macdoor615 created FLINK-29712:
----------------------------------
Summary: The same batch task works fine in 1.15.2 and 1.16.0-rc1,
but fails in 1.16.0-rc2
Key: FLINK-29712
URL: https://issues.apache.org/jira/browse/FLINK-29712
Project: Flink
Issue Type: Bug
Components: Table SQL / Client
Affects Versions: 1.16.0
Environment: Flink 1.16.0-rc2
Hive 3.1.3
Hadoop 3.3.4
Reporter: macdoor615
Fix For: 1.16.0
All my tasks have failed with same error **
{code:java}
org.apache.flink.runtime.JobException: Recovery is suppressed by
FixedDelayRestartBackoffTimeStrategy(maxNumberRestartAttempts=2,
backoffTimeMS=60000)
at
org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.handleFailure(ExecutionFailureHandler.java:139)
at
org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.getGlobalFailureHandlingResult(ExecutionFailureHandler.java:102)
at
org.apache.flink.runtime.scheduler.DefaultScheduler.handleGlobalFailure(DefaultScheduler.java:299)
at
org.apache.flink.runtime.operators.coordination.OperatorCoordinatorHolder$LazyInitializedCoordinatorContext.lambda$failJob$0(OperatorCoordinatorHolder.java:635)
at
org.apache.flink.runtime.rpc.akka.AkkaRpcActor.lambda$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.util.concurrent.ForkJoinTask.doExec(ForkJoinTask.java:289)
at
java.util.concurrent.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1056)
at java.util.concurrent.ForkJoinPool.runWorker(ForkJoinPool.java:1692)
at
java.util.concurrent.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:175)
Caused by: org.apache.flink.util.FlinkException: Global failure triggered by
OperatorCoordinator for 'Source: p_hswtv[4] -> Calc[5]' (operator
6cdc5bb954874d922eaee11a8e7b5dd5).
at
org.apache.flink.runtime.operators.coordination.OperatorCoordinatorHolder$LazyInitializedCoordinatorContext.failJob(OperatorCoordinatorHolder.java:617)
at
org.apache.flink.runtime.operators.coordination.RecreateOnResetOperatorCoordinator$QuiesceableContext.failJob(RecreateOnResetOperatorCoordinator.java:237)
at
org.apache.flink.runtime.source.coordinator.SourceCoordinatorContext.failJob(SourceCoordinatorContext.java:360)
at
org.apache.flink.runtime.source.coordinator.SourceCoordinator.start(SourceCoordinator.java:217)
at
org.apache.flink.runtime.operators.coordination.RecreateOnResetOperatorCoordinator$DeferrableCoordinator.applyCall(RecreateOnResetOperatorCoordinator.java:315)
at
org.apache.flink.runtime.operators.coordination.RecreateOnResetOperatorCoordinator.start(RecreateOnResetOperatorCoordinator.java:70)
at
org.apache.flink.runtime.operators.coordination.OperatorCoordinatorHolder.start(OperatorCoordinatorHolder.java:198)
at
org.apache.flink.runtime.scheduler.DefaultOperatorCoordinatorHandler.startOperatorCoordinators(DefaultOperatorCoordinatorHandler.java:165)
at
org.apache.flink.runtime.scheduler.DefaultOperatorCoordinatorHandler.startAllOperatorCoordinators(DefaultOperatorCoordinatorHandler.java:82)
at
org.apache.flink.runtime.scheduler.SchedulerBase.startScheduling(SchedulerBase.java:605)
at
org.apache.flink.runtime.jobmaster.JobMaster.startScheduling(JobMaster.java:1046)
at
org.apache.flink.runtime.jobmaster.JobMaster.startJobExecution(JobMaster.java:963)
at org.apache.flink.runtime.jobmaster.JobMaster.onStart(JobMaster.java:422)
at
org.apache.flink.runtime.rpc.RpcEndpoint.internalCallOnStart(RpcEndpoint.java:198)
at
org.apache.flink.runtime.rpc.akka.AkkaRpcActor$StoppedState.lambda$start$0(AkkaRpcActor.java:622)
at
org.apache.flink.runtime.concurrent.akka.ClassLoadingUtils.runWithContextClassLoader(ClassLoadingUtils.java:68)
at
org.apache.flink.runtime.rpc.akka.AkkaRpcActor$StoppedState.start(AkkaRpcActor.java:621)
at
org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleControlMessage(AkkaRpcActor.java:190)
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)
... 13 more
Caused by: java.lang.NumberFormatException: null
at java.lang.Integer.parseInt(Integer.java:542)
at java.lang.Integer.parseInt(Integer.java:615)
at
org.apache.flink.connectors.hive.HiveSourceFileEnumerator.calculateFilesSizeWithOpenCost(HiveSourceFileEnumerator.java:157)
at
org.apache.flink.connectors.hive.HiveSourceFileEnumerator.setSplitMaxSize(HiveSourceFileEnumerator.java:135)
at
org.apache.flink.connectors.hive.HiveSourceFileEnumerator.createInputSplits(HiveSourceFileEnumerator.java:89)
at
org.apache.flink.connectors.hive.HiveSourceFileEnumerator.enumerateSplits(HiveSourceFileEnumerator.java:67)
at
org.apache.flink.connector.file.src.AbstractFileSource.createEnumerator(AbstractFileSource.java:141)
at
org.apache.flink.connectors.hive.HiveSource.createEnumerator(HiveSource.java:129)
at
org.apache.flink.runtime.source.coordinator.SourceCoordinator.start(SourceCoordinator.java:213)
... 33 more
{code}
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
