You are viewing a plain text version of this content. The canonical link for it is here.
Posted to user-zh@flink.apache.org by chanamper <ch...@163.com> on 2019/12/15 13:55:11 UTC

Flink运行一段时间后出现异常重启

请教一下,flink采用1.8.0版本,任务运行一段时间后出现AskTimeoutException异常,之后flink状态由Running转Failed,紧接着出现FlinkKafkaException:Failed to send data to kafka失败,任务定期出现这种异常重启。请教一下,这种通常有什么问题导致的呀,应该如何排除处理?


2019-12-15 19:25:14,954 WARN  org.apache.flink.runtime.rest.handler.legacy.metrics.MetricFetcherImpl  - Requesting TaskManager's path for query services failed.
java.util.concurrent.CompletionException: akka.pattern.AskTimeoutException: Ask timed out on [Actor[akka://flink/user/dispatcher#-587518171]] after [10000 ms]. Sender[null] sent message of type "org.apache.flink.runtime.rpc.messages.LocalFencedMessage".
        at java.util.concurrent.CompletableFuture.encodeThrowable(CompletableFuture.java:292)
        at java.util.concurrent.CompletableFuture.completeThrowable(CompletableFuture.java:308)
        at java.util.concurrent.CompletableFuture.uniApply(CompletableFuture.java:593)
        at java.util.concurrent.CompletableFuture$UniApply.tryFire(CompletableFuture.java:577)
        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$1.onComplete(FutureUtils.java:815)
        at akka.dispatch.OnComplete.internal(Future.scala:258)
        at akka.dispatch.OnComplete.internal(Future.scala:256)
        at akka.dispatch.japi$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:74)
        at scala.concurrent.impl.CallbackRunnable.executeWithValue(Promise.scala:44)
        at scala.concurrent.impl.Promise$DefaultPromise.tryComplete(Promise.scala:252)
        at akka.pattern.PromiseActorRef$$anonfun$1.apply$mcV$sp(AskSupport.scala:603)
        at akka.actor.Scheduler$$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$$anon$4.run(LightArrayRevolverScheduler.scala:236)
        at java.lang.Thread.run(Thread.java:748)
Caused by: akka.pattern.AskTimeoutException: Ask timed out on [Actor[akka://flink/user/dispatcher#-587518171]] after [10000 ms]. Sender[null] sent message of type "org.apache.flink.runtime.rpc.messages.LocalFencedMessage".
        at akka.pattern.PromiseActorRef$$anonfun$1.apply$mcV$sp(AskSupport.scala:604)
        ... 9 more
2019-12-15 19:29:24,815 INFO  org.apache.flink.runtime.executiongraph.ExecutionGraph        - Window(SlidingProcessingTimeWindows(1200000, 300000), TkEventTimeTrigger, TkProcessWindowFunction) -> Sink: 98___2019-12-12.15:48:59.736577 (5/12) (6819729aa4e1a7966cd65e69cd125eea) switched from RUNNING to FAILED.
org.apache.flink.streaming.connectors.kafka.FlinkKafkaException: Failed to send data to Kafka: Expiring 1 record(s) for sink_98-4: 47883 ms has passed since batch creation plus linger time
        at org.apache.flink.streaming.connectors.kafka.FlinkKafkaProducer.checkErroneous(FlinkKafkaProducer.java:1002)
        at org.apache.flink.streaming.connectors.kafka.FlinkKafkaProducer.invoke(FlinkKafkaProducer.java:619)
        at org.apache.flink.streaming.connectors.kafka.FlinkKafkaProducer.invoke(FlinkKafkaProducer.java:97)
        at org.apache.flink.streaming.api.functions.sink.TwoPhaseCommitSinkFunction.invoke(TwoPhaseCommitSinkFunction.java:228)
        at org.apache.flink.streaming.api.operators.StreamSink.processElement(StreamSink.java:56)
        at org.apache.flink.streaming.runtime.tasks.OperatorChain$CopyingChainingOutput.pushToOperator(OperatorChain.java:579)
        at org.apache.flink.streaming.runtime.tasks.OperatorChain$CopyingChainingOutput.collect(OperatorChain.java:554)
        at org.apache.flink.streaming.runtime.tasks.OperatorChain$CopyingChainingOutput.collect(OperatorChain.java:534)
        at org.apache.flink.streaming.api.operators.AbstractStreamOperator$CountingOutput.collect(AbstractStreamOperator.java:718)
        at org.apache.flink.streaming.api.operators.AbstractStreamOperator$CountingOutput.collect(AbstractStreamOperator.java:696)
        at org.apache.flink.streaming.api.operators.TimestampedCollector.collect(TimestampedCollector.java:51)
        at com.tencent.sec.tlink.op.TkProcessWindowFunction.process(TkProcessWindowFunction.java:102)
        at com.tencent.sec.tlink.op.TkProcessWindowFunction.process(TkProcessWindowFunction.java:35)
        at org.apache.flink.streaming.runtime.operators.windowing.functions.InternalIterableProcessWindowFunction.process(InternalIterableProcessWindowFunction.java:50)
        at org.apache.flink.streaming.runtime.operators.windowing.functions.InternalIterableProcessWindowFunction.process(InternalIterableProcessWindowFunction.java:32)
        at org.apache.flink.streaming.runtime.operators.windowing.WindowOperator.emitWindowContents(WindowOperator.java:546)
        at org.apache.flink.streaming.runtime.operators.windowing.WindowOperator.processElement(WindowOperator.java:403)
        at org.apache.flink.streaming.runtime.io.StreamInputProcessor.processInput(StreamInputProcessor.java:202)
        at org.apache.flink.streaming.runtime.tasks.OneInputStreamTask.run(OneInputStreamTask.java:105)
        at org.apache.flink.streaming.runtime.tasks.StreamTask.invoke(StreamTask.java:300)
        at org.apache.flink.runtime.taskmanager.Task.run(Task.java:711)
        at java.lang.Thread.run(Thread.java:748)
Caused by: org.apache.kafka.common.errors.TimeoutException: Expiring 1 record(s) for sink_98-4: 47883 ms has passed since batch creation plus linger time
2019-12-15 19:29:24,815 INFO  org.apache.flink.runtime.executiongraph.ExecutionGraph        - Job tlink<98><98___2019-12-12.15:48:59.736577> (45d316df2a701327b81903bae101b8e7) switched from state RUNNING to FAILING.
org.apache.flink.streaming.connectors.kafka.FlinkKafkaException: Failed to send data to Kafka: Expiring 1 record(s) for sink_98-4: 47883 ms has passed since batch creation plus linger time
        at org.apache.flink.streaming.connectors.kafka.FlinkKafkaProducer.checkErroneous(FlinkKafkaProducer.java:1002)
        at org.apache.flink.streaming.connectors.kafka.FlinkKafkaProducer.invoke(FlinkKafkaProducer.java:619)
        at org.apache.flink.streaming.connectors.kafka.FlinkKafkaProducer.invoke(FlinkKafkaProducer.java:97)
        at org.apache.flink.streaming.api.functions.sink.TwoPhaseCommitSinkFunction.invoke(TwoPhaseCommitSinkFunction.java:228)
        at org.apache.flink.streaming.api.operators.StreamSink.processElement(StreamSink.java:56)
        at org.apache.flink.streaming.runtime.tasks.OperatorChain$CopyingChainingOutput.pushToOperator(OperatorChain.java:579)
        at org.apache.flink.streaming.runtime.tasks.OperatorChain$CopyingChainingOutput.collect(OperatorChain.java:554)
        at org.apache.flink.streaming.runtime.tasks.OperatorChain$CopyingChainingOutput.collect(OperatorChain.java:534)
        at org.apache.flink.streaming.api.operators.AbstractStreamOperator$CountingOutput.collect(AbstractStreamOperator.java:718)
        at org.apache.flink.streaming.api.operators.AbstractStreamOperator$CountingOutput.collect(AbstractStreamOperator.java:696)
        at org.apache.flink.streaming.api.operators.TimestampedCollector.collect(TimestampedCollector.java:51)
        at com.tencent.sec.tlink.op.TkProcessWindowFunction.process(TkProcessWindowFunction.java:102)
        at com.tencent.sec.tlink.op.TkProcessWindowFunction.process(TkProcessWindowFunction.java:35)
        at org.apache.flink.streaming.runtime.operators.windowing.functions.InternalIterableProcessWindowFunction.process(InternalIterableProcessWindowFunction.java:50)
        at org.apache.flink.streaming.runtime.operators.windowing.functions.InternalIterableProcessWindowFunction.process(InternalIterableProcessWindowFunction.java:32)
        at org.apache.flink.streaming.runtime.operators.windowing.WindowOperator.emitWindowContents(WindowOperator.java:546)
        at org.apache.flink.streaming.runtime.operators.windowing.WindowOperator.processElement(WindowOperator.java:403)
        at org.apache.flink.streaming.runtime.io.StreamInputProcessor.processInput(StreamInputProcessor.java:202)
        at org.apache.flink.streaming.runtime.tasks.OneInputStreamTask.run(OneInputStreamTask.java:105)
        at org.apache.flink.streaming.runtime.tasks.StreamTask.invoke(StreamTask.java:300)
        at org.apache.flink.runtime.taskmanager.Task.run(Task.java:711)
        at java.lang.Thread.run(Thread.java:748)
Caused by: org.apache.kafka.common.errors.TimeoutException: Expiring 1 record(s) for sink_98-4: 47883 ms has passed since batch creation plus linger time