Github user tdas commented on the pull request:
https://github.com/apache/spark/pull/2538#issuecomment-58735252
@davies unfortunately the last update to statebykey introduced some bug.
Here is the error in jenkins logs.
Traceback (most recent call last):
File
"/home/jenkins/workspace/SparkPullRequestBuilder@2/python/pyspark/streaming/util.py",
line 57, in call
r = self.func(t, *rdds)
File
"/home/jenkins/workspace/SparkPullRequestBuilder@2/python/pyspark/streaming/dstream.py",
line 254, in saveAsTextFile
rdd.saveAsTextFile(path)
File
"/home/jenkins/workspace/SparkPullRequestBuilder@2/python/pyspark/rdd.py", line
1267, in saveAsTextFile
keyed._jrdd.map(self.ctx._jvm.BytesToString()).saveAsTextFile(path)
File
"/home/jenkins/workspace/SparkPullRequestBuilder@2/python/lib/py4j-0.8.2.1-src.zip/py4j/java_gateway.py",
line 538, in __call__
self.target_id, self.name)
File
"/home/jenkins/workspace/SparkPullRequestBuilder@2/python/lib/py4j-0.8.2.1-src.zip/py4j/protocol.py",
line 300, in get_return_value
format(target_id, '.', name), value)
Py4JJavaError: An error occurred while calling o62024.saveAsTextFile.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0
in stage 296848.0 failed 1 times, most recent failure: Lost task 0.0 in stage
296848.0 (TID 780, localhost): org.apache.spark.api.python.PythonException:
Traceback (most recent call last):
File "pyspark/worker.py", line 109, in main
process()
File "pyspark/worker.py", line 100, in process
serializer.dump_stream(func(split_index, iterator), outfile)
File "pyspark/serializers.py", line 234, in dump_stream
vs = list(itertools.islice(iterator, batch))
File
"/home/jenkins/workspace/SparkPullRequestBuilder@2/python/pyspark/rdd.py", line
1641, in <lambda>
map_values_fn = lambda (k, v): (k, f(v))
File
"/home/jenkins/workspace/SparkPullRequestBuilder@2/python/pyspark/streaming/dstream.py",
line 579, in <lambda>
state = g.mapValues(lambda (vs, s): updateFunc(vs, s))
TypeError: updater() takes exactly 1 argument (2 given)
org.apache.spark.api.python.PythonRDD$$anon$1.read(PythonRDD.scala:135)
org.apache.spark.api.python.PythonRDD$$anon$1.<init>(PythonRDD.scala:166)
org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:94)
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
org.apache.spark.api.python.PythonRDD$WriterThread$$anonfun$run$1.apply$mcV$sp(PythonRDD.scala:235)
org.apache.spark.api.python.PythonRDD$WriterThread$$anonfun$run$1.apply(PythonRDD.scala:196)
org.apache.spark.api.python.PythonRDD$WriterThread$$anonfun$run$1.apply(PythonRDD.scala:196)
org.apache.spark.util.Utils$.logUncaughtExceptions(Utils.scala:1321)
org.apache.spark.api.python.PythonRDD$WriterThread.run(PythonRDD.scala:195)
Driver stacktrace:
at
org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1191)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1180)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1179)
at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at
org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1179)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:694)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:694)
at scala.Option.foreach(Option.scala:236)
at
org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:694)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessActor$$anonfun$receive$2.applyOrElse(DAGScheduler.scala:1397)
at akka.actor.Actor$class.aroundReceive(Actor.scala:465)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessActor.aroundReceive(DAGScheduler.scala:1352)
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)
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
