTableCfsConfigConflict2 is conflict with namespaces ns2 in peer config 2024-11-18T05:19:13,065 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-11-18T05:19:13,066 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=37, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-11-18T05:19:13,067 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=37 2024-11-18T05:19:13,070 DEBUG [PEWorker-1 {}] zookeeper.ZKUtil(111): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-11-18T05:19:13,072 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-11-18T05:19:13,072 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-11-18T05:19:13,072 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-11-18T05:19:13,074 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=38, ppid=37, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:13,173 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=37 2024-11-18T05:19:13,226 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:13,226 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=38 2024-11-18T05:19:13,227 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=38}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-11-18T05:19:13,227 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=38}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-11-18T05:19:13,227 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=38}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-11-18T05:19:13,227 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-11-18T05:19:13,227 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1000911699b0026, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:13,228 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1000911699b0026, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:13,330 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1000911699b0026, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:13,330 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=38}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x60114f58 to 127.0.0.1:61937 2024-11-18T05:19:13,330 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=38}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-11-18T05:19:13,330 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=38}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-11-18T05:19:13,332 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=38}] zookeeper.ZKUtil(111): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/1/7cf745f7364a%2C32867%2C1731907139252.1731907142013 2024-11-18T05:19:13,337 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/1/7cf745f7364a%2C32867%2C1731907139252.1731907142013 2024-11-18T05:19:13,337 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/1 2024-11-18T05:19:13,337 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/1 2024-11-18T05:19:13,338 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=38}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-11-18T05:19:13,338 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=38}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=38 2024-11-18T05:19:13,339 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=38 2024-11-18T05:19:13,342 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:13,345 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=38, resume processing ppid=37 2024-11-18T05:19:13,345 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=38, ppid=37, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 268 msec 2024-11-18T05:19:13,349 DEBUG [PEWorker-2 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-11-18T05:19:13,349 INFO [PEWorker-2 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-11-18T05:19:13,351 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=37, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 284 msec 2024-11-18T05:19:13,383 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=37 2024-11-18T05:19:13,383 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-11-18T05:19:13,384 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-11-18T05:19:13,385 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=39, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-11-18T05:19:13,386 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=39 2024-11-18T05:19:13,386 WARN [PEWorker-3 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-11-18T05:19:13,388 ERROR [PEWorker-3 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=39, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-11-18T05:19:13,389 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=39, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=4 msec 2024-11-18T05:19:13,389 WARN [PEWorker-3 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-11-18T05:19:13,493 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=39 2024-11-18T05:19:13,494 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-11-18T05:19:13,494 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-11-18T05:19:13,496 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=40, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-11-18T05:19:13,498 WARN [PEWorker-1 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-11-18T05:19:13,499 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=40 2024-11-18T05:19:13,499 ERROR [PEWorker-1 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=40, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-11-18T05:19:13,500 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=40, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=5 msec 2024-11-18T05:19:13,500 WARN [PEWorker-1 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-11-18T05:19:13,603 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=40 2024-11-18T05:19:13,604 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-11-18T05:19:13,619 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testNamespacesAndTableCfsConfigConflict[0] Thread=223 (was 223), OpenFileDescriptor=452 (was 452), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=392 (was 392), ProcessCount=11 (was 11), AvailableMemoryMB=12042 (was 12056) 2024-11-18T05:19:13,629 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testAddRemovePeer[0] Thread=223, OpenFileDescriptor=452, MaxFileDescriptor=1048576, SystemLoadAverage=392, ProcessCount=11, AvailableMemoryMB=12042 2024-11-18T05:19:13,630 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-11-18T05:19:13,631 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=41, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-11-18T05:19:13,632 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=41 2024-11-18T05:19:13,652 INFO [PEWorker-4 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:13,652 INFO [PEWorker-4 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:13,655 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id0x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:13,655 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0028 connected 2024-11-18T05:19:13,743 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=41 2024-11-18T05:19:13,757 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0028, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:13,764 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=42, ppid=41, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:13,918 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:13,919 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=42 2024-11-18T05:19:13,919 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=42}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-11-18T05:19:13,944 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=42}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:13,954 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=41 2024-11-18T05:19:13,966 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=42}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-11-18T05:19:13,974 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=42}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=42 2024-11-18T05:19:13,974 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=42 2024-11-18T05:19:13,977 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:13,980 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=42, resume processing ppid=41 2024-11-18T05:19:13,980 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=42, ppid=41, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 213 msec 2024-11-18T05:19:13,980 INFO [PEWorker-2 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-11-18T05:19:13,982 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=41, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 350 msec 2024-11-18T05:19:14,016 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x139a3c3f to 127.0.0.1:61937 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@7e728a43 2024-11-18T05:19:14,021 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-11-18T05:19:14,021 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-11-18T05:19:14,022 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@3552c530, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-11-18T05:19:14,023 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:14,025 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:14,026 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1000911699b002a connected 2024-11-18T05:19:14,026 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-11-18T05:19:14,263 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=41 2024-11-18T05:19:14,264 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-11-18T05:19:14,264 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-11-18T05:19:14,266 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=43, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-11-18T05:19:14,267 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=43 2024-11-18T05:19:14,289 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:14,290 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:14,295 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id0x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:14,295 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b002b connected 2024-11-18T05:19:14,373 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=43 2024-11-18T05:19:14,397 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b002b, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:14,397 WARN [PEWorker-1 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.AddPeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.DoNotRetryIOException: Replication peer 1 already exists at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preAddPeer(ReplicationPeerManager.java:121) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.AddPeerProcedure.prePeerModification(AddPeerProcedure.java:90) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-11-18T05:19:14,399 ERROR [PEWorker-1 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=43, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.DoNotRetryIOException via master-add-peer:org.apache.hadoop.hbase.DoNotRetryIOException: Replication peer 1 already exists; org.apache.hadoop.hbase.master.replication.AddPeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.DoNotRetryIOException: Replication peer 1 already exists at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.DoNotRetryIOException: Replication peer 1 already exists at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preAddPeer(ReplicationPeerManager.java:121) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.AddPeerProcedure.prePeerModification(AddPeerProcedure.java:90) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-11-18T05:19:14,401 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=43, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.DoNotRetryIOException via master-add-peer:org.apache.hadoop.hbase.DoNotRetryIOException: Replication peer 1 already exists; org.apache.hadoop.hbase.master.replication.AddPeerProcedure exec-time=135 msec 2024-11-18T05:19:14,401 WARN [PEWorker-1 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-11-18T05:19:14,584 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=43 2024-11-18T05:19:14,584 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: ADD_REPLICATION_PEER, peerId: 1 failed with Replication peer 1 already exists 2024-11-18T05:19:14,590 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3971): Client=jenkins//172.17.0.2 list replication peers, regex=null 2024-11-18T05:19:14,593 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-11-18T05:19:14,594 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=44, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-11-18T05:19:14,595 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=44 2024-11-18T05:19:14,595 WARN [PEWorker-5 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-11-18T05:19:14,596 ERROR [PEWorker-5 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=44, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-11-18T05:19:14,598 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=44, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=4 msec 2024-11-18T05:19:14,598 WARN [PEWorker-5 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-11-18T05:19:14,704 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=44 2024-11-18T05:19:14,705 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-11-18T05:19:14,706 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3971): Client=jenkins//172.17.0.2 list replication peers, regex=null 2024-11-18T05:19:14,709 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=2, config=clusterKey=127.0.0.1:61937:/hbase-test2,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-11-18T05:19:14,710 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=45, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-11-18T05:19:14,712 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=45 2024-11-18T05:19:14,730 INFO [PEWorker-4 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:14,731 INFO [PEWorker-4 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:14,734 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id0x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test2 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:14,736 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b002c connected 2024-11-18T05:19:14,834 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=45 2024-11-18T05:19:14,840 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b002c, quorum=127.0.0.1:61937, baseZNode=/hbase-test2 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:14,849 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=46, ppid=45, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:15,001 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:15,002 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=46 2024-11-18T05:19:15,002 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=46}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=2, type=ADD_PEER 2024-11-18T05:19:15,026 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=46}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:15,027 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 2000 millis 2024-11-18T05:19:15,043 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=45 2024-11-18T05:19:15,047 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=46}] regionserver.ReplicationSource(229): queueId=2, ReplicationSource: 2, currentBandwidth=0 2024-11-18T05:19:15,051 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=46}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=46 2024-11-18T05:19:15,052 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=46 2024-11-18T05:19:15,055 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 2 for ADD on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:15,058 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=46, resume processing ppid=45 2024-11-18T05:19:15,058 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=46, ppid=45, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 206 msec 2024-11-18T05:19:15,058 INFO [PEWorker-2 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 2, config clusterKey=127.0.0.1:61937:/hbase-test2,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-11-18T05:19:15,060 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=45, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 349 msec 2024-11-18T05:19:15,090 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,2 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x1275624e to 127.0.0.1:61937 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@2efbc5c9 2024-11-18T05:19:15,094 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,2 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test2/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test2/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-11-18T05:19:15,094 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,2 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-11-18T05:19:15,095 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,2 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@1f53527, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-11-18T05:19:15,096 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,2 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 2 connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:15,099 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,2-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 20x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test2 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:15,099 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,2 {}] regionserver.ReplicationSource(569): peerId=2, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-11-18T05:19:15,099 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 2-0x1000911699b002e connected 2024-11-18T05:19:15,181 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-11-18T05:19:15,353 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=45 2024-11-18T05:19:15,354 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 2 completed 2024-11-18T05:19:15,354 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3971): Client=jenkins//172.17.0.2 list replication peers, regex=null 2024-11-18T05:19:15,355 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-11-18T05:19:15,357 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=47, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-11-18T05:19:15,357 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=47 2024-11-18T05:19:15,360 DEBUG [PEWorker-5 {}] zookeeper.ZKUtil(111): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-11-18T05:19:15,363 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-11-18T05:19:15,363 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-11-18T05:19:15,363 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-11-18T05:19:15,364 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=48, ppid=47, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:15,463 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=47 2024-11-18T05:19:15,522 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:15,523 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=48 2024-11-18T05:19:15,523 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=48}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-11-18T05:19:15,523 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=48}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-11-18T05:19:15,523 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=48}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-11-18T05:19:15,524 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-11-18T05:19:15,524 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1000911699b002a, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:15,524 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1000911699b002a, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:15,626 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1000911699b002a, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:15,626 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=48}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x139a3c3f to 127.0.0.1:61937 2024-11-18T05:19:15,626 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=48}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-11-18T05:19:15,626 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=48}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-11-18T05:19:15,628 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=48}] zookeeper.ZKUtil(111): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/1/7cf745f7364a%2C32867%2C1731907139252.1731907142013 2024-11-18T05:19:15,632 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/1/7cf745f7364a%2C32867%2C1731907139252.1731907142013 2024-11-18T05:19:15,632 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/1 2024-11-18T05:19:15,632 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/1 2024-11-18T05:19:15,632 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=48}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-11-18T05:19:15,632 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=48}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=48 2024-11-18T05:19:15,633 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=48 2024-11-18T05:19:15,636 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:15,639 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=48, resume processing ppid=47 2024-11-18T05:19:15,639 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=48, ppid=47, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 272 msec 2024-11-18T05:19:15,643 DEBUG [PEWorker-1 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-11-18T05:19:15,643 INFO [PEWorker-1 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-11-18T05:19:15,646 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=47, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 288 msec 2024-11-18T05:19:15,673 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=47 2024-11-18T05:19:15,674 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-11-18T05:19:15,674 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3971): Client=jenkins//172.17.0.2 list replication peers, regex=null 2024-11-18T05:19:15,675 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-11-18T05:19:15,677 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=49, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-11-18T05:19:15,678 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=49 2024-11-18T05:19:15,681 DEBUG [PEWorker-2 {}] zookeeper.ZKUtil(111): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/2/peer-state 2024-11-18T05:19:15,684 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/2/peer-state 2024-11-18T05:19:15,684 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/2 2024-11-18T05:19:15,685 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/2 2024-11-18T05:19:15,686 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=50, ppid=49, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:15,783 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=49 2024-11-18T05:19:15,839 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:15,840 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=50 2024-11-18T05:19:15,840 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=50}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=2, type=REMOVE_PEER 2024-11-18T05:19:15,840 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=50}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 2: 0 2024-11-18T05:19:15,841 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=50}] regionserver.ReplicationSource(657): peerId=2, Closing source 2 because: Replication stream was removed by a user 2024-11-18T05:19:15,841 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,2 {}] regionserver.ReplicationSource(508): peerId=2, Interrupted while sleeping between retries 2024-11-18T05:19:15,841 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,2 {}] zookeeper.ZKUtil(165): connection to cluster: 2-0x1000911699b002e, quorum=127.0.0.1:61937, baseZNode=/hbase-test2 Unable to set watcher on znode (/hbase-test2/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:15,841 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,2 {}] zookeeper.ZKWatcher(734): connection to cluster: 2-0x1000911699b002e, quorum=127.0.0.1:61937, baseZNode=/hbase-test2 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:15,943 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,2-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 2-0x1000911699b002e, quorum=127.0.0.1:61937, baseZNode=/hbase-test2 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:15,943 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=50}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x1275624e to 127.0.0.1:61937 2024-11-18T05:19:15,944 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=50}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-11-18T05:19:15,944 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=50}] regionserver.ReplicationSourceManager(430): Done with the queue 2 2024-11-18T05:19:15,946 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=50}] zookeeper.ZKUtil(111): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/2/7cf745f7364a%2C32867%2C1731907139252.1731907142013 2024-11-18T05:19:15,949 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/2/7cf745f7364a%2C32867%2C1731907139252.1731907142013 2024-11-18T05:19:15,949 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/2 2024-11-18T05:19:15,949 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/2 2024-11-18T05:19:15,950 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=50}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/2 not found in hfile reference queue. 2024-11-18T05:19:15,951 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=50}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=50 2024-11-18T05:19:15,951 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=50 2024-11-18T05:19:15,954 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 2 for REMOVE on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:15,957 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=50, resume processing ppid=49 2024-11-18T05:19:15,957 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=50, ppid=49, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 268 msec 2024-11-18T05:19:15,960 DEBUG [PEWorker-3 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/2 not found in hfile reference queue. 2024-11-18T05:19:15,960 INFO [PEWorker-3 {}] replication.RemovePeerProcedure(76): Successfully removed peer 2 2024-11-18T05:19:15,962 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=49, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 285 msec 2024-11-18T05:19:15,993 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=49 2024-11-18T05:19:15,993 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 2 completed 2024-11-18T05:19:15,994 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3971): Client=jenkins//172.17.0.2 list replication peers, regex=null 2024-11-18T05:19:15,995 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-11-18T05:19:15,996 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=51, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-11-18T05:19:15,997 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=51 2024-11-18T05:19:15,997 WARN [PEWorker-1 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-11-18T05:19:15,998 ERROR [PEWorker-1 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=51, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-11-18T05:19:16,000 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=51, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=4 msec 2024-11-18T05:19:16,000 WARN [PEWorker-1 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-11-18T05:19:16,103 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=51 2024-11-18T05:19:16,104 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-11-18T05:19:16,105 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-11-18T05:19:16,106 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=52, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-11-18T05:19:16,107 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=52 2024-11-18T05:19:16,108 WARN [PEWorker-5 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-11-18T05:19:16,109 ERROR [PEWorker-5 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=52, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-11-18T05:19:16,111 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=52, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=5 msec 2024-11-18T05:19:16,111 WARN [PEWorker-5 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-11-18T05:19:16,213 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=52 2024-11-18T05:19:16,214 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-11-18T05:19:16,228 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testAddRemovePeer[0] Thread=220 (was 223), OpenFileDescriptor=446 (was 452), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=392 (was 392), ProcessCount=11 (was 11), AvailableMemoryMB=12027 (was 12042) 2024-11-18T05:19:16,238 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testInvalidReplicationEndpoint[0] Thread=220, OpenFileDescriptor=446, MaxFileDescriptor=1048576, SystemLoadAverage=392, ProcessCount=11, AvailableMemoryMB=12026 2024-11-18T05:19:16,239 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=,replicationEndpointImpl=whatever,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-11-18T05:19:16,241 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=53, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-11-18T05:19:16,242 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=53 2024-11-18T05:19:16,243 WARN [PEWorker-2 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.AddPeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.DoNotRetryIOException: Can not instantiate configured replication endpoint class=whatever at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerConfig(ReplicationPeerManager.java:291) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preAddPeer(ReplicationPeerManager.java:119) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.AddPeerProcedure.prePeerModification(AddPeerProcedure.java:90) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: java.lang.ClassNotFoundException: whatever at jdk.internal.loader.BuiltinClassLoader.loadClass(BuiltinClassLoader.java:641) ~[?:?] at jdk.internal.loader.ClassLoaders$AppClassLoader.loadClass(ClassLoaders.java:188) ~[?:?] at java.lang.ClassLoader.loadClass(ClassLoader.java:525) ~[?:?] at java.lang.Class.forName0(Native Method) ~[?:?] at java.lang.Class.forName(Class.java:375) ~[?:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerConfig(ReplicationPeerManager.java:288) ~[classes/:?] ... 12 more 2024-11-18T05:19:16,252 ERROR [PEWorker-2 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=53, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.DoNotRetryIOException via master-add-peer:org.apache.hadoop.hbase.DoNotRetryIOException: Can not instantiate configured replication endpoint class=whatever; org.apache.hadoop.hbase.master.replication.AddPeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.DoNotRetryIOException: Can not instantiate configured replication endpoint class=whatever at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.DoNotRetryIOException: Can not instantiate configured replication endpoint class=whatever at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerConfig(ReplicationPeerManager.java:291) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preAddPeer(ReplicationPeerManager.java:119) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.AddPeerProcedure.prePeerModification(AddPeerProcedure.java:90) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more Caused by: java.lang.ClassNotFoundException: whatever at jdk.internal.loader.BuiltinClassLoader.loadClass(BuiltinClassLoader.java:641) ~[?:?] at jdk.internal.loader.ClassLoaders$AppClassLoader.loadClass(ClassLoaders.java:188) ~[?:?] at java.lang.ClassLoader.loadClass(ClassLoader.java:525) ~[?:?] at java.lang.Class.forName0(Native Method) ~[?:?] at java.lang.Class.forName(Class.java:375) ~[?:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerConfig(ReplicationPeerManager.java:288) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preAddPeer(ReplicationPeerManager.java:119) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.AddPeerProcedure.prePeerModification(AddPeerProcedure.java:90) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-11-18T05:19:16,254 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=53, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.DoNotRetryIOException via master-add-peer:org.apache.hadoop.hbase.DoNotRetryIOException: Can not instantiate configured replication endpoint class=whatever; org.apache.hadoop.hbase.master.replication.AddPeerProcedure exec-time=14 msec 2024-11-18T05:19:16,254 WARN [PEWorker-2 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-11-18T05:19:16,353 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=53 2024-11-18T05:19:16,354 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: ADD_REPLICATION_PEER, peerId: 1 failed with Can not instantiate configured replication endpoint class=whatever 2024-11-18T05:19:16,360 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-11-18T05:19:16,361 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=54, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-11-18T05:19:16,363 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=54 2024-11-18T05:19:16,363 WARN [PEWorker-4 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-11-18T05:19:16,364 ERROR [PEWorker-4 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=54, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-11-18T05:19:16,366 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=54, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=5 msec 2024-11-18T05:19:16,366 WARN [PEWorker-4 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-11-18T05:19:16,473 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=54 2024-11-18T05:19:16,474 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-11-18T05:19:16,475 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-11-18T05:19:16,476 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=55, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-11-18T05:19:16,477 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=55 2024-11-18T05:19:16,477 WARN [PEWorker-3 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-11-18T05:19:16,479 ERROR [PEWorker-3 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=55, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-11-18T05:19:16,480 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=55, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=4 msec 2024-11-18T05:19:16,480 WARN [PEWorker-3 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-11-18T05:19:16,583 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=55 2024-11-18T05:19:16,585 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-11-18T05:19:16,601 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testInvalidReplicationEndpoint[0] Thread=220 (was 220), OpenFileDescriptor=444 (was 446), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=392 (was 392), ProcessCount=11 (was 11), AvailableMemoryMB=12025 (was 12026) 2024-11-18T05:19:16,612 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testInvalidClusterKey[0] Thread=220, OpenFileDescriptor=444, MaxFileDescriptor=1048576, SystemLoadAverage=392, ProcessCount=11, AvailableMemoryMB=12025 2024-11-18T05:19:16,613 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=whatever,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-11-18T05:19:16,615 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=56, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-11-18T05:19:16,616 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=56 2024-11-18T05:19:16,617 WARN [PEWorker-1 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.AddPeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.DoNotRetryIOException: Invalid cluster key: whatever at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkClusterKey(ReplicationPeerManager.java:395) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerConfig(ReplicationPeerManager.java:298) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preAddPeer(ReplicationPeerManager.java:119) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.AddPeerProcedure.prePeerModification(AddPeerProcedure.java:90) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: java.io.IOException: Cluster key passed whatever is invalid, the format should be:hbase.zookeeper.quorum:hbase.zookeeper.property.clientPort:zookeeper.znode.parent at org.apache.hadoop.hbase.zookeeper.ZKConfig.transformClusterKey(ZKConfig.java:228) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKConfig.validateClusterKey(ZKConfig.java:178) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkClusterKey(ReplicationPeerManager.java:393) ~[classes/:?] ... 13 more 2024-11-18T05:19:16,618 ERROR [PEWorker-1 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=56, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.DoNotRetryIOException via master-add-peer:org.apache.hadoop.hbase.DoNotRetryIOException: Invalid cluster key: whatever; org.apache.hadoop.hbase.master.replication.AddPeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.DoNotRetryIOException: Invalid cluster key: whatever at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.DoNotRetryIOException: Invalid cluster key: whatever at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkClusterKey(ReplicationPeerManager.java:395) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerConfig(ReplicationPeerManager.java:298) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preAddPeer(ReplicationPeerManager.java:119) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.AddPeerProcedure.prePeerModification(AddPeerProcedure.java:90) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more Caused by: java.io.IOException: Cluster key passed whatever is invalid, the format should be:hbase.zookeeper.quorum:hbase.zookeeper.property.clientPort:zookeeper.znode.parent at org.apache.hadoop.hbase.zookeeper.ZKConfig.transformClusterKey(ZKConfig.java:228) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKConfig.validateClusterKey(ZKConfig.java:178) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkClusterKey(ReplicationPeerManager.java:393) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerConfig(ReplicationPeerManager.java:298) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preAddPeer(ReplicationPeerManager.java:119) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.AddPeerProcedure.prePeerModification(AddPeerProcedure.java:90) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-11-18T05:19:16,620 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=56, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.DoNotRetryIOException via master-add-peer:org.apache.hadoop.hbase.DoNotRetryIOException: Invalid cluster key: whatever; org.apache.hadoop.hbase.master.replication.AddPeerProcedure exec-time=6 msec 2024-11-18T05:19:16,620 WARN [PEWorker-1 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-11-18T05:19:16,724 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=56 2024-11-18T05:19:16,725 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: ADD_REPLICATION_PEER, peerId: 1 failed with Invalid cluster key: whatever 2024-11-18T05:19:16,725 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-11-18T05:19:16,727 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=57, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-11-18T05:19:16,728 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=57 2024-11-18T05:19:16,729 WARN [PEWorker-5 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-11-18T05:19:16,730 ERROR [PEWorker-5 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=57, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-11-18T05:19:16,731 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=57, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=5 msec 2024-11-18T05:19:16,731 WARN [PEWorker-5 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-11-18T05:19:16,834 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=57 2024-11-18T05:19:16,834 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-11-18T05:19:16,835 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-11-18T05:19:16,836 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=58, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-11-18T05:19:16,837 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=58 2024-11-18T05:19:16,838 WARN [PEWorker-2 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-11-18T05:19:16,839 ERROR [PEWorker-2 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=58, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-11-18T05:19:16,841 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=58, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=5 msec 2024-11-18T05:19:16,841 WARN [PEWorker-2 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-11-18T05:19:16,944 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=58 2024-11-18T05:19:16,944 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-11-18T05:19:16,958 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testInvalidClusterKey[0] Thread=220 (was 220), OpenFileDescriptor=444 (was 444), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=392 (was 392), ProcessCount=11 (was 11), AvailableMemoryMB=12024 (was 12025) 2024-11-18T05:19:16,967 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testSetPeerNamespaces[0] Thread=220, OpenFileDescriptor=444, MaxFileDescriptor=1048576, SystemLoadAverage=392, ProcessCount=11, AvailableMemoryMB=12024 2024-11-18T05:19:16,968 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-11-18T05:19:16,969 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=59, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-11-18T05:19:16,970 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=59 2024-11-18T05:19:16,987 INFO [PEWorker-4 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:16,988 INFO [PEWorker-4 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:16,991 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id0x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:16,991 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b002f connected 2024-11-18T05:19:17,073 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=59 2024-11-18T05:19:17,093 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b002f, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:17,099 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=60, ppid=59, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:17,251 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:17,252 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=60 2024-11-18T05:19:17,252 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=60}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-11-18T05:19:17,276 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=60}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:17,283 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=59 2024-11-18T05:19:17,298 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=60}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-11-18T05:19:17,305 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=60}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=60 2024-11-18T05:19:17,306 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=60 2024-11-18T05:19:17,308 INFO [PEWorker-1 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:17,311 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=60, resume processing ppid=59 2024-11-18T05:19:17,311 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=60, ppid=59, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 209 msec 2024-11-18T05:19:17,311 INFO [PEWorker-1 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-11-18T05:19:17,313 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=59, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 343 msec 2024-11-18T05:19:17,337 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x0923d7a5 to 127.0.0.1:61937 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@715728c 2024-11-18T05:19:17,341 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-11-18T05:19:17,341 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-11-18T05:19:17,341 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@1ef5a792, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-11-18T05:19:17,343 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:17,345 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:17,345 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-11-18T05:19:17,346 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1000911699b0031 connected 2024-11-18T05:19:17,593 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=59 2024-11-18T05:19:17,593 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-11-18T05:19:17,594 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-11-18T05:19:17,595 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=61, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-11-18T05:19:17,596 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=61 2024-11-18T05:19:17,619 INFO [PEWorker-2 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:17,620 INFO [PEWorker-2 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:17,623 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id0x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:17,623 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0032 connected 2024-11-18T05:19:17,703 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=61 2024-11-18T05:19:17,725 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0032, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:17,730 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=62, ppid=61, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:17,882 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:17,883 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=62 2024-11-18T05:19:17,883 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=62}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-11-18T05:19:17,885 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=62}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-11-18T05:19:17,885 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=62}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-11-18T05:19:17,885 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-11-18T05:19:17,885 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1000911699b0031, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:17,885 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1000911699b0031, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:17,913 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=61 2024-11-18T05:19:17,988 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1000911699b0031, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:17,988 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=62}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x0923d7a5 to 127.0.0.1:61937 2024-11-18T05:19:17,988 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=62}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-11-18T05:19:18,014 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=62}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-11-18T05:19:18,014 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=62}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-11-18T05:19:18,015 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=62}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=62 2024-11-18T05:19:18,016 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=62 2024-11-18T05:19:18,019 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:18,022 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=62, resume processing ppid=61 2024-11-18T05:19:18,022 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=62, ppid=61, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 289 msec 2024-11-18T05:19:18,022 INFO [PEWorker-3 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-11-18T05:19:18,024 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=61, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 428 msec 2024-11-18T05:19:18,059 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x13c33846 to 127.0.0.1:61937 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@26910cf8 2024-11-18T05:19:18,068 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-11-18T05:19:18,068 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-11-18T05:19:18,068 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@9f81639, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-11-18T05:19:18,069 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:18,074 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:18,074 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-11-18T05:19:18,074 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1000911699b0034 connected 2024-11-18T05:19:18,223 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=61 2024-11-18T05:19:18,223 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-11-18T05:19:18,224 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:18,225 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns2, ns1],bandwidth=0,serial=false 2024-11-18T05:19:18,226 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=63, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-11-18T05:19:18,227 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=63 2024-11-18T05:19:18,245 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:18,245 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:18,248 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id0x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:18,249 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0035 connected 2024-11-18T05:19:18,333 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=63 2024-11-18T05:19:18,350 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0035, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:18,355 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=64, ppid=63, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:18,509 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:18,509 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=64 2024-11-18T05:19:18,510 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=64}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-11-18T05:19:18,511 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=64}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-11-18T05:19:18,511 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=64}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-11-18T05:19:18,511 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-11-18T05:19:18,511 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1000911699b0034, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:18,512 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1000911699b0034, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:18,543 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=63 2024-11-18T05:19:18,614 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1000911699b0034, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:18,614 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=64}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x13c33846 to 127.0.0.1:61937 2024-11-18T05:19:18,614 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=64}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-11-18T05:19:18,630 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=64}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-11-18T05:19:18,630 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=64}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-11-18T05:19:18,631 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=64}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=64 2024-11-18T05:19:18,631 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=64 2024-11-18T05:19:18,634 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:18,636 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=64, resume processing ppid=63 2024-11-18T05:19:18,636 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=64, ppid=63, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 279 msec 2024-11-18T05:19:18,636 INFO [PEWorker-5 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns2, ns1],bandwidth=0,serial=false 2024-11-18T05:19:18,638 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=63, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 411 msec 2024-11-18T05:19:18,674 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x031d7ca0 to 127.0.0.1:61937 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@2dfa24bf 2024-11-18T05:19:18,688 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-11-18T05:19:18,689 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-11-18T05:19:18,690 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@7ed611d4, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-11-18T05:19:18,691 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:18,694 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:18,695 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-11-18T05:19:18,700 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1000911699b0037 connected 2024-11-18T05:19:18,853 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=63 2024-11-18T05:19:18,854 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-11-18T05:19:18,854 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:18,855 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:18,856 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns1],bandwidth=0,serial=false 2024-11-18T05:19:18,858 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=65, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-11-18T05:19:18,858 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=65 2024-11-18T05:19:18,877 INFO [PEWorker-3 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:18,878 INFO [PEWorker-3 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:18,880 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id0x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:18,881 ERROR [PEWorker-3-EventThread {}] zookeeper.ClientCnxn$EventThread(581): Error while calling watcher. java.util.concurrent.RejectedExecutionException: Task org.apache.hadoop.hbase.trace.TraceUtil$$Lambda$361/0x00007f63688d5db0@68e3840 rejected from java.util.concurrent.ThreadPoolExecutor@438ca6f5[Terminated, pool size = 0, active threads = 0, queued tasks = 0, completed tasks = 0] at java.util.concurrent.ThreadPoolExecutor$AbortPolicy.rejectedExecution(ThreadPoolExecutor.java:2065) ~[?:?] at java.util.concurrent.ThreadPoolExecutor.reject(ThreadPoolExecutor.java:833) ~[?:?] at java.util.concurrent.ThreadPoolExecutor.execute(ThreadPoolExecutor.java:1365) ~[?:?] at java.util.concurrent.Executors$DelegatedExecutorService.execute(Executors.java:721) ~[?:?] at org.apache.hadoop.hbase.zookeeper.ZKWatcher.process(ZKWatcher.java:613) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.PendingWatcher.process(PendingWatcher.java:38) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.zookeeper.ClientCnxn$EventThread.processEvent(ClientCnxn.java:579) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn$EventThread.run(ClientCnxn.java:554) ~[zookeeper-3.8.4.jar:3.8.4] 2024-11-18T05:19:18,963 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=65 2024-11-18T05:19:18,983 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id0x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:18,987 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=66, ppid=65, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:19,140 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:19,141 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=66 2024-11-18T05:19:19,141 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=66}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-11-18T05:19:19,142 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=66}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-11-18T05:19:19,142 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=66}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-11-18T05:19:19,142 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-11-18T05:19:19,143 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1000911699b0037, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:19,143 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1000911699b0037, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:19,173 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=65 2024-11-18T05:19:19,245 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1000911699b0037, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:19,245 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=66}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x031d7ca0 to 127.0.0.1:61937 2024-11-18T05:19:19,245 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=66}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-11-18T05:19:19,265 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=66}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-11-18T05:19:19,265 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=66}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-11-18T05:19:19,266 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=66}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=66 2024-11-18T05:19:19,266 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=66 2024-11-18T05:19:19,272 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:19,275 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=66, resume processing ppid=65 2024-11-18T05:19:19,275 INFO [PEWorker-4 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns1],bandwidth=0,serial=false 2024-11-18T05:19:19,275 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=66, ppid=65, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 285 msec 2024-11-18T05:19:19,277 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=65, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 419 msec 2024-11-18T05:19:19,303 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x38fcdc0b to 127.0.0.1:61937 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@33d75a1 2024-11-18T05:19:19,307 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-11-18T05:19:19,309 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-11-18T05:19:19,309 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@6fa162dd, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-11-18T05:19:19,310 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:19,313 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:19,314 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-11-18T05:19:19,332 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1000911699b003a connected 2024-11-18T05:19:19,483 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=65 2024-11-18T05:19:19,484 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-11-18T05:19:19,484 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:19,485 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-11-18T05:19:19,487 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=67, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-11-18T05:19:19,491 DEBUG [PEWorker-5 {}] zookeeper.ZKUtil(111): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-11-18T05:19:19,491 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=67 2024-11-18T05:19:19,493 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-11-18T05:19:19,494 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-11-18T05:19:19,494 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-11-18T05:19:19,494 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=68, ppid=67, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:19,593 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=67 2024-11-18T05:19:19,647 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:19,648 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=68 2024-11-18T05:19:19,648 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=68}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-11-18T05:19:19,648 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=68}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-11-18T05:19:19,649 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=68}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-11-18T05:19:19,649 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-11-18T05:19:19,649 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1000911699b003a, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:19,649 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1000911699b003a, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:19,751 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1000911699b003a, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:19,752 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=68}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x38fcdc0b to 127.0.0.1:61937 2024-11-18T05:19:19,752 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=68}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-11-18T05:19:19,752 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=68}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-11-18T05:19:19,754 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=68}] zookeeper.ZKUtil(111): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/1/7cf745f7364a%2C32867%2C1731907139252.1731907142013 2024-11-18T05:19:19,756 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/1/7cf745f7364a%2C32867%2C1731907139252.1731907142013 2024-11-18T05:19:19,756 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/1 2024-11-18T05:19:19,756 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/1 2024-11-18T05:19:19,757 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=68}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-11-18T05:19:19,757 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=68}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=68 2024-11-18T05:19:19,757 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=68 2024-11-18T05:19:19,759 INFO [PEWorker-1 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:19,762 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=68, resume processing ppid=67 2024-11-18T05:19:19,762 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=68, ppid=67, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 265 msec 2024-11-18T05:19:19,764 DEBUG [PEWorker-2 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-11-18T05:19:19,764 INFO [PEWorker-2 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-11-18T05:19:19,766 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=67, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 279 msec 2024-11-18T05:19:19,803 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=67 2024-11-18T05:19:19,803 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-11-18T05:19:19,804 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-11-18T05:19:19,805 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=69, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-11-18T05:19:19,805 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=69 2024-11-18T05:19:19,805 WARN [PEWorker-4 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-11-18T05:19:19,807 ERROR [PEWorker-4 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=69, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-11-18T05:19:19,808 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=69, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=3 msec 2024-11-18T05:19:19,808 WARN [PEWorker-4 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-11-18T05:19:19,913 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=69 2024-11-18T05:19:19,914 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-11-18T05:19:19,914 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-11-18T05:19:19,915 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=70, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-11-18T05:19:19,916 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=70 2024-11-18T05:19:19,917 WARN [PEWorker-5 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-11-18T05:19:19,918 ERROR [PEWorker-5 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=70, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-11-18T05:19:19,920 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=70, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=4 msec 2024-11-18T05:19:19,920 WARN [PEWorker-5 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-11-18T05:19:20,023 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=70 2024-11-18T05:19:20,024 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-11-18T05:19:20,039 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testSetPeerNamespaces[0] Thread=220 (was 220), OpenFileDescriptor=444 (was 444), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=409 (was 392) - SystemLoadAverage LEAK? -, ProcessCount=11 (was 11), AvailableMemoryMB=12003 (was 12024) 2024-11-18T05:19:20,050 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testAppendPeerTableCFs[0] Thread=220, OpenFileDescriptor=444, MaxFileDescriptor=1048576, SystemLoadAverage=409, ProcessCount=11, AvailableMemoryMB=12003 2024-11-18T05:19:20,051 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-11-18T05:19:20,053 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=71, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-11-18T05:19:20,054 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=71 2024-11-18T05:19:20,077 INFO [PEWorker-3 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:20,078 INFO [PEWorker-3 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:20,080 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id0x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:20,081 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b003b connected 2024-11-18T05:19:20,163 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=71 2024-11-18T05:19:20,186 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b003b, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:20,193 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=72, ppid=71, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:20,345 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:20,346 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=72 2024-11-18T05:19:20,346 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=72}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-11-18T05:19:20,370 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=72}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:20,373 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=71 2024-11-18T05:19:20,392 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=72}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-11-18T05:19:20,399 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=72}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=72 2024-11-18T05:19:20,400 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=72 2024-11-18T05:19:20,403 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:20,405 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=72, resume processing ppid=71 2024-11-18T05:19:20,405 INFO [PEWorker-4 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-11-18T05:19:20,405 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=72, ppid=71, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 211 msec 2024-11-18T05:19:20,407 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=71, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 354 msec 2024-11-18T05:19:20,439 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x34168c81 to 127.0.0.1:61937 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@c30c5ff 2024-11-18T05:19:20,443 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-11-18T05:19:20,444 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-11-18T05:19:20,444 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@54052e12, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-11-18T05:19:20,445 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:20,456 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:20,456 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-11-18T05:19:20,462 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1000911699b003d connected 2024-11-18T05:19:20,684 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=71 2024-11-18T05:19:20,684 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-11-18T05:19:20,685 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-11-18T05:19:20,686 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=73, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-11-18T05:19:20,687 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=73 2024-11-18T05:19:20,711 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:20,712 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:20,715 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id0x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:20,715 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b003e connected 2024-11-18T05:19:20,794 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=73 2024-11-18T05:19:20,817 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b003e, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:20,822 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=74, ppid=73, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:20,975 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:20,975 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=74 2024-11-18T05:19:20,976 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=74}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-11-18T05:19:20,977 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=74}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-11-18T05:19:20,977 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=74}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-11-18T05:19:20,977 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-11-18T05:19:20,978 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1000911699b003d, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:20,978 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1000911699b003d, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:21,004 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=73 2024-11-18T05:19:21,080 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1000911699b003d, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:21,081 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=74}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x34168c81 to 127.0.0.1:61937 2024-11-18T05:19:21,081 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=74}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-11-18T05:19:21,101 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=74}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-11-18T05:19:21,101 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=74}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-11-18T05:19:21,102 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=74}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=74 2024-11-18T05:19:21,103 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=74 2024-11-18T05:19:21,106 INFO [PEWorker-1 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:21,108 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=74, resume processing ppid=73 2024-11-18T05:19:21,108 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=74, ppid=73, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 284 msec 2024-11-18T05:19:21,108 INFO [PEWorker-2 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-11-18T05:19:21,111 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=73, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 423 msec 2024-11-18T05:19:21,128 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-11-18T05:19:21,150 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x4276af3f to 127.0.0.1:61937 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@545da869 2024-11-18T05:19:21,153 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-11-18T05:19:21,154 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-11-18T05:19:21,154 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@690ea369, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-11-18T05:19:21,155 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:21,174 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:21,174 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-11-18T05:19:21,176 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1000911699b0040 connected 2024-11-18T05:19:21,313 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=73 2024-11-18T05:19:21,314 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-11-18T05:19:21,314 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:21,315 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null},bandwidth=0,serial=false 2024-11-18T05:19:21,317 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=75, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-11-18T05:19:21,319 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=75 2024-11-18T05:19:21,338 INFO [PEWorker-4 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:21,339 INFO [PEWorker-4 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:21,348 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id0x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:21,360 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0041 connected 2024-11-18T05:19:21,423 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=75 2024-11-18T05:19:21,466 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0041, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:21,470 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=76, ppid=75, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:21,622 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:21,623 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=76 2024-11-18T05:19:21,623 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=76}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-11-18T05:19:21,624 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=76}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-11-18T05:19:21,624 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=76}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-11-18T05:19:21,625 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-11-18T05:19:21,625 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1000911699b0040, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:21,625 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1000911699b0040, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:21,633 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=75 2024-11-18T05:19:21,727 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1000911699b0040, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:21,727 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=76}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x4276af3f to 127.0.0.1:61937 2024-11-18T05:19:21,728 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=76}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-11-18T05:19:21,752 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=76}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-11-18T05:19:21,752 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=76}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-11-18T05:19:21,753 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=76}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=76 2024-11-18T05:19:21,753 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=76 2024-11-18T05:19:21,756 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:21,758 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=76, resume processing ppid=75 2024-11-18T05:19:21,758 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=76, ppid=75, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 286 msec 2024-11-18T05:19:21,758 INFO [PEWorker-1 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null},bandwidth=0,serial=false 2024-11-18T05:19:21,760 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=75, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 442 msec 2024-11-18T05:19:21,796 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x7bb1719d to 127.0.0.1:61937 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@a50ba93 2024-11-18T05:19:21,800 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-11-18T05:19:21,801 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-11-18T05:19:21,801 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@2d26b829, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-11-18T05:19:21,802 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:21,805 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:21,805 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-11-18T05:19:21,806 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1000911699b0043 connected 2024-11-18T05:19:21,943 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=75 2024-11-18T05:19:21,944 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-11-18T05:19:21,944 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:21,945 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:21,946 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst2=null},bandwidth=0,serial=false 2024-11-18T05:19:21,948 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=77, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-11-18T05:19:21,948 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=77 2024-11-18T05:19:21,967 INFO [PEWorker-2 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:21,968 INFO [PEWorker-2 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:21,974 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id0x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:21,975 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0044 connected 2024-11-18T05:19:22,053 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=77 2024-11-18T05:19:22,076 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0044, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:22,081 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=78, ppid=77, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:22,232 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:22,233 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=78 2024-11-18T05:19:22,233 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=78}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-11-18T05:19:22,234 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=78}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-11-18T05:19:22,234 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=78}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-11-18T05:19:22,234 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-11-18T05:19:22,235 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1000911699b0043, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:22,235 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1000911699b0043, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:22,263 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=77 2024-11-18T05:19:22,337 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1000911699b0043, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:22,337 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=78}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x7bb1719d to 127.0.0.1:61937 2024-11-18T05:19:22,337 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=78}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-11-18T05:19:22,354 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=78}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-11-18T05:19:22,354 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=78}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-11-18T05:19:22,355 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=78}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=78 2024-11-18T05:19:22,355 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=78 2024-11-18T05:19:22,357 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:22,359 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=78, resume processing ppid=77 2024-11-18T05:19:22,360 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=78, ppid=77, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 276 msec 2024-11-18T05:19:22,360 INFO [PEWorker-5 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst2=null},bandwidth=0,serial=false 2024-11-18T05:19:22,362 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=77, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 414 msec 2024-11-18T05:19:22,399 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x66f4f19b to 127.0.0.1:61937 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@7c04544b 2024-11-18T05:19:22,404 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-11-18T05:19:22,405 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-11-18T05:19:22,405 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@71da2111, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-11-18T05:19:22,406 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:22,416 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:22,417 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-11-18T05:19:22,417 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1000911699b0046 connected 2024-11-18T05:19:22,573 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=77 2024-11-18T05:19:22,574 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-11-18T05:19:22,574 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:22,575 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:22,577 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null},bandwidth=0,serial=false 2024-11-18T05:19:22,578 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=79, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-11-18T05:19:22,579 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=79 2024-11-18T05:19:22,602 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:22,603 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:22,606 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id0x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:22,608 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0047 connected 2024-11-18T05:19:22,684 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=79 2024-11-18T05:19:22,710 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0047, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:22,714 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=80, ppid=79, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:22,867 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:22,868 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=80 2024-11-18T05:19:22,868 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=80}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-11-18T05:19:22,881 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=80}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-11-18T05:19:22,882 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=80}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-11-18T05:19:22,882 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-11-18T05:19:22,882 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1000911699b0046, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:22,882 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1000911699b0046, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:22,893 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=79 2024-11-18T05:19:22,993 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1000911699b0046, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:22,993 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=80}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x66f4f19b to 127.0.0.1:61937 2024-11-18T05:19:22,993 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=80}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-11-18T05:19:23,019 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=80}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-11-18T05:19:23,020 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=80}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-11-18T05:19:23,020 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=80}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=80 2024-11-18T05:19:23,021 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=80 2024-11-18T05:19:23,024 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:23,027 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=80, resume processing ppid=79 2024-11-18T05:19:23,027 INFO [PEWorker-3 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null},bandwidth=0,serial=false 2024-11-18T05:19:23,027 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=80, ppid=79, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 310 msec 2024-11-18T05:19:23,028 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=79, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 450 msec 2024-11-18T05:19:23,068 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x42b55610 to 127.0.0.1:61937 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@2dc67824 2024-11-18T05:19:23,077 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-11-18T05:19:23,077 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-11-18T05:19:23,078 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@7eaf75cf, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-11-18T05:19:23,079 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:23,090 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:23,091 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-11-18T05:19:23,092 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1000911699b0049 connected 2024-11-18T05:19:23,203 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=79 2024-11-18T05:19:23,204 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-11-18T05:19:23,204 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:23,205 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:23,206 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst4=[f1, f2]},bandwidth=0,serial=false 2024-11-18T05:19:23,208 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=81, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-11-18T05:19:23,209 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=81 2024-11-18T05:19:23,232 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:23,233 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:23,236 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id0x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:23,239 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b004a connected 2024-11-18T05:19:23,313 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=81 2024-11-18T05:19:23,340 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b004a, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:23,345 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=82, ppid=81, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:23,497 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:23,498 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=82 2024-11-18T05:19:23,498 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=82}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-11-18T05:19:23,500 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=82}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-11-18T05:19:23,500 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=82}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-11-18T05:19:23,500 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-11-18T05:19:23,500 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1000911699b0049, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:23,501 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1000911699b0049, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:23,524 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=81 2024-11-18T05:19:23,602 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1000911699b0049, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:23,603 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=82}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x42b55610 to 127.0.0.1:61937 2024-11-18T05:19:23,603 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=82}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-11-18T05:19:23,626 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=82}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-11-18T05:19:23,627 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=82}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-11-18T05:19:23,627 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=82}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=82 2024-11-18T05:19:23,628 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=82 2024-11-18T05:19:23,630 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:23,633 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=82, resume processing ppid=81 2024-11-18T05:19:23,633 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=82, ppid=81, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 285 msec 2024-11-18T05:19:23,634 INFO [PEWorker-2 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst4=[f1, f2]},bandwidth=0,serial=false 2024-11-18T05:19:23,636 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=81, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 428 msec 2024-11-18T05:19:23,663 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x108e3e09 to 127.0.0.1:61937 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@6828dbb5 2024-11-18T05:19:23,667 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-11-18T05:19:23,668 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-11-18T05:19:23,668 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@49439d96, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-11-18T05:19:23,669 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:23,673 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:23,673 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-11-18T05:19:23,676 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1000911699b004c connected 2024-11-18T05:19:23,833 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=81 2024-11-18T05:19:23,834 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-11-18T05:19:23,834 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:23,836 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:23,838 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst5=null, testAppendPeerTableCFst4=[f1, f2]},bandwidth=0,serial=false 2024-11-18T05:19:23,839 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=83, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-11-18T05:19:23,840 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=83 2024-11-18T05:19:23,863 INFO [PEWorker-3 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:23,864 INFO [PEWorker-3 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:23,867 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id0x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:23,867 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b004d connected 2024-11-18T05:19:23,944 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=83 2024-11-18T05:19:23,969 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b004d, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:23,974 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=84, ppid=83, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:24,127 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:24,128 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=84 2024-11-18T05:19:24,128 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=84}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-11-18T05:19:24,130 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=84}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-11-18T05:19:24,130 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=84}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-11-18T05:19:24,130 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-11-18T05:19:24,131 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1000911699b004c, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:24,131 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1000911699b004c, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:24,154 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=83 2024-11-18T05:19:24,233 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1000911699b004c, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:24,233 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=84}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x108e3e09 to 127.0.0.1:61937 2024-11-18T05:19:24,233 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=84}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-11-18T05:19:24,255 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=84}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-11-18T05:19:24,256 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=84}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-11-18T05:19:24,256 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=84}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=84 2024-11-18T05:19:24,257 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=84 2024-11-18T05:19:24,260 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:24,264 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=84, resume processing ppid=83 2024-11-18T05:19:24,265 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=84, ppid=83, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 286 msec 2024-11-18T05:19:24,265 INFO [PEWorker-5 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst5=null, testAppendPeerTableCFst4=[f1, f2]},bandwidth=0,serial=false 2024-11-18T05:19:24,268 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=83, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 427 msec 2024-11-18T05:19:24,295 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x4d5287d7 to 127.0.0.1:61937 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@6c386e76 2024-11-18T05:19:24,300 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-11-18T05:19:24,301 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-11-18T05:19:24,301 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@474f4e2, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-11-18T05:19:24,302 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:24,314 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:24,315 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-11-18T05:19:24,320 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1000911699b004f connected 2024-11-18T05:19:24,463 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=83 2024-11-18T05:19:24,463 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-11-18T05:19:24,464 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:24,465 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst5=null, testAppendPeerTableCFst4=[f1, f2]},bandwidth=0,serial=false 2024-11-18T05:19:24,466 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=85, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-11-18T05:19:24,467 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=85 2024-11-18T05:19:24,482 INFO [PEWorker-2 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:24,482 INFO [PEWorker-2 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:24,485 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id0x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:24,485 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0050 connected 2024-11-18T05:19:24,574 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=85 2024-11-18T05:19:24,586 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0050, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:24,590 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=86, ppid=85, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:24,741 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:24,741 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=86 2024-11-18T05:19:24,742 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=86}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-11-18T05:19:24,743 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=86}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=86 2024-11-18T05:19:24,743 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=86 2024-11-18T05:19:24,745 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:24,747 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=86, resume processing ppid=85 2024-11-18T05:19:24,747 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=86, ppid=85, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 155 msec 2024-11-18T05:19:24,747 INFO [PEWorker-4 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst5=null, testAppendPeerTableCFst4=[f1, f2]},bandwidth=0,serial=false 2024-11-18T05:19:24,748 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=85, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 282 msec 2024-11-18T05:19:24,783 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=85 2024-11-18T05:19:24,783 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-11-18T05:19:24,784 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:24,785 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:24,785 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst5=null, testAppendPeerTableCFst4=[f1, f2], testAppendPeerTableCFst6=[f1]},bandwidth=0,serial=false 2024-11-18T05:19:24,786 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=87, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-11-18T05:19:24,787 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=87 2024-11-18T05:19:24,802 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:24,803 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:24,805 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id0x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:24,805 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0051 connected 2024-11-18T05:19:24,893 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=87 2024-11-18T05:19:24,907 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0051, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:24,910 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=88, ppid=87, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:25,062 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:25,063 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=88 2024-11-18T05:19:25,063 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=88}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-11-18T05:19:25,064 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=88}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-11-18T05:19:25,064 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=88}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-11-18T05:19:25,064 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-11-18T05:19:25,064 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1000911699b004f, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:25,065 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1000911699b004f, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:25,103 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=87 2024-11-18T05:19:25,167 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1000911699b004f, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:25,167 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=88}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x4d5287d7 to 127.0.0.1:61937 2024-11-18T05:19:25,167 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=88}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-11-18T05:19:25,182 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=88}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-11-18T05:19:25,182 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=88}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-11-18T05:19:25,183 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=88}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=88 2024-11-18T05:19:25,183 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=88 2024-11-18T05:19:25,185 INFO [PEWorker-1 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:25,186 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=88, resume processing ppid=87 2024-11-18T05:19:25,186 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=88, ppid=87, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 275 msec 2024-11-18T05:19:25,186 INFO [PEWorker-3 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst5=null, testAppendPeerTableCFst4=[f1, f2], testAppendPeerTableCFst6=[f1]},bandwidth=0,serial=false 2024-11-18T05:19:25,188 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=87, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 401 msec 2024-11-18T05:19:25,211 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x7171fd3e to 127.0.0.1:61937 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@cd57b85 2024-11-18T05:19:25,214 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-11-18T05:19:25,214 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-11-18T05:19:25,215 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@3ad2b314, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-11-18T05:19:25,215 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:25,217 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:25,218 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-11-18T05:19:25,218 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1000911699b0053 connected 2024-11-18T05:19:25,413 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=87 2024-11-18T05:19:25,414 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-11-18T05:19:25,414 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:25,415 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst5=null, testAppendPeerTableCFst4=[f1, f2], testAppendPeerTableCFst6=null},bandwidth=0,serial=false 2024-11-18T05:19:25,416 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=89, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-11-18T05:19:25,417 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=89 2024-11-18T05:19:25,432 INFO [PEWorker-4 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:25,433 INFO [PEWorker-4 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:25,435 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id0x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:25,436 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0054 connected 2024-11-18T05:19:25,523 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=89 2024-11-18T05:19:25,537 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0054, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:25,542 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=90, ppid=89, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:25,694 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:25,694 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=90 2024-11-18T05:19:25,694 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=90}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-11-18T05:19:25,695 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=90}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-11-18T05:19:25,695 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=90}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-11-18T05:19:25,695 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-11-18T05:19:25,696 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1000911699b0053, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:25,696 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1000911699b0053, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:25,733 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=89 2024-11-18T05:19:25,798 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1000911699b0053, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:25,798 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=90}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x7171fd3e to 127.0.0.1:61937 2024-11-18T05:19:25,798 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=90}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-11-18T05:19:25,813 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=90}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-11-18T05:19:25,813 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=90}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-11-18T05:19:25,814 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=90}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=90 2024-11-18T05:19:25,814 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=90 2024-11-18T05:19:25,816 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:25,817 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=90, resume processing ppid=89 2024-11-18T05:19:25,818 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=90, ppid=89, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 274 msec 2024-11-18T05:19:25,818 INFO [PEWorker-1 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst5=null, testAppendPeerTableCFst4=[f1, f2], testAppendPeerTableCFst6=null},bandwidth=0,serial=false 2024-11-18T05:19:25,819 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=89, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 403 msec 2024-11-18T05:19:25,843 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x79303a29 to 127.0.0.1:61937 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@2bf2a9d8 2024-11-18T05:19:25,847 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-11-18T05:19:25,847 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-11-18T05:19:25,847 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@378580d6, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-11-18T05:19:25,848 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:25,850 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:25,851 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-11-18T05:19:25,851 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1000911699b0056 connected 2024-11-18T05:19:26,043 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=89 2024-11-18T05:19:26,043 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-11-18T05:19:26,044 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:26,044 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-11-18T05:19:26,045 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=91, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-11-18T05:19:26,046 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=91 2024-11-18T05:19:26,048 DEBUG [PEWorker-3 {}] zookeeper.ZKUtil(111): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-11-18T05:19:26,050 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-11-18T05:19:26,050 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-11-18T05:19:26,050 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-11-18T05:19:26,051 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=92, ppid=91, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:26,153 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=91 2024-11-18T05:19:26,202 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:26,203 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=92 2024-11-18T05:19:26,203 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=92}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-11-18T05:19:26,203 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=92}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-11-18T05:19:26,203 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=92}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-11-18T05:19:26,203 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-11-18T05:19:26,204 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1000911699b0056, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:26,204 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1000911699b0056, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:26,305 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1000911699b0056, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:26,306 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=92}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x79303a29 to 127.0.0.1:61937 2024-11-18T05:19:26,306 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=92}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-11-18T05:19:26,306 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=92}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-11-18T05:19:26,307 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=92}] zookeeper.ZKUtil(111): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/1/7cf745f7364a%2C32867%2C1731907139252.1731907142013 2024-11-18T05:19:26,309 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/1/7cf745f7364a%2C32867%2C1731907139252.1731907142013 2024-11-18T05:19:26,309 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/1 2024-11-18T05:19:26,309 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/1 2024-11-18T05:19:26,309 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=92}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-11-18T05:19:26,310 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=92}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=92 2024-11-18T05:19:26,310 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=92 2024-11-18T05:19:26,312 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:26,314 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=92, resume processing ppid=91 2024-11-18T05:19:26,314 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=92, ppid=91, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 261 msec 2024-11-18T05:19:26,316 DEBUG [PEWorker-2 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-11-18T05:19:26,316 INFO [PEWorker-2 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-11-18T05:19:26,317 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=91, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 272 msec 2024-11-18T05:19:26,363 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=91 2024-11-18T05:19:26,363 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-11-18T05:19:26,363 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-11-18T05:19:26,364 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=93, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-11-18T05:19:26,365 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=93 2024-11-18T05:19:26,365 WARN [PEWorker-1 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-11-18T05:19:26,366 ERROR [PEWorker-1 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=93, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-11-18T05:19:26,366 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=93, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=2 msec 2024-11-18T05:19:26,366 WARN [PEWorker-1 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-11-18T05:19:26,473 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=93 2024-11-18T05:19:26,473 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-11-18T05:19:26,474 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-11-18T05:19:26,475 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=94, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-11-18T05:19:26,475 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=94 2024-11-18T05:19:26,475 WARN [PEWorker-4 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-11-18T05:19:26,476 ERROR [PEWorker-4 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=94, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-11-18T05:19:26,477 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=94, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=2 msec 2024-11-18T05:19:26,477 WARN [PEWorker-4 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-11-18T05:19:26,583 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=94 2024-11-18T05:19:26,583 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-11-18T05:19:26,595 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testAppendPeerTableCFs[0] Thread=219 (was 220), OpenFileDescriptor=444 (was 444), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=432 (was 409) - SystemLoadAverage LEAK? -, ProcessCount=11 (was 11), AvailableMemoryMB=11888 (was 12003) 2024-11-18T05:19:26,604 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testEnableDisablePeer[0] Thread=219, OpenFileDescriptor=444, MaxFileDescriptor=1048576, SystemLoadAverage=432, ProcessCount=11, AvailableMemoryMB=11888 2024-11-18T05:19:26,605 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-11-18T05:19:26,606 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=95, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-11-18T05:19:26,607 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=95 2024-11-18T05:19:26,627 INFO [PEWorker-3 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:26,628 INFO [PEWorker-3 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:26,632 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id0x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:26,632 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0057 connected 2024-11-18T05:19:26,713 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=95 2024-11-18T05:19:26,734 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0057, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:26,739 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=96, ppid=95, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:26,891 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:26,891 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=96 2024-11-18T05:19:26,891 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=96}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-11-18T05:19:26,907 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=96}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:26,921 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=96}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-11-18T05:19:26,923 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=95 2024-11-18T05:19:26,927 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=96}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=96 2024-11-18T05:19:26,928 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=96 2024-11-18T05:19:26,929 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:26,931 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=96, resume processing ppid=95 2024-11-18T05:19:26,931 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=96, ppid=95, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 190 msec 2024-11-18T05:19:26,931 INFO [PEWorker-1 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-11-18T05:19:26,932 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=95, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 326 msec 2024-11-18T05:19:26,956 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x172b63ca to 127.0.0.1:61937 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@381a7f27 2024-11-18T05:19:26,966 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-11-18T05:19:26,966 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-11-18T05:19:26,966 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@6a7c2b84, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-11-18T05:19:26,967 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:26,972 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:26,972 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-11-18T05:19:26,972 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1000911699b0059 connected 2024-11-18T05:19:27,233 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=95 2024-11-18T05:19:27,233 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-11-18T05:19:27,234 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3971): Client=jenkins//172.17.0.2 list replication peers, regex=null 2024-11-18T05:19:27,237 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3938): Client=jenkins//172.17.0.2 disable replication peer, id=1 2024-11-18T05:19:27,239 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=97, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.DisablePeerProcedure 2024-11-18T05:19:27,241 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=97 2024-11-18T05:19:27,243 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=98, ppid=97, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:27,353 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=97 2024-11-18T05:19:27,395 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:27,395 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=98 2024-11-18T05:19:27,395 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=98}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=DISABLE_PEER 2024-11-18T05:19:27,396 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=98}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-11-18T05:19:27,396 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=98}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-11-18T05:19:27,396 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-11-18T05:19:27,397 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1000911699b0059, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:27,397 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1000911699b0059, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:27,499 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1000911699b0059, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:27,499 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=98}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x172b63ca to 127.0.0.1:61937 2024-11-18T05:19:27,499 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=98}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-11-18T05:19:27,514 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=98}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-11-18T05:19:27,514 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=98}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-11-18T05:19:27,515 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=98}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=98 2024-11-18T05:19:27,515 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=98 2024-11-18T05:19:27,517 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for DISABLE on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:27,519 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=98, resume processing ppid=97 2024-11-18T05:19:27,519 INFO [PEWorker-2 {}] replication.DisablePeerProcedure(67): Successfully disabled peer 1 2024-11-18T05:19:27,519 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=98, ppid=97, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 274 msec 2024-11-18T05:19:27,520 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=97, state=SUCCESS; org.apache.hadoop.hbase.master.replication.DisablePeerProcedure in 282 msec 2024-11-18T05:19:27,544 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x007a1f09 to 127.0.0.1:61937 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@3c4ad20b 2024-11-18T05:19:27,548 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-11-18T05:19:27,548 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-11-18T05:19:27,548 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@841d683, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-11-18T05:19:27,549 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:27,551 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:27,551 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-11-18T05:19:27,551 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1000911699b005b connected 2024-11-18T05:19:27,563 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=97 2024-11-18T05:19:27,564 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: DISABLE_REPLICATION_PEER, peerId: 1 completed 2024-11-18T05:19:27,564 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3971): Client=jenkins//172.17.0.2 list replication peers, regex=null 2024-11-18T05:19:27,565 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-11-18T05:19:27,566 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=99, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-11-18T05:19:27,566 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=99 2024-11-18T05:19:27,568 DEBUG [PEWorker-1 {}] zookeeper.ZKUtil(111): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-11-18T05:19:27,570 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-11-18T05:19:27,570 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-11-18T05:19:27,570 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-11-18T05:19:27,570 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=100, ppid=99, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:27,659 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:19:27,673 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=99 2024-11-18T05:19:27,722 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:27,723 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=100 2024-11-18T05:19:27,723 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=100}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-11-18T05:19:27,723 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=100}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-11-18T05:19:27,723 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=100}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-11-18T05:19:27,723 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-11-18T05:19:27,723 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1000911699b005b, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:27,724 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1000911699b005b, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:27,825 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1000911699b005b, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:27,825 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=100}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x007a1f09 to 127.0.0.1:61937 2024-11-18T05:19:27,825 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=100}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-11-18T05:19:27,826 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=100}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-11-18T05:19:27,827 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=100}] zookeeper.ZKUtil(111): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/1/7cf745f7364a%2C32867%2C1731907139252.1731907142013 2024-11-18T05:19:27,829 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/1/7cf745f7364a%2C32867%2C1731907139252.1731907142013 2024-11-18T05:19:27,829 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/1 2024-11-18T05:19:27,829 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/1 2024-11-18T05:19:27,830 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=100}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-11-18T05:19:27,830 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=100}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=100 2024-11-18T05:19:27,830 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=100 2024-11-18T05:19:27,832 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:27,834 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=100, resume processing ppid=99 2024-11-18T05:19:27,834 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=100, ppid=99, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 262 msec 2024-11-18T05:19:27,836 DEBUG [PEWorker-5 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-11-18T05:19:27,836 INFO [PEWorker-5 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-11-18T05:19:27,838 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=99, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 271 msec 2024-11-18T05:19:27,883 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=99 2024-11-18T05:19:27,883 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-11-18T05:19:27,883 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-11-18T05:19:27,884 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=101, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-11-18T05:19:27,885 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=101 2024-11-18T05:19:27,885 WARN [PEWorker-2 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-11-18T05:19:27,886 ERROR [PEWorker-2 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=101, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-11-18T05:19:27,886 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=101, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=3 msec 2024-11-18T05:19:27,887 WARN [PEWorker-2 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-11-18T05:19:27,993 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=101 2024-11-18T05:19:27,994 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-11-18T05:19:27,995 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-11-18T05:19:27,995 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=102, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-11-18T05:19:27,996 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=102 2024-11-18T05:19:27,996 WARN [PEWorker-1 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-11-18T05:19:27,997 ERROR [PEWorker-1 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=102, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-11-18T05:19:27,998 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=102, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=3 msec 2024-11-18T05:19:27,998 WARN [PEWorker-1 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-11-18T05:19:28,103 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=102 2024-11-18T05:19:28,104 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-11-18T05:19:28,115 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testEnableDisablePeer[0] Thread=221 (was 219) - Thread LEAK? -, OpenFileDescriptor=446 (was 444) - OpenFileDescriptor LEAK? -, MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=432 (was 432), ProcessCount=11 (was 11), AvailableMemoryMB=11873 (was 11888) 2024-11-18T05:19:28,123 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testReplicationPeerNotFoundException[0] Thread=221, OpenFileDescriptor=446, MaxFileDescriptor=1048576, SystemLoadAverage=432, ProcessCount=11, AvailableMemoryMB=11873 2024-11-18T05:19:28,124 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=dummy_peer 2024-11-18T05:19:28,125 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=103, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-11-18T05:19:28,125 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=103 2024-11-18T05:19:28,125 WARN [PEWorker-4 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer dummy_peer, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: dummy_peer at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-11-18T05:19:28,126 ERROR [PEWorker-4 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=103, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: dummy_peer; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: dummy_peer at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: dummy_peer at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-11-18T05:19:28,127 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=103, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: dummy_peer; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=2 msec 2024-11-18T05:19:28,127 WARN [PEWorker-4 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-11-18T05:19:28,233 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=103 2024-11-18T05:19:28,234 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: dummy_peer failed with dummy_peer 2024-11-18T05:19:28,234 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-11-18T05:19:28,235 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=104, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-11-18T05:19:28,236 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=104 2024-11-18T05:19:28,236 WARN [PEWorker-3 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-11-18T05:19:28,237 ERROR [PEWorker-3 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=104, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-11-18T05:19:28,238 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=104, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=2 msec 2024-11-18T05:19:28,238 WARN [PEWorker-3 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-11-18T05:19:28,343 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=104 2024-11-18T05:19:28,344 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-11-18T05:19:28,344 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-11-18T05:19:28,345 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=105, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-11-18T05:19:28,346 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=105 2024-11-18T05:19:28,346 WARN [PEWorker-5 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-11-18T05:19:28,347 ERROR [PEWorker-5 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=105, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-11-18T05:19:28,347 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=105, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=3 msec 2024-11-18T05:19:28,348 WARN [PEWorker-5 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-11-18T05:19:28,453 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=105 2024-11-18T05:19:28,454 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-11-18T05:19:28,465 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testReplicationPeerNotFoundException[0] Thread=221 (was 221), OpenFileDescriptor=446 (was 446), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=432 (was 432), ProcessCount=11 (was 11), AvailableMemoryMB=11871 (was 11873) 2024-11-18T05:19:28,473 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testPeerConfig[0] Thread=221, OpenFileDescriptor=446, MaxFileDescriptor=1048576, SystemLoadAverage=432, ProcessCount=11, AvailableMemoryMB=11871 2024-11-18T05:19:28,474 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-11-18T05:19:28,475 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=106, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-11-18T05:19:28,476 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=106 2024-11-18T05:19:28,491 INFO [PEWorker-2 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:28,491 INFO [PEWorker-2 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:28,494 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id0x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:28,494 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b005c connected 2024-11-18T05:19:28,583 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=106 2024-11-18T05:19:28,596 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b005c, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:28,602 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=107, ppid=106, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:28,754 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:28,754 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=107 2024-11-18T05:19:28,754 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=107}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-11-18T05:19:28,770 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=107}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:28,784 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=107}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-11-18T05:19:28,793 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=107}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=107 2024-11-18T05:19:28,793 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=107 2024-11-18T05:19:28,793 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=106 2024-11-18T05:19:28,795 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:28,796 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=107, resume processing ppid=106 2024-11-18T05:19:28,796 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=107, ppid=106, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 193 msec 2024-11-18T05:19:28,796 INFO [PEWorker-3 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-11-18T05:19:28,798 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=106, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 322 msec 2024-11-18T05:19:28,823 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x09f4afcd to 127.0.0.1:61937 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@9f7b453 2024-11-18T05:19:28,826 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-11-18T05:19:28,826 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-11-18T05:19:28,827 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@684965b6, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-11-18T05:19:28,828 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:28,830 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:28,830 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-11-18T05:19:28,830 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1000911699b005e connected 2024-11-18T05:19:29,103 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=106 2024-11-18T05:19:29,104 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-11-18T05:19:29,104 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3971): Client=jenkins//172.17.0.2 list replication peers, regex=null 2024-11-18T05:19:29,105 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-11-18T05:19:29,106 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=108, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-11-18T05:19:29,107 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=108 2024-11-18T05:19:29,109 DEBUG [PEWorker-5 {}] zookeeper.ZKUtil(111): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-11-18T05:19:29,111 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-11-18T05:19:29,111 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-11-18T05:19:29,111 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-11-18T05:19:29,112 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=109, ppid=108, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:29,214 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=108 2024-11-18T05:19:29,264 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:29,264 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=109 2024-11-18T05:19:29,265 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=109}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-11-18T05:19:29,265 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=109}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-11-18T05:19:29,265 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=109}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-11-18T05:19:29,265 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-11-18T05:19:29,265 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1000911699b005e, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:29,265 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1000911699b005e, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:29,367 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1000911699b005e, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:29,367 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=109}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x09f4afcd to 127.0.0.1:61937 2024-11-18T05:19:29,367 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=109}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-11-18T05:19:29,367 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=109}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-11-18T05:19:29,369 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=109}] zookeeper.ZKUtil(111): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/1/7cf745f7364a%2C32867%2C1731907139252.1731907142013 2024-11-18T05:19:29,370 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/1/7cf745f7364a%2C32867%2C1731907139252.1731907142013 2024-11-18T05:19:29,371 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/1 2024-11-18T05:19:29,371 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/1 2024-11-18T05:19:29,371 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=109}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-11-18T05:19:29,371 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=109}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=109 2024-11-18T05:19:29,371 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=109 2024-11-18T05:19:29,373 INFO [PEWorker-1 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:29,375 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=109, resume processing ppid=108 2024-11-18T05:19:29,375 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=109, ppid=108, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 261 msec 2024-11-18T05:19:29,377 DEBUG [PEWorker-4 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-11-18T05:19:29,377 INFO [PEWorker-4 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-11-18T05:19:29,378 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=108, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 272 msec 2024-11-18T05:19:29,423 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=108 2024-11-18T05:19:29,423 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-11-18T05:19:29,424 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-11-18T05:19:29,424 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=110, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-11-18T05:19:29,425 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=110 2024-11-18T05:19:29,425 WARN [PEWorker-3 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-11-18T05:19:29,427 ERROR [PEWorker-3 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=110, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-11-18T05:19:29,428 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=110, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=3 msec 2024-11-18T05:19:29,428 WARN [PEWorker-3 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-11-18T05:19:29,533 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=110 2024-11-18T05:19:29,534 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-11-18T05:19:29,534 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-11-18T05:19:29,535 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=111, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-11-18T05:19:29,535 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=111 2024-11-18T05:19:29,536 WARN [PEWorker-5 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-11-18T05:19:29,536 ERROR [PEWorker-5 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=111, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-11-18T05:19:29,537 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=111, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=3 msec 2024-11-18T05:19:29,537 WARN [PEWorker-5 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-11-18T05:19:29,642 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=111 2024-11-18T05:19:29,643 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-11-18T05:19:29,654 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testPeerConfig[0] Thread=221 (was 221), OpenFileDescriptor=446 (was 446), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=414 (was 432), ProcessCount=11 (was 11), AvailableMemoryMB=11855 (was 11871) 2024-11-18T05:19:29,662 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testReplicationPeerModificationSwitch[0] Thread=221, OpenFileDescriptor=446, MaxFileDescriptor=1048576, SystemLoadAverage=414, ProcessCount=11, AvailableMemoryMB=11854 2024-11-18T05:19:29,668 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-11-18T05:19:29,668 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] ipc.MetricsHBaseServer(152): Unknown exception type java.io.IOException: Replication peer modification disabled at org.apache.hadoop.hbase.master.HMaster.executePeerProcedure(HMaster.java:3909) ~[classes/:?] at org.apache.hadoop.hbase.master.HMaster.addReplicationPeer(HMaster.java:3921) ~[classes/:?] at org.apache.hadoop.hbase.master.MasterRpcServices.addReplicationPeer(MasterRpcServices.java:2115) ~[classes/:?] at org.apache.hadoop.hbase.shaded.protobuf.generated.MasterProtos$MasterService$2.callBlockingMethod(MasterProtos.java) ~[hbase-protocol-shaded-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.RpcServer.call(RpcServer.java:443) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.CallRunner.run(CallRunner.java:124) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:105) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) ~[classes/:2.7.0-SNAPSHOT] 2024-11-18T05:19:29,668 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] ipc.CallRunner(138): callId: 341 service: MasterService methodName: AddReplicationPeer size: 80 connection: 172.17.0.2:35970 deadline: 1731907229668, exception=java.io.IOException: Replication peer modification disabled 2024-11-18T05:19:29,688 WARN [RPCClient-NioEventLoopGroup-4-2 {}] client.AsyncRpcRetryingCaller(168): Call to master failed, tries = 1, maxAttempts = 2, timeout = 120000 ms, time elapsed = 20 ms java.io.IOException: java.io.IOException: Replication peer modification disabled at org.apache.hadoop.hbase.master.HMaster.executePeerProcedure(HMaster.java:3909) at org.apache.hadoop.hbase.master.HMaster.addReplicationPeer(HMaster.java:3921) at org.apache.hadoop.hbase.master.MasterRpcServices.addReplicationPeer(MasterRpcServices.java:2115) at org.apache.hadoop.hbase.shaded.protobuf.generated.MasterProtos$MasterService$2.callBlockingMethod(MasterProtos.java) at org.apache.hadoop.hbase.ipc.RpcServer.call(RpcServer.java:443) at org.apache.hadoop.hbase.ipc.CallRunner.run(CallRunner.java:124) at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:105) at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.ipc.RemoteWithExtrasException.instantiateException(RemoteWithExtrasException.java:110) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.RemoteWithExtrasException.unwrapRemoteException(RemoteWithExtrasException.java:100) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionUtils.translateException(ConnectionUtils.java:245) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.AsyncRpcRetryingCaller.onError(AsyncRpcRetryingCaller.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.AsyncMasterRequestRpcRetryingCaller.lambda$doCall$4(AsyncMasterRequestRpcRetryingCaller.java:76) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.util.FutureUtils.lambda$addListener$0(FutureUtils.java:71) ~[hbase-common-2.7.0-SNAPSHOT.jar:?] at java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:863) ~[?:?] at java.util.concurrent.CompletableFuture$UniWhenComplete.tryFire(CompletableFuture.java:841) ~[?:?] at java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:510) ~[?:?] at java.util.concurrent.CompletableFuture.completeExceptionally(CompletableFuture.java:2162) ~[?:?] at org.apache.hadoop.hbase.client.RawAsyncHBaseAdmin$1.run(RawAsyncHBaseAdmin.java:431) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hbase.thirdparty.com.google.protobuf.RpcUtil$1.run(RpcUtil.java:56) ~[hbase-shaded-protobuf-4.1.9.jar:4.1.9] at org.apache.hbase.thirdparty.com.google.protobuf.RpcUtil$1.run(RpcUtil.java:47) ~[hbase-shaded-protobuf-4.1.9.jar:4.1.9] at org.apache.hadoop.hbase.ipc.AbstractRpcClient.onCallFinished(AbstractRpcClient.java:397) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.AbstractRpcClient.access$100(AbstractRpcClient.java:94) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.AbstractRpcClient$3.run(AbstractRpcClient.java:430) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.AbstractRpcClient$3.run(AbstractRpcClient.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.Call.callComplete(Call.java:116) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.Call.setException(Call.java:131) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.RpcConnection.readResponse(RpcConnection.java:457) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.NettyRpcDuplexHandler.readResponse(NettyRpcDuplexHandler.java:125) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.NettyRpcDuplexHandler.channelRead(NettyRpcDuplexHandler.java:140) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:442) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:420) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:412) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.handler.codec.ByteToMessageDecoder.fireChannelRead(ByteToMessageDecoder.java:346) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.handler.codec.ByteToMessageDecoder.channelRead(ByteToMessageDecoder.java:318) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:444) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:420) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:412) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.handler.timeout.IdleStateHandler.channelRead(IdleStateHandler.java:289) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:442) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:420) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:412) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.DefaultChannelPipeline$HeadContext.channelRead(DefaultChannelPipeline.java:1357) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:440) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:420) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.DefaultChannelPipeline.fireChannelRead(DefaultChannelPipeline.java:868) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.nio.AbstractNioByteChannel$NioByteUnsafe.read(AbstractNioByteChannel.java:166) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.nio.NioEventLoop.processSelectedKey(NioEventLoop.java:788) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.nio.NioEventLoop.processSelectedKeysOptimized(NioEventLoop.java:724) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.nio.NioEventLoop.processSelectedKeys(NioEventLoop.java:650) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:562) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:997) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) ~[hbase-shaded-netty-4.1.9.jar:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.hadoop.hbase.ipc.RemoteWithExtrasException: java.io.IOException: Replication peer modification disabled at org.apache.hadoop.hbase.master.HMaster.executePeerProcedure(HMaster.java:3909) at org.apache.hadoop.hbase.master.HMaster.addReplicationPeer(HMaster.java:3921) at org.apache.hadoop.hbase.master.MasterRpcServices.addReplicationPeer(MasterRpcServices.java:2115) at org.apache.hadoop.hbase.shaded.protobuf.generated.MasterProtos$MasterService$2.callBlockingMethod(MasterProtos.java) at org.apache.hadoop.hbase.ipc.RpcServer.call(RpcServer.java:443) at org.apache.hadoop.hbase.ipc.CallRunner.run(CallRunner.java:124) at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:105) at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) at org.apache.hadoop.hbase.ipc.AbstractRpcClient.onCallFinished(AbstractRpcClient.java:392) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 33 more 2024-11-18T05:19:29,793 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-11-18T05:19:29,793 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] ipc.MetricsHBaseServer(152): Unknown exception type java.io.IOException: Replication peer modification disabled at org.apache.hadoop.hbase.master.HMaster.executePeerProcedure(HMaster.java:3909) ~[classes/:?] at org.apache.hadoop.hbase.master.HMaster.addReplicationPeer(HMaster.java:3921) ~[classes/:?] at org.apache.hadoop.hbase.master.MasterRpcServices.addReplicationPeer(MasterRpcServices.java:2115) ~[classes/:?] at org.apache.hadoop.hbase.shaded.protobuf.generated.MasterProtos$MasterService$2.callBlockingMethod(MasterProtos.java) ~[hbase-protocol-shaded-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.RpcServer.call(RpcServer.java:443) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.CallRunner.run(CallRunner.java:124) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:105) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) ~[classes/:2.7.0-SNAPSHOT] 2024-11-18T05:19:29,793 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] ipc.CallRunner(138): callId: 342 service: MasterService methodName: AddReplicationPeer size: 80 connection: 172.17.0.2:35970 deadline: 1731907229792, exception=java.io.IOException: Replication peer modification disabled 2024-11-18T05:19:29,793 WARN [RPCClient-NioEventLoopGroup-4-2 {}] client.AsyncRpcRetryingCaller(168): Call to master failed, tries = 2, maxAttempts = 2, timeout = 120000 ms, time elapsed = 125 ms java.io.IOException: java.io.IOException: Replication peer modification disabled at org.apache.hadoop.hbase.master.HMaster.executePeerProcedure(HMaster.java:3909) at org.apache.hadoop.hbase.master.HMaster.addReplicationPeer(HMaster.java:3921) at org.apache.hadoop.hbase.master.MasterRpcServices.addReplicationPeer(MasterRpcServices.java:2115) at org.apache.hadoop.hbase.shaded.protobuf.generated.MasterProtos$MasterService$2.callBlockingMethod(MasterProtos.java) at org.apache.hadoop.hbase.ipc.RpcServer.call(RpcServer.java:443) at org.apache.hadoop.hbase.ipc.CallRunner.run(CallRunner.java:124) at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:105) at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.ipc.RemoteWithExtrasException.instantiateException(RemoteWithExtrasException.java:110) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.RemoteWithExtrasException.unwrapRemoteException(RemoteWithExtrasException.java:100) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionUtils.translateException(ConnectionUtils.java:245) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.AsyncRpcRetryingCaller.onError(AsyncRpcRetryingCaller.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.AsyncMasterRequestRpcRetryingCaller.lambda$doCall$4(AsyncMasterRequestRpcRetryingCaller.java:76) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.util.FutureUtils.lambda$addListener$0(FutureUtils.java:71) ~[hbase-common-2.7.0-SNAPSHOT.jar:?] at java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:863) ~[?:?] at java.util.concurrent.CompletableFuture$UniWhenComplete.tryFire(CompletableFuture.java:841) ~[?:?] at java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:510) ~[?:?] at java.util.concurrent.CompletableFuture.completeExceptionally(CompletableFuture.java:2162) ~[?:?] at org.apache.hadoop.hbase.client.RawAsyncHBaseAdmin$1.run(RawAsyncHBaseAdmin.java:431) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hbase.thirdparty.com.google.protobuf.RpcUtil$1.run(RpcUtil.java:56) ~[hbase-shaded-protobuf-4.1.9.jar:4.1.9] at org.apache.hbase.thirdparty.com.google.protobuf.RpcUtil$1.run(RpcUtil.java:47) ~[hbase-shaded-protobuf-4.1.9.jar:4.1.9] at org.apache.hadoop.hbase.ipc.AbstractRpcClient.onCallFinished(AbstractRpcClient.java:397) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.AbstractRpcClient.access$100(AbstractRpcClient.java:94) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.AbstractRpcClient$3.run(AbstractRpcClient.java:430) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.AbstractRpcClient$3.run(AbstractRpcClient.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.Call.callComplete(Call.java:116) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.Call.setException(Call.java:131) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.RpcConnection.readResponse(RpcConnection.java:457) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.NettyRpcDuplexHandler.readResponse(NettyRpcDuplexHandler.java:125) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.NettyRpcDuplexHandler.channelRead(NettyRpcDuplexHandler.java:140) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:442) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:420) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:412) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.handler.codec.ByteToMessageDecoder.fireChannelRead(ByteToMessageDecoder.java:346) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.handler.codec.ByteToMessageDecoder.channelRead(ByteToMessageDecoder.java:318) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:444) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:420) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:412) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.handler.timeout.IdleStateHandler.channelRead(IdleStateHandler.java:289) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:442) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:420) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:412) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.DefaultChannelPipeline$HeadContext.channelRead(DefaultChannelPipeline.java:1357) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:440) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:420) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.DefaultChannelPipeline.fireChannelRead(DefaultChannelPipeline.java:868) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.nio.AbstractNioByteChannel$NioByteUnsafe.read(AbstractNioByteChannel.java:166) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.nio.NioEventLoop.processSelectedKey(NioEventLoop.java:788) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.nio.NioEventLoop.processSelectedKeysOptimized(NioEventLoop.java:724) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.nio.NioEventLoop.processSelectedKeys(NioEventLoop.java:650) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:562) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:997) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) ~[hbase-shaded-netty-4.1.9.jar:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.hadoop.hbase.ipc.RemoteWithExtrasException: java.io.IOException: Replication peer modification disabled at org.apache.hadoop.hbase.master.HMaster.executePeerProcedure(HMaster.java:3909) at org.apache.hadoop.hbase.master.HMaster.addReplicationPeer(HMaster.java:3921) at org.apache.hadoop.hbase.master.MasterRpcServices.addReplicationPeer(MasterRpcServices.java:2115) at org.apache.hadoop.hbase.shaded.protobuf.generated.MasterProtos$MasterService$2.callBlockingMethod(MasterProtos.java) at org.apache.hadoop.hbase.ipc.RpcServer.call(RpcServer.java:443) at org.apache.hadoop.hbase.ipc.CallRunner.run(CallRunner.java:124) at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:105) at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) at org.apache.hadoop.hbase.ipc.AbstractRpcClient.onCallFinished(AbstractRpcClient.java:392) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 33 more 2024-11-18T05:19:29,794 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: ADD_REPLICATION_PEER, peerId: 1 failed with Failed after attempts=2, exceptions: 2024-11-18T05:19:29.689Z, java.io.IOException: java.io.IOException: Replication peer modification disabled at org.apache.hadoop.hbase.master.HMaster.executePeerProcedure(HMaster.java:3909) at org.apache.hadoop.hbase.master.HMaster.addReplicationPeer(HMaster.java:3921) at org.apache.hadoop.hbase.master.MasterRpcServices.addReplicationPeer(MasterRpcServices.java:2115) at org.apache.hadoop.hbase.shaded.protobuf.generated.MasterProtos$MasterService$2.callBlockingMethod(MasterProtos.java) at org.apache.hadoop.hbase.ipc.RpcServer.call(RpcServer.java:443) at org.apache.hadoop.hbase.ipc.CallRunner.run(CallRunner.java:124) at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:105) at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) 2024-11-18T05:19:29.794Z, java.io.IOException: java.io.IOException: Replication peer modification disabled at org.apache.hadoop.hbase.master.HMaster.executePeerProcedure(HMaster.java:3909) at org.apache.hadoop.hbase.master.HMaster.addReplicationPeer(HMaster.java:3921) at org.apache.hadoop.hbase.master.MasterRpcServices.addReplicationPeer(MasterRpcServices.java:2115) at org.apache.hadoop.hbase.shaded.protobuf.generated.MasterProtos$MasterService$2.callBlockingMethod(MasterProtos.java) at org.apache.hadoop.hbase.ipc.RpcServer.call(RpcServer.java:443) at org.apache.hadoop.hbase.ipc.CallRunner.run(CallRunner.java:124) at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:105) at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) 2024-11-18T05:19:29,796 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-11-18T05:19:29,796 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=112, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-11-18T05:19:29,797 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=112 2024-11-18T05:19:29,797 WARN [PEWorker-2 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-11-18T05:19:29,799 ERROR [PEWorker-2 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=112, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-11-18T05:19:29,800 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=112, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=3 msec 2024-11-18T05:19:29,800 WARN [PEWorker-2 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-11-18T05:19:29,903 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=112 2024-11-18T05:19:29,904 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-11-18T05:19:29,904 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-11-18T05:19:29,905 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=113, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-11-18T05:19:29,906 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=113 2024-11-18T05:19:29,906 WARN [PEWorker-1 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-11-18T05:19:29,907 ERROR [PEWorker-1 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=113, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-11-18T05:19:29,908 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=113, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=3 msec 2024-11-18T05:19:29,908 WARN [PEWorker-1 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-11-18T05:19:30,013 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=113 2024-11-18T05:19:30,014 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-11-18T05:19:30,025 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testReplicationPeerModificationSwitch[0] Thread=221 (was 221), OpenFileDescriptor=446 (was 446), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=414 (was 414), ProcessCount=11 (was 11), AvailableMemoryMB=11849 (was 11854) 2024-11-18T05:19:30,033 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testClusterKeyWithTrailingSpace[0] Thread=221, OpenFileDescriptor=446, MaxFileDescriptor=1048576, SystemLoadAverage=414, ProcessCount=11, AvailableMemoryMB=11849 2024-11-18T05:19:30,034 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-11-18T05:19:30,035 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=114, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-11-18T05:19:30,035 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=114 2024-11-18T05:19:30,050 INFO [PEWorker-4 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:30,051 INFO [PEWorker-4 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:30,053 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id0x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:30,054 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b005f connected 2024-11-18T05:19:30,143 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=114 2024-11-18T05:19:30,155 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b005f, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:30,160 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=115, ppid=114, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:30,312 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:30,312 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=115 2024-11-18T05:19:30,312 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=115}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-11-18T05:19:30,328 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=115}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:30,343 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=115}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-11-18T05:19:30,349 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=115}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=115 2024-11-18T05:19:30,350 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=115 2024-11-18T05:19:30,351 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:30,352 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=114 2024-11-18T05:19:30,353 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=115, resume processing ppid=114 2024-11-18T05:19:30,353 INFO [PEWorker-2 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-11-18T05:19:30,353 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=115, ppid=114, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 191 msec 2024-11-18T05:19:30,354 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=114, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 319 msec 2024-11-18T05:19:30,378 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x18a5cfa5 to 127.0.0.1:61937 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@5db478b 2024-11-18T05:19:30,381 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-11-18T05:19:30,382 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-11-18T05:19:30,382 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@73be874c, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-11-18T05:19:30,383 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:30,385 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:30,385 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-11-18T05:19:30,385 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1000911699b0061 connected 2024-11-18T05:19:30,663 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=114 2024-11-18T05:19:30,663 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-11-18T05:19:30,663 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:30,664 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-11-18T05:19:30,665 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=116, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-11-18T05:19:30,665 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=116 2024-11-18T05:19:30,667 DEBUG [PEWorker-1 {}] zookeeper.ZKUtil(111): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-11-18T05:19:30,669 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-11-18T05:19:30,669 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-11-18T05:19:30,669 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-11-18T05:19:30,670 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=117, ppid=116, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:30,773 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=116 2024-11-18T05:19:30,821 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:30,822 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=117 2024-11-18T05:19:30,822 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=117}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-11-18T05:19:30,822 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=117}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-11-18T05:19:30,822 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=117}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-11-18T05:19:30,822 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-11-18T05:19:30,822 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1000911699b0061, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:30,822 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1000911699b0061, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:30,924 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1000911699b0061, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:30,924 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=117}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x18a5cfa5 to 127.0.0.1:61937 2024-11-18T05:19:30,924 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=117}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-11-18T05:19:30,925 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=117}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-11-18T05:19:30,927 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=117}] zookeeper.ZKUtil(111): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/1/7cf745f7364a%2C32867%2C1731907139252.1731907142013 2024-11-18T05:19:30,929 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/1/7cf745f7364a%2C32867%2C1731907139252.1731907142013 2024-11-18T05:19:30,929 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/1 2024-11-18T05:19:30,929 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/1 2024-11-18T05:19:30,929 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=117}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-11-18T05:19:30,929 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=117}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=117 2024-11-18T05:19:30,930 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=117 2024-11-18T05:19:30,931 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:30,932 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=117, resume processing ppid=116 2024-11-18T05:19:30,933 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=117, ppid=116, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 261 msec 2024-11-18T05:19:30,935 DEBUG [PEWorker-5 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-11-18T05:19:30,935 INFO [PEWorker-5 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-11-18T05:19:30,936 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=116, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 271 msec 2024-11-18T05:19:30,983 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=116 2024-11-18T05:19:30,983 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-11-18T05:19:30,983 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-11-18T05:19:30,984 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=118, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-11-18T05:19:30,985 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=118 2024-11-18T05:19:30,985 WARN [PEWorker-2 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-11-18T05:19:30,986 ERROR [PEWorker-2 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=118, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-11-18T05:19:30,987 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=118, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=3 msec 2024-11-18T05:19:30,987 WARN [PEWorker-2 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-11-18T05:19:31,093 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=118 2024-11-18T05:19:31,094 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-11-18T05:19:31,111 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testClusterKeyWithTrailingSpace[0] Thread=221 (was 221), OpenFileDescriptor=446 (was 446), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=414 (was 414), ProcessCount=11 (was 11), AvailableMemoryMB=11828 (was 11849) 2024-11-18T05:19:31,120 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testPeerBandwidth[0] Thread=221, OpenFileDescriptor=446, MaxFileDescriptor=1048576, SystemLoadAverage=414, ProcessCount=11, AvailableMemoryMB=11828 2024-11-18T05:19:31,121 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-11-18T05:19:31,122 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=119, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-11-18T05:19:31,123 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=119 2024-11-18T05:19:31,138 INFO [PEWorker-4 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:31,139 INFO [PEWorker-4 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:31,142 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id0x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:31,142 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0062 connected 2024-11-18T05:19:31,233 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=119 2024-11-18T05:19:31,244 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0062, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:31,250 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=120, ppid=119, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:31,401 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:31,402 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=120 2024-11-18T05:19:31,402 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=120}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-11-18T05:19:31,418 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=120}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:31,432 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=120}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-11-18T05:19:31,441 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=120}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=120 2024-11-18T05:19:31,441 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=120 2024-11-18T05:19:31,442 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=119 2024-11-18T05:19:31,443 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:31,444 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=120, resume processing ppid=119 2024-11-18T05:19:31,445 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=120, ppid=119, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 194 msec 2024-11-18T05:19:31,445 INFO [PEWorker-5 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-11-18T05:19:31,446 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=119, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 324 msec 2024-11-18T05:19:31,469 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x7c22df40 to 127.0.0.1:61937 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@6e4e38dc 2024-11-18T05:19:31,472 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-11-18T05:19:31,472 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-11-18T05:19:31,473 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@fbec2af, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-11-18T05:19:31,473 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:31,476 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:31,476 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-11-18T05:19:31,476 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1000911699b0064 connected 2024-11-18T05:19:31,721 DEBUG [BootstrapNodeManager {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=RegionServerStatusService, sasl=false 2024-11-18T05:19:31,723 INFO [RS-EventLoopGroup-1-1 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.2:36620, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins.hfs.0 (auth:SIMPLE), service=RegionServerStatusService 2024-11-18T05:19:31,752 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=119 2024-11-18T05:19:31,753 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-11-18T05:19:31,753 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:31,754 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=2097152,serial=false 2024-11-18T05:19:31,754 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=121, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-11-18T05:19:31,755 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=121 2024-11-18T05:19:31,770 INFO [PEWorker-2 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:31,770 INFO [PEWorker-2 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:31,773 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id0x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:31,773 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0065 connected 2024-11-18T05:19:31,822 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-11-18T05:19:31,863 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=121 2024-11-18T05:19:31,875 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0065, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:31,878 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=122, ppid=121, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:32,029 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:32,030 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=122 2024-11-18T05:19:32,030 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=122}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-11-18T05:19:32,031 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=122}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=122 2024-11-18T05:19:32,031 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=122 2024-11-18T05:19:32,033 INFO [PEWorker-1 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:32,035 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=122, resume processing ppid=121 2024-11-18T05:19:32,035 INFO [PEWorker-3 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=2097152,serial=false 2024-11-18T05:19:32,035 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=122, ppid=121, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 155 msec 2024-11-18T05:19:32,036 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=121, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 281 msec 2024-11-18T05:19:32,073 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=121 2024-11-18T05:19:32,073 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-11-18T05:19:32,073 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:32,074 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-11-18T05:19:32,075 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=123, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-11-18T05:19:32,075 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=123 2024-11-18T05:19:32,077 DEBUG [PEWorker-5 {}] zookeeper.ZKUtil(111): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-11-18T05:19:32,079 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-11-18T05:19:32,079 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-11-18T05:19:32,079 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-11-18T05:19:32,080 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=124, ppid=123, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:32,183 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=123 2024-11-18T05:19:32,231 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:32,231 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=124 2024-11-18T05:19:32,232 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=124}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-11-18T05:19:32,232 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=124}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-11-18T05:19:32,232 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=124}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-11-18T05:19:32,232 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-11-18T05:19:32,232 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1000911699b0064, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:32,232 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1000911699b0064, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:32,334 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1000911699b0064, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:32,334 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=124}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x7c22df40 to 127.0.0.1:61937 2024-11-18T05:19:32,335 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=124}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-11-18T05:19:32,335 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=124}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-11-18T05:19:32,337 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=124}] zookeeper.ZKUtil(111): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/1/7cf745f7364a%2C32867%2C1731907139252.1731907142013 2024-11-18T05:19:32,339 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/1/7cf745f7364a%2C32867%2C1731907139252.1731907142013 2024-11-18T05:19:32,339 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/1 2024-11-18T05:19:32,339 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/1 2024-11-18T05:19:32,339 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=124}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-11-18T05:19:32,340 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=124}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=124 2024-11-18T05:19:32,340 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=124 2024-11-18T05:19:32,342 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:32,343 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=124, resume processing ppid=123 2024-11-18T05:19:32,343 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=124, ppid=123, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 262 msec 2024-11-18T05:19:32,346 DEBUG [PEWorker-1 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-11-18T05:19:32,346 INFO [PEWorker-1 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-11-18T05:19:32,347 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=123, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 272 msec 2024-11-18T05:19:32,393 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=123 2024-11-18T05:19:32,394 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-11-18T05:19:32,394 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-11-18T05:19:32,395 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=125, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-11-18T05:19:32,395 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=125 2024-11-18T05:19:32,395 WARN [PEWorker-3 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-11-18T05:19:32,396 ERROR [PEWorker-3 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=125, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-11-18T05:19:32,397 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=125, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=2 msec 2024-11-18T05:19:32,397 WARN [PEWorker-3 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-11-18T05:19:32,503 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=125 2024-11-18T05:19:32,504 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-11-18T05:19:32,504 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-11-18T05:19:32,505 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=126, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-11-18T05:19:32,505 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=126 2024-11-18T05:19:32,506 WARN [PEWorker-5 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-11-18T05:19:32,506 ERROR [PEWorker-5 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=126, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-11-18T05:19:32,507 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=126, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=2 msec 2024-11-18T05:19:32,507 WARN [PEWorker-5 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-11-18T05:19:32,613 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=126 2024-11-18T05:19:32,613 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-11-18T05:19:32,626 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testPeerBandwidth[0] Thread=223 (was 221) - Thread LEAK? -, OpenFileDescriptor=450 (was 446) - OpenFileDescriptor LEAK? -, MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=414 (was 414), ProcessCount=11 (was 11), AvailableMemoryMB=11798 (was 11828) 2024-11-18T05:19:32,633 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testSetReplicationEndpoint[0] Thread=223, OpenFileDescriptor=450, MaxFileDescriptor=1048576, SystemLoadAverage=414, ProcessCount=11, AvailableMemoryMB=11797 2024-11-18T05:19:32,635 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=,replicationEndpointImpl=org.apache.hadoop.hbase.replication.VerifyWALEntriesReplicationEndpoint,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-11-18T05:19:32,635 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=127, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-11-18T05:19:32,636 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=127 2024-11-18T05:19:32,642 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=128, ppid=127, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:32,743 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=127 2024-11-18T05:19:32,794 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:32,794 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=128 2024-11-18T05:19:32,794 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=128}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-11-18T05:19:32,825 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=128}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-11-18T05:19:32,835 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=128}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=128 2024-11-18T05:19:32,835 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(587): peerId=1, queueId=1 (queues=1) is replicating from cluster=447e98b2-1824-4bc5-9f42-421c6abc30fb to cluster=447e98b2-1824-4bc5-9f42-421c6abc30fb 2024-11-18T05:19:32,835 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=128 2024-11-18T05:19:32,836 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(343): peerId=1, starting shipping worker for walGroupId=7cf745f7364a%2C32867%2C1731907139252 2024-11-18T05:19:32,837 INFO [PEWorker-1 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:32,838 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=128, resume processing ppid=127 2024-11-18T05:19:32,838 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=128, ppid=127, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 195 msec 2024-11-18T05:19:32,838 INFO [PEWorker-3 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=,replicationEndpointImpl=org.apache.hadoop.hbase.replication.VerifyWALEntriesReplicationEndpoint,replicateAllUserTables=true,bandwidth=0,serial=false 2024-11-18T05:19:32,839 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSourceWALReader(112): peerClusterZnode=1, ReplicationSourceWALReaderThread : 1 inited, replicationBatchSizeCapacity=67108864, replicationBatchCountCapacity=25000, replicationBatchQueueCapacity=1 2024-11-18T05:19:32,839 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=127, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 203 msec 2024-11-18T05:19:32,840 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1.replicationSource.shipper7cf745f7364a%2C32867%2C1731907139252,1 {}] regionserver.ReplicationSourceShipper(98): Running ReplicationSourceShipper Thread for wal group: 7cf745f7364a%2C32867%2C1731907139252 2024-11-18T05:19:32,840 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1.replicationSource.wal-reader.7cf745f7364a%2C32867%2C1731907139252,1 {}] regionserver.WALEntryStream(260): Creating new reader hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/WALs/7cf745f7364a,32867,1731907139252/7cf745f7364a%2C32867%2C1731907139252.1731907142013, startPosition=0, beingWritten=true 2024-11-18T05:19:32,907 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1.replicationSource.wal-reader.7cf745f7364a%2C32867%2C1731907139252,1 {}] regionserver.ReplicationSourceWALReader(181): Read 0 WAL entries eligible for replication 2024-11-18T05:19:32,907 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1.replicationSource.wal-reader.7cf745f7364a%2C32867%2C1731907139252,1 {}] regionserver.WALEntryStream(223): Reset reader hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/WALs/7cf745f7364a,32867,1731907139252/7cf745f7364a%2C32867%2C1731907139252.1731907142013 to pos 589, reset compression=false 2024-11-18T05:19:32,907 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1.replicationSource.shipper7cf745f7364a%2C32867%2C1731907139252,1 {}] regionserver.ReplicationSourceShipper(110): Shipper from source 1 got entry batch from reader: WALEntryBatch [walEntries=[], lastWalPath=hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/WALs/7cf745f7364a,32867,1731907139252/7cf745f7364a%2C32867%2C1731907139252.1731907142013, lastWalPosition=589, nbRowKeys=0, nbHFiles=0, heapSize=0, lastSeqIds={}, endOfFile=false,usedBufferSize=0] 2024-11-18T05:19:32,953 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=127 2024-11-18T05:19:32,954 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-11-18T05:19:32,954 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=2, config=clusterKey=,replicationEndpointImpl=org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-11-18T05:19:32,955 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=129, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-11-18T05:19:32,956 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=129 2024-11-18T05:19:32,956 WARN [PEWorker-5 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.AddPeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.DoNotRetryIOException: Invalid cluster key: at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkClusterKey(ReplicationPeerManager.java:395) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerConfig(ReplicationPeerManager.java:298) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preAddPeer(ReplicationPeerManager.java:119) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.AddPeerProcedure.prePeerModification(AddPeerProcedure.java:90) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: java.io.IOException: Cluster key passed is invalid, the format should be:hbase.zookeeper.quorum:hbase.zookeeper.property.clientPort:zookeeper.znode.parent at org.apache.hadoop.hbase.zookeeper.ZKConfig.transformClusterKey(ZKConfig.java:228) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKConfig.validateClusterKey(ZKConfig.java:178) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkClusterKey(ReplicationPeerManager.java:393) ~[classes/:?] ... 13 more 2024-11-18T05:19:32,957 ERROR [PEWorker-5 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=129, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.DoNotRetryIOException via master-add-peer:org.apache.hadoop.hbase.DoNotRetryIOException: Invalid cluster key: ; org.apache.hadoop.hbase.master.replication.AddPeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.DoNotRetryIOException: Invalid cluster key: at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.DoNotRetryIOException: Invalid cluster key: at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkClusterKey(ReplicationPeerManager.java:395) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerConfig(ReplicationPeerManager.java:298) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preAddPeer(ReplicationPeerManager.java:119) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.AddPeerProcedure.prePeerModification(AddPeerProcedure.java:90) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more Caused by: java.io.IOException: Cluster key passed is invalid, the format should be:hbase.zookeeper.quorum:hbase.zookeeper.property.clientPort:zookeeper.znode.parent at org.apache.hadoop.hbase.zookeeper.ZKConfig.transformClusterKey(ZKConfig.java:228) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKConfig.validateClusterKey(ZKConfig.java:178) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkClusterKey(ReplicationPeerManager.java:393) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerConfig(ReplicationPeerManager.java:298) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preAddPeer(ReplicationPeerManager.java:119) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.AddPeerProcedure.prePeerModification(AddPeerProcedure.java:90) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-11-18T05:19:32,958 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=129, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.DoNotRetryIOException via master-add-peer:org.apache.hadoop.hbase.DoNotRetryIOException: Invalid cluster key: ; org.apache.hadoop.hbase.master.replication.AddPeerProcedure exec-time=3 msec 2024-11-18T05:19:32,958 WARN [PEWorker-5 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-11-18T05:19:33,063 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=129 2024-11-18T05:19:33,064 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: ADD_REPLICATION_PEER, peerId: 2 failed with Invalid cluster key: 2024-11-18T05:19:33,065 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-11-18T05:19:33,066 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=130, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-11-18T05:19:33,067 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=130 2024-11-18T05:19:33,069 DEBUG [PEWorker-2 {}] zookeeper.ZKUtil(111): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-11-18T05:19:33,071 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-11-18T05:19:33,071 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-11-18T05:19:33,071 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-11-18T05:19:33,072 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=131, ppid=130, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:33,173 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=130 2024-11-18T05:19:33,224 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:33,225 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=131 2024-11-18T05:19:33,225 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=131}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-11-18T05:19:33,225 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=131}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-11-18T05:19:33,225 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=131}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-11-18T05:19:33,383 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=130 2024-11-18T05:19:33,693 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=130 2024-11-18T05:19:34,203 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=130 2024-11-18T05:19:34,225 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1.replicationSource.wal-reader.7cf745f7364a%2C32867%2C1731907139252,1 {}] util.Threads(127): sleep interrupted java.lang.InterruptedException: sleep interrupted at java.lang.Thread.sleep(Native Method) ~[?:?] at org.apache.hadoop.hbase.util.Threads.sleep(Threads.java:125) ~[hbase-common-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSourceWALReader.sleep(ReplicationSourceWALReader.java:131) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSourceWALReader.run(ReplicationSourceWALReader.java:166) ~[classes/:?] 2024-11-18T05:19:34,225 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1.replicationSource.shipper7cf745f7364a%2C32867%2C1731907139252,1 {}] regionserver.ReplicationSourceShipper(123): Interrupted while waiting for next replication entry batch java.lang.InterruptedException: null at java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1681) ~[?:?] at java.util.concurrent.LinkedBlockingQueue.poll(LinkedBlockingQueue.java:460) ~[?:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSourceWALReader.poll(ReplicationSourceWALReader.java:313) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSourceShipper.run(ReplicationSourceShipper.java:109) ~[classes/:?] 2024-11-18T05:19:35,213 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=130 2024-11-18T05:19:35,225 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=131}] regionserver.ReplicationSource(711): peerId=1, ReplicationSourceWorker RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1.replicationSource.shipper7cf745f7364a%2C32867%2C1731907139252,1 terminated 2024-11-18T05:19:35,226 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=131}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-11-18T05:19:35,227 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=131}] zookeeper.ZKUtil(111): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/1/7cf745f7364a%2C32867%2C1731907139252.1731907142013 2024-11-18T05:19:35,229 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/1/7cf745f7364a%2C32867%2C1731907139252.1731907142013 2024-11-18T05:19:35,229 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/1 2024-11-18T05:19:35,229 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/1 2024-11-18T05:19:35,229 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=131}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-11-18T05:19:35,230 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=131}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=131 2024-11-18T05:19:35,230 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=131 2024-11-18T05:19:35,232 INFO [PEWorker-1 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:35,233 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=131, resume processing ppid=130 2024-11-18T05:19:35,233 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=131, ppid=130, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 2.1600 sec 2024-11-18T05:19:35,236 DEBUG [PEWorker-3 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-11-18T05:19:35,237 INFO [PEWorker-3 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-11-18T05:19:35,239 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=130, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 2.1720 sec 2024-11-18T05:19:37,223 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=130 2024-11-18T05:19:37,224 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-11-18T05:19:37,224 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-11-18T05:19:37,225 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=132, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-11-18T05:19:37,226 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=132 2024-11-18T05:19:37,226 WARN [PEWorker-5 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-11-18T05:19:37,227 ERROR [PEWorker-5 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=132, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-11-18T05:19:37,228 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=132, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=3 msec 2024-11-18T05:19:37,228 WARN [PEWorker-5 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-11-18T05:19:37,333 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=132 2024-11-18T05:19:37,334 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-11-18T05:19:37,348 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testSetReplicationEndpoint[0] Thread=222 (was 223), OpenFileDescriptor=453 (was 450) - OpenFileDescriptor LEAK? -, MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=404 (was 414), ProcessCount=11 (was 11), AvailableMemoryMB=11768 (was 11797) 2024-11-18T05:19:37,358 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testRemovePeerTableCFs[1] Thread=222, OpenFileDescriptor=453, MaxFileDescriptor=1048576, SystemLoadAverage=404, ProcessCount=11, AvailableMemoryMB=11768 2024-11-18T05:19:37,360 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-11-18T05:19:37,361 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=133, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-11-18T05:19:37,361 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=133 2024-11-18T05:19:37,384 INFO [PEWorker-4 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:37,385 INFO [PEWorker-4 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:37,388 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id0x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:37,388 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0066 connected 2024-11-18T05:19:37,473 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=133 2024-11-18T05:19:37,490 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0066, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:37,495 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=134, ppid=133, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:37,647 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:37,647 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=134 2024-11-18T05:19:37,648 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=134}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-11-18T05:19:37,666 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=134}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:37,682 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=134}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-11-18T05:19:37,683 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=133 2024-11-18T05:19:37,689 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=134}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=134 2024-11-18T05:19:37,690 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=134 2024-11-18T05:19:37,693 INFO [PEWorker-1 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:37,694 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=134, resume processing ppid=133 2024-11-18T05:19:37,694 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=134, ppid=133, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 198 msec 2024-11-18T05:19:37,695 INFO [PEWorker-1 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-11-18T05:19:37,697 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=133, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 335 msec 2024-11-18T05:19:37,727 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x076e011d to 127.0.0.1:61937 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@58f337a7 2024-11-18T05:19:37,735 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-11-18T05:19:37,735 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-11-18T05:19:37,735 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@5d66ca2c, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-11-18T05:19:37,736 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:37,738 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:37,739 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-11-18T05:19:37,740 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1000911699b0068 connected 2024-11-18T05:19:37,837 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-11-18T05:19:37,993 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=133 2024-11-18T05:19:37,993 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-11-18T05:19:37,994 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-11-18T05:19:37,995 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=135, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-11-18T05:19:37,996 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=135 2024-11-18T05:19:38,015 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:38,016 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:38,028 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id0x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:38,029 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0069 connected 2024-11-18T05:19:38,103 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=135 2024-11-18T05:19:38,131 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0069, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:38,134 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=136, ppid=135, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:38,287 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:38,288 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=136 2024-11-18T05:19:38,288 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=136}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-11-18T05:19:38,289 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=136}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-11-18T05:19:38,289 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=136}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-11-18T05:19:38,289 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-11-18T05:19:38,289 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1000911699b0068, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:38,290 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1000911699b0068, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:38,313 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=135 2024-11-18T05:19:38,392 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1000911699b0068, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:38,392 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=136}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x076e011d to 127.0.0.1:61937 2024-11-18T05:19:38,392 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=136}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-11-18T05:19:38,410 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=136}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-11-18T05:19:38,410 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=136}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-11-18T05:19:38,411 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=136}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=136 2024-11-18T05:19:38,411 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=136 2024-11-18T05:19:38,413 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:38,417 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=136, resume processing ppid=135 2024-11-18T05:19:38,417 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=136, ppid=135, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 279 msec 2024-11-18T05:19:38,417 INFO [PEWorker-3 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-11-18T05:19:38,418 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=135, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 423 msec 2024-11-18T05:19:38,453 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x09f39963 to 127.0.0.1:61937 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@470e3591 2024-11-18T05:19:38,457 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-11-18T05:19:38,458 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-11-18T05:19:38,458 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@437f6a3b, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-11-18T05:19:38,459 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:38,463 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:38,464 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-11-18T05:19:38,464 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1000911699b006b connected 2024-11-18T05:19:38,623 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=135 2024-11-18T05:19:38,623 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-11-18T05:19:38,624 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:38,625 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:38,625 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:38,626 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst2=[cf1], testRemovePeerTableCFst1=null},bandwidth=0,serial=false 2024-11-18T05:19:38,628 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=137, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-11-18T05:19:38,628 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=137 2024-11-18T05:19:38,647 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:38,648 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:38,651 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id0x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:38,651 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b006c connected 2024-11-18T05:19:38,733 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=137 2024-11-18T05:19:38,753 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b006c, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:38,756 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=138, ppid=137, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:38,908 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:38,909 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=138 2024-11-18T05:19:38,909 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=138}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-11-18T05:19:38,910 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=138}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-11-18T05:19:38,910 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=138}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-11-18T05:19:38,910 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-11-18T05:19:38,911 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1000911699b006b, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:38,911 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1000911699b006b, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:38,943 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=137 2024-11-18T05:19:39,013 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1000911699b006b, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:39,013 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=138}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x09f39963 to 127.0.0.1:61937 2024-11-18T05:19:39,013 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=138}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-11-18T05:19:39,037 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=138}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-11-18T05:19:39,037 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=138}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-11-18T05:19:39,037 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=138}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=138 2024-11-18T05:19:39,038 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=138 2024-11-18T05:19:39,040 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:39,042 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=138, resume processing ppid=137 2024-11-18T05:19:39,042 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=138, ppid=137, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 284 msec 2024-11-18T05:19:39,043 INFO [PEWorker-4 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst2=[cf1], testRemovePeerTableCFst1=null},bandwidth=0,serial=false 2024-11-18T05:19:39,044 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=137, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 417 msec 2024-11-18T05:19:39,071 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x4320aca1 to 127.0.0.1:61937 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@77cf88ae 2024-11-18T05:19:39,075 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-11-18T05:19:39,075 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-11-18T05:19:39,075 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@4db3ba0a, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-11-18T05:19:39,076 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:39,079 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:39,079 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-11-18T05:19:39,079 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1000911699b006e connected 2024-11-18T05:19:39,254 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=137 2024-11-18T05:19:39,254 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-11-18T05:19:39,254 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:39,255 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:39,256 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:39,257 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:39,257 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst2=[cf1]},bandwidth=0,serial=false 2024-11-18T05:19:39,258 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=139, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-11-18T05:19:39,259 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=139 2024-11-18T05:19:39,282 INFO [PEWorker-3 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:39,283 INFO [PEWorker-3 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:39,286 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id0x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:39,286 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b006f connected 2024-11-18T05:19:39,363 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=139 2024-11-18T05:19:39,388 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b006f, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:39,391 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=140, ppid=139, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:39,543 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:39,543 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=140 2024-11-18T05:19:39,543 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=140}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-11-18T05:19:39,544 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=140}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-11-18T05:19:39,545 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=140}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-11-18T05:19:39,545 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-11-18T05:19:39,545 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1000911699b006e, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:39,545 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1000911699b006e, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:39,573 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=139 2024-11-18T05:19:39,647 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1000911699b006e, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:39,647 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=140}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x4320aca1 to 127.0.0.1:61937 2024-11-18T05:19:39,647 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=140}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-11-18T05:19:39,670 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=140}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-11-18T05:19:39,671 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=140}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-11-18T05:19:39,671 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=140}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=140 2024-11-18T05:19:39,672 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=140 2024-11-18T05:19:39,674 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:39,675 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=140, resume processing ppid=139 2024-11-18T05:19:39,676 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=140, ppid=139, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 283 msec 2024-11-18T05:19:39,675 INFO [PEWorker-2 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst2=[cf1]},bandwidth=0,serial=false 2024-11-18T05:19:39,677 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=139, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 418 msec 2024-11-18T05:19:39,706 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x5ffa8332 to 127.0.0.1:61937 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@e7c9d61 2024-11-18T05:19:39,710 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-11-18T05:19:39,711 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-11-18T05:19:39,711 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@39c4c5ae, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-11-18T05:19:39,712 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:39,714 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:39,715 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-11-18T05:19:39,755 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1000911699b0071 connected 2024-11-18T05:19:39,883 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=139 2024-11-18T05:19:39,884 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-11-18T05:19:39,884 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:39,885 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:39,885 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:39,886 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-11-18T05:19:39,887 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=141, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-11-18T05:19:39,888 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=141 2024-11-18T05:19:39,907 INFO [PEWorker-4 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:39,907 INFO [PEWorker-4 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:39,910 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id0x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:39,910 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0072 connected 2024-11-18T05:19:39,993 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=141 2024-11-18T05:19:40,012 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0072, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:40,015 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=142, ppid=141, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:40,167 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:40,167 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=142 2024-11-18T05:19:40,168 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=142}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-11-18T05:19:40,169 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=142}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-11-18T05:19:40,169 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=142}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-11-18T05:19:40,169 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-11-18T05:19:40,170 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1000911699b0071, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:40,170 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1000911699b0071, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:40,202 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=141 2024-11-18T05:19:40,273 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1000911699b0071, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:40,274 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=142}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x5ffa8332 to 127.0.0.1:61937 2024-11-18T05:19:40,274 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=142}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-11-18T05:19:40,296 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=142}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-11-18T05:19:40,296 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=142}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-11-18T05:19:40,296 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=142}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=142 2024-11-18T05:19:40,297 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=142 2024-11-18T05:19:40,299 INFO [PEWorker-1 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:40,300 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=142, resume processing ppid=141 2024-11-18T05:19:40,301 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=142, ppid=141, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 284 msec 2024-11-18T05:19:40,301 INFO [PEWorker-1 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-11-18T05:19:40,302 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=141, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 415 msec 2024-11-18T05:19:40,325 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x372015b0 to 127.0.0.1:61937 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@4ff2d248 2024-11-18T05:19:40,328 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-11-18T05:19:40,329 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-11-18T05:19:40,329 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@1229760f, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-11-18T05:19:40,330 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:40,331 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:40,332 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-11-18T05:19:40,332 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1000911699b0074 connected 2024-11-18T05:19:40,513 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=141 2024-11-18T05:19:40,513 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-11-18T05:19:40,513 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:40,514 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:40,515 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst4=null},bandwidth=0,serial=false 2024-11-18T05:19:40,515 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=143, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-11-18T05:19:40,516 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=143 2024-11-18T05:19:40,538 INFO [PEWorker-2 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:40,539 INFO [PEWorker-2 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:40,541 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id0x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:40,542 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0075 connected 2024-11-18T05:19:40,623 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=143 2024-11-18T05:19:40,643 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0075, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:40,646 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=144, ppid=143, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:40,798 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:40,798 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=144 2024-11-18T05:19:40,799 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=144}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-11-18T05:19:40,800 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=144}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-11-18T05:19:40,800 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=144}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-11-18T05:19:40,800 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-11-18T05:19:40,800 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1000911699b0074, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:40,801 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1000911699b0074, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:40,833 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=143 2024-11-18T05:19:40,903 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1000911699b0074, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:40,903 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=144}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x372015b0 to 127.0.0.1:61937 2024-11-18T05:19:40,903 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=144}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-11-18T05:19:40,925 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=144}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-11-18T05:19:40,925 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=144}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-11-18T05:19:40,926 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=144}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=144 2024-11-18T05:19:40,926 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=144 2024-11-18T05:19:40,928 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:40,929 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=144, resume processing ppid=143 2024-11-18T05:19:40,929 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=144, ppid=143, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 282 msec 2024-11-18T05:19:40,929 INFO [PEWorker-5 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst4=null},bandwidth=0,serial=false 2024-11-18T05:19:40,932 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=143, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 414 msec 2024-11-18T05:19:40,968 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x0de84aa9 to 127.0.0.1:61937 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@10e427b3 2024-11-18T05:19:40,971 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-11-18T05:19:40,971 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-11-18T05:19:40,971 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@1af498a9, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-11-18T05:19:40,972 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:40,974 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:40,975 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-11-18T05:19:40,975 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1000911699b0077 connected 2024-11-18T05:19:41,143 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=143 2024-11-18T05:19:41,144 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-11-18T05:19:41,144 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:41,145 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-11-18T05:19:41,146 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=145, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-11-18T05:19:41,146 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=145 2024-11-18T05:19:41,169 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-11-18T05:19:41,169 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:41,172 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id0x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:41,172 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0078 connected 2024-11-18T05:19:41,253 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=145 2024-11-18T05:19:41,274 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@420509abcheck-peer-cluster-id-0x1000911699b0078, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:41,277 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=146, ppid=145, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:41,429 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:41,429 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=146 2024-11-18T05:19:41,430 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=146}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-11-18T05:19:41,431 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=146}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-11-18T05:19:41,431 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=146}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-11-18T05:19:41,431 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-11-18T05:19:41,431 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1000911699b0077, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:41,431 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1000911699b0077, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:41,463 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=145 2024-11-18T05:19:41,533 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1000911699b0077, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:41,533 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=146}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x0de84aa9 to 127.0.0.1:61937 2024-11-18T05:19:41,533 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=146}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-11-18T05:19:41,556 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=146}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-11-18T05:19:41,556 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=146}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-11-18T05:19:41,556 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=146}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=146 2024-11-18T05:19:41,557 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=146 2024-11-18T05:19:41,558 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:41,560 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=146, resume processing ppid=145 2024-11-18T05:19:41,560 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=146, ppid=145, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 281 msec 2024-11-18T05:19:41,560 INFO [PEWorker-4 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:61937:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-11-18T05:19:41,562 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=145, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 415 msec 2024-11-18T05:19:41,588 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x0460ec8d to 127.0.0.1:61937 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@5d865051 2024-11-18T05:19:41,592 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-11-18T05:19:41,592 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-11-18T05:19:41,593 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@56e1482b, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-11-18T05:19:41,593 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:61937 2024-11-18T05:19:41,595 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-11-18T05:19:41,596 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-11-18T05:19:41,596 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1000911699b007a connected 2024-11-18T05:19:41,773 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=145 2024-11-18T05:19:41,774 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-11-18T05:19:41,774 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-11-18T05:19:41,775 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-11-18T05:19:41,775 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-11-18T05:19:41,776 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=147, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-11-18T05:19:41,776 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] procedure2.ProcedureExecutor(1098): Stored pid=148, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-11-18T05:19:41,776 DEBUG [PEWorker-1 {}] procedure.MasterProcedureScheduler(583): PEER '1', shared lock count=0, exclusively locked by procId=147 2024-11-18T05:19:41,776 DEBUG [PEWorker-1 {}] procedure2.ProcedureExecutor(1470): LOCK_EVENT_WAIT pid=148, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-11-18T05:19:41,777 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:19:41,777 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=147 2024-11-18T05:19:41,779 DEBUG [PEWorker-5 {}] zookeeper.ZKUtil(111): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-11-18T05:19:41,781 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-11-18T05:19:41,781 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-11-18T05:19:41,781 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:39359-0x1000911699b0000, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-11-18T05:19:41,782 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=149, ppid=147, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-11-18T05:19:41,883 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:19:41,883 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=147 2024-11-18T05:19:41,933 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 7cf745f7364a,32867,1731907139252 2024-11-18T05:19:41,934 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=32867 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=149 2024-11-18T05:19:41,934 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=149}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-11-18T05:19:41,934 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=149}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-11-18T05:19:41,934 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=149}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-11-18T05:19:41,934 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-11-18T05:19:41,934 WARN [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1000911699b007a, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:41,935 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1000911699b007a, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-11-18T05:19:42,037 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1000911699b007a, quorum=127.0.0.1:61937, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-11-18T05:19:42,037 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=149}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x0460ec8d to 127.0.0.1:61937 2024-11-18T05:19:42,037 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=149}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-11-18T05:19:42,037 INFO [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=149}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-11-18T05:19:42,039 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=149}] zookeeper.ZKUtil(111): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/1/7cf745f7364a%2C32867%2C1731907139252.1731907142013 2024-11-18T05:19:42,041 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/1/7cf745f7364a%2C32867%2C1731907139252.1731907142013 2024-11-18T05:19:42,041 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/1 2024-11-18T05:19:42,041 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:32867-0x1000911699b0001, quorum=127.0.0.1:61937, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/7cf745f7364a,32867,1731907139252/1 2024-11-18T05:19:42,042 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=149}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-11-18T05:19:42,042 DEBUG [RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0 {event_type=RS_REFRESH_PEER, pid=149}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=149 2024-11-18T05:19:42,042 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.HMaster(4106): Remote procedure done, pid=149 2024-11-18T05:19:42,044 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on 7cf745f7364a,32867,1731907139252 suceeded 2024-11-18T05:19:42,045 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=149, resume processing ppid=147 2024-11-18T05:19:42,045 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=149, ppid=147, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 263 msec 2024-11-18T05:19:42,050 DEBUG [PEWorker-4 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-11-18T05:19:42,050 INFO [PEWorker-4 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-11-18T05:19:42,051 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=147, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 275 msec 2024-11-18T05:19:42,093 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:19:42,093 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=147 2024-11-18T05:19:42,093 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-11-18T05:19:42,403 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:19:42,913 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:19:43,923 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:19:45,026 INFO [master/7cf745f7364a:0.Chore.1 {}] migrate.RollingUpgradeChore(116): There is no table to migrate StoreFileTracker! 2024-11-18T05:19:45,026 INFO [master/7cf745f7364a:0.Chore.1 {}] migrate.RollingUpgradeChore(85): All Rolling-Upgrade tasks are complete, shutdown RollingUpgradeChore! 2024-11-18T05:19:45,943 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:19:47,539 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-11-18T05:19:49,983 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:19:57,659 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:20:00,033 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:20:03,193 DEBUG [master/7cf745f7364a:0.Chore.1 {}] balancer.RegionLocationFinder(172): Locality for region fc40d990d84dd61268a80bc76a9a24b6 changed from -1.0 to 0.0, refreshing cache 2024-11-18T05:20:10,093 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:20:20,113 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:20:27,659 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:20:30,163 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:20:50,363 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:20:57,659 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:21:10,473 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:21:27,660 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:21:30,623 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:21:50,752 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:21:57,660 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:22:10,863 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:22:27,660 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:22:30,963 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:22:51,143 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:22:57,660 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:23:11,163 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:23:27,660 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:23:31,253 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:23:51,453 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:23:57,661 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:23:59,264 INFO [LruBlockCacheStatsExecutor {}] hfile.LruBlockCache(1020): totalSize=880 MB, usedSize=660.99 KB, freeSize=879.35 MB, max=880 MB, blockCount=0, accesses=0, hits=0, hitRatio=0, cachingAccesses=0, cachingHits=0, cachingHitsRatio=0,evictions=29, evicted=0, evictedPerRun=0.0 2024-11-18T05:23:59,330 DEBUG [master/7cf745f7364a:0:becomeActiveMaster-MemStoreChunkPool Statistics {}] regionserver.ChunkCreator$MemStoreChunkPool$StatisticsThread(417): data stats (chunk size=2097152): current pool size=0, created chunk count=7, reused chunk count=0, reuseRatio=0.00% 2024-11-18T05:23:59,331 DEBUG [master/7cf745f7364a:0:becomeActiveMaster-MemStoreChunkPool Statistics {}] regionserver.ChunkCreator$MemStoreChunkPool$StatisticsThread(417): index stats (chunk size=209715): current pool size=0, created chunk count=0, reused chunk count=0, reuseRatio=0 2024-11-18T05:24:01,897 INFO [7cf745f7364a:32867Replication Statistics #0 {}] regionserver.Replication$ReplicationStatisticsTask(247): Global stats: WAL Edits Buffer Used=0B, Limit=268435456B 2024-11-18T05:24:03,198 DEBUG [hconnection-0x6d9680e7-shared-pool-4 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=ClientService, sasl=false 2024-11-18T05:24:03,200 INFO [RS-EventLoopGroup-3-1 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.2:50558, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=ClientService 2024-11-18T05:24:03,207 DEBUG [master/7cf745f7364a:0.Chore.1 {}] janitor.CatalogJanitor(179): 2024-11-18T05:24:04,691 DEBUG [master/7cf745f7364a:0.Chore.1 {}] balancer.BaseLoadBalancer(778): Start Generate Balance plan for cluster. 2024-11-18T05:24:04,692 DEBUG [master/7cf745f7364a:0.Chore.1 {}] master.HMaster(2144): Balancer is going into sleep until next period in 300000ms 2024-11-18T05:24:04,897 INFO [regionserver/7cf745f7364a:0.Chore.1 {}] regionserver.HRegionServer$PeriodicMemStoreFlusher(2070): MemstoreFlusherChore requesting flush of hbase:meta,,1.1588230740 because 1588230740/info has an old edit so flush to free WALs after random delay 119883 ms 2024-11-18T05:24:04,897 INFO [regionserver/7cf745f7364a:0.Chore.1 {}] regionserver.HRegionServer$PeriodicMemStoreFlusher(2070): MemstoreFlusherChore requesting flush of hbase:namespace,,1731907143201.fc40d990d84dd61268a80bc76a9a24b6. because fc40d990d84dd61268a80bc76a9a24b6/info has an old edit so flush to free WALs after random delay 132632 ms 2024-11-18T05:24:08,567 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-11-18T05:24:11,533 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:24:27,661 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:24:31,692 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:24:51,803 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:24:57,661 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:25:11,933 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:25:27,661 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:25:32,013 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:25:52,133 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:25:57,661 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:26:04,780 DEBUG [MemStoreFlusher.0 {}] regionserver.FlushAllLargeStoresPolicy(69): Since none of the CFs were above the size, flushing all. 2024-11-18T05:26:04,781 INFO [MemStoreFlusher.0 {}] regionserver.HRegion(2837): Flushing 1588230740 3/3 column families, dataSize=1.23 KB heapSize=2.87 KB 2024-11-18T05:26:04,844 DEBUG [MemStoreFlusher.0 {}] hfile.HFileWriterImpl(814): Len of the biggest cell in hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/data/hbase/meta/1588230740/.tmp/info/712b6258e1fe45eab7a900f94dedecf8 is 143, key is hbase:namespace,,1731907143201.fc40d990d84dd61268a80bc76a9a24b6./info:regioninfo/1731907144443/Put/seqid=0 2024-11-18T05:26:04,853 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38965 is added to blk_1073741837_1013 (size=6595) 2024-11-18T05:26:05,255 INFO [MemStoreFlusher.0 {}] regionserver.DefaultStoreFlusher(81): Flushed memstore data size=1.14 KB at sequenceid=9 (bloomFilter=true), to=hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/data/hbase/meta/1588230740/.tmp/info/712b6258e1fe45eab7a900f94dedecf8 2024-11-18T05:26:05,314 DEBUG [MemStoreFlusher.0 {}] hfile.HFileWriterImpl(814): Len of the biggest cell in hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/data/hbase/meta/1588230740/.tmp/table/8a3198e19f2c4f7c985b073ab7278683 is 51, key is hbase:namespace/table:state/1731907144476/Put/seqid=0 2024-11-18T05:26:05,319 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38965 is added to blk_1073741838_1014 (size=5242) 2024-11-18T05:26:05,720 INFO [MemStoreFlusher.0 {}] regionserver.DefaultStoreFlusher(81): Flushed memstore data size=94 B at sequenceid=9 (bloomFilter=true), to=hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/data/hbase/meta/1588230740/.tmp/table/8a3198e19f2c4f7c985b073ab7278683 2024-11-18T05:26:05,729 DEBUG [MemStoreFlusher.0 {}] regionserver.HRegionFileSystem(442): Committing hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/data/hbase/meta/1588230740/.tmp/info/712b6258e1fe45eab7a900f94dedecf8 as hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/data/hbase/meta/1588230740/info/712b6258e1fe45eab7a900f94dedecf8 2024-11-18T05:26:05,737 INFO [MemStoreFlusher.0 {}] regionserver.HStore$StoreFlusherImpl(1989): Added hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/data/hbase/meta/1588230740/info/712b6258e1fe45eab7a900f94dedecf8, entries=10, sequenceid=9, filesize=6.4 K 2024-11-18T05:26:05,740 DEBUG [MemStoreFlusher.0 {}] regionserver.HRegionFileSystem(442): Committing hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/data/hbase/meta/1588230740/.tmp/table/8a3198e19f2c4f7c985b073ab7278683 as hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/data/hbase/meta/1588230740/table/8a3198e19f2c4f7c985b073ab7278683 2024-11-18T05:26:05,747 INFO [MemStoreFlusher.0 {}] regionserver.HStore$StoreFlusherImpl(1989): Added hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/data/hbase/meta/1588230740/table/8a3198e19f2c4f7c985b073ab7278683, entries=2, sequenceid=9, filesize=5.1 K 2024-11-18T05:26:05,748 INFO [MemStoreFlusher.0 {}] regionserver.HRegion(3040): Finished flush of dataSize ~1.23 KB/1264, heapSize ~2.59 KB/2648, currentSize=0 B/0 for 1588230740 in 967ms, sequenceid=9, compaction requested=false 2024-11-18T05:26:05,749 DEBUG [MemStoreFlusher.0 {}] regionserver.HRegion(2538): Flush status journal for 1588230740: 2024-11-18T05:26:12,313 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:26:17,529 INFO [MemStoreFlusher.0 {}] regionserver.HRegion(2837): Flushing fc40d990d84dd61268a80bc76a9a24b6 1/1 column families, dataSize=78 B heapSize=488 B 2024-11-18T05:26:17,548 DEBUG [MemStoreFlusher.0 {}] hfile.HFileWriterImpl(814): Len of the biggest cell in hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/data/hbase/namespace/fc40d990d84dd61268a80bc76a9a24b6/.tmp/info/bf3ca4cfbd1142a29726634b91d17df7 is 45, key is default/info:d/1731907144583/Put/seqid=0 2024-11-18T05:26:17,553 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38965 is added to blk_1073741839_1015 (size=5037) 2024-11-18T05:26:17,954 INFO [MemStoreFlusher.0 {}] regionserver.DefaultStoreFlusher(81): Flushed memstore data size=78 B at sequenceid=6 (bloomFilter=true), to=hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/data/hbase/namespace/fc40d990d84dd61268a80bc76a9a24b6/.tmp/info/bf3ca4cfbd1142a29726634b91d17df7 2024-11-18T05:26:17,964 DEBUG [MemStoreFlusher.0 {}] regionserver.HRegionFileSystem(442): Committing hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/data/hbase/namespace/fc40d990d84dd61268a80bc76a9a24b6/.tmp/info/bf3ca4cfbd1142a29726634b91d17df7 as hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/data/hbase/namespace/fc40d990d84dd61268a80bc76a9a24b6/info/bf3ca4cfbd1142a29726634b91d17df7 2024-11-18T05:26:17,973 INFO [MemStoreFlusher.0 {}] regionserver.HStore$StoreFlusherImpl(1989): Added hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/data/hbase/namespace/fc40d990d84dd61268a80bc76a9a24b6/info/bf3ca4cfbd1142a29726634b91d17df7, entries=2, sequenceid=6, filesize=4.9 K 2024-11-18T05:26:17,973 INFO [MemStoreFlusher.0 {}] regionserver.HRegion(3040): Finished flush of dataSize ~78 B/78, heapSize ~472 B/472, currentSize=0 B/0 for fc40d990d84dd61268a80bc76a9a24b6 in 444ms, sequenceid=6, compaction requested=false 2024-11-18T05:26:17,973 DEBUG [MemStoreFlusher.0 {}] regionserver.HRegion(2538): Flush status journal for fc40d990d84dd61268a80bc76a9a24b6: 2024-11-18T05:26:27,662 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:26:32,483 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:26:33,056 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-11-18T05:26:34,416 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region fc40d990d84dd61268a80bc76a9a24b6, had cached 0 bytes from a total of 5037 2024-11-18T05:26:52,543 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:26:57,662 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:27:12,553 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:27:18,056 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-11-18T05:27:19,416 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region fc40d990d84dd61268a80bc76a9a24b6, had cached 0 bytes from a total of 5037 2024-11-18T05:27:27,662 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:27:32,703 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:27:52,763 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:27:57,662 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:28:03,056 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-11-18T05:28:04,417 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region fc40d990d84dd61268a80bc76a9a24b6, had cached 0 bytes from a total of 5037 2024-11-18T05:28:12,813 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:28:27,662 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:28:32,883 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:28:48,057 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-11-18T05:28:49,417 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region fc40d990d84dd61268a80bc76a9a24b6, had cached 0 bytes from a total of 5037 2024-11-18T05:28:52,953 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:28:57,663 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:28:59,263 INFO [LruBlockCacheStatsExecutor {}] hfile.LruBlockCache(1020): totalSize=880 MB, usedSize=660.99 KB, freeSize=879.35 MB, max=880 MB, blockCount=0, accesses=0, hits=0, hitRatio=0, cachingAccesses=0, cachingHits=0, cachingHitsRatio=0,evictions=59, evicted=0, evictedPerRun=0.0 2024-11-18T05:28:59,330 DEBUG [master/7cf745f7364a:0:becomeActiveMaster-MemStoreChunkPool Statistics {}] regionserver.ChunkCreator$MemStoreChunkPool$StatisticsThread(417): data stats (chunk size=2097152): current pool size=3, created chunk count=7, reused chunk count=0, reuseRatio=0.00% 2024-11-18T05:28:59,331 DEBUG [master/7cf745f7364a:0:becomeActiveMaster-MemStoreChunkPool Statistics {}] regionserver.ChunkCreator$MemStoreChunkPool$StatisticsThread(417): index stats (chunk size=209715): current pool size=0, created chunk count=0, reused chunk count=0, reuseRatio=0 2024-11-18T05:29:01,897 INFO [7cf745f7364a:32867Replication Statistics #0 {}] regionserver.Replication$ReplicationStatisticsTask(247): Global stats: WAL Edits Buffer Used=0B, Limit=268435456B 2024-11-18T05:29:05,021 DEBUG [master/7cf745f7364a:0.Chore.1 {}] replication.ZKReplicationQueueStorage(530): Didn't find a RegionServer that replicates, won't prevent deletions. 2024-11-18T05:29:05,023 DEBUG [hconnection-0x6d9680e7-shared-pool-6 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=ClientService, sasl=false 2024-11-18T05:29:05,024 INFO [RS-EventLoopGroup-3-2 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.2:45800, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=ClientService 2024-11-18T05:29:05,040 DEBUG [master/7cf745f7364a:0.Chore.1 {}] balancer.BaseLoadBalancer(778): Start Generate Balance plan for cluster. 2024-11-18T05:29:05,040 DEBUG [master/7cf745f7364a:0.Chore.1 {}] master.HMaster(2144): Balancer is going into sleep until next period in 300000ms 2024-11-18T05:29:05,044 DEBUG [master/7cf745f7364a:0.Chore.1 {}] janitor.CatalogJanitor(179): 2024-11-18T05:29:08,569 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-11-18T05:29:13,073 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:29:27,663 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:29:33,057 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-11-18T05:29:33,213 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:29:34,417 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region fc40d990d84dd61268a80bc76a9a24b6, had cached 0 bytes from a total of 5037 2024-11-18T05:29:53,383 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:29:57,663 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:30:13,533 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:30:18,057 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-11-18T05:30:19,417 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region fc40d990d84dd61268a80bc76a9a24b6, had cached 0 bytes from a total of 5037 2024-11-18T05:30:27,663 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:30:33,643 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:30:53,842 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:30:57,664 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:31:03,058 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-11-18T05:31:04,418 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region fc40d990d84dd61268a80bc76a9a24b6, had cached 0 bytes from a total of 5037 2024-11-18T05:31:13,893 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:31:27,664 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:31:34,043 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:31:48,058 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-11-18T05:31:49,418 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region fc40d990d84dd61268a80bc76a9a24b6, had cached 0 bytes from a total of 5037 2024-11-18T05:31:54,123 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:31:57,664 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:32:14,223 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:32:27,664 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:32:33,058 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-11-18T05:32:34,342 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:32:34,418 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region fc40d990d84dd61268a80bc76a9a24b6, had cached 0 bytes from a total of 5037 2024-11-18T05:32:54,453 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:32:57,664 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:33:14,463 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:33:18,059 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-11-18T05:33:19,419 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region fc40d990d84dd61268a80bc76a9a24b6, had cached 0 bytes from a total of 5037 2024-11-18T05:33:27,665 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:33:34,553 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:33:54,603 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:33:57,665 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:33:59,263 INFO [LruBlockCacheStatsExecutor {}] hfile.LruBlockCache(1020): totalSize=880 MB, usedSize=663.48 KB, freeSize=879.35 MB, max=880 MB, blockCount=2, accesses=2, hits=0, hitRatio=0, cachingAccesses=2, cachingHits=0, cachingHitsRatio=0,evictions=89, evicted=0, evictedPerRun=0.0 2024-11-18T05:33:59,330 DEBUG [master/7cf745f7364a:0:becomeActiveMaster-MemStoreChunkPool Statistics {}] regionserver.ChunkCreator$MemStoreChunkPool$StatisticsThread(417): data stats (chunk size=2097152): current pool size=3, created chunk count=7, reused chunk count=0, reuseRatio=0.00% 2024-11-18T05:33:59,331 DEBUG [master/7cf745f7364a:0:becomeActiveMaster-MemStoreChunkPool Statistics {}] regionserver.ChunkCreator$MemStoreChunkPool$StatisticsThread(417): index stats (chunk size=209715): current pool size=0, created chunk count=0, reused chunk count=0, reuseRatio=0 2024-11-18T05:34:01,305 DEBUG [master:store-WAL-Roller {}] wal.AbstractWALRoller(200): WAL AsyncFSWAL 7cf745f7364a%2C39359%2C1731907138502:(num 1731907141214) roll period 900000 ms elapsed 2024-11-18T05:34:01,324 DEBUG [master:store-WAL-Roller {}] asyncfs.FanOutOneBlockAsyncDFSOutputHelper(617): When create output stream for /user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/MasterData/WALs/7cf745f7364a,39359,1731907138502/7cf745f7364a%2C39359%2C1731907138502.1731908041306, exclude list is [], retry=0 2024-11-18T05:34:01,328 DEBUG [RS-EventLoopGroup-3-3 {}] asyncfs.FanOutOneBlockAsyncDFSOutputSaslHelper(816): SASL client skipping handshake in unsecured configuration for addr = 127.0.0.1/127.0.0.1, datanodeId = DatanodeInfoWithStorage[127.0.0.1:38965,DS-564787d6-4f9e-4ae8-8ae2-11502196172f,DISK] 2024-11-18T05:34:01,331 INFO [master:store-WAL-Roller {}] wal.AbstractFSWAL(837): Rolled WAL /user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/MasterData/WALs/7cf745f7364a,39359,1731907138502/7cf745f7364a%2C39359%2C1731907138502.1731907141214 with entries=1165, filesize=507.09 KB; new WAL /user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/MasterData/WALs/7cf745f7364a,39359,1731907138502/7cf745f7364a%2C39359%2C1731907138502.1731908041306 2024-11-18T05:34:01,332 DEBUG [master:store-WAL-Roller {}] wal.AbstractFSWAL(925): Create new AsyncFSWAL writer with pipeline: [(127.0.0.1/127.0.0.1:45257:45257)] 2024-11-18T05:34:01,332 DEBUG [master:store-WAL-Roller {}] wal.AbstractFSWAL(751): hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/MasterData/WALs/7cf745f7364a,39359,1731907138502/7cf745f7364a%2C39359%2C1731907138502.1731907141214 is not closed yet, will try archiving it next time 2024-11-18T05:34:01,335 WARN [Close-WAL-Writer-0 {}] asyncfs.FanOutOneBlockAsyncDFSOutputHelper(743): complete file /user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/MasterData/WALs/7cf745f7364a,39359,1731907138502/7cf745f7364a%2C39359%2C1731907138502.1731907141214 not finished, retry = 0 2024-11-18T05:34:01,335 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38965 is added to blk_1073741830_1006 (size=519270) 2024-11-18T05:34:01,428 INFO [master:store-Flusher {}] regionserver.HRegion(2837): Flushing 1595e783b53d99cd5eef43b6debb2682 4/4 column families, dataSize=432.38 KB heapSize=534.71 KB 2024-11-18T05:34:01,447 DEBUG [master:store-Flusher {}] hfile.HFileWriterImpl(814): Len of the biggest cell in hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/info/d926ba1f16864d50b771865153540225 is 82, key is hbase:meta,,1/info:regioninfo/1731907143096/Put/seqid=0 2024-11-18T05:34:01,451 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38965 is added to blk_1073741841_1017 (size=5672) 2024-11-18T05:34:01,853 INFO [master:store-Flusher {}] regionserver.DefaultStoreFlusher(81): Flushed memstore data size=504 B at sequenceid=1168 (bloomFilter=true), to=hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/info/d926ba1f16864d50b771865153540225 2024-11-18T05:34:01,893 DEBUG [master:store-Flusher {}] hfile.HFileWriterImpl(814): Len of the biggest cell in hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/proc/fa7ada1cf1a84295869eaf579593db2e is 293, key is \x00\x00\x00\x00\x00\x00\x00\x94/proc:d/1731907181775/Put/seqid=0 2024-11-18T05:34:01,897 INFO [7cf745f7364a:32867Replication Statistics #0 {}] regionserver.Replication$ReplicationStatisticsTask(247): Global stats: WAL Edits Buffer Used=0B, Limit=268435456B 2024-11-18T05:34:01,899 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38965 is added to blk_1073741842_1018 (size=11283) 2024-11-18T05:34:02,300 INFO [master:store-Flusher {}] regionserver.DefaultStoreFlusher(81): Flushed memstore data size=430.82 KB at sequenceid=1168 (bloomFilter=true), to=hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/proc/fa7ada1cf1a84295869eaf579593db2e 2024-11-18T05:34:02,307 INFO [master:store-Flusher {}] regionserver.StoreFileReader(539): Loaded Delete Family Bloom (CompoundBloomFilter) metadata for fa7ada1cf1a84295869eaf579593db2e 2024-11-18T05:34:02,323 DEBUG [master:store-Flusher {}] hfile.HFileWriterImpl(814): Len of the biggest cell in hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/rs/88b09b415c6e40c1b40a7ae5f36f5c24 is 69, key is 7cf745f7364a,32867,1731907139252/rs:state/1731907141785/Put/seqid=0 2024-11-18T05:34:02,327 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38965 is added to blk_1073741843_1019 (size=5156) 2024-11-18T05:34:02,728 INFO [master:store-Flusher {}] regionserver.DefaultStoreFlusher(81): Flushed memstore data size=65 B at sequenceid=1168 (bloomFilter=true), to=hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/rs/88b09b415c6e40c1b40a7ae5f36f5c24 2024-11-18T05:34:02,752 DEBUG [master:store-Flusher {}] hfile.HFileWriterImpl(814): Len of the biggest cell in hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/state/69c2628f9c6547fbb2a46536f32e1715 is 68, key is replication_peer_modification_on/state:d/1731907177335/Put/seqid=0 2024-11-18T05:34:02,757 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38965 is added to blk_1073741844_1020 (size=5154) 2024-11-18T05:34:03,059 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-11-18T05:34:03,158 INFO [master:store-Flusher {}] regionserver.DefaultStoreFlusher(81): Flushed memstore data size=1 KB at sequenceid=1168 (bloomFilter=true), to=hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/state/69c2628f9c6547fbb2a46536f32e1715 2024-11-18T05:34:03,166 DEBUG [master:store-Flusher {}] regionserver.HRegionFileSystem(442): Committing hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/info/d926ba1f16864d50b771865153540225 as hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/info/d926ba1f16864d50b771865153540225 2024-11-18T05:34:03,174 INFO [master:store-Flusher {}] regionserver.HStore$StoreFlusherImpl(1989): Added hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/info/d926ba1f16864d50b771865153540225, entries=8, sequenceid=1168, filesize=5.5 K 2024-11-18T05:34:03,176 DEBUG [master:store-Flusher {}] regionserver.HRegionFileSystem(442): Committing hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/proc/fa7ada1cf1a84295869eaf579593db2e as hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/proc/fa7ada1cf1a84295869eaf579593db2e 2024-11-18T05:34:03,183 INFO [master:store-Flusher {}] regionserver.StoreFileReader(539): Loaded Delete Family Bloom (CompoundBloomFilter) metadata for fa7ada1cf1a84295869eaf579593db2e 2024-11-18T05:34:03,183 INFO [master:store-Flusher {}] regionserver.HStore$StoreFlusherImpl(1989): Added hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/proc/fa7ada1cf1a84295869eaf579593db2e, entries=149, sequenceid=1168, filesize=11.0 K 2024-11-18T05:34:03,184 DEBUG [master:store-Flusher {}] regionserver.HRegionFileSystem(442): Committing hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/rs/88b09b415c6e40c1b40a7ae5f36f5c24 as hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/rs/88b09b415c6e40c1b40a7ae5f36f5c24 2024-11-18T05:34:03,191 INFO [master:store-Flusher {}] regionserver.HStore$StoreFlusherImpl(1989): Added hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/rs/88b09b415c6e40c1b40a7ae5f36f5c24, entries=1, sequenceid=1168, filesize=5.0 K 2024-11-18T05:34:03,191 DEBUG [master/7cf745f7364a:0.Chore.1 {}] balancer.BaseLoadBalancer(778): Start Generate Balance plan for cluster. 2024-11-18T05:34:03,191 DEBUG [master/7cf745f7364a:0.Chore.1 {}] master.HMaster(2144): Balancer is going into sleep until next period in 300000ms 2024-11-18T05:34:03,193 DEBUG [hconnection-0x6d9680e7-shared-pool-8 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=ClientService, sasl=false 2024-11-18T05:34:03,193 DEBUG [master:store-Flusher {}] regionserver.HRegionFileSystem(442): Committing hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/state/69c2628f9c6547fbb2a46536f32e1715 as hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/state/69c2628f9c6547fbb2a46536f32e1715 2024-11-18T05:34:03,194 INFO [RS-EventLoopGroup-3-1 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.2:44304, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=ClientService 2024-11-18T05:34:03,199 DEBUG [master/7cf745f7364a:0.Chore.1 {}] janitor.CatalogJanitor(179): 2024-11-18T05:34:03,200 INFO [master:store-Flusher {}] regionserver.HStore$StoreFlusherImpl(1989): Added hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/state/69c2628f9c6547fbb2a46536f32e1715, entries=1, sequenceid=1168, filesize=5.0 K 2024-11-18T05:34:03,201 INFO [master:store-Flusher {}] regionserver.HRegion(3040): Finished flush of dataSize ~432.38 KB/442757, heapSize ~534.65 KB/547480, currentSize=0 B/0 for 1595e783b53d99cd5eef43b6debb2682 in 1772ms, sequenceid=1168, compaction requested=false 2024-11-18T05:34:03,201 DEBUG [master:store-Flusher {}] regionserver.HRegion(2538): Flush status journal for 1595e783b53d99cd5eef43b6debb2682: 2024-11-18T05:34:04,419 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region fc40d990d84dd61268a80bc76a9a24b6, had cached 0 bytes from a total of 5037 2024-11-18T05:34:08,567 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-11-18T05:34:14,743 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:34:27,665 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:34:34,813 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:34:48,059 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-11-18T05:34:49,419 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region fc40d990d84dd61268a80bc76a9a24b6, had cached 0 bytes from a total of 5037 2024-11-18T05:34:54,912 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:34:57,665 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:35:14,973 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:35:27,666 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:35:33,059 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-11-18T05:35:34,419 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region fc40d990d84dd61268a80bc76a9a24b6, had cached 0 bytes from a total of 5037 2024-11-18T05:35:35,043 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:35:55,053 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:35:57,666 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:36:15,113 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:36:18,060 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-11-18T05:36:19,420 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region fc40d990d84dd61268a80bc76a9a24b6, had cached 0 bytes from a total of 5037 2024-11-18T05:36:27,666 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:36:35,313 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:36:55,372 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:36:57,666 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:37:03,060 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-11-18T05:37:04,420 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region fc40d990d84dd61268a80bc76a9a24b6, had cached 0 bytes from a total of 5037 2024-11-18T05:37:15,493 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:37:27,666 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:37:35,662 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:37:48,060 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-11-18T05:37:49,420 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region fc40d990d84dd61268a80bc76a9a24b6, had cached 0 bytes from a total of 5037 2024-11-18T05:37:55,792 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:37:57,667 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:38:15,892 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:38:27,667 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:38:33,061 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-11-18T05:38:34,421 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region fc40d990d84dd61268a80bc76a9a24b6, had cached 0 bytes from a total of 5037 2024-11-18T05:38:36,053 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:38:56,183 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:38:57,667 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:38:59,263 INFO [LruBlockCacheStatsExecutor {}] hfile.LruBlockCache(1020): totalSize=880 MB, usedSize=663.48 KB, freeSize=879.35 MB, max=880 MB, blockCount=2, accesses=4, hits=2, hitRatio=50.00%, , cachingAccesses=4, cachingHits=2, cachingHitsRatio=50.00%, evictions=119, evicted=0, evictedPerRun=0.0 2024-11-18T05:38:59,330 DEBUG [master/7cf745f7364a:0:becomeActiveMaster-MemStoreChunkPool Statistics {}] regionserver.ChunkCreator$MemStoreChunkPool$StatisticsThread(417): data stats (chunk size=2097152): current pool size=6, created chunk count=7, reused chunk count=1, reuseRatio=12.50% 2024-11-18T05:38:59,331 DEBUG [master/7cf745f7364a:0:becomeActiveMaster-MemStoreChunkPool Statistics {}] regionserver.ChunkCreator$MemStoreChunkPool$StatisticsThread(417): index stats (chunk size=209715): current pool size=0, created chunk count=0, reused chunk count=0, reuseRatio=0 2024-11-18T05:39:01,897 INFO [7cf745f7364a:32867Replication Statistics #0 {}] regionserver.Replication$ReplicationStatisticsTask(247): Global stats: WAL Edits Buffer Used=0B, Limit=268435456B 2024-11-18T05:39:03,198 DEBUG [hconnection-0x6d9680e7-shared-pool-10 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=ClientService, sasl=false 2024-11-18T05:39:03,199 INFO [RS-EventLoopGroup-3-2 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.2:49478, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=ClientService 2024-11-18T05:39:03,202 DEBUG [master/7cf745f7364a:0.Chore.1 {}] balancer.BaseLoadBalancer(778): Start Generate Balance plan for cluster. 2024-11-18T05:39:03,202 DEBUG [master/7cf745f7364a:0.Chore.1 {}] master.HMaster(2144): Balancer is going into sleep until next period in 300000ms 2024-11-18T05:39:03,205 DEBUG [master/7cf745f7364a:0.Chore.1 {}] janitor.CatalogJanitor(179): 2024-11-18T05:39:03,206 DEBUG [master/7cf745f7364a:0.Chore.1 {}] replication.ZKReplicationQueueStorage(530): Didn't find a RegionServer that replicates, won't prevent deletions. 2024-11-18T05:39:08,578 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-11-18T05:39:16,343 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:39:18,061 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-11-18T05:39:19,421 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region fc40d990d84dd61268a80bc76a9a24b6, had cached 0 bytes from a total of 5037 2024-11-18T05:39:27,667 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:39:36,543 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:39:56,693 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:39:57,667 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:40:03,061 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-11-18T05:40:04,421 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region fc40d990d84dd61268a80bc76a9a24b6, had cached 0 bytes from a total of 5037 2024-11-18T05:40:16,813 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:40:27,668 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:40:36,973 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:40:48,061 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-11-18T05:40:49,421 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region fc40d990d84dd61268a80bc76a9a24b6, had cached 0 bytes from a total of 5037 2024-11-18T05:40:56,993 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:40:57,668 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:41:17,183 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:41:27,668 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:41:33,062 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-11-18T05:41:34,422 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region fc40d990d84dd61268a80bc76a9a24b6, had cached 0 bytes from a total of 5037 2024-11-18T05:41:37,353 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:41:57,532 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:41:57,668 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:42:17,572 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:42:18,062 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-11-18T05:42:19,422 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region fc40d990d84dd61268a80bc76a9a24b6, had cached 0 bytes from a total of 5037 2024-11-18T05:42:27,668 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:42:37,763 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:42:57,669 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:42:57,833 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:43:03,062 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-11-18T05:43:04,422 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region fc40d990d84dd61268a80bc76a9a24b6, had cached 0 bytes from a total of 5037 2024-11-18T05:43:18,012 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:43:27,669 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:43:38,103 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:43:48,063 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-11-18T05:43:49,422 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region fc40d990d84dd61268a80bc76a9a24b6, had cached 0 bytes from a total of 5037 2024-11-18T05:43:57,669 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:43:58,183 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:43:59,263 INFO [LruBlockCacheStatsExecutor {}] hfile.LruBlockCache(1020): totalSize=880 MB, usedSize=663.48 KB, freeSize=879.35 MB, max=880 MB, blockCount=2, accesses=6, hits=4, hitRatio=66.67%, , cachingAccesses=6, cachingHits=4, cachingHitsRatio=66.67%, evictions=149, evicted=0, evictedPerRun=0.0 2024-11-18T05:43:59,330 DEBUG [master/7cf745f7364a:0:becomeActiveMaster-MemStoreChunkPool Statistics {}] regionserver.ChunkCreator$MemStoreChunkPool$StatisticsThread(417): data stats (chunk size=2097152): current pool size=6, created chunk count=7, reused chunk count=1, reuseRatio=12.50% 2024-11-18T05:43:59,331 DEBUG [master/7cf745f7364a:0:becomeActiveMaster-MemStoreChunkPool Statistics {}] regionserver.ChunkCreator$MemStoreChunkPool$StatisticsThread(417): index stats (chunk size=209715): current pool size=0, created chunk count=0, reused chunk count=0, reuseRatio=0 2024-11-18T05:44:01,897 INFO [7cf745f7364a:32867Replication Statistics #0 {}] regionserver.Replication$ReplicationStatisticsTask(247): Global stats: WAL Edits Buffer Used=0B, Limit=268435456B 2024-11-18T05:44:03,385 DEBUG [hconnection-0x6d9680e7-shared-pool-12 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=ClientService, sasl=false 2024-11-18T05:44:03,387 INFO [RS-EventLoopGroup-3-3 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.2:60730, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=ClientService 2024-11-18T05:44:03,389 DEBUG [master/7cf745f7364a:0.Chore.1 {}] janitor.CatalogJanitor(179): 2024-11-18T05:44:03,390 DEBUG [master/7cf745f7364a:0.Chore.1 {}] balancer.BaseLoadBalancer(778): Start Generate Balance plan for cluster. 2024-11-18T05:44:03,390 DEBUG [master/7cf745f7364a:0.Chore.1 {}] master.HMaster(2144): Balancer is going into sleep until next period in 300000ms 2024-11-18T05:44:08,567 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-11-18T05:44:18,323 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-11-18T05:44:27,669 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-11-18T05:44:33,063 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-11-18T05:44:34,423 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region fc40d990d84dd61268a80bc76a9a24b6, had cached 0 bytes from a total of 5037 2024-11-18T05:44:38,423 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 ====> TEST TIMED OUT. PRINTING THREAD DUMP. <==== Timestamp: 2024-11-18 05:44:54,384 "IPC Server handler 0 on default port 38907" daemon prio=5 tid=104 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.poll(LinkedBlockingQueue.java:460) at app//org.apache.hadoop.ipc.CallQueueManager.take(CallQueueManager.java:370) at app//org.apache.hadoop.ipc.Server$Handler.run(Server.java:3165) "master/7cf745f7364a:0.Chore.1" daemon prio=5 tid=259 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "pool-1-thread-2" daemon prio=5 tid=15 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.ArrayBlockingQueue.take(ArrayBlockingQueue.java:420) at java.base@17.0.11/sun.nio.ch.EPollPort$EventHandlerTask.run(EPollPort.java:275) at java.base@17.0.11/sun.nio.ch.AsynchronousChannelGroupImpl$1.run(AsynchronousChannelGroupImpl.java:113) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1136) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "qtp1312628392-40" daemon prio=5 tid=40 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:146) at app//org.eclipse.jetty.io.ManagedSelector.nioSelect(ManagedSelector.java:183) at app//org.eclipse.jetty.io.ManagedSelector.select(ManagedSelector.java:190) at app//org.eclipse.jetty.io.ManagedSelector$SelectorProducer.select(ManagedSelector.java:606) at app//org.eclipse.jetty.io.ManagedSelector$SelectorProducer.produce(ManagedSelector.java:543) at app//org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.produceTask(EatWhatYouKill.java:362) at app//org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.doProduce(EatWhatYouKill.java:186) at app//org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.tryProduce(EatWhatYouKill.java:173) at app//org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.produce(EatWhatYouKill.java:137) at app//org.eclipse.jetty.io.ManagedSelector$$Lambda$257/0x00007f6368423440.run(Unknown Source) at app//org.eclipse.jetty.util.thread.QueuedThreadPool.runJob(QueuedThreadPool.java:883) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.run(QueuedThreadPool.java:1034) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "NIOWorkerThread-7" daemon prio=5 tid=163 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Timer for 'HBase' metrics system" daemon prio=5 tid=1013 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Object.wait(Native Method) at java.base@17.0.11/java.util.TimerThread.mainLoop(Timer.java:563) at java.base@17.0.11/java.util.TimerThread.run(Timer.java:516) "RS-EventLoopGroup-1-2" daemon prio=10 tid=267 runnable java.lang.Thread.State: RUNNABLE at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait(Native Method) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait(Native.java:220) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait(Native.java:213) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.EpollEventLoop.epollWaitNoTimerChange(EpollEventLoop.java:308) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.EpollEventLoop.run(EpollEventLoop.java:365) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:997) at app//org.apache.hbase.thirdparty.io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "region-location-2" daemon prio=5 tid=750 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1170) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcServer.priority.RWQ.Fifo.write.handler=0,queue=0,port=32867" daemon prio=5 tid=198 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at app//org.apache.hadoop.hbase.ipc.RpcHandler.getCallRunner(RpcHandler.java:71) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "NIOWorkerThread-13" daemon prio=5 tid=169 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RedundancyMonitor" daemon prio=5 tid=47 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at java.base@17.0.11/java.lang.Thread.sleep(Thread.java:344) at java.base@17.0.11/java.util.concurrent.TimeUnit.sleep(TimeUnit.java:446) at app//org.apache.hadoop.hdfs.server.blockmanagement.BlockManager$RedundancyMonitor.run(BlockManager.java:5352) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "NIOServerCxnFactory.SelectorThread-1" daemon prio=5 tid=139 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:146) at app//org.apache.zookeeper.server.NIOServerCnxnFactory$SelectorThread.select(NIOServerCnxnFactory.java:403) at app//org.apache.zookeeper.server.NIOServerCnxnFactory$SelectorThread.run(NIOServerCnxnFactory.java:368) "IPC Server handler 3 on default port 37393" daemon prio=5 tid=67 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.poll(LinkedBlockingQueue.java:460) at app//org.apache.hadoop.ipc.CallQueueManager.take(CallQueueManager.java:370) at app//org.apache.hadoop.ipc.Server$Handler.run(Server.java:3165) "RS-EventLoopGroup-3-1" daemon prio=10 tid=186 runnable java.lang.Thread.State: RUNNABLE at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait0(Native Method) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait(Native.java:193) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.EpollEventLoop.epollWait(EpollEventLoop.java:304) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.EpollEventLoop.run(EpollEventLoop.java:368) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:997) at app//org.apache.hbase.thirdparty.io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "OldWALsCleaner-0" daemon prio=5 tid=258 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at app//org.apache.hadoop.hbase.master.cleaner.LogCleaner.deleteFile(LogCleaner.java:172) at app//org.apache.hadoop.hbase.master.cleaner.LogCleaner.lambda$createOldWalsCleaner$1(LogCleaner.java:152) at app//org.apache.hadoop.hbase.master.cleaner.LogCleaner$$Lambda$591/0x00007f6368a5ccc0.run(Unknown Source) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Time-limited test-EventThread" daemon prio=5 tid=193 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at app//org.apache.zookeeper.ClientCnxn$EventThread.run(ClientCnxn.java:550) "NIOServerCxnFactory.SelectorThread-0" daemon prio=5 tid=138 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:146) at app//org.apache.zookeeper.server.NIOServerCnxnFactory$SelectorThread.select(NIOServerCnxnFactory.java:403) at app//org.apache.zookeeper.server.NIOServerCnxnFactory$SelectorThread.run(NIOServerCnxnFactory.java:368) "org.apache.hadoop.hdfs.PeerCache@7608a3fb" daemon prio=5 tid=215 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.hdfs.PeerCache.run(PeerCache.java:253) at app//org.apache.hadoop.hdfs.PeerCache.access$000(PeerCache.java:46) at app//org.apache.hadoop.hdfs.PeerCache$1.run(PeerCache.java:124) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Idle-Rpc-Conn-Sweeper-pool-0" daemon prio=5 tid=242 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "qtp1312628392-37" daemon prio=5 tid=37 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:146) at app//org.eclipse.jetty.io.ManagedSelector.nioSelect(ManagedSelector.java:183) at app//org.eclipse.jetty.io.ManagedSelector.select(ManagedSelector.java:190) at app//org.eclipse.jetty.io.ManagedSelector$SelectorProducer.select(ManagedSelector.java:606) at app//org.eclipse.jetty.io.ManagedSelector$SelectorProducer.produce(ManagedSelector.java:543) at app//org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.produceTask(EatWhatYouKill.java:362) at app//org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.doProduce(EatWhatYouKill.java:186) at app//org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.tryProduce(EatWhatYouKill.java:173) at app//org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.produce(EatWhatYouKill.java:137) at app//org.eclipse.jetty.io.ManagedSelector$$Lambda$257/0x00007f6368423440.run(Unknown Source) at app//org.eclipse.jetty.util.thread.QueuedThreadPool.runJob(QueuedThreadPool.java:883) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.run(QueuedThreadPool.java:1034) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=32867" daemon prio=5 tid=199 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at app//org.apache.hadoop.hbase.ipc.RpcHandler.getCallRunner(RpcHandler.java:71) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "pool-1-thread-1" daemon prio=5 tid=14 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollPort$EventHandlerTask.poll(EPollPort.java:200) at java.base@17.0.11/sun.nio.ch.EPollPort$EventHandlerTask.run(EPollPort.java:281) at java.base@17.0.11/sun.nio.ch.AsynchronousChannelGroupImpl$1.run(AsynchronousChannelGroupImpl.java:113) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1136) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "org.apache.hadoop.hdfs.server.blockmanagement.HeartbeatManager$Monitor@b364b1a" daemon prio=5 tid=49 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.hdfs.server.blockmanagement.HeartbeatManager$Monitor.run(HeartbeatManager.java:563) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "NIOWorkerThread-1" daemon prio=5 tid=145 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcClient-timer-pool-0" daemon prio=5 tid=241 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hbase.thirdparty.io.netty.util.HashedWheelTimer$Worker.waitForNextTick(HashedWheelTimer.java:598) at app//org.apache.hbase.thirdparty.io.netty.util.HashedWheelTimer$Worker.run(HashedWheelTimer.java:494) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "LeaseRenewer:jenkins.hfs.0@localhost:37393" daemon prio=5 tid=283 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.hdfs.client.impl.LeaseRenewer.run(LeaseRenewer.java:441) at app//org.apache.hadoop.hdfs.client.impl.LeaseRenewer.access$800(LeaseRenewer.java:77) at app//org.apache.hadoop.hdfs.client.impl.LeaseRenewer$1.run(LeaseRenewer.java:336) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "java.util.concurrent.ThreadPoolExecutor$Worker@5bf8d43f[State = -1, empty queue]" daemon prio=5 tid=135 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "normalizer-worker-0" daemon prio=5 tid=252 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at app//org.apache.hadoop.hbase.master.normalizer.RegionNormalizerWorkQueue.take(RegionNormalizerWorkQueue.java:146) at app//org.apache.hadoop.hbase.master.normalizer.RegionNormalizerWorker.run(RegionNormalizerWorker.java:191) at java.base@17.0.11/java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:539) at java.base@17.0.11/java.util.concurrent.FutureTask.run(FutureTask.java:264) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1136) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Finalizer" daemon prio=8 tid=3 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/java.lang.Object.wait(Native Method) at java.base@17.0.11/java.lang.ref.ReferenceQueue.remove(ReferenceQueue.java:155) at java.base@17.0.11/java.lang.ref.ReferenceQueue.remove(ReferenceQueue.java:176) at java.base@17.0.11/java.lang.ref.Finalizer$FinalizerThread.run(Finalizer.java:172) "process reaper" daemon prio=10 tid=1011 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.SynchronousQueue$TransferStack.transfer(SynchronousQueue.java:401) at java.base@17.0.11/java.util.concurrent.SynchronousQueue.poll(SynchronousQueue.java:903) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1061) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "refreshUsed-/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/e1a8447b-7280-f5aa-cebe-d7c1b39671e7/cluster_b7a7248c-30f6-7402-42f2-d4751190cb92/dfs/data/data2/current/BP-1100534618-172.17.0.2-1731907135498" daemon prio=5 tid=124 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.fs.CachingGetSpaceUsed$RefreshThread.run(CachingGetSpaceUsed.java:225) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "qtp1965036093-89" daemon prio=5 tid=89 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at app//org.eclipse.jetty.util.BlockingArrayQueue.poll(BlockingArrayQueue.java:382) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.idleJobPoll(QueuedThreadPool.java:974) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.run(QueuedThreadPool.java:1018) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "NIOWorkerThread-12" daemon prio=5 tid=168 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "ReadOnlyZKClient-127.0.0.1:61937@0x7502c059" daemon prio=5 tid=320 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.DelayQueue.poll(DelayQueue.java:265) at app//org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:370) at app//org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$$Lambda$760/0x00007f6368b4b1b0.run(Unknown Source) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39359" daemon prio=5 tid=175 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquire(AbstractQueuedSynchronizer.java:715) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1047) at java.base@17.0.11/java.util.concurrent.Semaphore.acquire(Semaphore.java:318) at app//org.apache.hadoop.hbase.ipc.FastPathRpcHandler.getCallRunner(FastPathRpcHandler.java:55) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "zk-event-processor-pool-0" daemon prio=5 tid=160 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39359" daemon prio=5 tid=174 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquire(AbstractQueuedSynchronizer.java:715) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1047) at java.base@17.0.11/java.util.concurrent.Semaphore.acquire(Semaphore.java:318) at app//org.apache.hadoop.hbase.ipc.FastPathRpcHandler.getCallRunner(FastPathRpcHandler.java:55) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "org.apache.hadoop.fs.FileSystem$Statistics$StatisticsDataReferenceCleaner" daemon prio=5 tid=23 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/java.lang.Object.wait(Native Method) at java.base@17.0.11/java.lang.ref.ReferenceQueue.remove(ReferenceQueue.java:155) at java.base@17.0.11/java.lang.ref.ReferenceQueue.remove(ReferenceQueue.java:176) at app//org.apache.hadoop.fs.FileSystem$Statistics$StatisticsDataReferenceCleaner.run(FileSystem.java:4171) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "qtp1312628392-39" daemon prio=5 tid=39 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:146) at app//org.eclipse.jetty.io.ManagedSelector.nioSelect(ManagedSelector.java:183) at app//org.eclipse.jetty.io.ManagedSelector.select(ManagedSelector.java:190) at app//org.eclipse.jetty.io.ManagedSelector$SelectorProducer.select(ManagedSelector.java:606) at app//org.eclipse.jetty.io.ManagedSelector$SelectorProducer.produce(ManagedSelector.java:543) at app//org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.produceTask(EatWhatYouKill.java:362) at app//org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.doProduce(EatWhatYouKill.java:186) at app//org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.tryProduce(EatWhatYouKill.java:173) at app//org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.produce(EatWhatYouKill.java:137) at app//org.eclipse.jetty.io.ManagedSelector$$Lambda$257/0x00007f6368423440.run(Unknown Source) at app//org.eclipse.jetty.util.thread.QueuedThreadPool.runJob(QueuedThreadPool.java:883) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.run(QueuedThreadPool.java:1034) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "ProcExecTimeout" daemon prio=5 tid=243 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.DelayQueue.poll(DelayQueue.java:279) at app//org.apache.hadoop.hbase.procedure2.util.DelayedUtil.takeWithoutInterrupt(DelayedUtil.java:81) at app//org.apache.hadoop.hbase.procedure2.TimeoutExecutorThread.run(TimeoutExecutorThread.java:56) "RS_REFRESH_PEER-regionserver/7cf745f7364a:0-0" daemon prio=5 tid=334 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "SSL Certificates Store Monitor" daemon prio=5 tid=25 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/java.lang.Object.wait(Native Method) at java.base@17.0.11/java.lang.Object.wait(Object.java:338) at java.base@17.0.11/java.util.TimerThread.mainLoop(Timer.java:537) at java.base@17.0.11/java.util.TimerThread.run(Timer.java:516) "regionserver/7cf745f7364a:0.procedureResultReporter" daemon prio=5 tid=276 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at app//org.apache.hadoop.hbase.regionserver.RemoteProcedureResultReporter.run(RemoteProcedureResultReporter.java:75) "pool-14-thread-1" daemon prio=5 tid=132 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1170) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "MemStoreFlusher.0" daemon prio=5 tid=277 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.DelayQueue.poll(DelayQueue.java:265) at java.base@17.0.11/java.util.concurrent.DelayQueue.poll(DelayQueue.java:77) at app//org.apache.hadoop.hbase.regionserver.MemStoreFlusher$FlushHandler.run(MemStoreFlusher.java:322) "NIOWorkerThread-4" daemon prio=5 tid=159 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "IPC Server idle connection scanner for port 37393" daemon prio=5 tid=56 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Object.wait(Native Method) at java.base@17.0.11/java.util.TimerThread.mainLoop(Timer.java:563) at java.base@17.0.11/java.util.TimerThread.run(Timer.java:516) "qtp1312628392-41-acceptor-0@5a8e340a-ServerConnector@1f7e2804{HTTP/1.1, (http/1.1)}{localhost:38479}" daemon prio=3 tid=41 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.Net.accept(Native Method) at java.base@17.0.11/sun.nio.ch.ServerSocketChannelImpl.implAccept(ServerSocketChannelImpl.java:425) at java.base@17.0.11/sun.nio.ch.ServerSocketChannelImpl.accept(ServerSocketChannelImpl.java:391) at app//org.eclipse.jetty.server.ServerConnector.accept(ServerConnector.java:388) at app//org.eclipse.jetty.server.AbstractConnector$Acceptor.run(AbstractConnector.java:704) at app//org.eclipse.jetty.util.thread.QueuedThreadPool.runJob(QueuedThreadPool.java:883) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.run(QueuedThreadPool.java:1034) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "NIOWorkerThread-3" daemon prio=5 tid=158 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "regionserver/7cf745f7364a:0.Chore.1" daemon prio=5 tid=273 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "PacketResponder: BP-1100534618-172.17.0.2-1731907135498:blk_1073741840_1016, type=LAST_IN_PIPELINE" daemon prio=5 tid=895 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/java.lang.Object.wait(Native Method) at java.base@17.0.11/java.lang.Object.wait(Object.java:338) at app//org.apache.hadoop.hdfs.server.datanode.BlockReceiver$PacketResponder.waitForAckHead(BlockReceiver.java:1367) at app//org.apache.hadoop.hdfs.server.datanode.BlockReceiver$PacketResponder.run(BlockReceiver.java:1439) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "BootstrapNodeManager" daemon prio=5 tid=257 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "surefire-forkedjvm-command-thread" daemon prio=5 tid=18 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquire(AbstractQueuedSynchronizer.java:715) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1047) at java.base@17.0.11/java.util.concurrent.CountDownLatch.await(CountDownLatch.java:230) at java.base@17.0.11/sun.nio.ch.PendingFuture.get(PendingFuture.java:178) at app//org.apache.maven.surefire.api.util.internal.Channels$2.read(Channels.java:127) at java.base@17.0.11/java.io.BufferedInputStream.fill(BufferedInputStream.java:244) at java.base@17.0.11/java.io.BufferedInputStream.read1(BufferedInputStream.java:284) at java.base@17.0.11/java.io.BufferedInputStream.read(BufferedInputStream.java:343) at app//org.apache.maven.surefire.api.util.internal.Channels$3.readImpl(Channels.java:169) at app//org.apache.maven.surefire.api.util.internal.AbstractNoninterruptibleReadableChannel.read(AbstractNoninterruptibleReadableChannel.java:50) at app//org.apache.maven.surefire.api.stream.AbstractStreamDecoder.read(AbstractStreamDecoder.java:430) at app//org.apache.maven.surefire.api.stream.AbstractStreamDecoder.read(AbstractStreamDecoder.java:419) at app//org.apache.maven.surefire.api.stream.AbstractStreamDecoder.readMessageType(AbstractStreamDecoder.java:116) at app//org.apache.maven.surefire.booter.stream.CommandDecoder.decode(CommandDecoder.java:77) at app//org.apache.maven.surefire.booter.spi.CommandChannelDecoder.decode(CommandChannelDecoder.java:60) at app//org.apache.maven.surefire.booter.CommandReader$CommandRunnable.run(CommandReader.java:290) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "CacheReplicationMonitor(1894465686)" daemon prio=5 tid=75 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1759) at app//org.apache.hadoop.hdfs.server.blockmanagement.CacheReplicationMonitor.run(CacheReplicationMonitor.java:186) "master/7cf745f7364a:0:becomeActiveMaster-MemStoreChunkPool Statistics" daemon prio=5 tid=213 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "AsyncFSWAL-0-hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc-prefix:7cf745f7364a,32867,1731907139252" daemon prio=5 tid=284 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RS-EventLoopGroup-1-1" daemon prio=10 tid=154 runnable java.lang.Thread.State: RUNNABLE at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait(Native Method) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait(Native.java:220) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait(Native.java:213) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.EpollEventLoop.epollWaitNoTimerChange(EpollEventLoop.java:308) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.EpollEventLoop.run(EpollEventLoop.java:365) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:997) at app//org.apache.hbase.thirdparty.io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "master/7cf745f7364a:0:becomeActiveMaster-HFileCleaner.small.0-1731907141731" daemon prio=5 tid=263 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.PriorityBlockingQueue.take(PriorityBlockingQueue.java:535) at app//org.apache.hadoop.hbase.master.cleaner.HFileCleaner.consumerLoop(HFileCleaner.java:285) at app//org.apache.hadoop.hbase.master.cleaner.HFileCleaner$2.run(HFileCleaner.java:269) "IPC Server handler 1 on default port 38907" daemon prio=5 tid=105 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.poll(LinkedBlockingQueue.java:460) at app//org.apache.hadoop.ipc.CallQueueManager.take(CallQueueManager.java:370) at app//org.apache.hadoop.ipc.Server$Handler.run(Server.java:3165) "Time-limited test-EventThread" daemon prio=5 tid=156 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at app//org.apache.zookeeper.ClientCnxn$EventThread.run(ClientCnxn.java:550) "Monitor thread for TaskMonitor" daemon prio=5 tid=209 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.hbase.monitoring.TaskMonitor$MonitorRunnable.run(TaskMonitor.java:325) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "qtp1965036093-90" daemon prio=5 tid=90 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at app//org.eclipse.jetty.util.BlockingArrayQueue.poll(BlockingArrayQueue.java:382) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.idleJobPoll(QueuedThreadPool.java:974) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.run(QueuedThreadPool.java:1018) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Session-HouseKeeper-67bf5572-1" prio=5 tid=45 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Time-limited test.named-queue-events-pool-0" daemon prio=5 tid=152 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at app//com.lmax.disruptor.BlockingWaitStrategy.waitFor(BlockingWaitStrategy.java:47) at app//com.lmax.disruptor.ProcessingSequenceBarrier.waitFor(ProcessingSequenceBarrier.java:56) at app//com.lmax.disruptor.BatchEventProcessor.processEvents(BatchEventProcessor.java:159) at app//com.lmax.disruptor.BatchEventProcessor.run(BatchEventProcessor.java:125) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "MarkedDeleteBlockScrubberThread" daemon prio=5 tid=48 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.hdfs.server.blockmanagement.BlockManager$MarkedDeleteBlockScrubber.run(BlockManager.java:5326) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "master/7cf745f7364a:0:becomeActiveMaster-MemStoreChunkPool Statistics" daemon prio=5 tid=211 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "master:store-WAL-Roller" daemon prio=5 tid=225 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Object.wait(Native Method) at app//org.apache.hadoop.hbase.wal.AbstractWALRoller.run(AbstractWALRoller.java:179) "NIOWorkerThread-10" daemon prio=5 tid=166 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "7cf745f7364a:39359" daemon prio=5 tid=251 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at app//org.apache.hadoop.hbase.master.assignment.AssignmentManager.waitOnAssignQueue(AssignmentManager.java:2370) at app//org.apache.hadoop.hbase.master.assignment.AssignmentManager.processAssignQueue(AssignmentManager.java:2392) at app//org.apache.hadoop.hbase.master.assignment.AssignmentManager.access$600(AssignmentManager.java:112) at app//org.apache.hadoop.hbase.master.assignment.AssignmentManager$1.run(AssignmentManager.java:2332) "IPC Client (1877429482) connection to localhost/127.0.0.1:37393 from jenkins" daemon prio=5 tid=109 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Object.wait(Native Method) at app//org.apache.hadoop.ipc.Client$Connection.waitForWork(Client.java:1042) at app//org.apache.hadoop.ipc.Client$Connection.run(Client.java:1093) "pool-5-thread-1" prio=5 tid=36 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcServer.replication.FPBQ.Fifo.handler=2,queue=0,port=39359" daemon prio=5 tid=181 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquire(AbstractQueuedSynchronizer.java:715) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1047) at java.base@17.0.11/java.util.concurrent.Semaphore.acquire(Semaphore.java:318) at app//org.apache.hadoop.hbase.ipc.FastPathRpcHandler.getCallRunner(FastPathRpcHandler.java:55) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "HBase-Metrics2-1" daemon prio=5 tid=153 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Block report processor" daemon prio=5 tid=51 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.ArrayBlockingQueue.take(ArrayBlockingQueue.java:420) at app//org.apache.hadoop.hdfs.server.blockmanagement.BlockManager$BlockReportProcessingThread.processQueue(BlockManager.java:5627) at app//org.apache.hadoop.hdfs.server.blockmanagement.BlockManager$BlockReportProcessingThread.run(BlockManager.java:5614) "zk-event-processor-pool-0" daemon prio=5 tid=194 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "qtp1312628392-38" daemon prio=5 tid=38 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:146) at app//org.eclipse.jetty.io.ManagedSelector.nioSelect(ManagedSelector.java:183) at app//org.eclipse.jetty.io.ManagedSelector.select(ManagedSelector.java:190) at app//org.eclipse.jetty.io.ManagedSelector$SelectorProducer.select(ManagedSelector.java:606) at app//org.eclipse.jetty.io.ManagedSelector$SelectorProducer.produce(ManagedSelector.java:543) at app//org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.produceTask(EatWhatYouKill.java:362) at app//org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.doProduce(EatWhatYouKill.java:186) at app//org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.tryProduce(EatWhatYouKill.java:173) at app//org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.produce(EatWhatYouKill.java:137) at app//org.eclipse.jetty.io.ManagedSelector$$Lambda$257/0x00007f6368423440.run(Unknown Source) at app//org.eclipse.jetty.util.thread.QueuedThreadPool.runJob(QueuedThreadPool.java:883) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.run(QueuedThreadPool.java:1034) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "nioEventLoopGroup-2-1" prio=10 tid=92 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:146) at app//io.netty.channel.nio.SelectedSelectionKeySetSelector.select(SelectedSelectionKeySetSelector.java:68) at app//io.netty.channel.nio.NioEventLoop.select(NioEventLoop.java:879) at app//io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:526) at app//io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:994) at app//io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74) at app//io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=32867" daemon prio=5 tid=196 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquire(AbstractQueuedSynchronizer.java:715) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1047) at java.base@17.0.11/java.util.concurrent.Semaphore.acquire(Semaphore.java:318) at app//org.apache.hadoop.hbase.ipc.FastPathRpcHandler.getCallRunner(FastPathRpcHandler.java:55) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "IPC Server handler 2 on default port 37393" daemon prio=5 tid=66 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.poll(LinkedBlockingQueue.java:460) at app//org.apache.hadoop.ipc.CallQueueManager.take(CallQueueManager.java:370) at app//org.apache.hadoop.ipc.Server$Handler.run(Server.java:3165) "SessionTracker" daemon prio=5 tid=141 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.zookeeper.server.SessionTrackerImpl.run(SessionTrackerImpl.java:163) "RequestThrottler" daemon prio=5 tid=144 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at app//org.apache.zookeeper.server.RequestThrottler.run(RequestThrottler.java:147) "IPC Server Responder" daemon prio=5 tid=97 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:141) at app//org.apache.hadoop.ipc.Server$Responder.doRunLoop(Server.java:1733) at app//org.apache.hadoop.ipc.Server$Responder.run(Server.java:1716) "NIOServerCxnFactory.AcceptThread:localhost/127.0.0.1:61937" daemon prio=5 tid=140 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:146) at app//org.apache.zookeeper.server.NIOServerCnxnFactory$AcceptThread.select(NIOServerCnxnFactory.java:205) at app//org.apache.zookeeper.server.NIOServerCnxnFactory$AcceptThread.run(NIOServerCnxnFactory.java:181) "RpcServer.metaPriority.FPBQ.Fifo.handler=0,queue=0,port=39359" daemon prio=5 tid=182 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquire(AbstractQueuedSynchronizer.java:715) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1047) at java.base@17.0.11/java.util.concurrent.Semaphore.acquire(Semaphore.java:318) at app//org.apache.hadoop.hbase.ipc.FastPathRpcHandler.getCallRunner(FastPathRpcHandler.java:55) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "main" prio=5 tid=1 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/java.lang.Thread.dumpThreads(Native Method) at java.base@17.0.11/java.lang.Thread.getAllStackTraces(Thread.java:1671) at app//org.apache.hadoop.hbase.TimedOutTestsListener.buildThreadDump(TimedOutTestsListener.java:92) at app//org.apache.hadoop.hbase.TimedOutTestsListener.buildThreadDiagnosticString(TimedOutTestsListener.java:78) at app//org.apache.hadoop.hbase.TimedOutTestsListener.testFailure(TimedOutTestsListener.java:65) at app//org.junit.runner.notification.SynchronizedRunListener.testFailure(SynchronizedRunListener.java:94) at app//org.junit.runner.notification.RunNotifier$6.notifyListener(RunNotifier.java:177) at app//org.junit.runner.notification.RunNotifier$SafeNotifier.run(RunNotifier.java:72) at app//org.junit.runner.notification.RunNotifier.fireTestFailures(RunNotifier.java:173) at app//org.junit.runner.notification.RunNotifier.fireTestFailure(RunNotifier.java:167) at app//org.apache.maven.surefire.common.junit4.Notifier.fireTestFailure(Notifier.java:100) at app//org.junit.internal.runners.model.EachTestNotifier.addFailure(EachTestNotifier.java:23) at app//org.junit.internal.runners.model.EachTestNotifier.addMultipleFailureException(EachTestNotifier.java:29) at app//org.junit.internal.runners.model.EachTestNotifier.addFailure(EachTestNotifier.java:21) at app//org.junit.runners.ParentRunner.run(ParentRunner.java:419) at app//org.apache.maven.surefire.junit4.JUnit4Provider.execute(JUnit4Provider.java:316) at app//org.apache.maven.surefire.junit4.JUnit4Provider.executeWithRerun(JUnit4Provider.java:240) at app//org.apache.maven.surefire.junit4.JUnit4Provider.executeTestSet(JUnit4Provider.java:214) at app//org.apache.maven.surefire.junit4.JUnit4Provider.invoke(JUnit4Provider.java:155) at app//org.apache.maven.surefire.booter.ForkedBooter.runSuitesInProcess(ForkedBooter.java:385) at app//org.apache.maven.surefire.booter.ForkedBooter.execute(ForkedBooter.java:162) at app//org.apache.maven.surefire.booter.ForkedBooter.run(ForkedBooter.java:507) at app//org.apache.maven.surefire.booter.ForkedBooter.main(ForkedBooter.java:495) "Async-Client-Retry-Timer-pool-0" daemon prio=5 tid=319 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hbase.thirdparty.io.netty.util.HashedWheelTimer$Worker.waitForNextTick(HashedWheelTimer.java:598) at app//org.apache.hbase.thirdparty.io.netty.util.HashedWheelTimer$Worker.run(HashedWheelTimer.java:494) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "JvmPauseMonitor" daemon prio=5 tid=271 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.hbase.util.JvmPauseMonitor$Monitor.run(JvmPauseMonitor.java:148) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "PacketResponder: BP-1100534618-172.17.0.2-1731907135498:blk_1073741832_1008, type=LAST_IN_PIPELINE" daemon prio=5 tid=282 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/java.lang.Object.wait(Native Method) at java.base@17.0.11/java.lang.Object.wait(Object.java:338) at app//org.apache.hadoop.hdfs.server.datanode.BlockReceiver$PacketResponder.waitForAckHead(BlockReceiver.java:1367) at app//org.apache.hadoop.hdfs.server.datanode.BlockReceiver$PacketResponder.run(BlockReceiver.java:1439) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Hadoop-Metrics-Updater-0" daemon prio=5 tid=98 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "pool-11-thread-1" prio=5 tid=69 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "org.apache.hadoop.hdfs.server.namenode.FSNamesystem$LazyPersistFileScrubber@262e079b" daemon prio=5 tid=74 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.hdfs.server.namenode.FSNamesystem$LazyPersistFileScrubber.run(FSNamesystem.java:4689) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "MobFileCache #0" daemon prio=5 tid=191 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "NIOWorkerThread-11" daemon prio=5 tid=167 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "master:store-Flusher" daemon prio=5 tid=240 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1759) at app//org.apache.hadoop.hbase.master.region.MasterRegionFlusherAndCompactor.flushLoop(MasterRegionFlusherAndCompactor.java:200) at app//org.apache.hadoop.hbase.master.region.MasterRegionFlusherAndCompactor$$Lambda$481/0x00007f63689be2f8.run(Unknown Source) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "NIOWorkerThread-2" daemon prio=5 tid=157 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "pool-17-thread-1" prio=5 tid=86 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcServer.replication.FPBQ.Fifo.handler=0,queue=0,port=39359" daemon prio=5 tid=179 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquire(AbstractQueuedSynchronizer.java:715) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1047) at java.base@17.0.11/java.util.concurrent.Semaphore.acquire(Semaphore.java:318) at app//org.apache.hadoop.hbase.ipc.FastPathRpcHandler.getCallRunner(FastPathRpcHandler.java:55) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "org.apache.hadoop.hdfs.server.namenode.FSNamesystem$NameNodeResourceMonitor@6b49abe4" daemon prio=5 tid=72 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.hdfs.server.namenode.FSNamesystem$NameNodeResourceMonitor.run(FSNamesystem.java:4550) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "org.apache.hadoop.util.JvmPauseMonitor$Monitor@df7e1a0" daemon prio=5 tid=93 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.util.JvmPauseMonitor$Monitor.run(JvmPauseMonitor.java:189) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "ReadOnlyZKClient-127.0.0.1:61937@0x57d89e0d" daemon prio=5 tid=325 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.DelayQueue.poll(DelayQueue.java:265) at app//org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:370) at app//org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$$Lambda$760/0x00007f6368b4b1b0.run(Unknown Source) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Signal Dispatcher" daemon prio=9 tid=4 runnable java.lang.Thread.State: RUNNABLE "IPC Server handler 3 on default port 38907" daemon prio=5 tid=107 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.poll(LinkedBlockingQueue.java:460) at app//org.apache.hadoop.ipc.CallQueueManager.take(CallQueueManager.java:370) at app//org.apache.hadoop.ipc.Server$Handler.run(Server.java:3165) "refreshUsed-/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/e1a8447b-7280-f5aa-cebe-d7c1b39671e7/cluster_b7a7248c-30f6-7402-42f2-d4751190cb92/dfs/data/data1/current/BP-1100534618-172.17.0.2-1731907135498" daemon prio=5 tid=123 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.fs.CachingGetSpaceUsed$RefreshThread.run(CachingGetSpaceUsed.java:225) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "SyncThread:0" daemon prio=5 tid=142 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at app//org.apache.zookeeper.server.SyncRequestProcessor.run(SyncRequestProcessor.java:170) "regionserver/7cf745f7364a:0.leaseChecker" daemon prio=5 tid=274 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.hbase.regionserver.LeaseManager.run(LeaseManager.java:82) "NIOWorkerThread-14" daemon prio=5 tid=170 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "SnapshotHandlerChoreCleaner" daemon prio=5 tid=253 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RS-EventLoopGroup-1-3" daemon prio=10 tid=329 runnable java.lang.Thread.State: RUNNABLE at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait(Native Method) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait(Native.java:220) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait(Native.java:213) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.EpollEventLoop.epollWaitNoTimerChange(EpollEventLoop.java:308) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.EpollEventLoop.run(EpollEventLoop.java:365) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:997) at app//org.apache.hbase.thirdparty.io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Common-Cleaner" daemon prio=8 tid=12 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Object.wait(Native Method) at java.base@17.0.11/java.lang.ref.ReferenceQueue.remove(ReferenceQueue.java:155) at java.base@17.0.11/jdk.internal.ref.CleanerImpl.run(CleanerImpl.java:140) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) at java.base@17.0.11/jdk.internal.misc.InnocuousThread.run(InnocuousThread.java:162) "org.apache.hadoop.hdfs.server.namenode.LeaseManager$Monitor@6132670e" daemon prio=5 tid=71 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.hdfs.server.namenode.LeaseManager$Monitor.run(LeaseManager.java:537) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "qtp1312628392-42" daemon prio=5 tid=42 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at app//org.eclipse.jetty.util.BlockingArrayQueue.poll(BlockingArrayQueue.java:382) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.idleJobPoll(QueuedThreadPool.java:974) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.run(QueuedThreadPool.java:1018) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RS:0;7cf745f7364a:32867-longCompactions-0" daemon prio=5 tid=272 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at app//org.apache.hadoop.hbase.util.StealJobQueue.take(StealJobQueue.java:101) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RS_OPEN_META-regionserver/7cf745f7364a:0-0" daemon prio=5 tid=294 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "pool-19-thread-1" prio=5 tid=103 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "NIOWorkerThread-8" daemon prio=5 tid=164 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "LruBlockCacheStatsExecutor" daemon prio=5 tid=189 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "AsyncFSWAL-0-hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc-prefix:7cf745f7364a,32867,1731907139252.meta" daemon prio=5 tid=297 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "PacketResponder: BP-1100534618-172.17.0.2-1731907135498:blk_1073741834_1010, type=LAST_IN_PIPELINE" daemon prio=5 tid=296 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/java.lang.Object.wait(Native Method) at java.base@17.0.11/java.lang.Object.wait(Object.java:338) at app//org.apache.hadoop.hdfs.server.datanode.BlockReceiver$PacketResponder.waitForAckHead(BlockReceiver.java:1367) at app//org.apache.hadoop.hdfs.server.datanode.BlockReceiver$PacketResponder.run(BlockReceiver.java:1439) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "IPC Server idle connection scanner for port 38907" daemon prio=5 tid=96 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Object.wait(Native Method) at java.base@17.0.11/java.util.TimerThread.mainLoop(Timer.java:563) at java.base@17.0.11/java.util.TimerThread.run(Timer.java:516) "RpcServer.priority.RWQ.Fifo.write.handler=0,queue=0,port=39359" daemon prio=5 tid=176 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at app//org.apache.hadoop.hbase.ipc.RpcHandler.getCallRunner(RpcHandler.java:71) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "org.apache.hadoop.util.JvmPauseMonitor$Monitor@7eb48b85" daemon prio=5 tid=34 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.util.JvmPauseMonitor$Monitor.run(JvmPauseMonitor.java:189) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Time-limited test-SendThread(127.0.0.1:61937)" daemon prio=5 tid=403 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:141) at app//org.apache.zookeeper.ClientCnxnSocketNIO.doTransport(ClientCnxnSocketNIO.java:332) at app//org.apache.zookeeper.ClientCnxn$SendThread.run(ClientCnxn.java:1289) "zk-event-processor-pool-0" daemon prio=5 tid=405 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcServer.default.FPBQ.Fifo.handler=0,queue=0,port=39359" daemon prio=5 tid=173 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquire(AbstractQueuedSynchronizer.java:715) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1047) at java.base@17.0.11/java.util.concurrent.Semaphore.acquire(Semaphore.java:318) at app//org.apache.hadoop.hbase.ipc.FastPathRpcHandler.getCallRunner(FastPathRpcHandler.java:55) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=39359" daemon prio=5 tid=177 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at app//org.apache.hadoop.hbase.ipc.RpcHandler.getCallRunner(RpcHandler.java:71) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "VolumeScannerThread(/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/e1a8447b-7280-f5aa-cebe-d7c1b39671e7/cluster_b7a7248c-30f6-7402-42f2-d4751190cb92/dfs/data/data2)" daemon prio=5 tid=118 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Object.wait(Native Method) at app//org.apache.hadoop.hdfs.server.datanode.VolumeScanner.run(VolumeScanner.java:656) "IPC Server listener on 0" daemon prio=5 tid=94 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:146) at app//org.apache.hadoop.ipc.Server$Listener.run(Server.java:1559) "Notification Thread" daemon prio=9 tid=13 runnable java.lang.Thread.State: RUNNABLE "qtp1965036093-87" daemon prio=5 tid=87 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:146) at app//org.eclipse.jetty.io.ManagedSelector.nioSelect(ManagedSelector.java:183) at app//org.eclipse.jetty.io.ManagedSelector.select(ManagedSelector.java:190) at app//org.eclipse.jetty.io.ManagedSelector$SelectorProducer.select(ManagedSelector.java:606) at app//org.eclipse.jetty.io.ManagedSelector$SelectorProducer.produce(ManagedSelector.java:543) at app//org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.produceTask(EatWhatYouKill.java:362) at app//org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.doProduce(EatWhatYouKill.java:186) at app//org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.tryProduce(EatWhatYouKill.java:173) at app//org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.produce(EatWhatYouKill.java:137) at app//org.eclipse.jetty.io.ManagedSelector$$Lambda$257/0x00007f6368423440.run(Unknown Source) at app//org.eclipse.jetty.util.thread.QueuedThreadPool.runJob(QueuedThreadPool.java:883) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.run(QueuedThreadPool.java:1034) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RPCClient-NioEventLoopGroup-4-1" daemon prio=5 tid=324 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:146) at app//org.apache.hbase.thirdparty.io.netty.channel.nio.SelectedSelectionKeySetSelector.select(SelectedSelectionKeySetSelector.java:68) at app//org.apache.hbase.thirdparty.io.netty.channel.nio.NioEventLoop.select(NioEventLoop.java:879) at app//org.apache.hbase.thirdparty.io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:526) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:997) at app//org.apache.hbase.thirdparty.io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "ConnnectionExpirer" daemon prio=5 tid=137 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.zookeeper.server.NIOServerCnxnFactory$ConnectionExpirerThread.run(NIOServerCnxnFactory.java:554) "DataXceiver for client DFSClient_NONMAPREDUCE_440915301_22 at /127.0.0.1:58574 [Receiving block BP-1100534618-172.17.0.2-1731907135498:blk_1073741832_1008]" daemon prio=5 tid=281 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:141) at app//org.apache.hadoop.net.SocketIOWithTimeout$SelectorPool.select(SocketIOWithTimeout.java:335) at app//org.apache.hadoop.net.SocketIOWithTimeout.doIO(SocketIOWithTimeout.java:156) at app//org.apache.hadoop.net.SocketInputStream.read(SocketInputStream.java:161) at app//org.apache.hadoop.net.SocketInputStream.read(SocketInputStream.java:131) at java.base@17.0.11/java.io.BufferedInputStream.fill(BufferedInputStream.java:244) at java.base@17.0.11/java.io.BufferedInputStream.read1(BufferedInputStream.java:284) at java.base@17.0.11/java.io.BufferedInputStream.read(BufferedInputStream.java:343) at java.base@17.0.11/java.io.DataInputStream.read(DataInputStream.java:151) at app//org.apache.hadoop.io.IOUtils.readFully(IOUtils.java:214) at app//org.apache.hadoop.hdfs.protocol.datatransfer.PacketReceiver.doReadFully(PacketReceiver.java:221) at app//org.apache.hadoop.hdfs.protocol.datatransfer.PacketReceiver.doRead(PacketReceiver.java:144) at app//org.apache.hadoop.hdfs.protocol.datatransfer.PacketReceiver.receiveNextPacket(PacketReceiver.java:119) at app//org.apache.hadoop.hdfs.server.datanode.BlockReceiver.receivePacket(BlockReceiver.java:553) at app//org.apache.hadoop.hdfs.server.datanode.BlockReceiver.receiveBlock(BlockReceiver.java:1011) at app//org.apache.hadoop.hdfs.server.datanode.DataXceiver.writeBlock(DataXceiver.java:920) at app//org.apache.hadoop.hdfs.protocol.datatransfer.Receiver.opWriteBlock(Receiver.java:176) at app//org.apache.hadoop.hdfs.protocol.datatransfer.Receiver.processOp(Receiver.java:110) at app//org.apache.hadoop.hdfs.server.datanode.DataXceiver.run(DataXceiver.java:299) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcServer.metaPriority.FPBQ.Fifo.handler=0,queue=0,port=32867" daemon prio=5 tid=204 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquire(AbstractQueuedSynchronizer.java:715) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1047) at java.base@17.0.11/java.util.concurrent.Semaphore.acquire(Semaphore.java:318) at app//org.apache.hadoop.hbase.ipc.FastPathRpcHandler.getCallRunner(FastPathRpcHandler.java:55) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "VolumeScannerThread(/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/e1a8447b-7280-f5aa-cebe-d7c1b39671e7/cluster_b7a7248c-30f6-7402-42f2-d4751190cb92/dfs/data/data1)" daemon prio=5 tid=117 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Object.wait(Native Method) at app//org.apache.hadoop.hdfs.server.datanode.VolumeScanner.run(VolumeScanner.java:656) "Session-HouseKeeper-3685d53b-1" prio=5 tid=91 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=32867" daemon prio=5 tid=197 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquire(AbstractQueuedSynchronizer.java:715) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1047) at java.base@17.0.11/java.util.concurrent.Semaphore.acquire(Semaphore.java:318) at app//org.apache.hadoop.hbase.ipc.FastPathRpcHandler.getCallRunner(FastPathRpcHandler.java:55) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "IPC Server handler 4 on default port 37393" daemon prio=5 tid=68 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.poll(LinkedBlockingQueue.java:460) at app//org.apache.hadoop.ipc.CallQueueManager.take(CallQueueManager.java:370) at app//org.apache.hadoop.ipc.Server$Handler.run(Server.java:3165) "Hadoop-Metrics-Updater-0" daemon prio=5 tid=58 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "org.apache.hadoop.hdfs.server.blockmanagement.PendingReconstructionBlocks$PendingReconstructionMonitor@5ec1d4f9" daemon prio=5 tid=61 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.hdfs.server.blockmanagement.PendingReconstructionBlocks$PendingReconstructionMonitor.run(PendingReconstructionBlocks.java:267) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RPCClient-NioEventLoopGroup-4-2" daemon prio=5 tid=328 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:141) at app//org.apache.hbase.thirdparty.io.netty.channel.nio.SelectedSelectionKeySetSelector.select(SelectedSelectionKeySetSelector.java:62) at app//org.apache.hbase.thirdparty.io.netty.channel.nio.NioEventLoop.select(NioEventLoop.java:883) at app//org.apache.hbase.thirdparty.io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:526) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:997) at app//org.apache.hbase.thirdparty.io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "region-location-1" daemon prio=5 tid=318 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1170) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "7cf745f7364a:32867Replication Statistics #0" daemon prio=5 tid=279 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcServer.replication.FPBQ.Fifo.handler=1,queue=0,port=32867" daemon prio=5 tid=202 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquire(AbstractQueuedSynchronizer.java:715) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1047) at java.base@17.0.11/java.util.concurrent.Semaphore.acquire(Semaphore.java:318) at app//org.apache.hadoop.hbase.ipc.FastPathRpcHandler.getCallRunner(FastPathRpcHandler.java:55) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "DatanodeAdminMonitor-0" daemon prio=5 tid=62 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Socket Reader #1 for port 0" daemon prio=5 tid=95 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:146) at app//org.apache.hadoop.ipc.Server$Listener$Reader.doRunLoop(Server.java:1497) at app//org.apache.hadoop.ipc.Server$Listener$Reader.run(Server.java:1476) "RS-EventLoopGroup-3-2" daemon prio=10 tid=234 runnable java.lang.Thread.State: RUNNABLE at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait0(Native Method) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait(Native.java:193) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.EpollEventLoop.epollWait(EpollEventLoop.java:304) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.EpollEventLoop.run(EpollEventLoop.java:368) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:997) at app//org.apache.hbase.thirdparty.io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "WorkerMonitor" daemon prio=5 tid=244 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.DelayQueue.poll(DelayQueue.java:279) at app//org.apache.hadoop.hbase.procedure2.util.DelayedUtil.takeWithoutInterrupt(DelayedUtil.java:81) at app//org.apache.hadoop.hbase.procedure2.TimeoutExecutorThread.run(TimeoutExecutorThread.java:56) "AsyncFSWAL-0-hdfs://localhost:37393/user/jenkins/test-data/c5fd44ef-7cc1-db9d-09e6-13b5a5f073cc/MasterData-prefix:7cf745f7364a,39359,1731907138502" daemon prio=5 tid=237 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "NIOWorkerThread-5" daemon prio=5 tid=161 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "PEWorker-4" daemon prio=5 tid=248 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at app//org.apache.hadoop.hbase.procedure2.AbstractProcedureScheduler.poll(AbstractProcedureScheduler.java:167) at app//org.apache.hadoop.hbase.procedure2.AbstractProcedureScheduler.poll(AbstractProcedureScheduler.java:149) at app//org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2128) "NIOWorkerThread-6" daemon prio=5 tid=162 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "PEWorker-2" daemon prio=5 tid=246 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at app//org.apache.hadoop.hbase.procedure2.AbstractProcedureScheduler.poll(AbstractProcedureScheduler.java:167) at app//org.apache.hadoop.hbase.procedure2.AbstractProcedureScheduler.poll(AbstractProcedureScheduler.java:149) at app//org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2128) "RpcServer.replication.FPBQ.Fifo.handler=0,queue=0,port=32867" daemon prio=5 tid=201 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquire(AbstractQueuedSynchronizer.java:715) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1047) at java.base@17.0.11/java.util.concurrent.Semaphore.acquire(Semaphore.java:318) at app//org.apache.hadoop.hbase.ipc.FastPathRpcHandler.getCallRunner(FastPathRpcHandler.java:55) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "Time-limited test" daemon prio=5 tid=22 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.CompletableFuture$Signaller.block(CompletableFuture.java:1864) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.CompletableFuture.waitingGet(CompletableFuture.java:1898) at java.base@17.0.11/java.util.concurrent.CompletableFuture.join(CompletableFuture.java:2117) at app//org.apache.hadoop.hbase.client.TestAsyncReplicationAdminApi.clearPeerAndQueues(TestAsyncReplicationAdminApi.java:96) at java.base@17.0.11/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at java.base@17.0.11/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) at java.base@17.0.11/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) at java.base@17.0.11/java.lang.reflect.Method.invoke(Method.java:568) at app//org.junit.runners.model.FrameworkMethod$1.runReflectiveCall(FrameworkMethod.java:59) at app//org.junit.internal.runners.model.ReflectiveCallable.run(ReflectiveCallable.java:12) at app//org.junit.runners.model.FrameworkMethod.invokeExplosively(FrameworkMethod.java:56) at app//org.junit.internal.runners.statements.RunAfters.invokeMethod(RunAfters.java:46) at app//org.junit.internal.runners.statements.RunAfters.evaluate(RunAfters.java:33) at app//org.junit.rules.TestWatcher$1.evaluate(TestWatcher.java:61) at app//org.junit.runners.ParentRunner$3.evaluate(ParentRunner.java:306) at app//org.junit.runners.BlockJUnit4ClassRunner$1.evaluate(BlockJUnit4ClassRunner.java:100) at app//org.junit.runners.ParentRunner.runLeaf(ParentRunner.java:366) at app//org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:103) at app//org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:63) at app//org.junit.runners.ParentRunner$4.run(ParentRunner.java:331) at app//org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:79) at app//org.junit.runners.ParentRunner.runChildren(ParentRunner.java:329) at app//org.junit.runners.ParentRunner.access$100(ParentRunner.java:66) at app//org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:293) at app//org.junit.runners.ParentRunner.run(ParentRunner.java:413) at app//org.junit.runners.Suite.runChild(Suite.java:128) at app//org.junit.runners.Suite.runChild(Suite.java:27) at app//org.junit.runners.ParentRunner$4.run(ParentRunner.java:331) at app//org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:79) at app//org.junit.runners.ParentRunner.runChildren(ParentRunner.java:329) at app//org.junit.runners.ParentRunner.access$100(ParentRunner.java:66) at app//org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:293) at app//org.junit.internal.runners.statements.RunBefores.evaluate(RunBefores.java:26) at app//org.junit.internal.runners.statements.RunAfters.evaluate(RunAfters.java:27) at app//org.junit.internal.runners.statements.FailOnTimeout$CallableStatement.call(FailOnTimeout.java:299) at app//org.junit.internal.runners.statements.FailOnTimeout$CallableStatement.call(FailOnTimeout.java:293) at java.base@17.0.11/java.util.concurrent.FutureTask.run(FutureTask.java:264) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RS_COMPACTED_FILES_DISCHARGER-regionserver/7cf745f7364a:0-0" daemon prio=5 tid=757 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "FSEditLogAsync" daemon prio=5 tid=53 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.ArrayBlockingQueue.take(ArrayBlockingQueue.java:420) at app//org.apache.hadoop.hdfs.server.namenode.FSEditLogAsync.dequeueEdit(FSEditLogAsync.java:241) at app//org.apache.hadoop.hdfs.server.namenode.FSEditLogAsync.run(FSEditLogAsync.java:250) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "IPC Server handler 0 on default port 37393" daemon prio=5 tid=64 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.poll(LinkedBlockingQueue.java:460) at app//org.apache.hadoop.ipc.CallQueueManager.take(CallQueueManager.java:370) at app//org.apache.hadoop.ipc.Server$Handler.run(Server.java:3165) "BP-1100534618-172.17.0.2-1731907135498 heartbeating to localhost/127.0.0.1:37393" daemon prio=5 tid=102 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Object.wait(Native Method) at app//org.apache.hadoop.hdfs.server.datanode.IncrementalBlockReportManager.waitTillNextIBR(IncrementalBlockReportManager.java:158) at app//org.apache.hadoop.hdfs.server.datanode.BPServiceActor.offerService(BPServiceActor.java:771) at app//org.apache.hadoop.hdfs.server.datanode.BPServiceActor.run(BPServiceActor.java:914) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RS-EventLoopGroup-3-3" daemon prio=10 tid=293 runnable java.lang.Thread.State: RUNNABLE at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait0(Native Method) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait(Native.java:193) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.EpollEventLoop.epollWait(EpollEventLoop.java:304) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.EpollEventLoop.run(EpollEventLoop.java:368) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:997) at app//org.apache.hbase.thirdparty.io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Command processor" daemon prio=5 tid=101 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at app//org.apache.hadoop.hdfs.server.datanode.BPServiceActor$CommandProcessingThread.processQueue(BPServiceActor.java:1411) at app//org.apache.hadoop.hdfs.server.datanode.BPServiceActor$CommandProcessingThread.run(BPServiceActor.java:1395) "qtp1312628392-43" daemon prio=5 tid=43 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at app//org.eclipse.jetty.util.BlockingArrayQueue.poll(BlockingArrayQueue.java:382) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.idleJobPoll(QueuedThreadPool.java:974) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.run(QueuedThreadPool.java:1018) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "org.apache.hadoop.hdfs.server.namenode.FSNamesystem$NameNodeEditLogRoller@7a30b880" daemon prio=5 tid=73 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.hdfs.server.namenode.FSNamesystem$NameNodeEditLogRoller.run(FSNamesystem.java:4592) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "pool-6-thread-1" prio=5 tid=46 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "IPC Parameter Sending Thread for localhost/127.0.0.1:37393" daemon prio=5 tid=110 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.SynchronousQueue$TransferQueue.transfer(SynchronousQueue.java:704) at java.base@17.0.11/java.util.concurrent.SynchronousQueue.poll(SynchronousQueue.java:903) at app//org.apache.hadoop.ipc.Client$Connection$RpcRequestSender.run(Client.java:1121) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "NIOWorkerThread-16" daemon prio=5 tid=172 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "region-location-0" daemon prio=5 tid=317 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1170) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=39359" daemon prio=5 tid=178 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at app//org.apache.hadoop.hbase.ipc.RpcHandler.getCallRunner(RpcHandler.java:71) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "FsDatasetAsyncDiskServiceFixer" daemon prio=5 tid=136 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer.run(HBaseTestingUtility.java:599) "GcTimeMonitor obsWindow = 60000, sleepInterval = 5000, maxGcTimePerc = 100" daemon prio=5 tid=35 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.util.GcTimeMonitor.run(GcTimeMonitor.java:161) "PEWorker-1" daemon prio=5 tid=245 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at app//org.apache.hadoop.hbase.procedure2.AbstractProcedureScheduler.poll(AbstractProcedureScheduler.java:167) at app//org.apache.hadoop.hbase.procedure2.AbstractProcedureScheduler.poll(AbstractProcedureScheduler.java:149) at app//org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2128) "IPC Server Responder" daemon prio=5 tid=57 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:141) at app//org.apache.hadoop.ipc.Server$Responder.doRunLoop(Server.java:1733) at app//org.apache.hadoop.ipc.Server$Responder.run(Server.java:1716) "RS:0;7cf745f7364a:32867" daemon prio=5 tid=206 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Object.wait(Native Method) at app//org.apache.hadoop.hbase.util.Sleeper.sleep(Sleeper.java:81) at app//org.apache.hadoop.hbase.util.Sleeper.sleep(Sleeper.java:64) at app//org.apache.hadoop.hbase.regionserver.HRegionServer.run(HRegionServer.java:1164) at app//org.apache.hadoop.hbase.MiniHBaseCluster$MiniHBaseClusterRegionServer.runRegionServer(MiniHBaseCluster.java:176) at app//org.apache.hadoop.hbase.MiniHBaseCluster$MiniHBaseClusterRegionServer.access$000(MiniHBaseCluster.java:124) at app//org.apache.hadoop.hbase.MiniHBaseCluster$MiniHBaseClusterRegionServer$1.run(MiniHBaseCluster.java:160) at java.base@17.0.11/java.security.AccessController.executePrivileged(AccessController.java:776) at java.base@17.0.11/java.security.AccessController.doPrivileged(AccessController.java:399) at java.base@17.0.11/javax.security.auth.Subject.doAs(Subject.java:376) at app//org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1930) at app//org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:322) at app//org.apache.hadoop.hbase.MiniHBaseCluster$MiniHBaseClusterRegionServer.run(MiniHBaseCluster.java:157) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RegionServerTracker-0" daemon prio=5 tid=268 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "regionserver/7cf745f7364a:0.logRoller" daemon prio=5 tid=275 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Object.wait(Native Method) at app//org.apache.hadoop.hbase.wal.AbstractWALRoller.run(AbstractWALRoller.java:179) "IPC Server handler 1 on default port 37393" daemon prio=5 tid=65 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.poll(LinkedBlockingQueue.java:460) at app//org.apache.hadoop.ipc.CallQueueManager.take(CallQueueManager.java:370) at app//org.apache.hadoop.ipc.Server$Handler.run(Server.java:3165) "org.apache.hadoop.hdfs.server.datanode.DataXceiverServer@a467a69" daemon prio=5 tid=85 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.Net.accept(Native Method) at java.base@17.0.11/sun.nio.ch.ServerSocketChannelImpl.implAccept(ServerSocketChannelImpl.java:425) at java.base@17.0.11/sun.nio.ch.ServerSocketChannelImpl.accept(ServerSocketChannelImpl.java:391) at java.base@17.0.11/sun.nio.ch.ServerSocketAdaptor.accept(ServerSocketAdaptor.java:126) at app//org.apache.hadoop.hdfs.net.TcpPeerServer.accept(TcpPeerServer.java:85) at app//org.apache.hadoop.hdfs.server.datanode.DataXceiverServer.run(DataXceiverServer.java:242) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcServer.replication.FPBQ.Fifo.handler=2,queue=0,port=32867" daemon prio=5 tid=203 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquire(AbstractQueuedSynchronizer.java:715) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1047) at java.base@17.0.11/java.util.concurrent.Semaphore.acquire(Semaphore.java:318) at app//org.apache.hadoop.hbase.ipc.FastPathRpcHandler.getCallRunner(FastPathRpcHandler.java:55) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "DataXceiver for client DFSClient_NONMAPREDUCE_440915301_22 at /127.0.0.1:48230 [Receiving block BP-1100534618-172.17.0.2-1731907135498:blk_1073741834_1010]" daemon prio=5 tid=295 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:141) at app//org.apache.hadoop.net.SocketIOWithTimeout$SelectorPool.select(SocketIOWithTimeout.java:335) at app//org.apache.hadoop.net.SocketIOWithTimeout.doIO(SocketIOWithTimeout.java:156) at app//org.apache.hadoop.net.SocketInputStream.read(SocketInputStream.java:161) at app//org.apache.hadoop.net.SocketInputStream.read(SocketInputStream.java:131) at java.base@17.0.11/java.io.BufferedInputStream.fill(BufferedInputStream.java:244) at java.base@17.0.11/java.io.BufferedInputStream.read1(BufferedInputStream.java:284) at java.base@17.0.11/java.io.BufferedInputStream.read(BufferedInputStream.java:343) at java.base@17.0.11/java.io.DataInputStream.read(DataInputStream.java:151) at app//org.apache.hadoop.io.IOUtils.readFully(IOUtils.java:214) at app//org.apache.hadoop.hdfs.protocol.datatransfer.PacketReceiver.doReadFully(PacketReceiver.java:221) at app//org.apache.hadoop.hdfs.protocol.datatransfer.PacketReceiver.doRead(PacketReceiver.java:144) at app//org.apache.hadoop.hdfs.protocol.datatransfer.PacketReceiver.receiveNextPacket(PacketReceiver.java:119) at app//org.apache.hadoop.hdfs.server.datanode.BlockReceiver.receivePacket(BlockReceiver.java:553) at app//org.apache.hadoop.hdfs.server.datanode.BlockReceiver.receiveBlock(BlockReceiver.java:1011) at app//org.apache.hadoop.hdfs.server.datanode.DataXceiver.writeBlock(DataXceiver.java:920) at app//org.apache.hadoop.hdfs.protocol.datatransfer.Receiver.opWriteBlock(Receiver.java:176) at app//org.apache.hadoop.hdfs.protocol.datatransfer.Receiver.processOp(Receiver.java:110) at app//org.apache.hadoop.hdfs.server.datanode.DataXceiver.run(DataXceiver.java:299) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "surefire-forkedjvm-stream-flusher" daemon prio=5 tid=16 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "PEWorker-3" daemon prio=5 tid=247 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at app//org.apache.hadoop.hbase.procedure2.AbstractProcedureScheduler.poll(AbstractProcedureScheduler.java:167) at app//org.apache.hadoop.hbase.procedure2.AbstractProcedureScheduler.poll(AbstractProcedureScheduler.java:149) at app//org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2128) "NIOWorkerThread-9" daemon prio=5 tid=165 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=32867" daemon prio=5 tid=200 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at app//org.apache.hadoop.hbase.ipc.RpcHandler.getCallRunner(RpcHandler.java:71) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "PEWorker-5" daemon prio=5 tid=249 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at app//org.apache.hadoop.hbase.procedure2.AbstractProcedureScheduler.poll(AbstractProcedureScheduler.java:167) at app//org.apache.hadoop.hbase.procedure2.AbstractProcedureScheduler.poll(AbstractProcedureScheduler.java:149) at app//org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2128) "master/7cf745f7364a:0:becomeActiveMaster-HFileCleaner.large.0-1731907141731" daemon prio=5 tid=262 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at app//org.apache.hadoop.hbase.util.StealJobQueue.take(StealJobQueue.java:101) at app//org.apache.hadoop.hbase.master.cleaner.HFileCleaner.consumerLoop(HFileCleaner.java:285) at app//org.apache.hadoop.hbase.master.cleaner.HFileCleaner$1.run(HFileCleaner.java:254) "RpcServer.default.FPBQ.Fifo.handler=0,queue=0,port=32867" daemon prio=5 tid=195 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquire(AbstractQueuedSynchronizer.java:715) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1047) at java.base@17.0.11/java.util.concurrent.Semaphore.acquire(Semaphore.java:318) at app//org.apache.hadoop.hbase.ipc.FastPathRpcHandler.getCallRunner(FastPathRpcHandler.java:55) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "M:0;7cf745f7364a:39359" daemon prio=5 tid=184 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Object.wait(Native Method) at app//org.apache.hadoop.hbase.util.Sleeper.sleep(Sleeper.java:81) at app//org.apache.hadoop.hbase.util.Sleeper.sleep(Sleeper.java:64) at app//org.apache.hadoop.hbase.master.HMaster.waitForMasterActive(HMaster.java:702) at app//org.apache.hadoop.hbase.regionserver.HRegionServer.initializeZooKeeper(HRegionServer.java:1014) at app//org.apache.hadoop.hbase.regionserver.HRegionServer.preRegistrationInitialization(HRegionServer.java:954) at app//org.apache.hadoop.hbase.regionserver.HRegionServer.run(HRegionServer.java:1075) at app//org.apache.hadoop.hbase.master.HMaster.run(HMaster.java:603) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Time-limited test-EventThread" daemon prio=5 tid=404 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at app//org.apache.zookeeper.ClientCnxn$EventThread.run(ClientCnxn.java:550) "qtp1312628392-44" daemon prio=5 tid=44 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at app//org.eclipse.jetty.util.BlockingArrayQueue.poll(BlockingArrayQueue.java:382) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.idleJobPoll(QueuedThreadPool.java:974) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.run(QueuedThreadPool.java:1018) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "LeaseRenewer:jenkins@localhost:37393" daemon prio=5 tid=147 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.hdfs.client.impl.LeaseRenewer.run(LeaseRenewer.java:441) at app//org.apache.hadoop.hdfs.client.impl.LeaseRenewer.access$800(LeaseRenewer.java:77) at app//org.apache.hadoop.hdfs.client.impl.LeaseRenewer$1.run(LeaseRenewer.java:336) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Time-limited test-SendThread(127.0.0.1:61937)" daemon prio=5 tid=155 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:141) at app//org.apache.zookeeper.ClientCnxnSocketNIO.doTransport(ClientCnxnSocketNIO.java:332) at app//org.apache.zookeeper.ClientCnxn$SendThread.run(ClientCnxn.java:1289) "RS_OPEN_PRIORITY_REGION-regionserver/7cf745f7364a:0-0" daemon prio=5 tid=312 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "qtp1965036093-88-acceptor-0@597ed123-ServerConnector@723ec49{HTTP/1.1, (http/1.1)}{localhost:35063}" daemon prio=3 tid=88 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.Net.accept(Native Method) at java.base@17.0.11/sun.nio.ch.ServerSocketChannelImpl.implAccept(ServerSocketChannelImpl.java:425) at java.base@17.0.11/sun.nio.ch.ServerSocketChannelImpl.accept(ServerSocketChannelImpl.java:391) at app//org.eclipse.jetty.server.ServerConnector.accept(ServerConnector.java:388) at app//org.eclipse.jetty.server.AbstractConnector$Acceptor.run(AbstractConnector.java:704) at app//org.eclipse.jetty.util.thread.QueuedThreadPool.runJob(QueuedThreadPool.java:883) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.run(QueuedThreadPool.java:1034) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "ProcessThread(sid:0 cport:61937):" daemon prio=5 tid=143 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at app//org.apache.zookeeper.server.PrepRequestProcessor.run(PrepRequestProcessor.java:142) "NIOWorkerThread-15" daemon prio=5 tid=171 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Time-limited test-SendThread(127.0.0.1:61937)" daemon prio=5 tid=192 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:141) at app//org.apache.zookeeper.ClientCnxnSocketNIO.doTransport(ClientCnxnSocketNIO.java:332) at app//org.apache.zookeeper.ClientCnxn$SendThread.run(ClientCnxn.java:1289) "snapshot-hfile-cleaner-cache-refresher" daemon prio=5 tid=260 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Object.wait(Native Method) at java.base@17.0.11/java.util.TimerThread.mainLoop(Timer.java:563) at java.base@17.0.11/java.util.TimerThread.run(Timer.java:516) "Reference Handler" daemon prio=10 tid=2 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/java.lang.ref.Reference.waitForReferencePendingList(Native Method) at java.base@17.0.11/java.lang.ref.Reference.processPendingReferences(Reference.java:253) at java.base@17.0.11/java.lang.ref.Reference$ReferenceHandler.run(Reference.java:215) "Time-limited test.LruBlockCache.EvictionThread" daemon prio=5 tid=187 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Object.wait(Native Method) at app//org.apache.hadoop.hbase.io.hfile.LruBlockCache$EvictionThread.run(LruBlockCache.java:957) "IPC Server handler 2 on default port 38907" daemon prio=5 tid=106 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.poll(LinkedBlockingQueue.java:460) at app//org.apache.hadoop.ipc.CallQueueManager.take(CallQueueManager.java:370) at app//org.apache.hadoop.ipc.Server$Handler.run(Server.java:3165) "DataXceiver for client DFSClient_NONMAPREDUCE_-883898987_22 at /127.0.0.1:57166 [Receiving block BP-1100534618-172.17.0.2-1731907135498:blk_1073741840_1016]" daemon prio=5 tid=894 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:141) at app//org.apache.hadoop.net.SocketIOWithTimeout$SelectorPool.select(SocketIOWithTimeout.java:335) at app//org.apache.hadoop.net.SocketIOWithTimeout.doIO(SocketIOWithTimeout.java:156) at app//org.apache.hadoop.net.SocketInputStream.read(SocketInputStream.java:161) at app//org.apache.hadoop.net.SocketInputStream.read(SocketInputStream.java:131) at java.base@17.0.11/java.io.BufferedInputStream.fill(BufferedInputStream.java:244) at java.base@17.0.11/java.io.BufferedInputStream.read1(BufferedInputStream.java:284) at java.base@17.0.11/java.io.BufferedInputStream.read(BufferedInputStream.java:343) at java.base@17.0.11/java.io.DataInputStream.read(DataInputStream.java:151) at app//org.apache.hadoop.io.IOUtils.readFully(IOUtils.java:214) at app//org.apache.hadoop.hdfs.protocol.datatransfer.PacketReceiver.doReadFully(PacketReceiver.java:221) at app//org.apache.hadoop.hdfs.protocol.datatransfer.PacketReceiver.doRead(PacketReceiver.java:144) at app//org.apache.hadoop.hdfs.protocol.datatransfer.PacketReceiver.receiveNextPacket(PacketReceiver.java:119) at app//org.apache.hadoop.hdfs.server.datanode.BlockReceiver.receivePacket(BlockReceiver.java:553) at app//org.apache.hadoop.hdfs.server.datanode.BlockReceiver.receiveBlock(BlockReceiver.java:1011) at app//org.apache.hadoop.hdfs.server.datanode.DataXceiver.writeBlock(DataXceiver.java:920) at app//org.apache.hadoop.hdfs.protocol.datatransfer.Receiver.opWriteBlock(Receiver.java:176) at app//org.apache.hadoop.hdfs.protocol.datatransfer.Receiver.processOp(Receiver.java:110) at app//org.apache.hadoop.hdfs.server.datanode.DataXceiver.run(DataXceiver.java:299) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcServer.replication.FPBQ.Fifo.handler=1,queue=0,port=39359" daemon prio=5 tid=180 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquire(AbstractQueuedSynchronizer.java:715) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1047) at java.base@17.0.11/java.util.concurrent.Semaphore.acquire(Semaphore.java:318) at app//org.apache.hadoop.hbase.ipc.FastPathRpcHandler.getCallRunner(FastPathRpcHandler.java:55) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "ProcedureDispatcherTimeoutThread" daemon prio=5 tid=250 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.DelayQueue.poll(DelayQueue.java:265) at app//org.apache.hadoop.hbase.procedure2.util.DelayedUtil.takeWithoutInterrupt(DelayedUtil.java:81) at app//org.apache.hadoop.hbase.procedure2.RemoteProcedureDispatcher$TimeoutExecutorThread.run(RemoteProcedureDispatcher.java:328) "IPC Server handler 4 on default port 38907" daemon prio=5 tid=108 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.poll(LinkedBlockingQueue.java:460) at app//org.apache.hadoop.ipc.CallQueueManager.take(CallQueueManager.java:370) at app//org.apache.hadoop.ipc.Server$Handler.run(Server.java:3165) "IPC Server listener on 0" daemon prio=5 tid=54 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:146) at app//org.apache.hadoop.ipc.Server$Listener.run(Server.java:1559) "Socket Reader #1 for port 0" daemon prio=5 tid=55 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:146) at app//org.apache.hadoop.ipc.Server$Listener$Reader.doRunLoop(Server.java:1497) at app//org.apache.hadoop.ipc.Server$Listener$Reader.run(Server.java:1476)