CODEWITHSUNDEEP
apache-sparkpyspark
Simone
Simone

Reputation: 4940

Error: " Python worker failed to connect back" when fit() function is called

I am trying to train an ANNfor text classification:

mlp = MultilayerPerceptronClassifier(maxIter=10, layers=[5,3], blockSize=128, seed=123)
model_stacking = mlp.fit(input_vector.select(['features', 'label']))
preditions_foo = model_stacking.transform(validation)
predition = evaluator.evaluate(preditions_foo)

When the fit() function is applied, I get this error:

C:\Users\Simone\Desktop\Università\BigData\Spark\spark-2.4.0-bin-hadoop2.7\python\pyspark\ml\base.py in fit(self, dataset, params)
    130                 return self.copy(params)._fit(dataset)
    131             else:
--> 132                 return self._fit(dataset)
    133         else:
    134             raise ValueError("Params must be either a param map or a list/tuple of param maps, "

C:\Users\Simone\Desktop\Università\BigData\Spark\spark-2.4.0-bin-hadoop2.7\python\pyspark\ml\wrapper.py in _fit(self, dataset)
    293 
    294     def _fit(self, dataset):
--> 295         java_model = self._fit_java(dataset)
    296         model = self._create_model(java_model)
    297         return self._copyValues(model)

C:\Users\Simone\Desktop\Università\BigData\Spark\spark-2.4.0-bin-hadoop2.7\python\pyspark\ml\wrapper.py in _fit_java(self, dataset)
    290         """
    291         self._transfer_params_to_java()
--> 292         return self._java_obj.fit(dataset._jdf)
    293 
    294     def _fit(self, dataset):

C:\Users\Simone\Desktop\Università\BigData\Spark\spark-2.4.0-bin-hadoop2.7\python\lib\py4j-0.10.7-src.zip\py4j\java_gateway.py in __call__(self, *args)
   1255         answer = self.gateway_client.send_command(command)
   1256         return_value = get_return_value(
-> 1257             answer, self.gateway_client, self.target_id, self.name)
   1258 
   1259         for temp_arg in temp_args:

C:\Users\Simone\Desktop\Università\BigData\Spark\spark-2.4.0-bin-hadoop2.7\python\pyspark\sql\utils.py in deco(*a, **kw)
     61     def deco(*a, **kw):
     62         try:
---> 63             return f(*a, **kw)
     64         except py4j.protocol.Py4JJavaError as e:
     65             s = e.java_exception.toString()

C:\Users\Simone\Desktop\Università\BigData\Spark\spark-2.4.0-bin-hadoop2.7\python\lib\py4j-0.10.7-src.zip\py4j\protocol.py in get_return_value(answer, gateway_client, target_id, name)
    326                 raise Py4JJavaError(
    327                     "An error occurred while calling {0}{1}{2}.\n".
--> 328                     format(target_id, ".", name), value)
    329             else:
    330                 raise Py4JError(

Py4JJavaError: An error occurred while calling o2602.fit.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 2 in stage 414.0 failed 1 times, most recent failure: Lost task 2.0 in stage 414.0 (TID 32375, localhost, executor driver): org.apache.spark.SparkException: Python worker failed to connect back.
    at org.apache.spark.api.python.PythonWorkerFactory.createSimpleWorker(PythonWorkerFactory.scala:170)
    at org.apache.spark.api.python.PythonWorkerFactory.create(PythonWorkerFactory.scala:97)
    at org.apache.spark.SparkEnv.createPythonWorker(SparkEnv.scala:117)
    at org.apache.spark.api.python.BasePythonRunner.compute(PythonRunner.scala:108)
    at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:65)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
    at org.apache.spark.rdd.RDD$$anonfun$7.apply(RDD.scala:337)
    at org.apache.spark.rdd.RDD$$anonfun$7.apply(RDD.scala:335)
    at org.apache.spark.storage.BlockManager$$anonfun$doPutIterator$1.apply(BlockManager.scala:1165)
    at org.apache.spark.storage.BlockManager$$anonfun$doPutIterator$1.apply(BlockManager.scala:1156)
    at org.apache.spark.storage.BlockManager.doPut(BlockManager.scala:1091)
    at org.apache.spark.storage.BlockManager.doPutIterator(BlockManager.scala:1156)
    at org.apache.spark.storage.BlockManager.getOrElseUpdate(BlockManager.scala:882)
    at org.apache.spark.rdd.RDD.getOrCompute(RDD.scala:335)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:286)
    at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
    at org.apache.spark.scheduler.Task.run(Task.scala:121)
    at org.apache.spark.executor.Executor$TaskRunner$$anonfun$10.apply(Executor.scala:402)
    at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1360)
    at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:408)
    at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
    at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
    at java.lang.Thread.run(Unknown Source)
Caused by: java.net.SocketTimeoutException: Accept timed out
    at java.net.DualStackPlainSocketImpl.waitForNewConnection(Native Method)
    at java.net.DualStackPlainSocketImpl.socketAccept(Unknown Source)
    at java.net.AbstractPlainSocketImpl.accept(Unknown Source)
    at java.net.PlainSocketImpl.accept(Unknown Source)
    at java.net.ServerSocket.implAccept(Unknown Source)
    at java.net.ServerSocket.accept(Unknown Source)
    at org.apache.spark.api.python.PythonWorkerFactory.createSimpleWorker(PythonWorkerFactory.scala:164)
    ... 52 more

Driver stacktrace:
    at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1887)
    at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1875)
    at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1874)
    at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
    at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
    at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1874)
    at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:926)
    at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:926)
    at scala.Option.foreach(Option.scala:257)
    at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:926)
    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2108)
    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2057)
    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2046)
    at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
    at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:737)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:2061)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:2082)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:2101)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:2126)
    at org.apache.spark.rdd.RDD.count(RDD.scala:1168)
    at org.apache.spark.mllib.optimization.LBFGS$.runLBFGS(LBFGS.scala:195)
    at org.apache.spark.mllib.optimization.LBFGS.optimize(LBFGS.scala:142)
    at org.apache.spark.ml.ann.FeedForwardTrainer.train(Layer.scala:854)
    at org.apache.spark.ml.classification.MultilayerPerceptronClassifier$$anonfun$train$1.apply(MultilayerPerceptronClassifier.scala:249)
    at org.apache.spark.ml.classification.MultilayerPerceptronClassifier$$anonfun$train$1.apply(MultilayerPerceptronClassifier.scala:205)
    at org.apache.spark.ml.util.Instrumentation$$anonfun$11.apply(Instrumentation.scala:183)
    at scala.util.Try$.apply(Try.scala:192)
    at org.apache.spark.ml.util.Instrumentation$.instrumented(Instrumentation.scala:183)
    at org.apache.spark.ml.classification.MultilayerPerceptronClassifier.train(MultilayerPerceptronClassifier.scala:205)
    at org.apache.spark.ml.classification.MultilayerPerceptronClassifier.train(MultilayerPerceptronClassifier.scala:114)
    at org.apache.spark.ml.Predictor.fit(Predictor.scala:118)
    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
    at sun.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
    at java.lang.reflect.Method.invoke(Unknown Source)
    at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
    at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
    at py4j.Gateway.invoke(Gateway.java:282)
    at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
    at py4j.commands.CallCommand.execute(CallCommand.java:79)
    at py4j.GatewayConnection.run(GatewayConnection.java:238)
    at java.lang.Thread.run(Unknown Source)
Caused by: org.apache.spark.SparkException: Python worker failed to connect back.
    at org.apache.spark.api.python.PythonWorkerFactory.createSimpleWorker(PythonWorkerFactory.scala:170)
    at org.apache.spark.api.python.PythonWorkerFactory.create(PythonWorkerFactory.scala:97)
    at org.apache.spark.SparkEnv.createPythonWorker(SparkEnv.scala:117)
    at org.apache.spark.api.python.BasePythonRunner.compute(PythonRunner.scala:108)
    at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:65)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
    at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
    at org.apache.spark.rdd.RDD$$anonfun$7.apply(RDD.scala:337)
    at org.apache.spark.rdd.RDD$$anonfun$7.apply(RDD.scala:335)
    at org.apache.spark.storage.BlockManager$$anonfun$doPutIterator$1.apply(BlockManager.scala:1165)
    at org.apache.spark.storage.BlockManager$$anonfun$doPutIterator$1.apply(BlockManager.scala:1156)
    at org.apache.spark.storage.BlockManager.doPut(BlockManager.scala:1091)
    at org.apache.spark.storage.BlockManager.doPutIterator(BlockManager.scala:1156)
    at org.apache.spark.storage.BlockManager.getOrElseUpdate(BlockManager.scala:882)
    at org.apache.spark.rdd.RDD.getOrCompute(RDD.scala:335)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:286)
    at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
    at org.apache.spark.scheduler.Task.run(Task.scala:121)
    at org.apache.spark.executor.Executor$TaskRunner$$anonfun$10.apply(Executor.scala:402)
    at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1360)
    at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:408)
    at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
    at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
    ... 1 more
Caused by: java.net.SocketTimeoutException: Accept timed out
    at java.net.DualStackPlainSocketImpl.waitForNewConnection(Native Method)
    at java.net.DualStackPlainSocketImpl.socketAccept(Unknown Source)
    at java.net.AbstractPlainSocketImpl.accept(Unknown Source)
    at java.net.PlainSocketImpl.accept(Unknown Source)
    at java.net.ServerSocket.implAccept(Unknown Source)
    at java.net.ServerSocket.accept(Unknown Source)
    at org.apache.spark.api.python.PythonWorkerFactory.createSimpleWorker(PythonWorkerFactory.scala:164)
    ... 52 more

What has caused this kind of error?

Could it be about a time out occurred during the execution?

I have tried to increase the set('spark.executor.heartbeatInterval','3600s'), but I get the same error.

Upvotes: 1

Views: 1183

Answers (1)

mazaneicha
mazaneicha

Reputation: 9427

According to the source code for PythonWorkerFactory, worker initialization timeout is hardcoded to 10000 ms, so it cannot be increased via Spark settings. (There is also a SPARK-24405 JIRA open for that but has no observable activity in the past year.) What you can try is to use the spark.python.use.daemon=true setting to see if it helps to speed up spawning new python workers in your environment. Here is the comment from the source code:

// Because forking processes from Java is expensive, we prefer to launch a single Python daemon,
// pyspark/daemon.py (by default) and tell it to fork new workers for our tasks. This daemon
// currently only works on UNIX-based systems now because it uses signals for child management,
// so we can also fall back to launching workers, pyspark/worker.py (by default) directly.

Upvotes: 1

Related Questions