Vishva Mahadevan
07/25/2024, 1:50 PM2024-07-25 19:12:05
org.apache.flink.runtime.JobException: Recovery is suppressed by NoRestartBackoffTimeStrategy
at org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.handleFailure(ExecutionFailureHandler.java:139)
at org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.getFailureHandlingResult(ExecutionFailureHandler.java:83)
at org.apache.flink.runtime.scheduler.DefaultScheduler.recordTaskFailure(DefaultScheduler.java:256)
at org.apache.flink.runtime.scheduler.DefaultScheduler.handleTaskFailure(DefaultScheduler.java:247)
at org.apache.flink.runtime.scheduler.DefaultScheduler.onTaskFailed(DefaultScheduler.java:240)
at org.apache.flink.runtime.scheduler.SchedulerBase.onTaskExecutionStateUpdate(SchedulerBase.java:738)
at org.apache.flink.runtime.scheduler.SchedulerBase.updateTaskExecutionState(SchedulerBase.java:715)
at org.apache.flink.runtime.scheduler.UpdateSchedulerNgOnInternalFailuresListener.notifyTaskFailure(UpdateSchedulerNgOnInternalFailuresListener.java:51)
at org.apache.flink.runtime.executiongraph.DefaultExecutionGraph.notifySchedulerNgAboutInternalTaskFailure(DefaultExecutionGraph.java:1622)
at org.apache.flink.runtime.executiongraph.Execution.processFail(Execution.java:1137)
at org.apache.flink.runtime.executiongraph.Execution.processFail(Execution.java:1077)
at org.apache.flink.runtime.executiongraph.Execution.fail(Execution.java:778)
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$4(SharedSlot.java:270)
at java.base/java.util.concurrent.CompletableFuture.uniAcceptNow(Unknown Source)
at java.base/java.util.concurrent.CompletableFuture.uniAcceptStage(Unknown Source)
at java.base/java.util.concurrent.CompletableFuture.thenAccept(Unknown Source)
at org.apache.flink.runtime.scheduler.SharedSlot.release(SharedSlot.java:270)
at org.apache.flink.runtime.jobmaster.slotpool.AllocatedSlot.releasePayload(AllocatedSlot.java:152)
at org.apache.flink.runtime.jobmaster.slotpool.DefaultDeclarativeSlotPool.releasePayload(DefaultDeclarativeSlotPool.java:483)
at org.apache.flink.runtime.jobmaster.slotpool.DefaultDeclarativeSlotPool.freeAndReleaseSlots(DefaultDeclarativeSlotPool.java:475)
at org.apache.flink.runtime.jobmaster.slotpool.DefaultDeclarativeSlotPool.releaseSlots(DefaultDeclarativeSlotPool.java:446)
at org.apache.flink.runtime.jobmaster.slotpool.DeclarativeSlotPoolService.internalReleaseTaskManager(DeclarativeSlotPoolService.java:275)
at org.apache.flink.runtime.jobmaster.slotpool.DeclarativeSlotPoolService.releaseTaskManager(DeclarativeSlotPoolService.java:231)
at org.apache.flink.runtime.jobmaster.JobMaster.disconnectTaskManager(JobMaster.java:533)
at org.apache.flink.runtime.jobmaster.JobMaster$TaskManagerHeartbeatListener.handleTaskManagerConnectionLoss(JobMaster.java:1440)
at org.apache.flink.runtime.jobmaster.JobMaster$TaskManagerHeartbeatListener.notifyHeartbeatTimeout(JobMaster.java:1435)
at org.apache.flink.runtime.heartbeat.HeartbeatMonitorImpl.run(HeartbeatMonitorImpl.java:155)
at java.base/java.util.concurrent.Executors$RunnableAdapter.call(Unknown Source)
at java.base/java.util.concurrent.FutureTask.run(Unknown Source)
at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.lambda$handleRunAsync$4(AkkaRpcActor.java:453)
at org.apache.flink.runtime.concurrent.akka.ClassLoadingUtils.runWithContextClassLoader(ClassLoadingUtils.java:68)
at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRunAsync(AkkaRpcActor.java:453)
at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:218)
at org.apache.flink.runtime.rpc.akka.FencedAkkaRpcActor.handleRpcMessage(FencedAkkaRpcActor.java:84)
at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleMessage(AkkaRpcActor.java:168)
at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:24)
at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:20)
at scala.PartialFunction.applyOrElse(PartialFunction.scala:123)
at scala.PartialFunction.applyOrElse$(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.base/java.util.concurrent.ForkJoinTask.doExec(Unknown Source)
at java.base/java.util.concurrent.ForkJoinPool$WorkQueue.topLevelExec(Unknown Source)
at java.base/java.util.concurrent.ForkJoinPool.scan(Unknown Source)
at java.base/java.util.concurrent.ForkJoinPool.runWorker(Unknown Source)
at java.base/java.util.concurrent.ForkJoinWorkerThread.run(Unknown Source)
Caused by: java.util.concurrent.TimeoutException: Heartbeat of TaskManager with id stream-join-batch-layer-taskmanager-1-21 timed out.
... 31 more