AnnotatedConnectException: finishConnect(..) failed: Connection refused: localhost/0:0:0:0:0:0:0:1:53686 error when executing beam pipeline on flink - apache-kafka

Question

I'm trying to setup a go-beam-flink-kafka cluster locally. I started the kafka cluster along with producer. I then started expansion service which is required for cross language features of kafkaio api of beam go sdk on port 8097. Then, I started flink job server with the command docker run --platform linux/amd64 --net=host apache/beam_flink1.14_job_server:latest which starts it's own embedded flink cluster. Then, I write a simple pipeline to read from kafka and print the values as below.
type LogFn struct{}
func (fn *LogFn) ProcessElement(ctx context.Context, elm []byte) {
log.Infof(ctx, "Ride info: %v", string(elm))
}
//FinishBundle waits a bit so the job server finishes receiving logs.
func (fn *LogFn) FinishBundle() {
time.Sleep(2 * time.Second)
}
func init() {
register.DoFn2x0[context.Context, []byte](&LogFn{})
}
func main() {
flag.Parse()
beam.Init()
p, s := beam.NewPipelineWithRoot()
ctx := context.Background()
messages := kafkaio.Read(s,
"localhost:8097",
"localhost:9092",
[]string{"quickstart-events"},
)
vals := beam.DropKey(s, messages)
beam.ParDo0(s, &LogFn{}, vals)
if _, err := flink.Execute(ctx, p); err != nil {
log.Fatalf(ctx, "Failed to execute job: %v", err.Error())
}
}
Then, I start the execution of the pipeline with the command go run main.go --endpoint localhost:8099 --environment_type LOOPBACK. But I'm getting this error
SEVERE: Error during job invocation go0job0101666771397124223000-root-1026080321-9741bbf6_e2058fe0-971e-4b98-b96e-77d2cb52fee0.
org.apache.flink.runtime.client.JobExecutionException: Job execution failed.
at org.apache.flink.runtime.jobmaster.JobResult.toJobExecutionResult(JobResult.java:144)
at org.apache.flink.runtime.minicluster.MiniClusterJobClient.lambda$getJobExecutionResult$3(MiniClusterJobClient.java:137)
at java.util.concurrent.CompletableFuture.uniApply(CompletableFuture.java:616)
at java.util.concurrent.CompletableFuture$UniApply.tryFire(CompletableFuture.java:591)
at java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:488)
at java.util.concurrent.CompletableFuture.complete(CompletableFuture.java:1975)
at org.apache.flink.runtime.rpc.akka.AkkaInvocationHandler.lambda$invokeRpc$1(AkkaInvocationHandler.java:258)
at java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:774)
at java.util.concurrent.CompletableFuture$UniWhenComplete.tryFire(CompletableFuture.java:750)
at java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:488)
at java.util.concurrent.CompletableFuture.complete(CompletableFuture.java:1975)
at org.apache.flink.util.concurrent.FutureUtils.doForward(FutureUtils.java:1389)
at org.apache.flink.runtime.concurrent.akka.ClassLoadingUtils.lambda$null$1(ClassLoadingUtils.java:93)
at org.apache.flink.runtime.concurrent.akka.ClassLoadingUtils.runWithContextClassLoader(ClassLoadingUtils.java:68)
at org.apache.flink.runtime.concurrent.akka.ClassLoadingUtils.lambda$guardCompletionWithContextClassLoader$2(ClassLoadingUtils.java:92)
at java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:774)
at java.util.concurrent.CompletableFuture$UniWhenComplete.tryFire(CompletableFuture.java:750)
at java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:488)
at java.util.concurrent.CompletableFuture.complete(CompletableFuture.java:1975)
at org.apache.flink.runtime.concurrent.akka.AkkaFutureUtils$1.onComplete(AkkaFutureUtils.java:47)
at akka.dispatch.OnComplete.internal(Future.scala:300)
at akka.dispatch.OnComplete.internal(Future.scala:297)
at akka.dispatch.japi$CallbackBridge.apply(Future.scala:224)
at akka.dispatch.japi$CallbackBridge.apply(Future.scala:221)
at scala.concurrent.impl.CallbackRunnable.run(Promise.scala:60)
at org.apache.flink.runtime.concurrent.akka.AkkaFutureUtils$DirectExecutionContext.execute(AkkaFutureUtils.java:65)
at scala.concurrent.impl.CallbackRunnable.executeWithValue(Promise.scala:68)
at scala.concurrent.impl.Promise$DefaultPromise.$anonfun$tryComplete$1(Promise.scala:284)
at scala.concurrent.impl.Promise$DefaultPromise.$anonfun$tryComplete$1$adapted(Promise.scala:284)
at scala.concurrent.impl.Promise$DefaultPromise.tryComplete(Promise.scala:284)
at akka.pattern.PromiseActorRef.$bang(AskSupport.scala:621)
at akka.pattern.PipeToSupport$PipeableFuture$$anonfun$pipeTo$1.applyOrElse(PipeToSupport.scala:24)
at akka.pattern.PipeToSupport$PipeableFuture$$anonfun$pipeTo$1.applyOrElse(PipeToSupport.scala:23)
at scala.concurrent.Future.$anonfun$andThen$1(Future.scala:532)
at scala.concurrent.impl.Promise.liftedTree1$1(Promise.scala:29)
at scala.concurrent.impl.Promise.$anonfun$transform$1(Promise.scala:29)
at scala.concurrent.impl.CallbackRunnable.run(Promise.scala:60)
at akka.dispatch.BatchingExecutor$AbstractBatch.processBatch(BatchingExecutor.scala:63)
at akka.dispatch.BatchingExecutor$BlockableBatch.$anonfun$run$1(BatchingExecutor.scala:100)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:12)
at scala.concurrent.BlockContext$.withBlockContext(BlockContext.scala:81)
at akka.dispatch.BatchingExecutor$BlockableBatch.run(BatchingExecutor.scala:100)
at akka.dispatch.TaskInvocation.run(AbstractDispatcher.scala:49)
at akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(ForkJoinExecutorConfigurator.scala:48)
at java.util.concurrent.ForkJoinTask.doExec(ForkJoinTask.java:289)
at java.util.concurrent.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1056)
at java.util.concurrent.ForkJoinPool.runWorker(ForkJoinPool.java:1692)
at java.util.concurrent.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:175)
Caused by: org.apache.flink.runtime.JobException: Recovery is suppressed by NoRestartBackoffTimeStrategy
at org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.handleFailure(ExecutionFailureHandler.java:138)
at org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.getFailureHandlingResult(ExecutionFailureHandler.java:82)
at org.apache.flink.runtime.scheduler.DefaultScheduler.handleTaskFailure(DefaultScheduler.java:252)
at org.apache.flink.runtime.scheduler.DefaultScheduler.maybeHandleTaskFailure(DefaultScheduler.java:242)
at org.apache.flink.runtime.scheduler.DefaultScheduler.updateTaskExecutionStateInternal(DefaultScheduler.java:233)
at org.apache.flink.runtime.scheduler.SchedulerBase.updateTaskExecutionState(SchedulerBase.java:684)
at org.apache.flink.runtime.scheduler.SchedulerNG.updateTaskExecutionState(SchedulerNG.java:79)
at org.apache.flink.runtime.jobmaster.JobMaster.updateTaskExecutionState(JobMaster.java:444)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.lambda$handleRpcInvocation$1(AkkaRpcActor.java:316)
at org.apache.flink.runtime.concurrent.akka.ClassLoadingUtils.runWithContextClassLoader(ClassLoadingUtils.java:83)
at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcInvocation(AkkaRpcActor.java:314)
at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:217)
at org.apache.flink.runtime.rpc.akka.FencedAkkaRpcActor.handleRpcMessage(FencedAkkaRpcActor.java:78)
at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleMessage(AkkaRpcActor.java:163)
at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:24)
at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:20)
at scala.PartialFunction.applyOrElse(PartialFunction.scala:123)
at scala.PartialFunction.applyOrElse$(PartialFunction.scala:122)
at akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:20)
at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171)
at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:172)
at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:172)
at akka.actor.Actor.aroundReceive(Actor.scala:537)
at akka.actor.Actor.aroundReceive$(Actor.scala:535)
at akka.actor.AbstractActor.aroundReceive(AbstractActor.scala:220)
at akka.actor.ActorCell.receiveMessage(ActorCell.scala:580)
at akka.actor.ActorCell.invoke(ActorCell.scala:548)
at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:270)
at akka.dispatch.Mailbox.run(Mailbox.scala:231)
at akka.dispatch.Mailbox.exec(Mailbox.scala:243)
... 4 more
Caused by: org.apache.beam.vendor.guava.v26_0_jre.com.google.common.util.concurrent.UncheckedExecutionException: org.apache.beam.vendor.grpc.v1p48p1.io.grpc.StatusRuntimeException: UNAVAILABLE: io exception
at org.apache.beam.vendor.guava.v26_0_jre.com.google.common.cache.LocalCache$Segment.get(LocalCache.java:2050)
at org.apache.beam.vendor.guava.v26_0_jre.com.google.common.cache.LocalCache.get(LocalCache.java:3952)
at org.apache.beam.vendor.guava.v26_0_jre.com.google.common.cache.LocalCache.getOrLoad(LocalCache.java:3974)
at org.apache.beam.vendor.guava.v26_0_jre.com.google.common.cache.LocalCache$LocalLoadingCache.get(LocalCache.java:4958)
at org.apache.beam.vendor.guava.v26_0_jre.com.google.common.cache.LocalCache$LocalLoadingCache.getUnchecked(LocalCache.java:4964)
at org.apache.beam.runners.fnexecution.control.DefaultJobBundleFactory$SimpleStageBundleFactory.<init>(DefaultJobBundleFactory.java:451)
at org.apache.beam.runners.fnexecution.control.DefaultJobBundleFactory$SimpleStageBundleFactory.<init>(DefaultJobBundleFactory.java:436)
at org.apache.beam.runners.fnexecution.control.DefaultJobBundleFactory.forStage(DefaultJobBundleFactory.java:303)
at org.apache.beam.runners.fnexecution.control.DefaultExecutableStageContext.getStageBundleFactory(DefaultExecutableStageContext.java:38)
at org.apache.beam.runners.fnexecution.control.ReferenceCountingExecutableStageContextFactory$WrappedContext.getStageBundleFactory(ReferenceCountingExecutableStageContextFactory.java:202)
at org.apache.beam.runners.flink.translation.wrappers.streaming.ExecutableStageDoFnOperator.open(ExecutableStageDoFnOperator.java:248)
at org.apache.flink.streaming.runtime.tasks.RegularOperatorChain.initializeStateAndOpenOperators(RegularOperatorChain.java:110)
at org.apache.flink.streaming.runtime.tasks.StreamTask.restoreGates(StreamTask.java:711)
at org.apache.flink.streaming.runtime.tasks.StreamTaskActionExecutor$1.call(StreamTaskActionExecutor.java:55)
at org.apache.flink.streaming.runtime.tasks.StreamTask.restoreInternal(StreamTask.java:687)
at org.apache.flink.streaming.runtime.tasks.StreamTask.restore(StreamTask.java:654)
at org.apache.flink.runtime.taskmanager.Task.runWithSystemExitMonitoring(Task.java:958)
at org.apache.flink.runtime.taskmanager.Task.restoreAndInvoke(Task.java:927)
at org.apache.flink.runtime.taskmanager.Task.doRun(Task.java:766)
at org.apache.flink.runtime.taskmanager.Task.run(Task.java:575)
at java.lang.Thread.run(Thread.java:750)
Caused by: org.apache.beam.vendor.grpc.v1p48p1.io.grpc.StatusRuntimeException: UNAVAILABLE: io exception
at org.apache.beam.vendor.grpc.v1p48p1.io.grpc.stub.ClientCalls.toStatusRuntimeException(ClientCalls.java:271)
at org.apache.beam.vendor.grpc.v1p48p1.io.grpc.stub.ClientCalls.getUnchecked(ClientCalls.java:252)
at org.apache.beam.vendor.grpc.v1p48p1.io.grpc.stub.ClientCalls.blockingUnaryCall(ClientCalls.java:165)
at org.apache.beam.model.fnexecution.v1.BeamFnExternalWorkerPoolGrpc$BeamFnExternalWorkerPoolBlockingStub.startWorker(BeamFnExternalWorkerPoolGrpc.java:225)
at org.apache.beam.runners.fnexecution.environment.ExternalEnvironmentFactory.createEnvironment(ExternalEnvironmentFactory.java:113)
at org.apache.beam.runners.fnexecution.control.DefaultJobBundleFactory$1.load(DefaultJobBundleFactory.java:252)
at org.apache.beam.runners.fnexecution.control.DefaultJobBundleFactory$1.load(DefaultJobBundleFactory.java:231)
at org.apache.beam.vendor.guava.v26_0_jre.com.google.common.cache.LocalCache$LoadingValueReference.loadFuture(LocalCache.java:3528)
at org.apache.beam.vendor.guava.v26_0_jre.com.google.common.cache.LocalCache$Segment.loadSync(LocalCache.java:2277)
at org.apache.beam.vendor.guava.v26_0_jre.com.google.common.cache.LocalCache$Segment.lockedGetOrLoad(LocalCache.java:2154)
at org.apache.beam.vendor.guava.v26_0_jre.com.google.common.cache.LocalCache$Segment.get(LocalCache.java:2044)
... 20 more
Caused by: org.apache.beam.vendor.grpc.v1p48p1.io.netty.channel.AbstractChannel$AnnotatedConnectException: finishConnect(..) failed: Connection refused: localhost/0:0:0:0:0:0:0:1:53686
Caused by: java.net.ConnectException: finishConnect(..) failed: Connection refused
at org.apache.beam.vendor.grpc.v1p48p1.io.netty.channel.unix.Errors.newConnectException0(Errors.java:155)
at org.apache.beam.vendor.grpc.v1p48p1.io.netty.channel.unix.Errors.handleConnectErrno(Errors.java:128)
at org.apache.beam.vendor.grpc.v1p48p1.io.netty.channel.unix.Socket.finishConnect(Socket.java:321)
at org.apache.beam.vendor.grpc.v1p48p1.io.netty.channel.epoll.AbstractEpollChannel$AbstractEpollUnsafe.doFinishConnect(AbstractEpollChannel.java:710)
at org.apache.beam.vendor.grpc.v1p48p1.io.netty.channel.epoll.AbstractEpollChannel$AbstractEpollUnsafe.finishConnect(AbstractEpollChannel.java:687)
at org.apache.beam.vendor.grpc.v1p48p1.io.netty.channel.epoll.AbstractEpollChannel$AbstractEpollUnsafe.epollOutReady(AbstractEpollChannel.java:567)
at org.apache.beam.vendor.grpc.v1p48p1.io.netty.channel.epoll.EpollEventLoop.processReady(EpollEventLoop.java:477)
at org.apache.beam.vendor.grpc.v1p48p1.io.netty.channel.epoll.EpollEventLoop.run(EpollEventLoop.java:385)
at org.apache.beam.vendor.grpc.v1p48p1.io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:995)
at org.apache.beam.vendor.grpc.v1p48p1.io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74)
at org.apache.beam.vendor.grpc.v1p48p1.io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30)
at java.lang.Thread.run(Thread.java:750)
If anyone has setup the exact stack, can you help resolving this issue?