[
https://issues.apache.org/jira/browse/FLINK-20283?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Dian Fu closed FLINK-20283.
---------------------------
Resolution: Fixed
Fixed in 1.12.0 via 625db70dc550e7fc6cb53f137eb5ea950a58f4db
> Make invalid managed memory fraction errors of python udf more user friendly
> ----------------------------------------------------------------------------
>
> Key: FLINK-20283
> URL: https://issues.apache.org/jira/browse/FLINK-20283
> Project: Flink
> Issue Type: Improvement
> Components: API / Python
> Affects Versions: 1.12.0
> Reporter: Zhu Zhu
> Assignee: Dian Fu
> Priority: Critical
> Labels: pull-request-available
> Fix For: 1.12.0
>
>
> When managed memory is required for python udf but its
> "taskmanager.memory.managed.consumer-weights" is set to 0, error will happen
> but the message is hard to understand for users, see [1].
> I think we should expose the invalid fraction error to users in this case and
> guide users to properly configure
> "taskmanager.memory.managed.consumer-weights".
> [1]
> {code:java}
> org.apache.flink.runtime.JobException: Recovery is suppressed by
> NoRestartBackoffTimeStrategy
> at
> org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.handleFailure(ExecutionFailureHandler.java:116)
> at
> org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.getFailureHandlingResult(ExecutionFailureHandler.java:78)
> at
> org.apache.flink.runtime.scheduler.DefaultScheduler.handleTaskFailure(DefaultScheduler.java:224)
> at
> org.apache.flink.runtime.scheduler.DefaultScheduler.maybeHandleTaskFailure(DefaultScheduler.java:217)
> at
> org.apache.flink.runtime.scheduler.DefaultScheduler.updateTaskExecutionStateInternal(DefaultScheduler.java:208)
> at
> org.apache.flink.runtime.scheduler.SchedulerBase.updateTaskExecutionState(SchedulerBase.java:534)
> at
> org.apache.flink.runtime.scheduler.SchedulerNG.updateTaskExecutionState(SchedulerNG.java:89)
> at
> org.apache.flink.runtime.jobmaster.JobMaster.updateTaskExecutionState(JobMaster.java:419)
> 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.runtime.rpc.akka.AkkaRpcActor.handleRpcInvocation(AkkaRpcActor.java:286)
> at
> org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:201)
> at
> org.apache.flink.runtime.rpc.akka.FencedAkkaRpcActor.handleRpcMessage(FencedAkkaRpcActor.java:74)
> at
> org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleMessage(AkkaRpcActor.java:154)
> at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:26)
> at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:21)
> at scala.PartialFunction$class.applyOrElse(PartialFunction.scala:123)
> at akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:21)
> at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:170)
> at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171)
> at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171)
> at akka.actor.Actor$class.aroundReceive(Actor.scala:517)
> at akka.actor.AbstractActor.aroundReceive(AbstractActor.scala:225)
> at akka.actor.ActorCell.receiveMessage(ActorCell.scala:592)
> at akka.actor.ActorCell.invoke(ActorCell.scala:561)
> at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:258)
> at akka.dispatch.Mailbox.run(Mailbox.scala:225)
> at akka.dispatch.Mailbox.exec(Mailbox.scala:235)
> at akka.dispatch.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)
> at
> akka.dispatch.forkjoin.ForkJoinPool$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.IllegalArgumentException
> at
> org.apache.flink.util.Preconditions.checkArgument(Preconditions.java:126)
> at
> org.apache.flink.streaming.api.runners.python.beam.BeamPythonFunctionRunner.open(BeamPythonFunctionRunner.java:254)
> at
> org.apache.flink.streaming.api.operators.python.AbstractPythonFunctionOperator.open(AbstractPythonFunctionOperator.java:121)
> at
> org.apache.flink.table.runtime.operators.python.AbstractStatelessFunctionOperator.open(AbstractStatelessFunctionOperator.java:134)
> at
> org.apache.flink.table.runtime.operators.python.scalar.AbstractPythonScalarFunctionOperator.open(AbstractPythonScalarFunctionOperator.java:94)
> at
> org.apache.flink.table.runtime.operators.python.scalar.AbstractRowPythonScalarFunctionOperator.open(AbstractRowPythonScalarFunctionOperator.java:67)
> at
> org.apache.flink.table.runtime.operators.python.scalar.PythonScalarFunctionOperator.open(PythonScalarFunctionOperator.java:64)
> at
> org.apache.flink.streaming.runtime.tasks.OperatorChain.initializeStateAndOpenOperators(OperatorChain.java:401)
> at
> org.apache.flink.streaming.runtime.tasks.StreamTask.lambda$beforeInvoke$2(StreamTask.java:506)
> at
> org.apache.flink.streaming.runtime.tasks.StreamTaskActionExecutor$SynchronizedStreamTaskActionExecutor.runThrowing(StreamTaskActionExecutor.java:92)
> at
> org.apache.flink.streaming.runtime.tasks.StreamTask.beforeInvoke(StreamTask.java:501)
> at
> org.apache.flink.streaming.runtime.tasks.StreamTask.invoke(StreamTask.java:530)
> at org.apache.flink.runtime.taskmanager.Task.doRun(Task.java:722)
> at org.apache.flink.runtime.taskmanager.Task.run(Task.java:547)
> at java.lang.Thread.run(Thread.java:748)
> {code}
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
