526互联

flink Connecting to remote task manager 'localhost/127.0.0.1:44489

发布时间 2023-05-08 21:55:00作者: aminor

问题：
启动集群后，执行任务时失败：

Caused by: org.apache.flink.runtime.io.network.partition.consumer.PartitionConnectionException: Connection for partition 47d4a412246bdbbc3447e1968e07c821#1@04049d45261135a1a8bae9c8f62a1ba4_0a448493b4782967b150582570326227_1_0 not reachable.
	at org.apache.flink.runtime.io.network.partition.consumer.RemoteInputChannel.requestSubpartition(RemoteInputChannel.java:190)
	at org.apache.flink.runtime.io.network.partition.consumer.SingleInputGate.internalRequestPartitions(SingleInputGate.java:342)
	at org.apache.flink.runtime.io.network.partition.consumer.SingleInputGate.requestPartitions(SingleInputGate.java:312)
	at org.apache.flink.runtime.taskmanager.InputGateWithMetrics.requestPartitions(InputGateWithMetrics.java:115)
	at org.apache.flink.streaming.runtime.tasks.StreamTaskActionExecutor$1.runThrowing(StreamTaskActionExecutor.java:50)
	at org.apache.flink.streaming.runtime.tasks.mailbox.Mail.run(Mail.java:90)
	at org.apache.flink.streaming.runtime.tasks.mailbox.MailboxProcessor.runMail(MailboxProcessor.java:398)
	at org.apache.flink.streaming.runtime.tasks.mailbox.MailboxProcessor.processMailsNonBlocking(MailboxProcessor.java:383)
	at org.apache.flink.streaming.runtime.tasks.mailbox.MailboxProcessor.processMail(MailboxProcessor.java:345)
	at org.apache.flink.streaming.runtime.tasks.mailbox.MailboxProcessor.runMailboxLoop(MailboxProcessor.java:229)
	at org.apache.flink.streaming.runtime.tasks.StreamTask.runMailboxLoop(StreamTask.java:839)
	at org.apache.flink.streaming.runtime.tasks.StreamTask.invoke(StreamTask.java:788)
	at org.apache.flink.runtime.taskmanager.Task.runWithSystemExitMonitoring(Task.java:952)
	at org.apache.flink.runtime.taskmanager.Task.restoreAndInvoke(Task.java:931)
	at org.apache.flink.runtime.taskmanager.Task.doRun(Task.java:745)
	at org.apache.flink.runtime.taskmanager.Task.run(Task.java:562)
	at java.base/java.lang.Thread.run(Thread.java:834)
Caused by: org.apache.flink.runtime.io.network.netty.exception.RemoteTransportException: Connecting to remote task manager 'localhost/127.0.0.1:44489 [ localhost:43648-584bc2 ] ' has failed. This might indicate that the remote task manager has been lost.
	at org.apache.flink.runtime.io.network.netty.PartitionRequestClientFactory.connect(PartitionRequestClientFactory.java:173)
	at org.apache.flink.runtime.io.network.netty.PartitionRequestClientFactory.connectWithRetries(PartitionRequestClientFactory.java:136)
	at org.apache.flink.runtime.io.network.netty.PartitionRequestClientFactory.createPartitionRequestClient(PartitionRequestClientFactory.java:97)
	at org.apache.flink.runtime.io.network.netty.NettyConnectionManager.createPartitionRequestClient(NettyConnectionManager.java:95)
	at org.apache.flink.runtime.io.network.partition.consumer.RemoteInputChannel.requestSubpartition(RemoteInputChannel.java:186)
	... 16 more
Caused by: org.apache.flink.shaded.netty4.io.netty.channel.AbstractChannel$AnnotatedConnectException: finishConnect(..) failed: 拒绝连接: localhost/127.0.0.1:44489
Caused by: java.net.ConnectException: finishConnect(..) failed: 拒绝连接
	at org.apache.flink.shaded.netty4.io.netty.channel.unix.Errors.newConnectException0(Errors.java:155)
	at org.apache.flink.shaded.netty4.io.netty.channel.unix.Errors.handleConnectErrno(Errors.java:128)
	at org.apache.flink.shaded.netty4.io.netty.channel.unix.Socket.finishConnect(Socket.java:359)
	at org.apache.flink.shaded.netty4.io.netty.channel.epoll.AbstractEpollChannel$AbstractEpollUnsafe.doFinishConnect(AbstractEpollChannel.java:710)
	at org.apache.flink.shaded.netty4.io.netty.channel.epoll.AbstractEpollChannel$AbstractEpollUnsafe.finishConnect(AbstractEpollChannel.java:687)
	at org.apache.flink.shaded.netty4.io.netty.channel.epoll.AbstractEpollChannel$AbstractEpollUnsafe.epollOutReady(AbstractEpollChannel.java:567)
	at org.apache.flink.shaded.netty4.io.netty.channel.epoll.EpollEventLoop.processReady(EpollEventLoop.java:489)
	at org.apache.flink.shaded.netty4.io.netty.channel.epoll.EpollEventLoop.run(EpollEventLoop.java:397)
	at org.apache.flink.shaded.netty4.io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:997)
	at org.apache.flink.shaded.netty4.io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74)
	at java.base/java.lang.Thread.run(Thread.java:834)

解决方案：
[flink-conf.yaml]

jobmanager.rpc.address: centos001
jobmanager.rpc.port: 6123
jobmanager.bind-host: 0.0.0.0
jobmanager.memory.process.size: 1600m
taskmanager.bind-host: 0.0.0.0
# taskmanager.host: localhost 修改为本机ip
taskmanager.host: centos002
taskmanager.memory.process.size: 1728m
taskmanager.numberOfTaskSlots: 1
parallelism.default: 1
jobmanager.execution.failover-strategy: region
rest.address: localhost
rest.bind-address: 0.0.0.0