[
https://issues.apache.org/jira/browse/FLINK-13887?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Zhu Zhu updated FLINK-13887:
----------------------------
Description:
If a user invokes ExecutionConfig#setDefaultInputDependencyConstraint(null) to
set the defaultInputDependencyConstraint to be null, the scheduling topology
building will throw NPE in ExecutionGraph creating stage, causing a master node
fatal error.
Thus we need to do checkNotNull on the
ExecutionConfig#setDefaultInputDependencyConstraint param to remind users in an
early stage.
Exception is as blow:
2019-08-28T15:19:21.287+0000 ERROR
org.apache.flink.runtime.entrypoint.ClusterEntrypoint - Fatal error
occurred in the cluster entrypoint.
org.apache.flink.runtime.dispatcher.DispatcherException: Failed to take
leadership with session id 2f8f7919-a81b-4529-ad57-9789dbf07707.
at
org.apache.flink.runtime.dispatcher.Dispatcher.lambda$null$30(Dispatcher.java:915)
at
java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:760)
at
java.util.concurrent.CompletableFuture$UniWhenComplete.tryFire(CompletableFuture.java:736)
at
java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:474)
at
java.util.concurrent.CompletableFuture.completeExceptionally(CompletableFuture.java:1977)
at
org.apache.flink.runtime.concurrent.FutureUtils$WaitingConjunctFuture.handleCompletedFuture(FutureUtils.java:691)
at
java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:760)
at
java.util.concurrent.CompletableFuture$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$UniWhenComplete.tryFire(CompletableFuture.java:739)
at
java.util.concurrent.CompletableFuture$Completion.run(CompletableFuture.java:442)
at
org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRunAsync(AkkaRpcActor.java:397)
at
org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:190)
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:123)
at scala.PartialFunction.applyOrElse$(PartialFunction.scala:122)
at akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:21)
at scala.PartialFunction$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: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.RuntimeException:
org.apache.flink.runtime.client.JobExecutionException: Could not set up
JobManager
at
org.apache.flink.util.function.CheckedSupplier.lambda$unchecked$0(CheckedSupplier.java:36)
at
java.util.concurrent.CompletableFuture$AsyncSupply.run(CompletableFuture.java:1590)
at akka.dispatch.TaskInvocation.run(AbstractDispatcher.scala:40)
at
akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(ForkJoinExecutorConfigurator.scala:44)
... 4 more
Caused by: org.apache.flink.runtime.client.JobExecutionException: Could not
set up JobManager
at
org.apache.flink.runtime.jobmaster.JobManagerRunner.<init>(JobManagerRunner.java:152)
at
org.apache.flink.runtime.dispatcher.DefaultJobManagerRunnerFactory.createJobManagerRunner(DefaultJobManagerRunnerFactory.java:83)
at
org.apache.flink.runtime.dispatcher.Dispatcher.lambda$createJobManagerRunner$5(Dispatcher.java:375)
at
org.apache.flink.util.function.CheckedSupplier.lambda$unchecked$0(CheckedSupplier.java:34)
... 7 more
Caused by: java.lang.NullPointerException
at
org.apache.flink.util.Preconditions.checkNotNull(Preconditions.java:58)
at
org.apache.flink.runtime.scheduler.adapter.DefaultSchedulingExecutionVertex.<init>(DefaultSchedulingExecutionVertex.java:59)
at
org.apache.flink.runtime.scheduler.adapter.ExecutionGraphToSchedulingTopologyAdapter.generateSchedulingExecutionVertex(ExecutionGraphToSchedulingTopologyAdapter.java:113)
at
org.apache.flink.runtime.scheduler.adapter.ExecutionGraphToSchedulingTopologyAdapter.<init>(ExecutionGraphToSchedulingTopologyAdapter.java:65)
at
org.apache.flink.runtime.executiongraph.ExecutionGraph.attachJobGraph(ExecutionGraph.java:939)
at
org.apache.flink.runtime.executiongraph.ExecutionGraphBuilder.buildGraph(ExecutionGraphBuilder.java:230)
at
org.apache.flink.runtime.executiongraph.ExecutionGraphBuilder.buildGraph(ExecutionGraphBuilder.java:106)
at
org.apache.flink.runtime.scheduler.LegacyScheduler.createExecutionGraph(LegacyScheduler.java:207)
at
org.apache.flink.runtime.scheduler.LegacyScheduler.createAndRestoreExecutionGraph(LegacyScheduler.java:184)
at
org.apache.flink.runtime.scheduler.LegacyScheduler.<init>(LegacyScheduler.java:176)
at
org.apache.flink.runtime.scheduler.LegacySchedulerFactory.createInstance(LegacySchedulerFactory.java:70)
at
org.apache.flink.runtime.jobmaster.JobMaster.createScheduler(JobMaster.java:275)
at
org.apache.flink.runtime.jobmaster.JobMaster.<init>(JobMaster.java:265)
at
org.apache.flink.runtime.jobmaster.factories.DefaultJobMasterServiceFactory.createJobMasterService(DefaultJobMasterServiceFactory.java:98)
at
org.apache.flink.runtime.jobmaster.factories.DefaultJobMasterServiceFactory.createJobMasterService(DefaultJobMasterServiceFactory.java:40)
at
org.apache.flink.runtime.jobmaster.JobManagerRunner.<init>(JobManagerRunner.java:146)
... 10 more
was:
If a user invokes ExecutionConfig#setDefaultInputDependencyConstraint(null) to
set the defaultInputDependencyConstraint to be null, the scheduling topology
building will throw NPE in ExecutionGraph creating stage which causes a fatal
error.
Thus we need to do checkNotNull on the
ExecutionConfig#setDefaultInputDependencyConstraint param.
Exception is as blow:
2019-08-28T15:19:21.287+0000 ERROR
org.apache.flink.runtime.entrypoint.ClusterEntrypoint - Fatal error
occurred in the cluster entrypoint.
org.apache.flink.runtime.dispatcher.DispatcherException: Failed to take
leadership with session id 2f8f7919-a81b-4529-ad57-9789dbf07707.
at
org.apache.flink.runtime.dispatcher.Dispatcher.lambda$null$30(Dispatcher.java:915)
at
java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:760)
at
java.util.concurrent.CompletableFuture$UniWhenComplete.tryFire(CompletableFuture.java:736)
at
java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:474)
at
java.util.concurrent.CompletableFuture.completeExceptionally(CompletableFuture.java:1977)
at
org.apache.flink.runtime.concurrent.FutureUtils$WaitingConjunctFuture.handleCompletedFuture(FutureUtils.java:691)
at
java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:760)
at
java.util.concurrent.CompletableFuture$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$UniWhenComplete.tryFire(CompletableFuture.java:739)
at
java.util.concurrent.CompletableFuture$Completion.run(CompletableFuture.java:442)
at
org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRunAsync(AkkaRpcActor.java:397)
at
org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:190)
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:123)
at scala.PartialFunction.applyOrElse$(PartialFunction.scala:122)
at akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:21)
at scala.PartialFunction$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: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.RuntimeException:
org.apache.flink.runtime.client.JobExecutionException: Could not set up
JobManager
at
org.apache.flink.util.function.CheckedSupplier.lambda$unchecked$0(CheckedSupplier.java:36)
at
java.util.concurrent.CompletableFuture$AsyncSupply.run(CompletableFuture.java:1590)
at akka.dispatch.TaskInvocation.run(AbstractDispatcher.scala:40)
at
akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(ForkJoinExecutorConfigurator.scala:44)
... 4 more
Caused by: org.apache.flink.runtime.client.JobExecutionException: Could not set
up JobManager
at
org.apache.flink.runtime.jobmaster.JobManagerRunner.<init>(JobManagerRunner.java:152)
at
org.apache.flink.runtime.dispatcher.DefaultJobManagerRunnerFactory.createJobManagerRunner(DefaultJobManagerRunnerFactory.java:83)
at
org.apache.flink.runtime.dispatcher.Dispatcher.lambda$createJobManagerRunner$5(Dispatcher.java:375)
at
org.apache.flink.util.function.CheckedSupplier.lambda$unchecked$0(CheckedSupplier.java:34)
... 7 more
Caused by: java.lang.NullPointerException
at
org.apache.flink.util.Preconditions.checkNotNull(Preconditions.java:58)
at
org.apache.flink.runtime.scheduler.adapter.DefaultSchedulingExecutionVertex.<init>(DefaultSchedulingExecutionVertex.java:59)
at
org.apache.flink.runtime.scheduler.adapter.ExecutionGraphToSchedulingTopologyAdapter.generateSchedulingExecutionVertex(ExecutionGraphToSchedulingTopologyAdapter.java:113)
at
org.apache.flink.runtime.scheduler.adapter.ExecutionGraphToSchedulingTopologyAdapter.<init>(ExecutionGraphToSchedulingTopologyAdapter.java:65)
at
org.apache.flink.runtime.executiongraph.ExecutionGraph.attachJobGraph(ExecutionGraph.java:939)
at
org.apache.flink.runtime.executiongraph.ExecutionGraphBuilder.buildGraph(ExecutionGraphBuilder.java:230)
at
org.apache.flink.runtime.executiongraph.ExecutionGraphBuilder.buildGraph(ExecutionGraphBuilder.java:106)
at
org.apache.flink.runtime.scheduler.LegacyScheduler.createExecutionGraph(LegacyScheduler.java:207)
at
org.apache.flink.runtime.scheduler.LegacyScheduler.createAndRestoreExecutionGraph(LegacyScheduler.java:184)
at
org.apache.flink.runtime.scheduler.LegacyScheduler.<init>(LegacyScheduler.java:176)
at
org.apache.flink.runtime.scheduler.LegacySchedulerFactory.createInstance(LegacySchedulerFactory.java:70)
at
org.apache.flink.runtime.jobmaster.JobMaster.createScheduler(JobMaster.java:275)
at
org.apache.flink.runtime.jobmaster.JobMaster.<init>(JobMaster.java:265)
at
org.apache.flink.runtime.jobmaster.factories.DefaultJobMasterServiceFactory.createJobMasterService(DefaultJobMasterServiceFactory.java:98)
at
org.apache.flink.runtime.jobmaster.factories.DefaultJobMasterServiceFactory.createJobMasterService(DefaultJobMasterServiceFactory.java:40)
at
org.apache.flink.runtime.jobmaster.JobManagerRunner.<init>(JobManagerRunner.java:146)
... 10 more
> ExecutionConfig#setDefaultInputDependencyConstraint should do NotNull check
> on params
> -------------------------------------------------------------------------------------
>
> Key: FLINK-13887
> URL: https://issues.apache.org/jira/browse/FLINK-13887
> Project: Flink
> Issue Type: Bug
> Components: Runtime / Coordination
> Affects Versions: 1.9.0, 1.10.0
> Reporter: Zhu Zhu
> Priority: Major
>
> If a user invokes ExecutionConfig#setDefaultInputDependencyConstraint(null)
> to set the defaultInputDependencyConstraint to be null, the scheduling
> topology building will throw NPE in ExecutionGraph creating stage, causing a
> master node fatal error.
> Thus we need to do checkNotNull on the
> ExecutionConfig#setDefaultInputDependencyConstraint param to remind users in
> an early stage.
>
> Exception is as blow:
> 2019-08-28T15:19:21.287+0000 ERROR
> org.apache.flink.runtime.entrypoint.ClusterEntrypoint - Fatal error
> occurred in the cluster entrypoint.
> org.apache.flink.runtime.dispatcher.DispatcherException: Failed to take
> leadership with session id 2f8f7919-a81b-4529-ad57-9789dbf07707.
> at
> org.apache.flink.runtime.dispatcher.Dispatcher.lambda$null$30(Dispatcher.java:915)
> at
> java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:760)
> at
> java.util.concurrent.CompletableFuture$UniWhenComplete.tryFire(CompletableFuture.java:736)
> at
> java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:474)
> at
> java.util.concurrent.CompletableFuture.completeExceptionally(CompletableFuture.java:1977)
> at
> org.apache.flink.runtime.concurrent.FutureUtils$WaitingConjunctFuture.handleCompletedFuture(FutureUtils.java:691)
> at
> java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:760)
> at
> java.util.concurrent.CompletableFuture$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$UniWhenComplete.tryFire(CompletableFuture.java:739)
> at
> java.util.concurrent.CompletableFuture$Completion.run(CompletableFuture.java:442)
> at
> org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRunAsync(AkkaRpcActor.java:397)
> at
> org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:190)
> 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:123)
> at scala.PartialFunction.applyOrElse$(PartialFunction.scala:122)
> at
> akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:21)
> at
> scala.PartialFunction$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: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.RuntimeException:
> org.apache.flink.runtime.client.JobExecutionException: Could not set up
> JobManager
> at
> org.apache.flink.util.function.CheckedSupplier.lambda$unchecked$0(CheckedSupplier.java:36)
> at
> java.util.concurrent.CompletableFuture$AsyncSupply.run(CompletableFuture.java:1590)
> at akka.dispatch.TaskInvocation.run(AbstractDispatcher.scala:40)
> at
> akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(ForkJoinExecutorConfigurator.scala:44)
> ... 4 more
> Caused by: org.apache.flink.runtime.client.JobExecutionException: Could not
> set up JobManager
> at
> org.apache.flink.runtime.jobmaster.JobManagerRunner.<init>(JobManagerRunner.java:152)
> at
> org.apache.flink.runtime.dispatcher.DefaultJobManagerRunnerFactory.createJobManagerRunner(DefaultJobManagerRunnerFactory.java:83)
> at
> org.apache.flink.runtime.dispatcher.Dispatcher.lambda$createJobManagerRunner$5(Dispatcher.java:375)
> at
> org.apache.flink.util.function.CheckedSupplier.lambda$unchecked$0(CheckedSupplier.java:34)
> ... 7 more
> Caused by: java.lang.NullPointerException
> at
> org.apache.flink.util.Preconditions.checkNotNull(Preconditions.java:58)
> at
> org.apache.flink.runtime.scheduler.adapter.DefaultSchedulingExecutionVertex.<init>(DefaultSchedulingExecutionVertex.java:59)
> at
> org.apache.flink.runtime.scheduler.adapter.ExecutionGraphToSchedulingTopologyAdapter.generateSchedulingExecutionVertex(ExecutionGraphToSchedulingTopologyAdapter.java:113)
> at
> org.apache.flink.runtime.scheduler.adapter.ExecutionGraphToSchedulingTopologyAdapter.<init>(ExecutionGraphToSchedulingTopologyAdapter.java:65)
> at
> org.apache.flink.runtime.executiongraph.ExecutionGraph.attachJobGraph(ExecutionGraph.java:939)
> at
> org.apache.flink.runtime.executiongraph.ExecutionGraphBuilder.buildGraph(ExecutionGraphBuilder.java:230)
> at
> org.apache.flink.runtime.executiongraph.ExecutionGraphBuilder.buildGraph(ExecutionGraphBuilder.java:106)
> at
> org.apache.flink.runtime.scheduler.LegacyScheduler.createExecutionGraph(LegacyScheduler.java:207)
> at
> org.apache.flink.runtime.scheduler.LegacyScheduler.createAndRestoreExecutionGraph(LegacyScheduler.java:184)
> at
> org.apache.flink.runtime.scheduler.LegacyScheduler.<init>(LegacyScheduler.java:176)
> at
> org.apache.flink.runtime.scheduler.LegacySchedulerFactory.createInstance(LegacySchedulerFactory.java:70)
> at
> org.apache.flink.runtime.jobmaster.JobMaster.createScheduler(JobMaster.java:275)
> at
> org.apache.flink.runtime.jobmaster.JobMaster.<init>(JobMaster.java:265)
> at
> org.apache.flink.runtime.jobmaster.factories.DefaultJobMasterServiceFactory.createJobMasterService(DefaultJobMasterServiceFactory.java:98)
> at
> org.apache.flink.runtime.jobmaster.factories.DefaultJobMasterServiceFactory.createJobMasterService(DefaultJobMasterServiceFactory.java:40)
> at
> org.apache.flink.runtime.jobmaster.JobManagerRunner.<init>(JobManagerRunner.java:146)
> ... 10 more
--
This message was sent by Atlassian Jira
(v8.3.2#803003)
