Flink报错Could not perform checkpoint（kafka数据大小限制kafka.max.request.size配置扩大）

定位到：

The request included a message larger than the max message size the server will accept.

 原文：

2022-06-23 17:09:05
org.apache.flink.runtime.JobException: Recovery is suppressed by FixedDelayRestartBackoffTimeStrategy(maxNumberRestartAttempts=20, backoffTimeMS=10000)
	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:192)
	at org.apache.flink.runtime.scheduler.DefaultScheduler.maybeHandleTaskFailure(DefaultScheduler.java:185)
	at org.apache.flink.runtime.scheduler.DefaultScheduler.updateTaskExecutionStateInternal(DefaultScheduler.java:179)
	at org.apache.flink.runtime.scheduler.SchedulerBase.updateTaskExecutionState(SchedulerBase.java:503)
	at org.apache.flink.runtime.jobmaster.JobMaster.updateTaskExecutionState(JobMaster.java:386)
	at sun.reflect.GeneratedMethodAccessor43.invoke(Unknown Source)
	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:284)
	at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:199)
	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$class.applyOrElse(PartialFunction.scala:123)
	at akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:21)
	at scala.PartialFunction$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.io.IOException: Could not perform checkpoint 1702 for operator 格式解析 -> (Filter -> Map -> Sink: WriteKafka(logbad), Filter -> Map -> Sink: WriteKafka(logfmt)) (4/5).
	at org.apache.flink.streaming.runtime.tasks.StreamTask.triggerCheckpointOnBarrier(StreamTask.java:892)
	at org.apache.flink.streaming.runtime.io.CheckpointBarrierHandler.notifyCheckpoint(CheckpointBarrierHandler.java:113)
	at org.apache.flink.streaming.runtime.io.CheckpointBarrierAligner.processBarrier(CheckpointBarrierAligner.java:198)
	at org.apache.flink.streaming.runtime.io.CheckpointedInputGate.pollNext(CheckpointedInputGate.java:93)
	at org.apache.flink.streaming.runtime.io.StreamTaskNetworkInput.emitNext(StreamTaskNetworkInput.java:158)
	at org.apache.flink.streaming.runtime.io.StreamTwoInputProcessor.processInput(StreamTwoInputProcessor.java:179)
	at org.apache.flink.streaming.runtime.tasks.StreamTask.processInput(StreamTask.java:351)
	at org.apache.flink.streaming.runtime.tasks.mailbox.MailboxProcessor.runMailboxStep(MailboxProcessor.java:191)
	at org.apache.flink.streaming.runtime.tasks.mailbox.MailboxProcessor.runMailboxLoop(MailboxProcessor.java:181)
	at org.apache.flink.streaming.runtime.tasks.StreamTask.runMailboxLoop(StreamTask.java:566)
	at org.apache.flink.streaming.runtime.tasks.StreamTask.invoke(StreamTask.java:536)
	at org.apache.flink.runtime.taskmanager.Task.doRun(Task.java:721)
	at org.apache.flink.runtime.taskmanager.Task.run(Task.java:546)
	at java.lang.Thread.run(Thread.java:748)
	Suppressed: java.lang.NoSuchMethodError: org.apache.kafka.clients.producer.KafkaProducer.close(Ljava/time/Duration;)V
		at org.apache.flink.streaming.connectors.kafka.internal.FlinkKafkaInternalProducer.close(FlinkKafkaInternalProducer.java:170)
		at org.apache.flink.streaming.connectors.kafka.FlinkKafkaProducer.close(FlinkKafkaProducer.java:894)
		at org.apache.flink.api.common.functions.util.FunctionUtils.closeFunction(FunctionUtils.java:43)
		at org.apache.flink.streaming.api.operators.AbstractUdfStreamOperator.dispose(AbstractUdfStreamOperator.java:117)
		at org.apache.flink.streaming.runtime.tasks.StreamTask.disposeAllOperators(StreamTask.java:729)
		at org.apache.flink.streaming.runtime.tasks.StreamTask.cleanUpInvoke(StreamTask.java:645)
		at org.apache.flink.streaming.runtime.tasks.StreamTask.invoke(StreamTask.java:549)
		... 3 more
Caused by: org.apache.flink.runtime.checkpoint.CheckpointException: Could not complete snapshot 1702 for operator 格式解析 -> (Filter -> Map -> Sink: WriteKafka(logbad), Filter -> Map -> Sink: WriteKafka(logfmt)) (4/5). Failure reason: Checkpoint was declined.
	at org.apache.flink.streaming.api.operators.StreamOperatorStateHandler.snapshotState(StreamOperatorStateHandler.java:215)
	at org.apache.flink.streaming.api.operators.StreamOperatorStateHandler.snapshotState(StreamOperatorStateHandler.java:156)
	at org.apache.flink.streaming.api.operators.AbstractStreamOperator.snapshotState(AbstractStreamOperator.java:314)
	at org.apache.flink.streaming.runtime.tasks.SubtaskCheckpointCoordinatorImpl.checkpointStreamOperator(SubtaskCheckpointCoordinatorImpl.java:614)
	at org.apache.flink.streaming.runtime.tasks.SubtaskCheckpointCoordinatorImpl.buildOperatorSnapshotFutures(SubtaskCheckpointCoordinatorImpl.java:540)
	at org.apache.flink.streaming.runtime.tasks.SubtaskCheckpointCoordinatorImpl.takeSnapshotSync(SubtaskCheckpointCoordinatorImpl.java:507)
	at org.apache.flink.streaming.runtime.tasks.SubtaskCheckpointCoordinatorImpl.checkpointState(SubtaskCheckpointCoordinatorImpl.java:266)
	at org.apache.flink.streaming.runtime.tasks.StreamTask.lambda$performCheckpoint$8(StreamTask.java:921)
	at org.apache.flink.streaming.runtime.tasks.StreamTaskActionExecutor$1.runThrowing(StreamTaskActionExecutor.java:47)
	at org.apache.flink.streaming.runtime.tasks.StreamTask.performCheckpoint(StreamTask.java:911)
	at org.apache.flink.streaming.runtime.tasks.StreamTask.triggerCheckpointOnBarrier(StreamTask.java:879)
	... 13 more
Caused by: org.apache.flink.streaming.connectors.kafka.FlinkKafkaException: Failed to send data to Kafka: The request included a message larger than the max message size the server will accept.
	at org.apache.flink.streaming.connectors.kafka.FlinkKafkaProducer.checkErroneous(FlinkKafkaProducer.java:1282)
	at org.apache.flink.streaming.connectors.kafka.FlinkKafkaProducer.flush(FlinkKafkaProducer.java:1042)
	at org.apache.flink.streaming.connectors.kafka.FlinkKafkaProducer.preCommit(FlinkKafkaProducer.java:951)
	at org.apache.flink.streaming.connectors.kafka.FlinkKafkaProducer.preCommit(FlinkKafkaProducer.java:99)
	at org.apache.flink.streaming.api.functions.sink.TwoPhaseCommitSinkFunction.snapshotState(TwoPhaseCommitSinkFunction.java:321)
	at org.apache.flink.streaming.connectors.kafka.FlinkKafkaProducer.snapshotState(FlinkKafkaProducer.java:1047)
	at org.apache.flink.streaming.util.functions.StreamingFunctionUtils.trySnapshotFunctionState(StreamingFunctionUtils.java:120)
	at org.apache.flink.streaming.util.functions.StreamingFunctionUtils.snapshotFunctionState(StreamingFunctionUtils.java:101)
	at org.apache.flink.streaming.api.operators.AbstractUdfStreamOperator.snapshotState(AbstractUdfStreamOperator.java:90)
	at org.apache.flink.streaming.api.operators.StreamOperatorStateHandler.snapshotState(StreamOperatorStateHandler.java:186)
	... 23 more
Caused by: org.apache.kafka.common.errors.RecordTooLargeException: The request included a message larger than the max message size the server will accept.

解决方案：

        按照客户实际日志大小修改kafka配置。