You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Xiangrui Meng (JIRA)" <ji...@apache.org> on 2014/12/14 05:13:13 UTC
[jira] [Created] (SPARK-4841) Batch serializer bug in PySpark's
RDD.zip
Xiangrui Meng created SPARK-4841:
------------------------------------
Summary: Batch serializer bug in PySpark's RDD.zip
Key: SPARK-4841
URL: https://issues.apache.org/jira/browse/SPARK-4841
Project: Spark
Issue Type: Bug
Components: PySpark
Affects Versions: 1.2.0
Reporter: Xiangrui Meng
{code}
t = sc.textFile("README.md")
t.zip(t).count()
{code}
{code}
Py4JJavaError Traceback (most recent call last)
<ipython-input-6-60fdeb8339fd> in <module>()
----> 1 readme.zip(readme).count()
/Users/meng/src/spark/python/pyspark/rdd.pyc in count(self)
817 3
818 """
--> 819 return self.mapPartitions(lambda i: [sum(1 for _ in i)]).sum()
820
821 def stats(self):
/Users/meng/src/spark/python/pyspark/rdd.pyc in sum(self)
808 6.0
809 """
--> 810 return self.mapPartitions(lambda x: [sum(x)]).reduce(operator.add)
811
812 def count(self):
/Users/meng/src/spark/python/pyspark/rdd.pyc in reduce(self, f)
713 yield reduce(f, iterator, initial)
714
--> 715 vals = self.mapPartitions(func).collect()
716 if vals:
717 return reduce(f, vals)
/Users/meng/src/spark/python/pyspark/rdd.pyc in collect(self)
674 """
675 with SCCallSiteSync(self.context) as css:
--> 676 bytesInJava = self._jrdd.collect().iterator()
677 return list(self._collect_iterator_through_file(bytesInJava))
678
/Users/meng/src/spark/python/lib/py4j-0.8.2.1-src.zip/py4j/java_gateway.py in __call__(self, *args)
536 answer = self.gateway_client.send_command(command)
537 return_value = get_return_value(answer, self.gateway_client,
--> 538 self.target_id, self.name)
539
540 for temp_arg in temp_args:
/Users/meng/src/spark/python/lib/py4j-0.8.2.1-src.zip/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)
298 raise Py4JJavaError(
299 'An error occurred while calling {0}{1}{2}.\n'.
--> 300 format(target_id, '.', name), value)
301 else:
302 raise Py4JError(
Py4JJavaError: An error occurred while calling o69.collect.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 1.0 failed 1 times, most recent failure: Lost task 0.0 in stage 1.0 (TID 2, localhost): org.apache.spark.api.python.PythonException: Traceback (most recent call last):
File "/Users/meng/src/spark/python/pyspark/worker.py", line 107, in main
process()
File "/Users/meng/src/spark/python/pyspark/worker.py", line 98, in process
serializer.dump_stream(func(split_index, iterator), outfile)
File "/Users/meng/src/spark/python/pyspark/serializers.py", line 198, in dump_stream
self.serializer.dump_stream(self._batched(iterator), stream)
File "/Users/meng/src/spark/python/pyspark/serializers.py", line 81, in dump_stream
raise NotImplementedError
NotImplementedError
at org.apache.spark.api.python.PythonRDD$$anon$1.read(PythonRDD.scala:137)
at org.apache.spark.api.python.PythonRDD$$anon$1.<init>(PythonRDD.scala:174)
at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:96)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:263)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:230)
at org.apache.spark.rdd.ZippedPartitionsRDD2.compute(ZippedPartitionsRDD.scala:88)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:263)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:230)
at org.apache.spark.api.python.PythonRDD$WriterThread$$anonfun$run$1.apply$mcV$sp(PythonRDD.scala:242)
at org.apache.spark.api.python.PythonRDD$WriterThread$$anonfun$run$1.apply(PythonRDD.scala:204)
at org.apache.spark.api.python.PythonRDD$WriterThread$$anonfun$run$1.apply(PythonRDD.scala:204)
at org.apache.spark.util.Utils$.logUncaughtExceptions(Utils.scala:1460)
at org.apache.spark.api.python.PythonRDD$WriterThread.run(PythonRDD.scala:203)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1214)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1203)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1202)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1202)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:696)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:696)
at scala.Option.foreach(Option.scala:236)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:696)
at org.apache.spark.scheduler.DAGSchedulerEventProcessActor$$anonfun$receive$2.applyOrElse(DAGScheduler.scala:1420)
at akka.actor.Actor$class.aroundReceive(Actor.scala:465)
at org.apache.spark.scheduler.DAGSchedulerEventProcessActor.aroundReceive(DAGScheduler.scala:1375)
at akka.actor.ActorCell.receiveMessage(ActorCell.scala:516)
at akka.actor.ActorCell.invoke(ActorCell.scala:487)
at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:238)
at akka.dispatch.Mailbox.run(Mailbox.scala:220)
at akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(AbstractDispatcher.scala:393)
at scala.concurrent.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)
at scala.concurrent.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
at scala.concurrent.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979)
at scala.concurrent.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107)
{code}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org