执行RDD出现问题

In [2]: tf = sc.textFile("passwd")
17/11/22 10:59:51 WARN util.SizeEstimator: Failed to check whether UseCompressedOops is set; assuming yes

In [3]: tf.map(lambda l:l.split("\t")).map(lambda x:(x[0],(x[1],x[2]))).collect()
[Stage 0:>                                                       (0 + 2) / 2]17/11/22 11:01:37 WARN scheduler.TaskSetManager: Lost task 1.0 in stage 0.0 (TID 1, elephant, executor 1): org.apache.spark.api.python.PythonException: Traceback (most recent call last):
  File "/opt/spark2/python/pyspark/worker.py", line 174, in main
process()
  File "/opt/spark2/python/pyspark/worker.py", line 169, in process
serializer.dump_stream(func(split_index, iterator), outfile)
  File "/opt/spark2/python/pyspark/serializers.py", line 268, in dump_stream
vs = list(itertools.islice(iterator, batch))
  File "<ipython-input-3-70665d9f328a>", line 1, in <lambda>
IndexError: list index out of range

at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRDD.scala:193)
at org.apache.spark.api.python.PythonRunner$$anon$1.<init>(PythonRDD.scala:234)
at org.apache.spark.api.python.PythonRunner.compute(PythonRDD.scala:152)
at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:63)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
at org.apache.spark.scheduler.Task.run(Task.scala:99)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:282)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)

17/11/22 11:01:38 ERROR scheduler.TaskSetManager: Task 0 in stage 0.0 failed 4 times; aborting job
[Stage 0:>                                                       (0 + 1) / 2]17/11/22 11:01:38 WARN scheduler.TaskSetManager: Lost task 1.3 in stage 0.0 (TID 7, elephant, executor 2): TaskKilled (killed intentionally)
---------------------------------------------------------------------------
Py4JJavaError                            Traceback (most recent call last)
<ipython-input-3-70665d9f328a> in <module>()
----> 1 tf.map(lambda l:l.split("\t")).map(lambda x:(x[0],(x[1],x[2]))).collect()

/opt/spark2/python/pyspark/rdd.py in collect(self)
807       """
808       with SCCallSiteSync(self.context) as css:
--> 809          port = self.ctx._jvm.PythonRDD.collectAndServe(self._jrdd.rdd())
810       return list(_load_from_socket(port, self._jrdd_deserializer))
811

/opt/spark2/python/lib/py4j-0.10.4-src.zip/py4j/java_gateway.py in __call__(self, *args)
1131       answer = self.gateway_client.send_command(command)
1132       return_value = get_return_value(
-> 1133          answer, self.gateway_client, self.target_id, self.name)
1134
1135       for temp_arg in temp_args:

/opt/spark2/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()

/opt/spark2/python/lib/py4j-0.10.4-src.zip/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)
317                raise Py4JJavaError(
318                   "An error occurred while calling {0}{1}{2}.\n".
--> 319                   format(target_id, ".", name), value)
320          else:
321                raise Py4JError(

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 0 in stage 0.0 failed 4 times, most recent failure: Lost task 0.3 in stage 0.0 (TID 6, elephant, executor 1): org.apache.spark.api.python.PythonException: Traceback (most recent call last):
  File "/opt/spark2/python/pyspark/worker.py", line 174, in main
process()
  File "/opt/spark2/python/pyspark/worker.py", line 169, in process
serializer.dump_stream(func(split_index, iterator), outfile)
  File "/opt/spark2/python/pyspark/serializers.py", line 268, in dump_stream
vs = list(itertools.islice(iterator, batch))
  File "<ipython-input-3-70665d9f328a>", line 1, in <lambda>
IndexError: list index out of range

at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRDD.scala:193)
at org.apache.spark.api.python.PythonRunner$$anon$1.<init>(PythonRDD.scala:234)
at org.apache.spark.api.python.PythonRunner.compute(PythonRDD.scala:152)
at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:63)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
at org.apache.spark.scheduler.Task.run(Task.scala:99)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:282)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)

Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1435)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1423)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1422)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1422)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:802)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:802)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:802)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1650)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1605)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1594)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:628)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1918)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1931)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1944)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1958)
at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:935)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:362)
at org.apache.spark.rdd.RDD.collect(RDD.scala:934)
at org.apache.spark.api.python.PythonRDD$.collectAndServe(PythonRDD.scala:453)
at org.apache.spark.api.python.PythonRDD.collectAndServe(PythonRDD.scala)
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 py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:280)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:214)
at java.lang.Thread.run(Thread.java:748)
Caused by: org.apache.spark.api.python.PythonException: Traceback (most recent call last):
  File "/opt/spark2/python/pyspark/worker.py", line 174, in main
process()
  File "/opt/spark2/python/pyspark/worker.py", line 169, in process
serializer.dump_stream(func(split_index, iterator), outfile)
  File "/opt/spark2/python/pyspark/serializers.py", line 268, in dump_stream
vs = list(itertools.islice(iterator, batch))
  File "<ipython-input-3-70665d9f328a>", line 1, in <lambda>
IndexError: list index out of range

at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRDD.scala:193)
at org.apache.spark.api.python.PythonRunner$$anon$1.<init>(PythonRDD.scala:234)
at org.apache.spark.api.python.PythonRunner.compute(PythonRDD.scala:152)
at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:63)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
at org.apache.spark.scheduler.Task.run(Task.scala:99)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:282)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)