flink on yarn job 模式運行flink任務,運行一段時間后任務自動退出並拋出異常!


運行一段時間后任務自動退出並拋出異常。異常如下:

Job has been submitted with JobID 2fe14a4a5acb49d49e0ad5994726fd69

------------------------------------------------------------
 The program finished with the following exception:

org.apache.flink.client.program.ProgramInvocationException: The main method caused an error: org.apache.flink.client.program.ProgramInvocationException: Job failed (JobID: 2fe14a4a5acb49d49e0ad5994726fd69)
	at org.apache.flink.client.program.PackagedProgram.callMainMethod(PackagedProgram.java:335)
	at org.apache.flink.client.program.PackagedProgram.invokeInteractiveModeForExecution(PackagedProgram.java:205)
	at org.apache.flink.client.ClientUtils.executeProgram(ClientUtils.java:139)
	at org.apache.flink.client.cli.CliFrontend.executeProgram(CliFrontend.java:670)
	at org.apache.flink.client.cli.CliFrontend.run(CliFrontend.java:213)
	at org.apache.flink.client.cli.CliFrontend.parseParameters(CliFrontend.java:901)
	at org.apache.flink.client.cli.CliFrontend.lambda$main$10(CliFrontend.java:974)
	at java.security.AccessController.doPrivileged(Native Method)
	at javax.security.auth.Subject.doAs(Subject.java:422)
	at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1875)
	at org.apache.flink.runtime.security.HadoopSecurityContext.runSecured(HadoopSecurityContext.java:41)
	at org.apache.flink.client.cli.CliFrontend.main(CliFrontend.java:974)
Caused by: java.util.concurrent.ExecutionException: org.apache.flink.client.program.ProgramInvocationException: Job failed (JobID: 2fe14a4a5acb49d49e0ad5994726fd69)
	at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:357)
	at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:1895)
	at org.apache.flink.streaming.api.environment.StreamContextEnvironment.getJobExecutionResult(StreamContextEnvironment.java:104)
	at org.apache.flink.streaming.api.environment.StreamContextEnvironment.execute(StreamContextEnvironment.java:70)
	at org.apache.flink.streaming.api.environment.StreamExecutionEnvironment.execute(StreamExecutionEnvironment.java:1627)
	at com.atguigu.hotitems_analysis.HotItems.main(HotItems.java:89)
	at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
	at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
	at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
	at java.lang.reflect.Method.invoke(Method.java:498)
	at org.apache.flink.client.program.PackagedProgram.callMainMethod(PackagedProgram.java:321)
	... 11 more
Caused by: org.apache.flink.client.program.ProgramInvocationException: Job failed (JobID: 2fe14a4a5acb49d49e0ad5994726fd69)
	at org.apache.flink.client.deployment.ClusterClientJobClientAdapter.lambda$null$6(ClusterClientJobClientAdapter.java:112)
	at java.util.concurrent.CompletableFuture.uniApply(CompletableFuture.java:602)
	at java.util.concurrent.CompletableFuture$UniApply.tryFire(CompletableFuture.java:577)
	at java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:474)
	at java.util.concurrent.CompletableFuture.complete(CompletableFuture.java:1962)
	at org.apache.flink.client.program.rest.RestClusterClient.lambda$pollResourceAsync$21(RestClusterClient.java:565)
	at java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:760)
	at java.util.concurrent.CompletableFuture$UniWhenComplete.tryFire(CompletableFuture.java:736)
	at java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:474)
	at java.util.concurrent.CompletableFuture.complete(CompletableFuture.java:1962)
	at org.apache.flink.runtime.concurrent.FutureUtils.lambda$retryOperationWithDelay$8(FutureUtils.java:291)
	at java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:760)
	at java.util.concurrent.CompletableFuture$UniWhenComplete.tryFire(CompletableFuture.java:736)
	at java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:474)
	at java.util.concurrent.CompletableFuture.postFire(CompletableFuture.java:561)
	at java.util.concurrent.CompletableFuture$UniCompose.tryFire(CompletableFuture.java:929)
	at java.util.concurrent.CompletableFuture$Completion.run(CompletableFuture.java:442)
	at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
	at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
	at java.lang.Thread.run(Thread.java:745)
Caused by: org.apache.flink.runtime.client.JobExecutionException: Job execution failed.
	at org.apache.flink.runtime.jobmaster.JobResult.toJobExecutionResult(JobResult.java:147)
	at org.apache.flink.client.deployment.ClusterClientJobClientAdapter.lambda$null$6(ClusterClientJobClientAdapter.java:110)
	... 19 more
Caused by: org.apache.flink.runtime.JobException: Recovery is suppressed by NoRestartBackoffTimeStrategy
	at org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.handleFailure(ExecutionFailureHandler.java:110)
	at org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.getFailureHandlingResult(ExecutionFailureHandler.java:76)
	at org.apache.flink.runtime.scheduler.DefaultScheduler.handleTaskFailure(DefaultScheduler.java:192)
	at org.apache.flink.runtime.scheduler.DefaultScheduler.maybeHandleTaskFailure(DefaultScheduler.java:186)
	at org.apache.flink.runtime.scheduler.DefaultScheduler.updateTaskExecutionStateInternal(DefaultScheduler.java:180)
	at org.apache.flink.runtime.scheduler.SchedulerBase.updateTaskExecutionState(SchedulerBase.java:496)
	at org.apache.flink.runtime.scheduler.UpdateSchedulerNgOnInternalFailuresListener.notifyTaskFailure(UpdateSchedulerNgOnInternalFailuresListener.java:49)
	at org.apache.flink.runtime.executiongraph.ExecutionGraph.notifySchedulerNgAboutInternalTaskFailure(ExecutionGraph.java:1703)
	at org.apache.flink.runtime.executiongraph.Execution.processFail(Execution.java:1252)
	at org.apache.flink.runtime.executiongraph.Execution.processFail(Execution.java:1220)
	at org.apache.flink.runtime.executiongraph.Execution.fail(Execution.java:955)
	at org.apache.flink.runtime.jobmaster.slotpool.SingleLogicalSlot.signalPayloadRelease(SingleLogicalSlot.java:173)
	at org.apache.flink.runtime.jobmaster.slotpool.SingleLogicalSlot.release(SingleLogicalSlot.java:165)
	at org.apache.flink.runtime.jobmaster.slotpool.SlotSharingManager$SingleTaskSlot.release(SlotSharingManager.java:732)
	at org.apache.flink.runtime.jobmaster.slotpool.SlotSharingManager$MultiTaskSlot.release(SlotSharingManager.java:537)
	at org.apache.flink.runtime.jobmaster.slotpool.AllocatedSlot.releasePayload(AllocatedSlot.java:149)
	at org.apache.flink.runtime.jobmaster.slotpool.SlotPoolImpl.tryFailingAllocatedSlot(SlotPoolImpl.java:733)
	at org.apache.flink.runtime.jobmaster.slotpool.SlotPoolImpl.failAllocation(SlotPoolImpl.java:713)
	at org.apache.flink.runtime.jobmaster.JobMaster.internalFailAllocation(JobMaster.java:541)
	at org.apache.flink.runtime.jobmaster.JobMaster.notifyAllocationFailure(JobMaster.java:667)
	at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
	at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
	at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
	at java.lang.reflect.Method.invoke(Method.java:498)
	at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcInvocation(AkkaRpcActor.java:279)
	at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:199)
	at org.apache.flink.runtime.rpc.akka.FencedAkkaRpcActor.handleRpcMessage(FencedAkkaRpcActor.java:74)
	at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleMessage(AkkaRpcActor.java:152)
	at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:26)
	at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:21)
	at scala.PartialFunction.applyOrElse(PartialFunction.scala:127)
	at scala.PartialFunction.applyOrElse$(PartialFunction.scala:126)
	at akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:21)
	at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:175)
	at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:176)
	at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:176)
	at akka.actor.Actor.aroundReceive(Actor.scala:517)
	at akka.actor.Actor.aroundReceive$(Actor.scala:515)
	at akka.actor.AbstractActor.aroundReceive(AbstractActor.scala:225)
	at akka.actor.ActorCell.receiveMessage(ActorCell.scala:592)
	at akka.actor.ActorCell.invoke(ActorCell.scala:561)
	at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:258)
	at akka.dispatch.Mailbox.run(Mailbox.scala:225)
	at akka.dispatch.Mailbox.exec(Mailbox.scala:235)
	at akka.dispatch.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)
	at akka.dispatch.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
	at akka.dispatch.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979)
	at akka.dispatch.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107)
Caused by: java.lang.Exception: [2021-05-06 14:14:27.818]Exception from container-launch.
Container id: container_1619436641297_0003_01_000002
Exit code: 239

[2021-05-06 14:14:27.821]Container exited with a non-zero exit code 239. Error file: prelaunch.err.
Last 4096 bytes of prelaunch.err :

[2021-05-06 14:14:27.822]Container exited with a non-zero exit code 239. Error file: prelaunch.err.
Last 4096 bytes of prelaunch.err :


	at org.apache.flink.yarn.YarnResourceManager.lambda$onContainersCompleted$0(YarnResourceManager.java:343)
	at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRunAsync(AkkaRpcActor.java:402)
	at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:195)
	... 22 more

解決辦法


免責聲明!

本站轉載的文章為個人學習借鑒使用,本站對版權不負任何法律責任。如果侵犯了您的隱私權益,請聯系本站郵箱yoyou2525@163.com刪除。



 
粵ICP備18138465號   © 2018-2025 CODEPRJ.COM