I am trying to develop a test Flink application that reads from and writes to a Kafka topic.
However, I have been getting this error:
start writing data to kafka
Traceback (most recent call last):
File "teste.py", line 71, in <module>
write_to_kafka(env)
File "teste.py", line 45, in write_to_kafka
env.execute()
File "/Users/lauracorssac/miniconda3/envs/pyflink_38/lib/python3.8/site-packages/pyflink/datastream/stream_execution_environment.py", line 764, in execute
return JobExecutionResult(self._j_stream_execution_environment.execute(j_stream_graph))
File "/Users/lauracorssac/miniconda3/envs/pyflink_38/lib/python3.8/site-packages/py4j/java_gateway.py", line 1321, in __call__
return_value = get_return_value(
File "/Users/lauracorssac/miniconda3/envs/pyflink_38/lib/python3.8/site-packages/pyflink/util/exceptions.py", line 146, in deco
return f(*a, **kw)
File "/Users/lauracorssac/miniconda3/envs/pyflink_38/lib/python3.8/site-packages/py4j/protocol.py", line 326, in get_return_value
raise Py4JJavaError(
py4j.protocol.Py4JJavaError: An error occurred while calling o0.execute.
: 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$3(MiniClusterJobClient.java:141)
at java.util.concurrent.CompletableFuture.uniApply(CompletableFuture.java:616)
at java.util.concurrent.CompletableFuture$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$1(AkkaInvocationHandler.java:268)
at java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:774)
at java.util.concurrent.CompletableFuture$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:1277)
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$WorkQueue.runTask(ForkJoinPool.java:1056)
at java.util.concurrent.ForkJoinPool.runWorker(ForkJoinPool.java:1692)
at java.util.concurrent.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:175)
Caused by: org.apache.flink.runtime.JobException: Recovery is suppressed by NoRestartBackoffTimeStrategy
at org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.handleFailure(ExecutionFailureHandler.java:139)
at org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.getFailureHandlingResult(ExecutionFailureHandler.java:83)
at org.apache.flink.runtime.scheduler.DefaultScheduler.recordTaskFailure(DefaultScheduler.java:256)
at org.apache.flink.runtime.scheduler.DefaultScheduler.handleTaskFailure(DefaultScheduler.java:247)
at org.apache.flink.runtime.scheduler.DefaultScheduler.onTaskFailed(DefaultScheduler.java:240)
at org.apache.flink.runtime.scheduler.SchedulerBase.onTaskExecutionStateUpdate(SchedulerBase.java:738)
at org.apache.flink.runtime.scheduler.SchedulerBase.updateTaskExecutionState(SchedulerBase.java:715)
at org.apache.flink.runtime.scheduler.SchedulerNG.updateTaskExecutionState(SchedulerNG.java:78)
at org.apache.flink.runtime.jobmaster.JobMaster.updateTaskExecutionState(JobMaster.java:477)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.lambda$handleRpcInvocation$1(AkkaRpcActor.java:309)
at org.apache.flink.runtime.concurrent.akka.ClassLoadingUtils.runWithContextClassLoader(ClassLoadingUtils.java:83)
at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcInvocation(AkkaRpcActor.java:307)
at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:222)
at org.apache.flink.runtime.rpc.akka.FencedAkkaRpcActor.handleRpcMessage(FencedAkkaRpcActor.java:84)
at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleMessage(AkkaRpcActor.java:168)
at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:24)
at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:20)
at scala.PartialFunction.applyOrElse(PartialFunction.scala:123)
at scala.PartialFunction.applyOrElse$(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: java.lang.NoSuchMethodError: org.apache.flink.api.common.functions.RuntimeContext.getMetricGroup()Lorg/apache/flink/metrics/MetricGroup;
at org.apache.flink.streaming.connectors.kafka.FlinkKafkaProducer.initProducer(FlinkKafkaProducer.java:1365)
at org.apache.flink.streaming.connectors.kafka.FlinkKafkaProducer.initNonTransactionalProducer(FlinkKafkaProducer.java:1342)
at org.apache.flink.streaming.connectors.kafka.FlinkKafkaProducer.beginTransaction(FlinkKafkaProducer.java:990)
at org.apache.flink.streaming.connectors.kafka.FlinkKafkaProducer.beginTransaction(FlinkKafkaProducer.java:99)
at org.apache.flink.streaming.api.functions.sink.TwoPhaseCommitSinkFunction.beginTransactionInternal(TwoPhaseCommitSinkFunction.java:436)
at org.apache.flink.streaming.api.functions.sink.TwoPhaseCommitSinkFunction.initializeState(TwoPhaseCommitSinkFunction.java:427)
at org.apache.flink.streaming.connectors.kafka.FlinkKafkaProducer.initializeState(FlinkKafkaProducer.java:1195)
at org.apache.flink.streaming.util.functions.StreamingFunctionUtils.tryRestoreFunction(StreamingFunctionUtils.java:189)
at org.apache.flink.streaming.util.functions.StreamingFunctionUtils.restoreFunctionState(StreamingFunctionUtils.java:171)
at org.apache.flink.streaming.api.operators.AbstractUdfStreamOperator.initializeState(AbstractUdfStreamOperator.java:94)
at org.apache.flink.streaming.api.operators.StreamOperatorStateHandler.initializeOperatorState(StreamOperatorStateHandler.java:122)
at org.apache.flink.streaming.api.operators.AbstractStreamOperator.initializeState(AbstractStreamOperator.java:283)
at org.apache.flink.streaming.runtime.tasks.RegularOperatorChain.initializeStateAndOpenOperators(RegularOperatorChain.java:106)
at org.apache.flink.streaming.runtime.tasks.StreamTask.restoreGates(StreamTask.java:726)
at org.apache.flink.streaming.runtime.tasks.StreamTaskActionExecutor$1.call(StreamTaskActionExecutor.java:55)
at org.apache.flink.streaming.runtime.tasks.StreamTask.restoreInternal(StreamTask.java:702)
at org.apache.flink.streaming.runtime.tasks.StreamTask.restore(StreamTask.java:669)
at org.apache.flink.runtime.taskmanager.Task.runWithSystemExitMonitoring(Task.java:935)
at org.apache.flink.runtime.taskmanager.Task.restoreAndInvoke(Task.java:904)
at org.apache.flink.runtime.taskmanager.Task.doRun(Task.java:728)
at org.apache.flink.runtime.taskmanager.Task.run(Task.java:550)
at java.lang.Thread.run(Thread.java:748)
My code:
# Make sure that the Kafka cluster is started and the topic 'test_json_topic' is
# created before executing this job.
def write_to_kafka(env):
type_info = Types.ROW([Types.INT(), Types.STRING()])
ds = env.from_collection(
[(1, 'hi'), (2, 'hello'), (3, 'hi'), (4, 'hello'), (5, 'hi'), (6, 'hello'), (6, 'hello')],
type_info=type_info)
serialization_schema = JsonRowSerializationSchema.Builder() \
.with_type_info(type_info) \
.build()
kafka_producer = FlinkKafkaProducer(
topic='test_json_topic',
serialization_schema=serialization_schema,
producer_config={'bootstrap.servers': 'localhost:9092', 'group.id': 'test_group'}
)
# note that the output type of ds must be RowTypeInfo
ds.add_sink(kafka_producer)
env.execute()
def read_from_kafka(env):
deserialization_schema = JsonRowDeserializationSchema.Builder() \
.type_info(Types.ROW([Types.INT(), Types.STRING()])) \
.build()
kafka_consumer = FlinkKafkaConsumer(
topics='test_json_topic',
deserialization_schema=deserialization_schema,
properties={'bootstrap.servers': 'localhost:9092', 'group.id': 'test_group_1'}
)
kafka_consumer.set_start_from_earliest()
env.add_source(kafka_consumer).print()
env.execute('oi')
if __name__ == '__main__':
logging.basicConfig(stream=sys.stdout, level=logging.INFO, format="%(message)s")
env = StreamExecutionEnvironment.get_execution_environment()
env.add_jars("file:///Users/lauracorssac/HiWiProj/flink-connector-base-1.16.0.jar")
env.add_jars("file:///Users/lauracorssac/HiWiProj/flink-sql-connector-kafka-1.16.0.jar")
print("start writing data to kafka")
write_to_kafka(env)
print("start reading data from kafka")
read_from_kafka(env)
As the code shows, I tried to download many and different jars from the Maven repository. Nothing worked.
It turns out that only by explicitly adding flink-sql-connector-kafka-1.16.0.jar by:
env.add_jars("file:///Users/lauracorssac/HiWiProj/flink-sql-connector-kafka-1.16.0.jar")
was not enough. I had also to delete the version of the jar that comes with pyflink located at: /path/to/python/site-packages/pyflink/lib/.
In my case it was :
.../miniconda3/envs/pyflink_38/lib/python3.8/site-packages/pyflink/lib/flink-sql-connector-kafka_2.11-1.13.0.jar
Also, do not forget to set Java version to 1.8. I was having this issue as well. Hope it helps someone!