You are viewing a plain text version of this content. The canonical link for it is here.
Posted to user@flink.apache.org by P Singh <bi...@gmail.com> on 2023/02/05 07:05:38 UTC
Task Manger is getting failed
Hi Team,
I am submitting a beam python job to flink clusters on a local machine by
minikube. when i submit the job it appears on the flink UI and getting
failed after some time with below traceback. I have defined memory in
flink-configuration-configmap.yaml
jobmanager.rpc.address: flink-jobmanager
taskmanager.numberOfTaskSlots: 2
blob.server.port: 6124
jobmanager.rpc.port: 6123
taskmanager.rpc.port: 6122
queryable-state.proxy.ports: 6125
jobmanager.memory.process.size: 2000m
taskmanager.memory.process.size: 2096m
parallelism.default: 2
org.apache.flink.runtime.JobException: Recovery is suppressed by
NoRestartBackoffTimeStrategy
at
org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.handleFailure(ExecutionFailureHandler.java:138)
at
org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.getFailureHandlingResult(ExecutionFailureHandler.java:82)
at
org.apache.flink.runtime.scheduler.DefaultScheduler.handleTaskFailure(DefaultScheduler.java:252)
at
org.apache.flink.runtime.scheduler.DefaultScheduler.maybeHandleTaskFailure(DefaultScheduler.java:242)
at
org.apache.flink.runtime.scheduler.DefaultScheduler.updateTaskExecutionStateInternal(DefaultScheduler.java:233)
at
org.apache.flink.runtime.scheduler.SchedulerBase.updateTaskExecutionState(SchedulerBase.java:684)
at
org.apache.flink.runtime.scheduler.UpdateSchedulerNgOnInternalFailuresListener.notifyTaskFailure(UpdateSchedulerNgOnInternalFailuresListener.java:51)
at
org.apache.flink.runtime.executiongraph.DefaultExecutionGraph.notifySchedulerNgAboutInternalTaskFailure(DefaultExecutionGraph.java:1473)
at
org.apache.flink.runtime.executiongraph.Execution.processFail(Execution.java:1133)
at
org.apache.flink.runtime.executiongraph.Execution.processFail(Execution.java:1073)
at
org.apache.flink.runtime.executiongraph.Execution.fail(Execution.java:776)
at
org.apache.flink.runtime.jobmaster.slotpool.SingleLogicalSlot.signalPayloadRelease(SingleLogicalSlot.java:195)
at
org.apache.flink.runtime.jobmaster.slotpool.SingleLogicalSlot.release(SingleLogicalSlot.java:182)
at
org.apache.flink.runtime.scheduler.SharedSlot.lambda$release$4(SharedSlot.java:271)
at
java.util.concurrent.CompletableFuture.uniAccept(CompletableFuture.java:670)
at
java.util.concurrent.CompletableFuture.uniAcceptStage(CompletableFuture.java:683)
at
java.util.concurrent.CompletableFuture.thenAccept(CompletableFuture.java:2010)
at
org.apache.flink.runtime.scheduler.SharedSlot.release(SharedSlot.java:271)
at
org.apache.flink.runtime.jobmaster.slotpool.AllocatedSlot.releasePayload(AllocatedSlot.java:152)
at
org.apache.flink.runtime.jobmaster.slotpool.DefaultDeclarativeSlotPool.releasePayload(DefaultDeclarativeSlotPool.java:419)
at
org.apache.flink.runtime.jobmaster.slotpool.DefaultDeclarativeSlotPool.freeAndReleaseSlots(DefaultDeclarativeSlotPool.java:411)
at
org.apache.flink.runtime.jobmaster.slotpool.DefaultDeclarativeSlotPool.releaseSlots(DefaultDeclarativeSlotPool.java:382)
at
org.apache.flink.runtime.jobmaster.slotpool.DeclarativeSlotPoolService.internalReleaseTaskManager(DeclarativeSlotPoolService.java:249)
at
org.apache.flink.runtime.jobmaster.slotpool.DeclarativeSlotPoolService.releaseTaskManager(DeclarativeSlotPoolService.java:230)
at
org.apache.flink.runtime.jobmaster.JobMaster.disconnectTaskManager(JobMaster.java:506)
at
org.apache.flink.runtime.jobmaster.JobMaster$TaskManagerHeartbeatListener.handleTaskManagerConnectionLoss(JobMaster.java:1348)
at
org.apache.flink.runtime.jobmaster.JobMaster$TaskManagerHeartbeatListener.notifyTargetUnreachable(JobMaster.java:1359)
at
org.apache.flink.runtime.heartbeat.HeartbeatMonitorImpl.reportHeartbeatRpcFailure(HeartbeatMonitorImpl.java:123)
at
org.apache.flink.runtime.heartbeat.HeartbeatManagerImpl.runIfHeartbeatMonitorExists(HeartbeatManagerImpl.java:275)
at
org.apache.flink.runtime.heartbeat.HeartbeatManagerImpl.reportHeartbeatTargetUnreachable(HeartbeatManagerImpl.java:267)
at
org.apache.flink.runtime.heartbeat.HeartbeatManagerImpl.handleHeartbeatRpcFailure(HeartbeatManagerImpl.java:262)
at
org.apache.flink.runtime.heartbeat.HeartbeatManagerImpl.lambda$handleHeartbeatRpc$0(HeartbeatManagerImpl.java:248)
at
java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:774)
at
java.util.concurrent.CompletableFuture$UniWhenComplete.tryFire(CompletableFuture.java:750)
at
java.util.concurrent.CompletableFuture$Completion.run(CompletableFuture.java:456)
at
org.apache.flink.runtime.rpc.akka.AkkaRpcActor.lambda$handleRunAsync$4(AkkaRpcActor.java:455)
at
org.apache.flink.runtime.concurrent.akka.ClassLoadingUtils.runWithContextClassLoader(ClassLoadingUtils.java:68)
at
org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRunAsync(AkkaRpcActor.java:455)
at
org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:213)
at
org.apache.flink.runtime.rpc.akka.FencedAkkaRpcActor.handleRpcMessage(FencedAkkaRpcActor.java:78)
at
org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleMessage(AkkaRpcActor.java:163)
at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:24)
at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:20)
at scala.PartialFunction.applyOrElse(PartialFunction.scala:123)
at scala.PartialFunction.applyOrElse$(PartialFunction.scala:122)
at akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:20)
at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171)
at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:172)
at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:172)
at akka.actor.Actor.aroundReceive(Actor.scala:537)
at akka.actor.Actor.aroundReceive$(Actor.scala:535)
at akka.actor.AbstractActor.aroundReceive(AbstractActor.scala:220)
at akka.actor.ActorCell.receiveMessage(ActorCell.scala:580)
at akka.actor.ActorCell.invoke(ActorCell.scala:548)
at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:270)
at akka.dispatch.Mailbox.run(Mailbox.scala:231)
at akka.dispatch.Mailbox.exec(Mailbox.scala:243)
at java.util.concurrent.ForkJoinTask.doExec(ForkJoinTask.java:289)
at
java.util.concurrent.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1056)
at java.util.concurrent.ForkJoinPool.runWorker(ForkJoinPool.java:1692)
at
java.util.concurrent.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:175)
Caused by: org.apache.flink.runtime.jobmaster.JobMasterException:
TaskManager with id 172.17.0.2:6122-ea8b37 is no longer reachable.
... 35 more
Any help?
Re: Task Manger is getting failed
Posted by weijie guo <gu...@gmail.com>.
Hi,
Maybe you should add the jvm.overhead memory. And you can do heap-dump to
find which object has occupied a large number of memory.
Best regards,
Weijie
P Singh <bi...@gmail.com> 于2023年2月6日周一 11:24写道：
> Hi weijie,
>
> I have 8gb memory still TM going oom though I have assigned all. Moreover
> I am just print 15 word in beam pipeline program. Any idea why taking too
> much memory?
>
> Get Outlook for iOS <https://aka.ms/o0ukef>
> ------------------------------
> *From:* weijie guo <gu...@gmail.com>
> *Sent:* Monday, February 6, 2023 8:37:58 AM
> *To:* P Singh <bi...@gmail.com>
> *Cc:* User <us...@flink.apache.org>
> *Subject:* Re: Task Manger is getting failed
>
> Hi,
>
> It seems that TM is unexpected un-reachable. You can confirm whether TM is
> OutOfMemory.
>
> Best regards,
>
> Weijie
>
>
> P Singh <bi...@gmail.com> 于2023年2月5日周日 15:06写道：
>
> Hi Team,
>
> I am submitting a beam python job to flink clusters on a local machine by
> minikube. when i submit the job it appears on the flink UI and getting
> failed after some time with below traceback. I have defined memory in
> flink-configuration-configmap.yaml
>
> jobmanager.rpc.address: flink-jobmanager
> taskmanager.numberOfTaskSlots: 2
> blob.server.port: 6124
> jobmanager.rpc.port: 6123
> taskmanager.rpc.port: 6122
> queryable-state.proxy.ports: 6125
> jobmanager.memory.process.size: 2000m
> taskmanager.memory.process.size: 2096m
> parallelism.default: 2
>
> org.apache.flink.runtime.JobException: Recovery is suppressed by
> NoRestartBackoffTimeStrategy
> at
> org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.handleFailure(ExecutionFailureHandler.java:138)
> at
> org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.getFailureHandlingResult(ExecutionFailureHandler.java:82)
> at
> org.apache.flink.runtime.scheduler.DefaultScheduler.handleTaskFailure(DefaultScheduler.java:252)
> at
> org.apache.flink.runtime.scheduler.DefaultScheduler.maybeHandleTaskFailure(DefaultScheduler.java:242)
> at
> org.apache.flink.runtime.scheduler.DefaultScheduler.updateTaskExecutionStateInternal(DefaultScheduler.java:233)
> at
> org.apache.flink.runtime.scheduler.SchedulerBase.updateTaskExecutionState(SchedulerBase.java:684)
> at
> org.apache.flink.runtime.scheduler.UpdateSchedulerNgOnInternalFailuresListener.notifyTaskFailure(UpdateSchedulerNgOnInternalFailuresListener.java:51)
> at
> org.apache.flink.runtime.executiongraph.DefaultExecutionGraph.notifySchedulerNgAboutInternalTaskFailure(DefaultExecutionGraph.java:1473)
> at
> org.apache.flink.runtime.executiongraph.Execution.processFail(Execution.java:1133)
> at
> org.apache.flink.runtime.executiongraph.Execution.processFail(Execution.java:1073)
> at
> org.apache.flink.runtime.executiongraph.Execution.fail(Execution.java:776)
> at
> org.apache.flink.runtime.jobmaster.slotpool.SingleLogicalSlot.signalPayloadRelease(SingleLogicalSlot.java:195)
> at
> org.apache.flink.runtime.jobmaster.slotpool.SingleLogicalSlot.release(SingleLogicalSlot.java:182)
> at
> org.apache.flink.runtime.scheduler.SharedSlot.lambda$release$4(SharedSlot.java:271)
> at
> java.util.concurrent.CompletableFuture.uniAccept(CompletableFuture.java:670)
> at
> java.util.concurrent.CompletableFuture.uniAcceptStage(CompletableFuture.java:683)
> at
> java.util.concurrent.CompletableFuture.thenAccept(CompletableFuture.java:2010)
> at
> org.apache.flink.runtime.scheduler.SharedSlot.release(SharedSlot.java:271)
> at
> org.apache.flink.runtime.jobmaster.slotpool.AllocatedSlot.releasePayload(AllocatedSlot.java:152)
> at
> org.apache.flink.runtime.jobmaster.slotpool.DefaultDeclarativeSlotPool.releasePayload(DefaultDeclarativeSlotPool.java:419)
> at
> org.apache.flink.runtime.jobmaster.slotpool.DefaultDeclarativeSlotPool.freeAndReleaseSlots(DefaultDeclarativeSlotPool.java:411)
> at
> org.apache.flink.runtime.jobmaster.slotpool.DefaultDeclarativeSlotPool.releaseSlots(DefaultDeclarativeSlotPool.java:382)
> at
> org.apache.flink.runtime.jobmaster.slotpool.DeclarativeSlotPoolService.internalReleaseTaskManager(DeclarativeSlotPoolService.java:249)
> at
> org.apache.flink.runtime.jobmaster.slotpool.DeclarativeSlotPoolService.releaseTaskManager(DeclarativeSlotPoolService.java:230)
> at
> org.apache.flink.runtime.jobmaster.JobMaster.disconnectTaskManager(JobMaster.java:506)
> at
> org.apache.flink.runtime.jobmaster.JobMaster$TaskManagerHeartbeatListener.handleTaskManagerConnectionLoss(JobMaster.java:1348)
> at
> org.apache.flink.runtime.jobmaster.JobMaster$TaskManagerHeartbeatListener.notifyTargetUnreachable(JobMaster.java:1359)
> at
> org.apache.flink.runtime.heartbeat.HeartbeatMonitorImpl.reportHeartbeatRpcFailure(HeartbeatMonitorImpl.java:123)
> at
> org.apache.flink.runtime.heartbeat.HeartbeatManagerImpl.runIfHeartbeatMonitorExists(HeartbeatManagerImpl.java:275)
> at
> org.apache.flink.runtime.heartbeat.HeartbeatManagerImpl.reportHeartbeatTargetUnreachable(HeartbeatManagerImpl.java:267)
> at
> org.apache.flink.runtime.heartbeat.HeartbeatManagerImpl.handleHeartbeatRpcFailure(HeartbeatManagerImpl.java:262)
> at
> org.apache.flink.runtime.heartbeat.HeartbeatManagerImpl.lambda$handleHeartbeatRpc$0(HeartbeatManagerImpl.java:248)
> at
> java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:774)
> at
> java.util.concurrent.CompletableFuture$UniWhenComplete.tryFire(CompletableFuture.java:750)
> at
> java.util.concurrent.CompletableFuture$Completion.run(CompletableFuture.java:456)
> at
> org.apache.flink.runtime.rpc.akka.AkkaRpcActor.lambda$handleRunAsync$4(AkkaRpcActor.java:455)
> at
> org.apache.flink.runtime.concurrent.akka.ClassLoadingUtils.runWithContextClassLoader(ClassLoadingUtils.java:68)
> at
> org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRunAsync(AkkaRpcActor.java:455)
> at
> org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:213)
> at
> org.apache.flink.runtime.rpc.akka.FencedAkkaRpcActor.handleRpcMessage(FencedAkkaRpcActor.java:78)
> at
> org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleMessage(AkkaRpcActor.java:163)
> at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:24)
> at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:20)
> at scala.PartialFunction.applyOrElse(PartialFunction.scala:123)
> at scala.PartialFunction.applyOrElse$(PartialFunction.scala:122)
> at akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:20)
> at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171)
> at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:172)
> at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:172)
> at akka.actor.Actor.aroundReceive(Actor.scala:537)
> at akka.actor.Actor.aroundReceive$(Actor.scala:535)
> at akka.actor.AbstractActor.aroundReceive(AbstractActor.scala:220)
> at akka.actor.ActorCell.receiveMessage(ActorCell.scala:580)
> at akka.actor.ActorCell.invoke(ActorCell.scala:548)
> at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:270)
> at akka.dispatch.Mailbox.run(Mailbox.scala:231)
> at akka.dispatch.Mailbox.exec(Mailbox.scala:243)
> at java.util.concurrent.ForkJoinTask.doExec(ForkJoinTask.java:289)
> at
> java.util.concurrent.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1056)
> at java.util.concurrent.ForkJoinPool.runWorker(ForkJoinPool.java:1692)
> at
> java.util.concurrent.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:175)
> Caused by: org.apache.flink.runtime.jobmaster.JobMasterException:
> TaskManager with id 172.17.0.2:6122-ea8b37 is no longer reachable.
> ... 35 more
>
>
> Any help?
>
>
>
Re: Task Manger is getting failed
Posted by P Singh <bi...@gmail.com>.
Hi weijie,
I have 8gb memory still TM going oom though I have assigned all. Moreover I am just print 15 word in beam pipeline program. Any idea why taking too much memory?
Get Outlook for iOS<https://aka.ms/o0ukef>
________________________________
From: weijie guo <gu...@gmail.com>
Sent: Monday, February 6, 2023 8:37:58 AM
To: P Singh <bi...@gmail.com>
Cc: User <us...@flink.apache.org>
Subject: Re: Task Manger is getting failed
Hi,
It seems that TM is unexpected un-reachable. You can confirm whether TM is OutOfMemory.
Best regards,
Weijie
P Singh <bi...@gmail.com>> 于2023年2月5日周日 15:06写道：
Hi Team,
I am submitting a beam python job to flink clusters on a local machine by minikube. when i submit the job it appears on the flink UI and getting failed after some time with below traceback. I have defined memory in flink-configuration-configmap.yaml
jobmanager.rpc.address: flink-jobmanager
taskmanager.numberOfTaskSlots: 2
blob.server.port: 6124
jobmanager.rpc.port: 6123
taskmanager.rpc.port: 6122
queryable-state.proxy.ports: 6125
jobmanager.memory.process.size: 2000m
taskmanager.memory.process.size: 2096m
parallelism.default: 2
org.apache.flink.runtime.JobException: Recovery is suppressed by NoRestartBackoffTimeStrategy
at org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.handleFailure(ExecutionFailureHandler.java:138)
at org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.getFailureHandlingResult(ExecutionFailureHandler.java:82)
at org.apache.flink.runtime.scheduler.DefaultScheduler.handleTaskFailure(DefaultScheduler.java:252)
at org.apache.flink.runtime.scheduler.DefaultScheduler.maybeHandleTaskFailure(DefaultScheduler.java:242)
at org.apache.flink.runtime.scheduler.DefaultScheduler.updateTaskExecutionStateInternal(DefaultScheduler.java:233)
at org.apache.flink.runtime.scheduler.SchedulerBase.updateTaskExecutionState(SchedulerBase.java:684)
at org.apache.flink.runtime.scheduler.UpdateSchedulerNgOnInternalFailuresListener.notifyTaskFailure(UpdateSchedulerNgOnInternalFailuresListener.java:51)
at org.apache.flink.runtime.executiongraph.DefaultExecutionGraph.notifySchedulerNgAboutInternalTaskFailure(DefaultExecutionGraph.java:1473)
at org.apache.flink.runtime.executiongraph.Execution.processFail(Execution.java:1133)
at org.apache.flink.runtime.executiongraph.Execution.processFail(Execution.java:1073)
at org.apache.flink.runtime.executiongraph.Execution.fail(Execution.java:776)
at org.apache.flink.runtime.jobmaster.slotpool.SingleLogicalSlot.signalPayloadRelease(SingleLogicalSlot.java:195)
at org.apache.flink.runtime.jobmaster.slotpool.SingleLogicalSlot.release(SingleLogicalSlot.java:182)
at org.apache.flink.runtime.scheduler.SharedSlot.lambda$release$4(SharedSlot.java:271)
at java.util.concurrent.CompletableFuture.uniAccept(CompletableFuture.java:670)
at java.util.concurrent.CompletableFuture.uniAcceptStage(CompletableFuture.java:683)
at java.util.concurrent.CompletableFuture.thenAccept(CompletableFuture.java:2010)
at org.apache.flink.runtime.scheduler.SharedSlot.release(SharedSlot.java:271)
at org.apache.flink.runtime.jobmaster.slotpool.AllocatedSlot.releasePayload(AllocatedSlot.java:152)
at org.apache.flink.runtime.jobmaster.slotpool.DefaultDeclarativeSlotPool.releasePayload(DefaultDeclarativeSlotPool.java:419)
at org.apache.flink.runtime.jobmaster.slotpool.DefaultDeclarativeSlotPool.freeAndReleaseSlots(DefaultDeclarativeSlotPool.java:411)
at org.apache.flink.runtime.jobmaster.slotpool.DefaultDeclarativeSlotPool.releaseSlots(DefaultDeclarativeSlotPool.java:382)
at org.apache.flink.runtime.jobmaster.slotpool.DeclarativeSlotPoolService.internalReleaseTaskManager(DeclarativeSlotPoolService.java:249)
at org.apache.flink.runtime.jobmaster.slotpool.DeclarativeSlotPoolService.releaseTaskManager(DeclarativeSlotPoolService.java:230)
at org.apache.flink.runtime.jobmaster.JobMaster.disconnectTaskManager(JobMaster.java:506)
at org.apache.flink.runtime.jobmaster.JobMaster$TaskManagerHeartbeatListener.handleTaskManagerConnectionLoss(JobMaster.java:1348)
at org.apache.flink.runtime.jobmaster.JobMaster$TaskManagerHeartbeatListener.notifyTargetUnreachable(JobMaster.java:1359)
at org.apache.flink.runtime.heartbeat.HeartbeatMonitorImpl.reportHeartbeatRpcFailure(HeartbeatMonitorImpl.java:123)
at org.apache.flink.runtime.heartbeat.HeartbeatManagerImpl.runIfHeartbeatMonitorExists(HeartbeatManagerImpl.java:275)
at org.apache.flink.runtime.heartbeat.HeartbeatManagerImpl.reportHeartbeatTargetUnreachable(HeartbeatManagerImpl.java:267)
at org.apache.flink.runtime.heartbeat.HeartbeatManagerImpl.handleHeartbeatRpcFailure(HeartbeatManagerImpl.java:262)
at org.apache.flink.runtime.heartbeat.HeartbeatManagerImpl.lambda$handleHeartbeatRpc$0(HeartbeatManagerImpl.java:248)
at java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:774)
at java.util.concurrent.CompletableFuture$UniWhenComplete.tryFire(CompletableFuture.java:750)
at java.util.concurrent.CompletableFuture$Completion.run(CompletableFuture.java:456)
at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.lambda$handleRunAsync$4(AkkaRpcActor.java:455)
at org.apache.flink.runtime.concurrent.akka.ClassLoadingUtils.runWithContextClassLoader(ClassLoadingUtils.java:68)
at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRunAsync(AkkaRpcActor.java:455)
at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:213)
at org.apache.flink.runtime.rpc.akka.FencedAkkaRpcActor.handleRpcMessage(FencedAkkaRpcActor.java:78)
at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleMessage(AkkaRpcActor.java:163)
at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:24)
at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:20)
at scala.PartialFunction.applyOrElse(PartialFunction.scala:123)
at scala.PartialFunction.applyOrElse$(PartialFunction.scala:122)
at akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:20)
at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171)
at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:172)
at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:172)
at akka.actor.Actor.aroundReceive(Actor.scala:537)
at akka.actor.Actor.aroundReceive$(Actor.scala:535)
at akka.actor.AbstractActor.aroundReceive(AbstractActor.scala:220)
at akka.actor.ActorCell.receiveMessage(ActorCell.scala:580)
at akka.actor.ActorCell.invoke(ActorCell.scala:548)
at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:270)
at akka.dispatch.Mailbox.run(Mailbox.scala:231)
at akka.dispatch.Mailbox.exec(Mailbox.scala:243)
at java.util.concurrent.ForkJoinTask.doExec(ForkJoinTask.java:289)
at java.util.concurrent.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1056)
at java.util.concurrent.ForkJoinPool.runWorker(ForkJoinPool.java:1692)
at java.util.concurrent.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:175)
Caused by: org.apache.flink.runtime.jobmaster.JobMasterException: TaskManager with id 172.17.0.2:6122-ea8b37 is no longer reachable.
... 35 more
Any help?
Re: Task Manger is getting failed
Posted by weijie guo <gu...@gmail.com>.
Hi,
It seems that TM is unexpected un-reachable. You can confirm whether TM is
OutOfMemory.
Best regards,
Weijie
P Singh <bi...@gmail.com> 于2023年2月5日周日 15:06写道：
> Hi Team,
>
> I am submitting a beam python job to flink clusters on a local machine by
> minikube. when i submit the job it appears on the flink UI and getting
> failed after some time with below traceback. I have defined memory in
> flink-configuration-configmap.yaml
>
> jobmanager.rpc.address: flink-jobmanager
> taskmanager.numberOfTaskSlots: 2
> blob.server.port: 6124
> jobmanager.rpc.port: 6123
> taskmanager.rpc.port: 6122
> queryable-state.proxy.ports: 6125
> jobmanager.memory.process.size: 2000m
> taskmanager.memory.process.size: 2096m
> parallelism.default: 2
>
> org.apache.flink.runtime.JobException: Recovery is suppressed by
> NoRestartBackoffTimeStrategy
> at
> org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.handleFailure(ExecutionFailureHandler.java:138)
> at
> org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.getFailureHandlingResult(ExecutionFailureHandler.java:82)
> at
> org.apache.flink.runtime.scheduler.DefaultScheduler.handleTaskFailure(DefaultScheduler.java:252)
> at
> org.apache.flink.runtime.scheduler.DefaultScheduler.maybeHandleTaskFailure(DefaultScheduler.java:242)
> at
> org.apache.flink.runtime.scheduler.DefaultScheduler.updateTaskExecutionStateInternal(DefaultScheduler.java:233)
> at
> org.apache.flink.runtime.scheduler.SchedulerBase.updateTaskExecutionState(SchedulerBase.java:684)
> at
> org.apache.flink.runtime.scheduler.UpdateSchedulerNgOnInternalFailuresListener.notifyTaskFailure(UpdateSchedulerNgOnInternalFailuresListener.java:51)
> at
> org.apache.flink.runtime.executiongraph.DefaultExecutionGraph.notifySchedulerNgAboutInternalTaskFailure(DefaultExecutionGraph.java:1473)
> at
> org.apache.flink.runtime.executiongraph.Execution.processFail(Execution.java:1133)
> at
> org.apache.flink.runtime.executiongraph.Execution.processFail(Execution.java:1073)
> at
> org.apache.flink.runtime.executiongraph.Execution.fail(Execution.java:776)
> at
> org.apache.flink.runtime.jobmaster.slotpool.SingleLogicalSlot.signalPayloadRelease(SingleLogicalSlot.java:195)
> at
> org.apache.flink.runtime.jobmaster.slotpool.SingleLogicalSlot.release(SingleLogicalSlot.java:182)
> at
> org.apache.flink.runtime.scheduler.SharedSlot.lambda$release$4(SharedSlot.java:271)
> at
> java.util.concurrent.CompletableFuture.uniAccept(CompletableFuture.java:670)
> at
> java.util.concurrent.CompletableFuture.uniAcceptStage(CompletableFuture.java:683)
> at
> java.util.concurrent.CompletableFuture.thenAccept(CompletableFuture.java:2010)
> at
> org.apache.flink.runtime.scheduler.SharedSlot.release(SharedSlot.java:271)
> at
> org.apache.flink.runtime.jobmaster.slotpool.AllocatedSlot.releasePayload(AllocatedSlot.java:152)
> at
> org.apache.flink.runtime.jobmaster.slotpool.DefaultDeclarativeSlotPool.releasePayload(DefaultDeclarativeSlotPool.java:419)
> at
> org.apache.flink.runtime.jobmaster.slotpool.DefaultDeclarativeSlotPool.freeAndReleaseSlots(DefaultDeclarativeSlotPool.java:411)
> at
> org.apache.flink.runtime.jobmaster.slotpool.DefaultDeclarativeSlotPool.releaseSlots(DefaultDeclarativeSlotPool.java:382)
> at
> org.apache.flink.runtime.jobmaster.slotpool.DeclarativeSlotPoolService.internalReleaseTaskManager(DeclarativeSlotPoolService.java:249)
> at
> org.apache.flink.runtime.jobmaster.slotpool.DeclarativeSlotPoolService.releaseTaskManager(DeclarativeSlotPoolService.java:230)
> at
> org.apache.flink.runtime.jobmaster.JobMaster.disconnectTaskManager(JobMaster.java:506)
> at
> org.apache.flink.runtime.jobmaster.JobMaster$TaskManagerHeartbeatListener.handleTaskManagerConnectionLoss(JobMaster.java:1348)
> at
> org.apache.flink.runtime.jobmaster.JobMaster$TaskManagerHeartbeatListener.notifyTargetUnreachable(JobMaster.java:1359)
> at
> org.apache.flink.runtime.heartbeat.HeartbeatMonitorImpl.reportHeartbeatRpcFailure(HeartbeatMonitorImpl.java:123)
> at
> org.apache.flink.runtime.heartbeat.HeartbeatManagerImpl.runIfHeartbeatMonitorExists(HeartbeatManagerImpl.java:275)
> at
> org.apache.flink.runtime.heartbeat.HeartbeatManagerImpl.reportHeartbeatTargetUnreachable(HeartbeatManagerImpl.java:267)
> at
> org.apache.flink.runtime.heartbeat.HeartbeatManagerImpl.handleHeartbeatRpcFailure(HeartbeatManagerImpl.java:262)
> at
> org.apache.flink.runtime.heartbeat.HeartbeatManagerImpl.lambda$handleHeartbeatRpc$0(HeartbeatManagerImpl.java:248)
> at
> java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:774)
> at
> java.util.concurrent.CompletableFuture$UniWhenComplete.tryFire(CompletableFuture.java:750)
> at
> java.util.concurrent.CompletableFuture$Completion.run(CompletableFuture.java:456)
> at
> org.apache.flink.runtime.rpc.akka.AkkaRpcActor.lambda$handleRunAsync$4(AkkaRpcActor.java:455)
> at
> org.apache.flink.runtime.concurrent.akka.ClassLoadingUtils.runWithContextClassLoader(ClassLoadingUtils.java:68)
> at
> org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRunAsync(AkkaRpcActor.java:455)
> at
> org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:213)
> at
> org.apache.flink.runtime.rpc.akka.FencedAkkaRpcActor.handleRpcMessage(FencedAkkaRpcActor.java:78)
> at
> org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleMessage(AkkaRpcActor.java:163)
> at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:24)
> at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:20)
> at scala.PartialFunction.applyOrElse(PartialFunction.scala:123)
> at scala.PartialFunction.applyOrElse$(PartialFunction.scala:122)
> at akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:20)
> at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171)
> at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:172)
> at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:172)
> at akka.actor.Actor.aroundReceive(Actor.scala:537)
> at akka.actor.Actor.aroundReceive$(Actor.scala:535)
> at akka.actor.AbstractActor.aroundReceive(AbstractActor.scala:220)
> at akka.actor.ActorCell.receiveMessage(ActorCell.scala:580)
> at akka.actor.ActorCell.invoke(ActorCell.scala:548)
> at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:270)
> at akka.dispatch.Mailbox.run(Mailbox.scala:231)
> at akka.dispatch.Mailbox.exec(Mailbox.scala:243)
> at java.util.concurrent.ForkJoinTask.doExec(ForkJoinTask.java:289)
> at
> java.util.concurrent.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1056)
> at java.util.concurrent.ForkJoinPool.runWorker(ForkJoinPool.java:1692)
> at
> java.util.concurrent.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:175)
> Caused by: org.apache.flink.runtime.jobmaster.JobMasterException:
> TaskManager with id 172.17.0.2:6122-ea8b37 is no longer reachable.
> ... 35 more
>
>
> Any help?
>
>
>