Robert Metzger created FLINK-25327:
--------------------------------------
Summary: ApplicationMode "DELETE /cluster" REST call leads to exit
code 2, instead of 0
Key: FLINK-25327
URL: https://issues.apache.org/jira/browse/FLINK-25327
Project: Flink
Issue Type: Bug
Components: Runtime / Coordination
Reporter: Robert Metzger
FLINK-24113 introduced a mode to keep the Application Mode JobManager running
after the Job has been cancelled. Cluster shutdown needs to be initiated for
example using the DELETE /cluster REST endpoint.
The problem is that there can be a fatal error during the shutdown, making the
JobManager exit with return code != 0 (making resource managers believe there
was an error with the Flink application)
Error
{code}
2021-12-15 08:09:55,708 ERROR
org.apache.flink.runtime.entrypoint.ClusterEntrypoint [] - Fatal error
occurred in the cluster entrypoint.
org.apache.flink.util.FlinkException: Application failed unexpectedly.
at
org.apache.flink.client.deployment.application.ApplicationDispatcherBootstrap.lambda$finishBootstrapTasks$1(ApplicationDispatcherBootstrap.java:177)
~[flink-dist-1.15-master-robert.jar:1.15-master-robert]
at
java.util.concurrent.CompletableFuture.uniExceptionally(CompletableFuture.java:884)
~[?:1.8.0_312]
at
java.util.concurrent.CompletableFuture$UniExceptionally.tryFire(CompletableFuture.java:866)
~[?:1.8.0_312]
at
java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:488)
~[?:1.8.0_312]
at
java.util.concurrent.CompletableFuture.cancel(CompletableFuture.java:2278)
~[?:1.8.0_312]
at
org.apache.flink.client.deployment.application.ApplicationDispatcherBootstrap.stop(ApplicationDispatcherBootstrap.java:125)
~[flink-dist-1.15-master-robert.jar:1.15-master-robert]
at
org.apache.flink.runtime.dispatcher.Dispatcher.lambda$onStop$0(Dispatcher.java:284)
~[flink-dist-1.15-master-robert.jar:1.15-master-robert]
at
org.apache.flink.util.concurrent.FutureUtils.lambda$runAfterwardsAsync$18(FutureUtils.java:696)
~[flink-dist-1.15-master-robert.jar:1.15-master-robert]
at
java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:774)
~[?:1.8.0_312]
at
java.util.concurrent.CompletableFuture$UniWhenComplete.tryFire(CompletableFuture.java:750)
~[?:1.8.0_312]
at
java.util.concurrent.CompletableFuture$Completion.run(CompletableFuture.java:456)
~[?:1.8.0_312]
at
org.apache.flink.util.concurrent.DirectExecutorService.execute(DirectExecutorService.java:217)
~[flink-dist-1.15-master-robert.jar:1.15-master-robert]
at
java.util.concurrent.CompletableFuture$UniCompletion.claim(CompletableFuture.java:543)
~[?:1.8.0_312]
at
java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:765)
~[?:1.8.0_312]
at
java.util.concurrent.CompletableFuture$UniWhenComplete.tryFire(CompletableFuture.java:750)
~[?:1.8.0_312]
at
java.util.concurrent.CompletableFuture.uniWhenCompleteStage(CompletableFuture.java:795)
~[?:1.8.0_312]
at
java.util.concurrent.CompletableFuture.whenCompleteAsync(CompletableFuture.java:2163)
~[?:1.8.0_312]
at
org.apache.flink.util.concurrent.FutureUtils.runAfterwardsAsync(FutureUtils.java:693)
~[flink-dist-1.15-master-robert.jar:1.15-master-robert]
at
org.apache.flink.util.concurrent.FutureUtils.runAfterwards(FutureUtils.java:660)
~[flink-dist-1.15-master-robert.jar:1.15-master-robert]
at
org.apache.flink.runtime.dispatcher.Dispatcher.onStop(Dispatcher.java:281)
~[flink-dist-1.15-master-robert.jar:1.15-master-robert]
at
org.apache.flink.runtime.rpc.RpcEndpoint.internalCallOnStop(RpcEndpoint.java:214)
~[flink-dist-1.15-master-robert.jar:1.15-master-robert]
at
org.apache.flink.runtime.rpc.akka.AkkaRpcActor$StartedState.lambda$terminate$0(AkkaRpcActor.java:580)
~[flink-rpc-akka_44e0316d-9cf7-4fc8-9b48-4f6084b0cc47.jar:1.15-master-robert]
at
org.apache.flink.runtime.concurrent.akka.ClassLoadingUtils.runWithContextClassLoader(ClassLoadingUtils.java:83)
~[flink-rpc-akka_44e0316d-9cf7-4fc8-9b48-4f6084b0cc47.jar:1.15-master-robert]
at
org.apache.flink.runtime.rpc.akka.AkkaRpcActor$StartedState.terminate(AkkaRpcActor.java:579)
~[flink-rpc-akka_44e0316d-9cf7-4fc8-9b48-4f6084b0cc47.jar:1.15-master-robert]
at
org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleControlMessage(AkkaRpcActor.java:191)
~[flink-rpc-akka_44e0316d-9cf7-4fc8-9b48-4f6084b0cc47.jar:1.15-master-robert]
at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:24)
[flink-rpc-akka_44e0316d-9cf7-4fc8-9b48-4f6084b0cc47.jar:1.15-master-robert]
at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:20)
[flink-rpc-akka_44e0316d-9cf7-4fc8-9b48-4f6084b0cc47.jar:1.15-master-robert]
at scala.PartialFunction.applyOrElse(PartialFunction.scala:123)
[flink-rpc-akka_44e0316d-9cf7-4fc8-9b48-4f6084b0cc47.jar:1.15-master-robert]
at scala.PartialFunction.applyOrElse$(PartialFunction.scala:122)
[flink-rpc-akka_44e0316d-9cf7-4fc8-9b48-4f6084b0cc47.jar:1.15-master-robert]
at akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:20)
[flink-rpc-akka_44e0316d-9cf7-4fc8-9b48-4f6084b0cc47.jar:1.15-master-robert]
at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171)
[flink-rpc-akka_44e0316d-9cf7-4fc8-9b48-4f6084b0cc47.jar:1.15-master-robert]
at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:172)
[flink-rpc-akka_44e0316d-9cf7-4fc8-9b48-4f6084b0cc47.jar:1.15-master-robert]
at akka.actor.Actor.aroundReceive(Actor.scala:537)
[flink-rpc-akka_44e0316d-9cf7-4fc8-9b48-4f6084b0cc47.jar:1.15-master-robert]
at akka.actor.Actor.aroundReceive$(Actor.scala:535)
[flink-rpc-akka_44e0316d-9cf7-4fc8-9b48-4f6084b0cc47.jar:1.15-master-robert]
at akka.actor.AbstractActor.aroundReceive(AbstractActor.scala:220)
[flink-rpc-akka_44e0316d-9cf7-4fc8-9b48-4f6084b0cc47.jar:1.15-master-robert]
at akka.actor.ActorCell.receiveMessage(ActorCell.scala:580)
[flink-rpc-akka_44e0316d-9cf7-4fc8-9b48-4f6084b0cc47.jar:1.15-master-robert]
at akka.actor.ActorCell.invoke(ActorCell.scala:548)
[flink-rpc-akka_44e0316d-9cf7-4fc8-9b48-4f6084b0cc47.jar:1.15-master-robert]
at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:270)
[flink-rpc-akka_44e0316d-9cf7-4fc8-9b48-4f6084b0cc47.jar:1.15-master-robert]
at akka.dispatch.Mailbox.run(Mailbox.scala:231)
[flink-rpc-akka_44e0316d-9cf7-4fc8-9b48-4f6084b0cc47.jar:1.15-master-robert]
at akka.dispatch.Mailbox.exec(Mailbox.scala:243)
[flink-rpc-akka_44e0316d-9cf7-4fc8-9b48-4f6084b0cc47.jar:1.15-master-robert]
at java.util.concurrent.ForkJoinTask.doExec(ForkJoinTask.java:289)
[?:1.8.0_312]
at
java.util.concurrent.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1056)
[?:1.8.0_312]
at java.util.concurrent.ForkJoinPool.runWorker(ForkJoinPool.java:1692)
[?:1.8.0_312]
at
java.util.concurrent.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:175)
[?:1.8.0_312]
Caused by: java.util.concurrent.CompletionException:
java.util.concurrent.CancellationException
at
java.util.concurrent.CompletableFuture.encodeThrowable(CompletableFuture.java:292)
~[?:1.8.0_312]
at
java.util.concurrent.CompletableFuture.completeThrowable(CompletableFuture.java:308)
~[?:1.8.0_312]
at
java.util.concurrent.CompletableFuture.uniApply(CompletableFuture.java:607)
~[?:1.8.0_312]
at
java.util.concurrent.CompletableFuture$UniApply.tryFire(CompletableFuture.java:591)
~[?:1.8.0_312]
... 41 more
Caused by: java.util.concurrent.CancellationException
at
java.util.concurrent.CompletableFuture.cancel(CompletableFuture.java:2276)
~[?:1.8.0_312]
... 39 more
2021-12-15 08:09:55,711 INFO org.apache.flink.runtime.blob.BlobServer
[] - Stopped BLOB server at 0.0.0.0:6124
{code}
--
This message was sent by Atlassian Jira
(v8.20.1#820001)