Matthias Pohl created FLINK-36301:
-------------------------------------
Summary: TPC-H end-to-end test fails due to TimeoutException
Key: FLINK-36301
URL: https://issues.apache.org/jira/browse/FLINK-36301
Project: Flink
Issue Type: Bug
Components: Runtime / Coordination, Tests
Affects Versions: 2.0-preview
Reporter: Matthias Pohl
https://dev.azure.com/apache-flink/apache-flink/_build/results?buildId=62146&view=logs&j=fb37c667-81b7-5c22-dd91-846535e99a97&t=011e961e-597c-5c96-04fe-7941c8b83f23&l=8589
The JobManager logs reveal a TimeoutException:
{code}
2024-09-15 01:37:53,628 INFO
org.apache.flink.runtime.executiongraph.ExecutionGraph [] - Job
insert-into_default_catalog.default_database.q5
(f40185b602e2336cba7299165d7078fa) switched from state RUNNING to FAILING.
org.apache.flink.runtime.JobException: Recovery is suppressed by
NoRestartBackoffTimeStrategy
at
org.apache.flink.runtime.executiongraph.failover.ExecutionFailureHandler.handleFailure(ExecutionFailureHandler.java:219)
~[flink-dist-2.0-SNAPSHOT.jar:2.0-SNAPSHOT]
at
org.apache.flink.runtime.executiongraph.failover.ExecutionFailureHandler.handleFailureAndReport(ExecutionFailureHandler.java:166)
~[flink-dist-2.0-SNAPSHOT.jar:2.0-SNAPSHOT]
at
org.apache.flink.runtime.executiongraph.failover.ExecutionFailureHandler.getFailureHandlingResult(ExecutionFailureHandler.java:121)
~[flink-dist-2.0-SNAPSHOT.jar:2.0-SNAPSHOT]
at
org.apache.flink.runtime.scheduler.DefaultScheduler.recordTaskFailure(DefaultScheduler.java:281)
~[flink-dist-2.0-SNAPSHOT.jar:2.0-SNAPSHOT]
at
org.apache.flink.runtime.scheduler.DefaultScheduler.handleTaskFailure(DefaultScheduler.java:272)
~[flink-dist-2.0-SNAPSHOT.jar:2.0-SNAPSHOT]
at
org.apache.flink.runtime.scheduler.adaptivebatch.AdaptiveBatchScheduler.handleTaskFailure(AdaptiveBatchScheduler.java:413)
~[flink-dist-2.0-SNAPSHOT.jar:2.0-SNAPSHOT]
at
org.apache.flink.runtime.scheduler.DefaultScheduler.onTaskFailed(DefaultScheduler.java:265)
~[flink-dist-2.0-SNAPSHOT.jar:2.0-SNAPSHOT]
at
org.apache.flink.runtime.scheduler.adaptivebatch.AdaptiveBatchScheduler.onTaskFailed(AdaptiveBatchScheduler.java:405)
~[flink-dist-2.0-SNAPSHOT.jar:2.0-SNAPSHOT]
at
org.apache.flink.runtime.scheduler.SchedulerBase.onTaskExecutionStateUpdate(SchedulerBase.java:800)
~[flink-dist-2.0-SNAPSHOT.jar:2.0-SNAPSHOT]
at
org.apache.flink.runtime.scheduler.SchedulerBase.updateTaskExecutionState(SchedulerBase.java:777)
~[flink-dist-2.0-SNAPSHOT.jar:2.0-SNAPSHOT]
at
org.apache.flink.runtime.scheduler.UpdateSchedulerNgOnInternalFailuresListener.notifyTaskFailure(UpdateSchedulerNgOnInternalFailuresListener.java:51)
~[flink-dist-2.0-SNAPSHOT.jar:2.0-SNAPSHOT]
at
org.apache.flink.runtime.executiongraph.DefaultExecutionGraph.notifySchedulerNgAboutInternalTaskFailure(DefaultExecutionGraph.java:1675)
~[flink-dist-2.0-SNAPSHOT.jar:2.0-SNAPSHOT]
at
org.apache.flink.runtime.executiongraph.Execution.processFail(Execution.java:1190)
~[flink-dist-2.0-SNAPSHOT.jar:2.0-SNAPSHOT]
at
org.apache.flink.runtime.executiongraph.Execution.processFail(Execution.java:1130)
~[flink-dist-2.0-SNAPSHOT.jar:2.0-SNAPSHOT]
at
org.apache.flink.runtime.executiongraph.Execution.fail(Execution.java:831)
~[flink-dist-2.0-SNAPSHOT.jar:2.0-SNAPSHOT]
at
org.apache.flink.runtime.jobmaster.slotpool.SingleLogicalSlot.signalPayloadRelease(SingleLogicalSlot.java:195)
~[flink-dist-2.0-SNAPSHOT.jar:2.0-SNAPSHOT]
at
org.apache.flink.runtime.jobmaster.slotpool.SingleLogicalSlot.release(SingleLogicalSlot.java:182)
~[flink-dist-2.0-SNAPSHOT.jar:2.0-SNAPSHOT]
at
org.apache.flink.runtime.scheduler.SimpleExecutionSlotAllocator$LogicalSlotHolder.release(SimpleExecutionSlotAllocator.java:203)
~[flink-dist-2.0-SNAPSHOT.jar:2.0-SNAPSHOT]
at
org.apache.flink.runtime.jobmaster.slotpool.AllocatedSlot.releasePayload(AllocatedSlot.java:152)
~[flink-dist-2.0-SNAPSHOT.jar:2.0-SNAPSHOT]
at
org.apache.flink.runtime.jobmaster.slotpool.DefaultDeclarativeSlotPool.releasePayload(DefaultDeclarativeSlotPool.java:515)
~[flink-dist-2.0-SNAPSHOT.jar:2.0-SNAPSHOT]
at
org.apache.flink.runtime.jobmaster.slotpool.DefaultDeclarativeSlotPool.freeAndReleaseSlots(DefaultDeclarativeSlotPool.java:507)
~[flink-dist-2.0-SNAPSHOT.jar:2.0-SNAPSHOT]
at
org.apache.flink.runtime.jobmaster.slotpool.DefaultDeclarativeSlotPool.releaseSlots(DefaultDeclarativeSlotPool.java:478)
~[flink-dist-2.0-SNAPSHOT.jar:2.0-SNAPSHOT]
at
org.apache.flink.runtime.jobmaster.slotpool.DeclarativeSlotPoolService.internalReleaseTaskManager(DeclarativeSlotPoolService.java:281)
~[flink-dist-2.0-SNAPSHOT.jar:2.0-SNAPSHOT]
at
org.apache.flink.runtime.jobmaster.slotpool.DeclarativeSlotPoolService.releaseTaskManager(DeclarativeSlotPoolService.java:237)
~[flink-dist-2.0-SNAPSHOT.jar:2.0-SNAPSHOT]
at
org.apache.flink.runtime.jobmaster.JobMaster.disconnectTaskManager(JobMaster.java:571)
~[flink-dist-2.0-SNAPSHOT.jar:2.0-SNAPSHOT]
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
~[?:1.8.0_422]
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
~[?:1.8.0_422]
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
~[?:1.8.0_422]
at java.lang.reflect.Method.invoke(Method.java:498) ~[?:1.8.0_422]
at
org.apache.flink.runtime.rpc.pekko.PekkoRpcActor.lambda$handleRpcInvocation$1(PekkoRpcActor.java:318)
~[flink-rpc-akka4a43504d-2771-44fe-8a7a-467eaf4ecf4b.jar:2.0-SNAPSHOT]
at
org.apache.flink.runtime.concurrent.ClassLoadingUtils.runWithContextClassLoader(ClassLoadingUtils.java:83)
~[flink-dist-2.0-SNAPSHOT.jar:2.0-SNAPSHOT]
at
org.apache.flink.runtime.rpc.pekko.PekkoRpcActor.handleRpcInvocation(PekkoRpcActor.java:316)
~[flink-rpc-akka4a43504d-2771-44fe-8a7a-467eaf4ecf4b.jar:2.0-SNAPSHOT]
at
org.apache.flink.runtime.rpc.pekko.PekkoRpcActor.handleRpcMessage(PekkoRpcActor.java:229)
~[flink-rpc-akka4a43504d-2771-44fe-8a7a-467eaf4ecf4b.jar:2.0-SNAPSHOT]
at
org.apache.flink.runtime.rpc.pekko.FencedPekkoRpcActor.handleRpcMessage(FencedPekkoRpcActor.java:88)
~[flink-rpc-akka4a43504d-2771-44fe-8a7a-467eaf4ecf4b.jar:2.0-SNAPSHOT]
at
org.apache.flink.runtime.rpc.pekko.PekkoRpcActor.handleMessage(PekkoRpcActor.java:174)
~[flink-rpc-akka4a43504d-2771-44fe-8a7a-467eaf4ecf4b.jar:2.0-SNAPSHOT]
at
org.apache.pekko.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:33)
[flink-rpc-akka4a43504d-2771-44fe-8a7a-467eaf4ecf4b.jar:2.0-SNAPSHOT]
at
org.apache.pekko.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:29)
[flink-rpc-akka4a43504d-2771-44fe-8a7a-467eaf4ecf4b.jar:2.0-SNAPSHOT]
at scala.PartialFunction.applyOrElse(PartialFunction.scala:127)
[flink-rpc-akka4a43504d-2771-44fe-8a7a-467eaf4ecf4b.jar:2.0-SNAPSHOT]
at scala.PartialFunction.applyOrElse$(PartialFunction.scala:126)
[flink-rpc-akka4a43504d-2771-44fe-8a7a-467eaf4ecf4b.jar:2.0-SNAPSHOT]
at
org.apache.pekko.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:29)
[flink-rpc-akka4a43504d-2771-44fe-8a7a-467eaf4ecf4b.jar:2.0-SNAPSHOT]
at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:175)
[flink-rpc-akka4a43504d-2771-44fe-8a7a-467eaf4ecf4b.jar:2.0-SNAPSHOT]
at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:176)
[flink-rpc-akka4a43504d-2771-44fe-8a7a-467eaf4ecf4b.jar:2.0-SNAPSHOT]
at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:176)
[flink-rpc-akka4a43504d-2771-44fe-8a7a-467eaf4ecf4b.jar:2.0-SNAPSHOT]
at org.apache.pekko.actor.Actor.aroundReceive(Actor.scala:547)
[flink-rpc-akka4a43504d-2771-44fe-8a7a-467eaf4ecf4b.jar:2.0-SNAPSHOT]
at org.apache.pekko.actor.Actor.aroundReceive$(Actor.scala:545)
[flink-rpc-akka4a43504d-2771-44fe-8a7a-467eaf4ecf4b.jar:2.0-SNAPSHOT]
at
org.apache.pekko.actor.AbstractActor.aroundReceive(AbstractActor.scala:229)
[flink-rpc-akka4a43504d-2771-44fe-8a7a-467eaf4ecf4b.jar:2.0-SNAPSHOT]
at org.apache.pekko.actor.ActorCell.receiveMessage(ActorCell.scala:590)
[flink-rpc-akka4a43504d-2771-44fe-8a7a-467eaf4ecf4b.jar:2.0-SNAPSHOT]
at org.apache.pekko.actor.ActorCell.invoke(ActorCell.scala:557)
[flink-rpc-akka4a43504d-2771-44fe-8a7a-467eaf4ecf4b.jar:2.0-SNAPSHOT]
at org.apache.pekko.dispatch.Mailbox.processMailbox(Mailbox.scala:280)
[flink-rpc-akka4a43504d-2771-44fe-8a7a-467eaf4ecf4b.jar:2.0-SNAPSHOT]
at org.apache.pekko.dispatch.Mailbox.run(Mailbox.scala:241)
[flink-rpc-akka4a43504d-2771-44fe-8a7a-467eaf4ecf4b.jar:2.0-SNAPSHOT]
at org.apache.pekko.dispatch.Mailbox.exec(Mailbox.scala:253)
[flink-rpc-akka4a43504d-2771-44fe-8a7a-467eaf4ecf4b.jar:2.0-SNAPSHOT]
at java.util.concurrent.ForkJoinTask.doExec(ForkJoinTask.java:289)
[?:1.8.0_422]
at
java.util.concurrent.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1056)
[?:1.8.0_422]
at java.util.concurrent.ForkJoinPool.runWorker(ForkJoinPool.java:1692)
[?:1.8.0_422]
at
java.util.concurrent.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:175)
[?:1.8.0_422]
Caused by: java.util.concurrent.TimeoutException: The heartbeat of TaskManager
with id localhost:46079-46f19c timed out.
at
org.apache.flink.runtime.resourcemanager.ResourceManager$TaskManagerHeartbeatListener.notifyHeartbeatTimeout(ResourceManager.java:1466)
~[flink-dist-2.0-SNAPSHOT.jar:2.0-SNAPSHOT]
at
org.apache.flink.runtime.heartbeat.DefaultHeartbeatMonitor.run(DefaultHeartbeatMonitor.java:158)
~[flink-dist-2.0-SNAPSHOT.jar:2.0-SNAPSHOT]
at
java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:511)
~[?:1.8.0_422]
at java.util.concurrent.FutureTask.run(FutureTask.java:266)
~[?:1.8.0_422]
at
org.apache.flink.runtime.rpc.pekko.PekkoRpcActor.lambda$handleRunAsync$4(PekkoRpcActor.java:460)
~[flink-rpc-akka4a43504d-2771-44fe-8a7a-467eaf4ecf4b.jar:2.0-SNAPSHOT]
at
org.apache.flink.runtime.concurrent.ClassLoadingUtils.runWithContextClassLoader(ClassLoadingUtils.java:68)
~[flink-dist-2.0-SNAPSHOT.jar:2.0-SNAPSHOT]
at
org.apache.flink.runtime.rpc.pekko.PekkoRpcActor.handleRunAsync(PekkoRpcActor.java:460)
~[flink-rpc-akka4a43504d-2771-44fe-8a7a-467eaf4ecf4b.jar:2.0-SNAPSHOT]
at
org.apache.flink.runtime.rpc.pekko.PekkoRpcActor.handleRpcMessage(PekkoRpcActor.java:225)
~[flink-rpc-akka4a43504d-2771-44fe-8a7a-467eaf4ecf4b.jar:2.0-SNAPSHOT]
{code}
--
This message was sent by Atlassian Jira
(v8.20.10#820010)