Py4JJavaError: произошла ошибка при вызове z:org.apache.spark.api.python.PythonRDD.collectAndServe. (проблема с PySpark) ⇐ Python

[Anonymous]

Код: Выделить всё

 from pyspark.sql import SparkSession

spark = SparkSession.builder.config("spark.driver.host",

"localhost").appName("MyApp").getOrCreate()

data = [("James", "Smith", "USA", "mon"),
("Michael", "Rose", "USA", "tue"),
("Robert","Williams", "USA", "sun")]

rdd = spark.sparkContext.parallelize(data)

def days_convert(dict_key):
return bcDays.value[dict_key]

rdd.map(lambda x : x[0]).collect()

Я использовал функции .map(), .take() в RDD. Это привело к этой ошибке. В чем может быть проблема?

Код: Выделить всё

Py4JJavaError                             Traceback (most recent call last)
Cell In[7], line 1
----> 1 rdd.map(lambda x : x[0]).collect()

File C:\PySpark\Spark\spark-3.5.3-bin-hadoop3\python\pyspark\rdd.py:1833, in RDD.collect(self)
1831 with SCCallSiteSync(self.context):
1832     assert self.ctx._jvm is not None
-> 1833     sock_info = self.ctx._jvm.PythonRDD.collectAndServe(self._jrdd.rdd())
1834 return list(_load_from_socket(sock_info, self._jrdd_deserializer))

File C:\PySpark\Spark\spark-3.5.3-bin-hadoop3\python\lib\py4j-0.10.9.7-src.zip\py4j\java_gateway.py:1322, in JavaMember.__call__(self, *args)
1316 command = proto.CALL_COMMAND_NAME +\
1317     self.command_header +\
1318     args_command +\
1319     proto.END_COMMAND_PART
1321 answer = self.gateway_client.send_command(command)
-> 1322 return_value = get_return_value(
1323     answer, self.gateway_client, self.target_id, self.name)
1325 for temp_arg in temp_args:
1326     if hasattr(temp_arg, "_detach"):

File C:\PySpark\Spark\spark-3.5.3-bin-hadoop3\python\pyspark\errors\exceptions\captured.py:179, in capture_sql_exception..deco(*a, **kw)
177 def deco(*a: Any, **kw: Any) -> Any:
178     try:
--> 179         return f(*a, **kw)
180     except Py4JJavaError as e:
181         converted = convert_exception(e.java_exception)

File C:\PySpark\Spark\spark-3.5.3-bin-hadoop3\python\lib\py4j-0.10.9.7-src.zip\py4j\protocol.py:326, in get_return_value(answer, gateway_client, target_id, name)
324 value = OUTPUT_CONVERTER[type](answer[2:], gateway_client)
325 if answer[1] == REFERENCE_TYPE:
--> 326     raise Py4JJavaError(
327         "An error occurred while calling {0}{1}{2}.\n".
328         format(target_id, ".", name), value)
329 else:
330     raise Py4JError(
331         "An error occurred while calling {0}{1}{2}.  Trace:\n{3}\n".
332         format(target_id, ".", name, value))

Py4JJavaError: An error occurred while calling z:org.apache.spark.api.python.PythonRDD.collectAndServe.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 4 in stage 2.0 failed 1 times, most recent failure: Lost task 4.0 in stage 2.0 (TID 6) (3JMRMJ3 executor driver): org.apache.spark.SparkException: Python worker failed to connect back.
at org.apache.spark.api.python.PythonWorkerFactory.createSimpleWorker(PythonWorkerFactory.scala:203)
at org.apache.spark.api.python.PythonWorkerFactory.create(PythonWorkerFactory.scala:109)
at org.apache.spark.SparkEnv.createPythonWorker(SparkEnv.scala:124)
at org.apache.spark.api.python.BasePythonRunner.compute(PythonRunner.scala:174)
at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:67)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:620)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:623)
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:190)
...  17 more

Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2856)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2792)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2791)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2791)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1247)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1247)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1247)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3060)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2994)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2983)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:989)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2458)
at org.apache.spark.rdd.RDD.$anonfun$collect$1(RDD.scala:1049)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:410)
at org.apache.spark.rdd.RDD.collect(RDD.scala:1048)
at org.apache.spark.api.python.PythonRDD$.collectAndServe(PythonRDD.scala:195)
at org.apache.spark.api.python.PythonRDD.collectAndServe(PythonRDD.scala)
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:374)
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.ClientServerConnection.waitForCommands(ClientServerConnection.java:182)
at py4j.ClientServerConnection.run(ClientServerConnection.java:106)
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:203)
at org.apache.spark.api.python.PythonWorkerFactory.create(PythonWorkerFactory.scala:109)
at org.apache.spark.SparkEnv.createPythonWorker(SparkEnv.scala:124)
at org.apache.spark.api.python.BasePythonRunner.compute(PythonRunner.scala:174)
at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:67)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:620)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:623)
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:190)
... 17 more
---------------------------------------------------------------------------
Py4JJavaError                             Traceback (most recent call last)
Cell In[9], line 1
----> 1 input = rdd.map(lambda x : (x[0], x[1], x[2], x[3])).collect()
2 output = rdd.map(lambda x: (x[0], x[1], x[2], days_convert(x[3]))).collect()
3 print(" Input : ")

File C:\PySpark\Spark\spark-3.5.3-bin-hadoop3\python\pyspark\rdd.py:1833, in RDD.collect(self)
1831 with SCCallSiteSync(self.context):
1832     assert self.ctx._jvm is not None
-> 1833     sock_info = self.ctx._jvm.PythonRDD.collectAndServe(self._jrdd.rdd())
1834 return list(_load_from_socket(sock_info, self._jrdd_deserializer))

File C:\PySpark\Spark\spark-3.5.3-bin-hadoop3\python\lib\py4j-0.10.9.7-src.zip\py4j\java_gateway.py:1322, in JavaMember.__call__(self, *args)
1316 command = proto.CALL_COMMAND_NAME +\
1317     self.command_header +\
1318     args_command +\
1319     proto.END_COMMAND_PART
1321 answer = self.gateway_client.send_command(command)
-> 1322 return_value = get_return_value(
1323     answer, self.gateway_client, self.target_id, self.name)
1325 for temp_arg in temp_args:
1326     if hasattr(temp_arg, "_detach"):

File C:\PySpark\Spark\spark-3.5.3-bin-hadoop3\python\pyspark\errors\exceptions\captured.py:179, in capture_sql_exception..deco(*a, **kw)
...
at java.base/java.net.ServerSocket.implAccept(ServerSocket.java:574)
at java.base/java.net.ServerSocket.accept(ServerSocket.java:532)
at org.apache.spark.api.python.PythonWorkerFactory.createSimpleWorker(PythonWorkerFactory.scala:190)
... 17 more
Output is truncated.

Я проверил установку. Все в порядке (версия Java 8, Spark 3.5, Python 3.12, WinUtils установлены, пользователь и переменная Windows созданы). В чем может быть проблема? Я получил эту ошибку только с функцией Python. Это связано с Python?

Подробнее здесь: https://stackoverflow.com/questions/792 ... python-pyt