Matthias Pohl created FLINK-34233:
-------------------------------------

             Summary: HybridShuffleITCase.testHybridSelectiveExchangesRestart 
failed due to a IllegalStateException
                 Key: FLINK-34233
                 URL: https://issues.apache.org/jira/browse/FLINK-34233
             Project: Flink
          Issue Type: Bug
          Components: Runtime / Network
    Affects Versions: 1.19.0
            Reporter: Matthias Pohl


https://dev.azure.com/apache-flink/apache-flink/_build/results?buildId=56791&view=logs&j=a596f69e-60d2-5a4b-7d39-dc69e4cdaed3&t=712ade8c-ca16-5b76-3acd-14df33bc1cb1&l=8357

{code}
Jan 24 02:10:03 02:10:03.582 [ERROR] Tests run: 12, Failures: 1, Errors: 0, 
Skipped: 0, Time elapsed: 34.74 s <<< FAILURE! -- in 
org.apache.flink.test.runtime.HybridShuffleITCase
Jan 24 02:10:03 02:10:03.582 [ERROR] 
org.apache.flink.test.runtime.HybridShuffleITCase.testHybridSelectiveExchangesRestart
 -- Time elapsed: 3.347 s <<< FAILURE!
Jan 24 02:10:03 java.lang.AssertionError: 
org.apache.flink.runtime.JobException: org.apache.flink.runtime.JobException: 
Recovery is suppressed by 
FixedDelayRestartBackoffTimeStrategy(maxNumberRestartAttempts=2, 
backoffTimeMS=0)
Jan 24 02:10:03         at 
org.apache.flink.test.runtime.JobGraphRunningUtil.execute(JobGraphRunningUtil.java:59)
Jan 24 02:10:03         at 
org.apache.flink.test.runtime.BatchShuffleITCaseBase.executeJob(BatchShuffleITCaseBase.java:137)
Jan 24 02:10:03         at 
org.apache.flink.test.runtime.HybridShuffleITCase.testHybridSelectiveExchangesRestart(HybridShuffleITCase.java:91)
Jan 24 02:10:03         at 
java.base/java.lang.reflect.Method.invoke(Method.java:568)
Jan 24 02:10:03         at 
java.base/java.util.stream.ForEachOps$ForEachOp$OfRef.accept(ForEachOps.java:183)
Jan 24 02:10:03         at 
java.base/java.util.stream.ReferencePipeline$3$1.accept(ReferencePipeline.java:197)
Jan 24 02:10:03         at 
java.base/java.util.stream.ReferencePipeline$2$1.accept(ReferencePipeline.java:179)
Jan 24 02:10:03         at 
java.base/java.util.stream.ReferencePipeline$3$1.accept(ReferencePipeline.java:197)
Jan 24 02:10:03         at 
java.base/java.util.stream.ForEachOps$ForEachOp$OfRef.accept(ForEachOps.java:183)
Jan 24 02:10:03         at 
java.base/java.util.stream.ReferencePipeline$3$1.accept(ReferencePipeline.java:197)
Jan 24 02:10:03         at 
java.base/java.util.stream.ReferencePipeline$3$1.accept(ReferencePipeline.java:197)
Jan 24 02:10:03         at 
java.base/java.util.Spliterators$ArraySpliterator.forEachRemaining(Spliterators.java:992)
Jan 24 02:10:03         at 
java.base/java.util.stream.AbstractPipeline.copyInto(AbstractPipeline.java:509)
Jan 24 02:10:03         at 
java.base/java.util.stream.AbstractPipeline.wrapAndCopyInto(AbstractPipeline.java:499)
Jan 24 02:10:03         at 
java.base/java.util.stream.ForEachOps$ForEachOp.evaluateSequential(ForEachOps.java:150)
Jan 24 02:10:03         at 
java.base/java.util.stream.ForEachOps$ForEachOp$OfRef.evaluateSequential(ForEachOps.java:173)
Jan 24 02:10:03         at 
java.base/java.util.stream.AbstractPipeline.evaluate(AbstractPipeline.java:234)
Jan 24 02:10:03         at 
java.base/java.util.stream.ReferencePipeline.forEach(ReferencePipeline.java:596)
Jan 24 02:10:03         at 
java.base/java.util.stream.ReferencePipeline$7$1.accept(ReferencePipeline.java:276)
Jan 24 02:10:03         at 
java.base/java.util.ArrayList$ArrayListSpliterator.forEachRemaining(ArrayList.java:1625)
Jan 24 02:10:03         at 
java.base/java.util.stream.AbstractPipeline.copyInto(AbstractPipeline.java:509)
Jan 24 02:10:03         at 
java.base/java.util.stream.AbstractPipeline.wrapAndCopyInto(AbstractPipeline.java:499)
Jan 24 02:10:03         at 
java.base/java.util.stream.ForEachOps$ForEachOp.evaluateSequential(ForEachOps.java:150)
Jan 24 02:10:03         at 
java.base/java.util.stream.ForEachOps$ForEachOp$OfRef.evaluateSequential(ForEachOps.java:173)
Jan 24 02:10:03         at 
java.base/java.util.stream.AbstractPipeline.evaluate(AbstractPipeline.java:234)
Jan 24 02:10:03         at 
java.base/java.util.stream.ReferencePipeline.forEach(ReferencePipeline.java:596)
Jan 24 02:10:03         at 
java.base/java.util.concurrent.RecursiveAction.exec(RecursiveAction.java:194)
Jan 24 02:10:03         at 
java.base/java.util.concurrent.ForkJoinTask.doExec(ForkJoinTask.java:373)
Jan 24 02:10:03         at 
java.base/java.util.concurrent.ForkJoinPool$WorkQueue.topLevelExec(ForkJoinPool.java:1182)
Jan 24 02:10:03         at 
java.base/java.util.concurrent.ForkJoinPool.scan(ForkJoinPool.java:1655)
Jan 24 02:10:03         at 
java.base/java.util.concurrent.ForkJoinPool.runWorker(ForkJoinPool.java:1622)
Jan 24 02:10:03         at 
java.base/java.util.concurrent.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:165)
Jan 24 02:10:03 Caused by: org.apache.flink.runtime.JobException: 
org.apache.flink.runtime.JobException: Recovery is suppressed by 
FixedDelayRestartBackoffTimeStrategy(maxNumberRestartAttempts=2, 
backoffTimeMS=0)
Jan 24 02:10:03         at 
org.apache.flink.runtime.executiongraph.failover.ExecutionFailureHandler.handleFailure(ExecutionFailureHandler.java:180)
Jan 24 02:10:03         at 
org.apache.flink.runtime.executiongraph.failover.ExecutionFailureHandler.getFailureHandlingResult(ExecutionFailureHandler.java:107)
Jan 24 02:10:03         at 
org.apache.flink.runtime.scheduler.DefaultScheduler.recordTaskFailure(DefaultScheduler.java:277)
Jan 24 02:10:03         at 
org.apache.flink.runtime.scheduler.DefaultScheduler.handleTaskFailure(DefaultScheduler.java:268)
Jan 24 02:10:03         at 
org.apache.flink.runtime.scheduler.DefaultScheduler.onTaskFailed(DefaultScheduler.java:261)
Jan 24 02:10:03         at 
org.apache.flink.runtime.scheduler.SchedulerBase.onTaskExecutionStateUpdate(SchedulerBase.java:787)
Jan 24 02:10:03         at 
org.apache.flink.runtime.scheduler.SchedulerBase.updateTaskExecutionState(SchedulerBase.java:764)
Jan 24 02:10:03         at 
org.apache.flink.runtime.scheduler.SchedulerNG.updateTaskExecutionState(SchedulerNG.java:83)
Jan 24 02:10:03         at 
org.apache.flink.runtime.jobmaster.JobMaster.updateTaskExecutionState(JobMaster.java:488)
Jan 24 02:10:03         at 
java.base/java.lang.reflect.Method.invoke(Method.java:568)
Jan 24 02:10:03         at 
org.apache.flink.runtime.rpc.pekko.PekkoRpcActor.lambda$handleRpcInvocation$1(PekkoRpcActor.java:309)
Jan 24 02:10:03         at 
org.apache.flink.runtime.concurrent.ClassLoadingUtils.runWithContextClassLoader(ClassLoadingUtils.java:83)
Jan 24 02:10:03         at 
org.apache.flink.runtime.rpc.pekko.PekkoRpcActor.handleRpcInvocation(PekkoRpcActor.java:307)
Jan 24 02:10:03         at 
org.apache.flink.runtime.rpc.pekko.PekkoRpcActor.handleRpcMessage(PekkoRpcActor.java:222)
Jan 24 02:10:03         at 
org.apache.flink.runtime.rpc.pekko.FencedPekkoRpcActor.handleRpcMessage(FencedPekkoRpcActor.java:85)
Jan 24 02:10:03         at 
org.apache.flink.runtime.rpc.pekko.PekkoRpcActor.handleMessage(PekkoRpcActor.java:168)
Jan 24 02:10:03         at 
org.apache.pekko.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:33)
Jan 24 02:10:03         at 
org.apache.pekko.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:29)
Jan 24 02:10:03         at 
scala.PartialFunction.applyOrElse(PartialFunction.scala:127)
Jan 24 02:10:03         at 
scala.PartialFunction.applyOrElse$(PartialFunction.scala:126)
Jan 24 02:10:03         at 
org.apache.pekko.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:29)
Jan 24 02:10:03         at 
scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:175)
Jan 24 02:10:03         at 
scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:176)
Jan 24 02:10:03         at 
scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:176)
Jan 24 02:10:03         at 
org.apache.pekko.actor.Actor.aroundReceive(Actor.scala:547)
Jan 24 02:10:03         at 
org.apache.pekko.actor.Actor.aroundReceive$(Actor.scala:545)
Jan 24 02:10:03         at 
org.apache.pekko.actor.AbstractActor.aroundReceive(AbstractActor.scala:229)
Jan 24 02:10:03         at 
org.apache.pekko.actor.ActorCell.receiveMessage(ActorCell.scala:590)
Jan 24 02:10:03         at 
org.apache.pekko.actor.ActorCell.invoke(ActorCell.scala:557)
Jan 24 02:10:03         at 
org.apache.pekko.dispatch.Mailbox.processMailbox(Mailbox.scala:280)
Jan 24 02:10:03         at 
org.apache.pekko.dispatch.Mailbox.run(Mailbox.scala:241)
Jan 24 02:10:03         at 
org.apache.pekko.dispatch.Mailbox.exec(Mailbox.scala:253)
Jan 24 02:10:03         ... 5 more
Jan 24 02:10:03 Caused by: java.lang.IllegalStateException: 
java.lang.IllegalStateException: Queried for a buffer before requesting the 
subpartition.
Jan 24 02:10:03         at 
org.apache.flink.util.Preconditions.checkState(Preconditions.java:193)
Jan 24 02:10:03         at 
org.apache.flink.runtime.io.network.partition.consumer.LocalInputChannel.checkAndWaitForSubpartitionView(LocalInputChannel.java:308)
Jan 24 02:10:03         at 
org.apache.flink.runtime.io.network.partition.consumer.LocalInputChannel.getNextBuffer(LocalInputChannel.java:248)
Jan 24 02:10:03         at 
org.apache.flink.runtime.io.network.partition.hybrid.tiered.netty.NettyConnectionReaderImpl.readBuffer(NettyConnectionReaderImpl.java:69)
Jan 24 02:10:03         at 
org.apache.flink.runtime.io.network.partition.hybrid.tiered.tier.memory.MemoryTierConsumerAgent.getNextBuffer(MemoryTierConsumerAgent.java:103)
Jan 24 02:10:03         at 
org.apache.flink.runtime.io.network.partition.hybrid.tiered.storage.TieredStorageConsumerClient.getNextBuffer(TieredStorageConsumerClient.java:102)
Jan 24 02:10:03         at 
org.apache.flink.runtime.io.network.partition.consumer.SingleInputGate.readBufferFromTieredStore(SingleInputGate.java:964)
Jan 24 02:10:03         at 
org.apache.flink.runtime.io.network.partition.consumer.SingleInputGate.readRecoveredOrNormalBuffer(SingleInputGate.java:899)
Jan 24 02:10:03         at 
org.apache.flink.runtime.io.network.partition.consumer.SingleInputGate.waitAndGetNextData(SingleInputGate.java:842)
Jan 24 02:10:03         at 
org.apache.flink.runtime.io.network.partition.consumer.SingleInputGate.getNextBufferOrEvent(SingleInputGate.java:813)
Jan 24 02:10:03         at 
org.apache.flink.runtime.io.network.partition.consumer.SingleInputGate.pollNext(SingleInputGate.java:801)
Jan 24 02:10:03         at 
org.apache.flink.runtime.taskmanager.InputGateWithMetrics.pollNext(InputGateWithMetrics.java:130)
Jan 24 02:10:03         at 
org.apache.flink.streaming.runtime.io.checkpointing.CheckpointedInputGate.pollNext(CheckpointedInputGate.java:150)
Jan 24 02:10:03         at 
org.apache.flink.streaming.runtime.io.AbstractStreamTaskNetworkInput.emitNext(AbstractStreamTaskNetworkInput.java:122)
Jan 24 02:10:03         at 
org.apache.flink.streaming.runtime.io.StreamOneInputProcessor.processInput(StreamOneInputProcessor.java:65)
Jan 24 02:10:03         at 
org.apache.flink.streaming.runtime.tasks.StreamTask.processInput(StreamTask.java:579)
Jan 24 02:10:03         at 
org.apache.flink.streaming.runtime.tasks.mailbox.MailboxProcessor.runMailboxLoop(MailboxProcessor.java:231)
Jan 24 02:10:03         at 
org.apache.flink.streaming.runtime.tasks.StreamTask.runMailboxLoop(StreamTask.java:909)
Jan 24 02:10:03         at 
org.apache.flink.streaming.runtime.tasks.StreamTask.invoke(StreamTask.java:858)
Jan 24 02:10:03         at 
org.apache.flink.runtime.taskmanager.Task.runWithSystemExitMonitoring(Task.java:958)
Jan 24 02:10:03         at 
org.apache.flink.runtime.taskmanager.Task.restoreAndInvoke(Task.java:937)
Jan 24 02:10:03         at 
org.apache.flink.runtime.taskmanager.Task.doRun(Task.java:751)
Jan 24 02:10:03         at 
org.apache.flink.runtime.taskmanager.Task.run(Task.java:566)
Jan 24 02:10:03         at java.base/java.lang.Thread.run(Thread.java:833)
{code}



--
This message was sent by Atlassian Jira
(v8.20.10#820010)

Reply via email to