My objective is to run apache beam python sdk with a flink execution engine using flink runner. I am using latest flink cluster supported by beam(2.24) i.e. 1.10 and runner1.10. source is kafka topic. Looks like the translator of runner is trying to run a docker command inside container and it does not find it. Is this behavior normal? Below is the code and error that we get:
import apache_beam as beam
from apache_beam.options.pipeline_options import PipelineOptions
from apache_beam.io.external.kafka import ReadFromKafka, WriteToKafka
class Hl7ToFhirTransform(beam.DoFn):
def process(self,element):
#print("element:",element)
yield element
def main():
options = PipelineOptions(["--runner=FlinkRunner","--flink_version=1.10","--flink_master=x.x.x.x:8081","--streaming"])
with beam.Pipeline(options=options) as p:
dataFromKafka = p | ReadFromKafka(consumer_config={"bootstrap.servers":'x.x.x.x:19092'},topics=['testData'])
dataFromKafka | beam.ParDo(Hl7ToFhirTransform())
if __name__=="__main__":
main()
Error
2020-10-01 20:01:00
org.apache.flink.runtime.JobException: Recovery is suppressed by NoRestartBackoffTimeStrategy
at org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.handleFailure(ExecutionFailureHandler.java:110)
at org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.getFailureHandlingResult(ExecutionFailureHandler.java:76)
at org.apache.flink.runtime.scheduler.DefaultScheduler.handleTaskFailure(DefaultScheduler.java:192)
at org.apache.flink.runtime.scheduler.DefaultScheduler.maybeHandleTaskFailure(DefaultScheduler.java:186)
at org.apache.flink.runtime.scheduler.DefaultScheduler.updateTaskExecutionStateInternal(DefaultScheduler.java:180)
at org.apache.flink.runtime.scheduler.SchedulerBase.updateTaskExecutionState(SchedulerBase.java:496)
at org.apache.flink.runtime.jobmaster.JobMaster.updateTaskExecutionState(JobMaster.java:380)
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: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.applyOrElse(PartialFunction.scala:123)
at scala.PartialFunction.applyOrElse$(PartialFunction.scala:122)
at akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:21)
at scala.PartialFunction$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:517)
at akka.actor.Actor.aroundReceive$(Actor.scala:515)
at akka.actor.AbstractActor.aroundReceive(AbstractActor.scala:225)
at akka.actor.ActorCell.receiveMessage(ActorCell.scala:592)
at akka.actor.ActorCell.invoke(ActorCell.scala:561)
at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:258)
at akka.dispatch.Mailbox.run(Mailbox.scala:225)
at akka.dispatch.Mailbox.exec(Mailbox.scala:235)
at akka.dispatch.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)
at akka.dispatch.forkjoin.ForkJoinPool$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: org.apache.beam.vendor.guava.v26_0_jre.com.google.common.util.concurrent.UncheckedExecutionException: java.io.IOException: Cannot run program "docker": error=2, No such file or directory
at org.apache.beam.vendor.guava.v26_0_jre.com.google.common.cache.LocalCache$LocalLoadingCache.getUnchecked(LocalCache.java:4966)
at org.apache.beam.runners.fnexecution.control.DefaultJobBundleFactory$SimpleStageBundleFactory.<init>(DefaultJobBundleFactory.java:447)
at org.apache.beam.runners.fnexecution.control.DefaultJobBundleFactory$SimpleStageBundleFactory.<init>(DefaultJobBundleFactory.java:432)
at org.apache.beam.runners.fnexecution.control.DefaultJobBundleFactory.forStage(DefaultJobBundleFactory.java:299)
at org.apache.beam.runners.fnexecution.control.DefaultExecutableStageContext.getStageBundleFactory(DefaultExecutableStageContext.java:38)
at org.apache.beam.runners.fnexecution.control.ReferenceCountingExecutableStageContextFactory$WrappedContext.getStageBundleFactory(ReferenceCountingExecutableStageContextFactory.java:199)
at org.apache.beam.runners.flink.translation.wrappers.streaming.ExecutableStageDoFnOperator.open(ExecutableStageDoFnOperator.java:212)
at org.apache.flink.streaming.runtime.tasks.StreamTask.initializeStateAndOpen(StreamTask.java:990)
at org.apache.flink.streaming.runtime.tasks.StreamTask.lambda$beforeInvoke$0(StreamTask.java:453)
at org.apache.flink.streaming.runtime.tasks.StreamTaskActionExecutor$SynchronizedStreamTaskActionExecutor.runThrowing(StreamTaskActionExecutor.java:94)
at org.apache.flink.streaming.runtime.tasks.StreamTask.beforeInvoke(StreamTask.java:448)
at org.apache.flink.streaming.runtime.tasks.StreamTask.invoke(StreamTask.java:460)
at org.apache.flink.runtime.taskmanager.Task.doRun(Task.java:708)
at org.apache.flink.runtime.taskmanager.Task.run(Task.java:533)
at java.lang.Thread.run(Thread.java:748)
Caused by: java.io.IOException: Cannot run program "docker": error=2, No such file or directory
at java.lang.ProcessBuilder.start(ProcessBuilder.java:1048)
at org.apache.beam.runners.fnexecution.environment.DockerCommand.runShortCommand(DockerCommand.java:186)
at org.apache.beam.runners.fnexecution.environment.DockerCommand.runShortCommand(DockerCommand.java:168)
at org.apache.beam.runners.fnexecution.environment.DockerCommand.runImage(DockerCommand.java:92)
at org.apache.beam.runners.fnexecution.environment.DockerEnvironmentFactory.createEnvironment(DockerEnvironmentFactory.java:131)
at org.apache.beam.runners.fnexecution.control.DefaultJobBundleFactory$1.load(DefaultJobBundleFactory.java:248)
at org.apache.beam.runners.fnexecution.control.DefaultJobBundleFactory$1.load(DefaultJobBundleFactory.java:227)
at org.apache.beam.vendor.guava.v26_0_jre.com.google.common.cache.LocalCache$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$Segment.get(LocalCache.java:2044)
at org.apache.beam.vendor.guava.v26_0_jre.com.google.common.cache.LocalCache.get(LocalCache.java:3952)
at org.apache.beam.vendor.guava.v26_0_jre.com.google.common.cache.LocalCache.getOrLoad(LocalCache.java:3974)
at org.apache.beam.vendor.guava.v26_0_jre.com.google.common.cache.LocalCache$LocalLoadingCache.get(LocalCache.java:4958)
at org.apache.beam.vendor.guava.v26_0_jre.com.google.common.cache.LocalCache$LocalLoadingCache.getUnchecked(LocalCache.java:4964)
... 14 more
Caused by: java.io.IOException: error=2, No such file or directory
at java.lang.UNIXProcess.forkAndExec(Native Method)
at java.lang.UNIXProcess.<init>(UNIXProcess.java:247)
at java.lang.ProcessImpl.start(ProcessImpl.java:134)
at java.lang.ProcessBuilder.start(ProcessBuilder.java:1029)
... 28 more