[
https://issues.apache.org/jira/browse/FLINK-9056?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16425271#comment-16425271
]
yuqi commented on FLINK-9056:
-----------------------------
Hi, [~mingleizhang], The following are detailed log
{code:java}
org.apache.flink.client.program.ProgramInvocationException:
org.apache.flink.runtime.jobmanager.scheduler.NoResourceAvailableException:
Could not allocate all requires slots within timeout of 30000 ms. Slots
required: 6, slots allocated: 4
at
org.apache.flink.client.program.rest.RestClusterClient.submitJob(RestClusterClient.java:258)
at org.apache.flink.client.program.ClusterClient.run(ClusterClient.java:463)
at
org.apache.flink.streaming.api.environment.StreamContextEnvironment.execute(StreamContextEnvironment.java:66)
at flink.package5.NewTest.main(NewTest.java:93)
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:528)
at
org.apache.flink.client.program.PackagedProgram.invokeInteractiveModeForExecution(PackagedProgram.java:420)
at org.apache.flink.client.program.ClusterClient.run(ClusterClient.java:403)
at org.apache.flink.client.cli.CliFrontend.executeProgram(CliFrontend.java:781)
at org.apache.flink.client.cli.CliFrontend.runProgram(CliFrontend.java:275)
at org.apache.flink.client.cli.CliFrontend.run(CliFrontend.java:210)
at
org.apache.flink.client.cli.CliFrontend.parseParameters(CliFrontend.java:1020)
at org.apache.flink.client.cli.CliFrontend.lambda$main$9(CliFrontend.java:1096)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Subject.java:422)
at
org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1556)
at
org.apache.flink.runtime.security.HadoopSecurityContext.runSecured(HadoopSecurityContext.java:41)
at org.apache.flink.client.cli.CliFrontend.main(CliFrontend.java:1096)
Caused by:
org.apache.flink.runtime.jobmanager.scheduler.NoResourceAvailableException:
Could not allocate all requires slots within timeout of 30000 ms. Slots
required: 6, slots allocated: 4
at
org.apache.flink.runtime.executiongraph.ExecutionGraph.lambda$scheduleEager$2(ExecutionGraph.java:997)
at
java.util.concurrent.CompletableFuture.uniExceptionally(CompletableFuture.java:870)
at
java.util.concurrent.CompletableFuture$UniExceptionally.tryFire(CompletableFuture.java:852)
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$ResultConjunctFuture.handleCompletedFuture(FutureUtils.java:551)
at
java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:760)
at
java.util.concurrent.CompletableFuture$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$1.onComplete(FutureUtils.java:789)
at akka.dispatch.OnComplete.internal(Future.scala:258)
at akka.dispatch.OnComplete.internal(Future.scala:256)
at akka.dispatch.japi$CallbackBridge.apply(Future.scala:186)
at akka.dispatch.japi$CallbackBridge.apply(Future.scala:183)
at scala.concurrent.impl.CallbackRunnable.run(Promise.scala:36)
at
org.apache.flink.runtime.concurrent.Executors$DirectExecutionContext.execute(Executors.java:83)
at scala.concurrent.impl.CallbackRunnable.executeWithValue(Promise.scala:44)
at scala.concurrent.impl.Promise$DefaultPromise.tryComplete(Promise.scala:252)
at akka.pattern.PromiseActorRef.$bang(AskSupport.scala:534)
at
akka.pattern.PipeToSupport$PipeableFuture$$anonfun$pipeTo$1.applyOrElse(PipeToSupport.scala:20)
at
akka.pattern.PipeToSupport$PipeableFuture$$anonfun$pipeTo$1.applyOrElse(PipeToSupport.scala:18)
at scala.concurrent.Future$$anonfun$andThen$1.apply(Future.scala:436)
at scala.concurrent.Future$$anonfun$andThen$1.apply(Future.scala:435)
at scala.concurrent.impl.CallbackRunnable.run(Promise.scala:36)
at
akka.dispatch.BatchingExecutor$AbstractBatch.processBatch(BatchingExecutor.scala:55)
at
akka.dispatch.BatchingExecutor$BlockableBatch$$anonfun$run$1.apply$mcV$sp(BatchingExecutor.scala:91)
at
akka.dispatch.BatchingExecutor$BlockableBatch$$anonfun$run$1.apply(BatchingExecutor.scala:91)
at
akka.dispatch.BatchingExecutor$BlockableBatch$$anonfun$run$1.apply(BatchingExecutor.scala:91)
at scala.concurrent.BlockContext$.withBlockContext(BlockContext.scala:72)
at akka.dispatch.BatchingExecutor$BlockableBatch.run(BatchingExecutor.scala:90)
at akka.dispatch.TaskInvocation.run(AbstractDispatcher.scala:39)
at
akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(AbstractDispatcher.scala:415)
at scala.concurrent.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)
at
scala.concurrent.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
at scala.concurrent.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979)
at
scala.concurrent.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107){code}
> Job submission fails with AskTimeoutException if not enough slots are
> available
> -------------------------------------------------------------------------------
>
> Key: FLINK-9056
> URL: https://issues.apache.org/jira/browse/FLINK-9056
> Project: Flink
> Issue Type: Improvement
> Components: Job-Submission
> Affects Versions: 1.5.0
> Environment: * FLIP-6 enabled
> * Local Flink instance with fixed number of TMs
> * Job parallelism exceeds available slots
> Reporter: Fabian Hueske
> Assignee: yuqi
> Priority: Major
>
> The error message if a job submission fails due to lack of available slots is
> not helpful:
> {code:java}
> Caused by: akka.pattern.AskTimeoutException: Ask timed out on
> [Actor[akka://flink/user/8f0fabba-4021-45b6-a1f7-b8afd6627640#-574617182|#-574617182]]
> after [300000 ms]. Sender[null] sent message of type
> "org.apache.flink.runtime.rpc.messages.LocalRpcInvocation".
> at
> akka.pattern.PromiseActorRef$$anonfun$1.apply$mcV$sp(AskSupport.scala:604)
> at akka.actor.Scheduler$$anon$4.run(Scheduler.scala:126)
> at
> scala.concurrent.Future$InternalCallbackExecutor$.unbatchedExecute(Future.scala:601)
> at
> scala.concurrent.BatchingExecutor$class.execute(BatchingExecutor.scala:109)
> at
> scala.concurrent.Future$InternalCallbackExecutor$.execute(Future.scala:599)
> at
> akka.actor.LightArrayRevolverScheduler$TaskHolder.executeTask(LightArrayRevolverScheduler.scala:329)
> at
> akka.actor.LightArrayRevolverScheduler$$anon$4.executeBucket$1(LightArrayRevolverScheduler.scala:280)
> at
> akka.actor.LightArrayRevolverScheduler$$anon$4.nextTick(LightArrayRevolverScheduler.scala:284)
> at
> akka.actor.LightArrayRevolverScheduler$$anon$4.run(LightArrayRevolverScheduler.scala:236)
> at java.lang.Thread.run(Thread.java:748)
> {code}
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
