[
https://issues.apache.org/jira/browse/FLINK-36570?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17891392#comment-17891392
]
Matthias Pohl commented on FLINK-36570:
---------------------------------------
Hi [~zyhh], one way to elect a new leader is to start two JobManagers and kill
the one that's currently the leader.
> Fatal error occurred in the cluster entrypoint
> ----------------------------------------------
>
> Key: FLINK-36570
> URL: https://issues.apache.org/jira/browse/FLINK-36570
> Project: Flink
> Issue Type: Bug
> Components: Deployment / Kubernetes
> Affects Versions: 1.17.2
> Environment: * flink 1.17.2
> * native kubernetes session cluster HA(3 jobmanager replica)
> Reporter: zyh
> Priority: Critical
> Attachments: flink-cluster-error.log
>
>
> I commit batch jobs to my session cluster with rest api. The jobmanager pod
> would restart when occurred the error.
> Seems to be because the new leader elected and exist running job at the
> same time. Then the job send to the new leader and error.
> {code:java}
> 2024-10-18 03:07:22,107 INFO
> org.apache.flink.client.deployment.application.executors.EmbeddedExecutor []
> - Submitting Job with JobId=a9d339b6ba26ab51746514cc7aea0537.
> 2024-10-18 03:07:22,546 INFO
> org.apache.flink.kubernetes.kubeclient.resources.KubernetesLeaderElector [] -
> New leader elected 57c4be1d-58f0-4c2c-89d8-11aefe1ec273 for
> flink-cluster-cluster-config-map.
> 2024-10-18 03:07:22,549 ERROR
> org.apache.flink.runtime.entrypoint.ClusterEntrypoint [] - Fatal error
> occurred in the cluster entrypoint.org.apache.flink.util.FlinkException:
> JobMaster for job 99c02051a54c77499f53f09cd4b7a0d9 failed.
> at
> org.apache.flink.runtime.dispatcher.Dispatcher.jobMasterFailed(Dispatcher.java:1360)
> ~[flink-dist-1.17.2.jar:1.17.2]
> at
> org.apache.flink.runtime.dispatcher.Dispatcher.jobManagerRunnerFailed(Dispatcher.java:772)
> ~[flink-dist-1.17.2.jar:1.17.2]
> at
> org.apache.flink.runtime.dispatcher.Dispatcher.lambda$runJob$6(Dispatcher.java:694)
> ~[flink-dist-1.17.2.jar:1.17.2]
> at java.util.concurrent.CompletableFuture.uniHandle(Unknown Source) ~[?:?]
> at java.util.concurrent.CompletableFuture$UniHandle.tryFire(Unknown
> Source) ~[?:?]
> at java.util.concurrent.CompletableFuture$Completion.run(Unknown Source)
> ~[?:?]
> at
> org.apache.flink.runtime.rpc.akka.AkkaRpcActor.lambda$handleRunAsync$4(AkkaRpcActor.java:453)
> ~[flink-rpc-akka_27725420-d3ff-407e-864b- d8e6936565db.jar:1.17.2]
> at
> org.apache.flink.runtime.concurrent.akka.ClassLoadingUtils.runWithContextClassLoader(ClassLoadingUtils.java:68)
> ~[flink-rpc-akka_27725420-d3ff-407e-864b-d8e6936565db.jar:1.17.2]
> at
> org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRunAsync(AkkaRpcActor.java:453)
> ~[flink-rpc-akka_27725420-d3ff-407e-864b-d8e6936565db.jar:1.17.2]
> at
> org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:218)
> ~[flink-rpc-akka_27725420-d3ff-407e-864b-d8e6936565db.jar:1.17.2]
> at
> org.apache.flink.runtime.rpc.akka.FencedAkkaRpcActor.handleRpcMessage(FencedAkkaRpcActor.java:84)
> ~[flink-rpc-akka_27725420-d3ff-407e-864b-d8e6936565db.jar:1.17.2]
> at
> org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleMessage(AkkaRpcActor.java:168)
> ~[flink-rpc-akka_27725420-d3ff-407e-864b-d8e6936565db.jar:1.17.2]
> at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:24)
> [flink-rpc-akka_27725420-d3ff-407e-864b-d8e6936565db.jar:1.17.2]
> at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:20)
> [flink-rpc-akka_27725420-d3ff-407e-864b-d8e6936565db.jar:1.17.2]
> at scala.PartialFunction.applyOrElse(PartialFunction.scala:127)
> [flink-rpc-akka_27725420-d3ff-407e-864b-d8e6936565db.jar:1.17.2]
> at scala.PartialFunction.applyOrElse$(PartialFunction.scala:126)
> [flink-rpc-akka_27725420-d3ff-407e-864b-d8e6936565db.jar:1.17.2]
> at akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:20)
> [flink-rpc-akka_27725420-d3ff-407e-864b-d8e6936565db.jar:1.17.2]
> at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:175)
> [flink-rpc-akka_27725420-d3ff-407e-864b-d8e6936565db.jar:1.17.2]
> at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:176)
> [flink-rpc-akka_27725420-d3ff-407e-864b-d8e6936565db.jar:1.17.2]
> at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:176)
> [flink-rpc-akka_27725420-d3ff-407e-864b-d8e6936565db.jar:1.17.2]
> at akka.actor.Actor.aroundReceive(Actor.scala:537)
> [flink-rpc-akka_27725420-d3ff-407e-864b-d8e6936565db.jar:1.17.2]
> at akka.actor.Actor.aroundReceive$(Actor.scala:535)
> [flink-rpc-akka_27725420-d3ff-407e-864b-d8e6936565db.jar:1.17.2]
> at akka.actor.AbstractActor.aroundReceive(AbstractActor.scala:220)
> [flink-rpc-akka_27725420-d3ff-407e-864b-d8e6936565db.jar:1.17.2]
> at akka.actor.ActorCell.receiveMessage(ActorCell.scala:579)
> [flink-rpc-akka_27725420-d3ff-407e-864b-d8e6936565db.jar:1.17.2]
> at akka.actor.ActorCell.invoke(ActorCell.scala:547)
> [flink-rpc-akka_27725420-d3ff-407e-864b-d8e6936565db.jar:1.17.2]
> at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:270)
> [flink-rpc-akka_27725420-d3ff-407e-864b-d8e6936565db.jar:1.17.2]
> at akka.dispatch.Mailbox.run(Mailbox.scala:231)
> [flink-rpc-akka_27725420-d3ff-407e-864b-d8e6936565db.jar:1.17.2]
> at akka.dispatch.Mailbox.exec(Mailbox.scala:243)
> [flink-rpc-akka_27725420-d3ff-407e-864b-d8e6936565db.jar:1.17.2]
> at java.util.concurrent.ForkJoinTask.doExec(Unknown Source) [?:?]
> at java.util.concurrent.ForkJoinPool$WorkQueue.topLevelExec(Unknown
> Source) [?:?]
> at java.util.concurrent.ForkJoinPool.scan(Unknown Source) [?:?]
> at java.util.concurrent.ForkJoinPool.runWorker(Unknown Source) [?:?]
> at java.util.concurrent.ForkJoinWorkerThread.run(Unknown Source) [?:?]
> caused by: org.apache.flink.util.FlinkException: Could not suspend the job
> manager.
> at
> org.apache.flink.runtime.jobmaster.JobMasterServiceLeadershipRunner.lambda$null$13(JobMasterServiceLeadershipRunner.java:438)
> ~[flink-dist-1.17.2.jar:1.17.2]
> at
> org.apache.flink.runtime.jobmaster.JobMasterServiceLeadershipRunner.runIfStateRunning(JobMasterServiceLeadershipRunner.java:456)
> ~[flink-dist-1.17.2.jar:1.17.2]
> at
> org.apache.flink.runtime.jobmaster.JobMasterServiceLeadershipRunner.lambda$handleAsyncOperationError$14(JobMasterServiceLeadershipRunner.java:436)
> ~[flink-dist-1.17.2.jar:1.17.2]
> at java.util.concurrent.CompletableFuture.uniWhenComplete(Unknown Source)
> ~[?:?]
> at java.util.concurrent.CompletableFuture.uniWhenCompleteStage(Unknown
> Source) ~[?:?]
> at java.util.concurrent.CompletableFuture.whenComplete(Unknown Source)
> ~[?:?]
> at
> org.apache.flink.runtime.jobmaster.JobMasterServiceLeadershipRunner.handleAsyncOperationError(JobMasterServiceLeadershipRunner.java:433)
> ~[flink-dist-1.17.2.jar:1.17.2]
> at
> org.apache.flink.runtime.jobmaster.JobMasterServiceLeadershipRunner.stopJobMasterServiceProcessAsync(JobMasterServiceLeadershipRunner.java:405)
> ~[flink-dist-1.17.2.jar:1.17.2]
> at
> org.apache.flink.runtime.jobmaster.JobMasterServiceLeadershipRunner.runIfStateRunning(JobMasterServiceLeadershipRunner.java:456)
> ~[flink-dist-1.17.2.jar:1.17.2]
> at
> org.apache.flink.runtime.jobmaster.JobMasterServiceLeadershipRunner.revokeLeadership(JobMasterServiceLeadershipRunner.java:390)
> ~[flink-dist-1.17.2.jar:1.17.2]
> at
> org.apache.flink.runtime.leaderelection.DefaultLeaderElectionService.onRevokeLeadership(DefaultLeaderElectionService.java:236)
> ~[flink-dist-1.17.2.jar:1.17.2]
> at
> org.apache.flink.runtime.leaderelection.DefaultMultipleComponentLeaderElectionService.lambda$forEachLeaderElectionEventHandler$2(DefaultMultipleComponentLeaderElectionService.java:225)
> ~[flink-dist-1.17.2.jar:1.17.2]
> at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
> ~[?:?]
> at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
> ~[?:?]
> at java.lang.Thread.run(Unknown Source) ~[?:?]
> caused by: java.util.concurrent.CompletionException:
> java.lang.UnsupportedOperationException: Still waiting for the leadership.
> at java.util.concurrent.CompletableFuture.encodeThrowable(Unknown Source)
> ~[?:?]
> at java.util.concurrent.CompletableFuture.uniComposeStage(Unknown Source)
> ~[?:?]
> at java.util.concurrent.CompletableFuture.thenCompose(Unknown Source)
> ~[?:?]
> at
> org.apache.flink.runtime.jobmaster.JobMasterServiceLeadershipRunner.stopJobMasterServiceProcessAsync(JobMasterServiceLeadershipRunner.java:398)
> ~[flink-dist-1.17.2.jar:1.17.2]
> at
> org.apache.flink.runtime.jobmaster.JobMasterServiceLeadershipRunner.runIfStateRunning(JobMasterServiceLeadershipRunner.java:456)
> ~[flink-dist-1.17.2.jar:1.17.2]
> at
> org.apache.flink.runtime.jobmaster.JobMasterServiceLeadershipRunner.revokeLeadership(JobMasterServiceLeadershipRunner.java:390)
> ~[flink-dist-1.17.2.jar:1.17.2]
> at
> org.apache.flink.runtime.leaderelection.DefaultLeaderElectionService.onRevokeLeadership(DefaultLeaderElectionService.java:236)
> ~[flink-dist-1.17.2.jar:1.17.2]
> at
> org.apache.flink.runtime.leaderelection.DefaultMultipleComponentLeaderElectionService.lambda$forEachLeaderElectionEventHandler$2(DefaultMultipleComponentLeaderElectionService.java:225)
> ~[flink-dist-1.17.2.jar:1.17.2]
> at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
> ~[?:?]
> at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
> ~[?:?]
> at java.lang.Thread.run(Unknown Source) ~[?:?]
> caused by: java.lang.UnsupportedOperationException: Still waiting for the
> leadership.
> at
> org.apache.flink.runtime.jobmaster.JobMasterServiceProcess$WaitingForLeadership.getLeaderSessionId(JobMasterServiceProcess.java:71)
> ~[flink-dist-1.17.2.jar:1.17.2]
> at
> org.apache.flink.runtime.jobmaster.JobMasterServiceLeadershipRunner.stopJobMasterServiceProcess(JobMasterServiceLeadershipRunner.java:414)
> ~[flink-dist-1.17.2.jar:1.17.2]
> at
> org.apache.flink.runtime.jobmaster.JobMasterServiceLeadershipRunner.callIfRunning(JobMasterServiceLeadershipRunner.java:469)
> ~[flink-dist-1.17.2.jar:1.17.2]
> at
> org.apache.flink.runtime.jobmaster.JobMasterServiceLeadershipRunner.lambda$stopJobMasterServiceProcessAsync$12(JobMasterServiceLeadershipRunner.java:400)
> ~[flink-dist-1.17.2.jar:1.17.2]
> at java.util.concurrent.CompletableFuture.uniComposeStage(Unknown Source)
> ~[?:?]
> at java.util.concurrent.CompletableFuture.thenCompose(Unknown Source)
> ~[?:?]
> at
> org.apache.flink.runtime.jobmaster.JobMasterServiceLeadershipRunner.stopJobMasterServiceProcessAsync(JobMasterServiceLeadershipRunner.java:398)
> ~[flink-dist-1.17.2.jar:1.17.2]
> at
> org.apache.flink.runtime.jobmaster.JobMasterServiceLeadershipRunner.runIfStateRunning(JobMasterServiceLeadershipRunner.java:456)
> ~[flink-dist-1.17.2.jar:1.17.2]
> at
> org.apache.flink.runtime.jobmaster.JobMasterServiceLeadershipRunner.revokeLeadership(JobMasterServiceLeadershipRunner.java:390)
> ~[flink-dist-1.17.2.jar:1.17.2]
> at
> org.apache.flink.runtime.leaderelection.DefaultLeaderElectionService.onRevokeLeadership(DefaultLeaderElectionService.java:236)
> ~[flink-dist-1.17.2.jar:1.17.2]
> at
> org.apache.flink.runtime.leaderelection.DefaultMultipleComponentLeaderElectionService.lambda$forEachLeaderElectionEventHandler$2(DefaultMultipleComponentLeaderElectionService.java:225)
> ~[flink-dist-1.17.2.jar:1.17.2]
> at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
> ~[?:?]
> at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
> ~[?:?]
> at java.lang.Thread.run(Unknown Source) ~[?:?]
> INFO org.apache.flink.runtime.entrypoint.ClusterEntrypoint [] -
> Shutting KubernetesSessionClusterEntrypoint down with application status
> UNKNOWN. Diagnostics Cluster entrypoint has been closed externally..INFO
> org.apache.flink.runtime.blob.BlobServer [] - Stopped
> BLOB server at 0.0.0.0:6124
> {code}
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
