Spark/PySpark errors on mysterious missing /tmp file - apache-spark

Question

I'm having issues with pyspark and a missing /tmp file. I've narrowed down the behavior to a short snippet.
>>> a=sc.parallelize([(16646160,1)])
>>> b=stuff
>>> # b=sc.parallelize(b.collect())
>>> a.join(b).take(10)
This fails, but if I include the commented line (which should be the same thing), then it succeeds. Here is the error:
---------------------------------------------------------------------------
Py4JJavaError Traceback (most recent call last)
<ipython-input-101-90fe86df7879> in <module>()
3 b=stuff.map(lambda x:(16646160,1))
4 #b=sc.parallelize(b.collect())
----> 5 a.join(b).take(10)
6 b.take(10)
/usr/lib/spark/python/pyspark/rdd.py in take(self, num)
1109
1110 p = range(partsScanned, min(partsScanned + numPartsToTry, totalParts))
-> 1111 res = self.context.runJob(self, takeUpToNumLeft, p, True)
1112
1113 items += res
/usr/lib/spark/python/pyspark/context.py in runJob(self, rdd, partitionFunc, partitions, allowLocal)
816 # SparkContext#runJob.
817 mappedRDD = rdd.mapPartitions(partitionFunc)
--> 818 it = self._jvm.PythonRDD.runJob(self._jsc.sc(), mappedRDD._jrdd, javaPartitions, allowLocal)
819 return list(mappedRDD._collect_iterator_through_file(it))
820
/usr/lib/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:
/usr/lib/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 z:org.apache.spark.api.python.PythonRDD.runJob.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 1 in stage 210.0 failed 1 times, most recent failure: Lost task 1.0 in stage 210.0 (TID 884, localhost): org.apache.spark.api.python.PythonException: Traceback (most recent call last):
File "/usr/lib/spark/python/pyspark/worker.py", line 92, in main
command = pickleSer.loads(command.value)
File "/usr/lib/spark/python/pyspark/broadcast.py", line 106, in value
self._value = self.load(self._path)
File "/usr/lib/spark/python/pyspark/broadcast.py", line 87, in load
with open(path, 'rb', 1 << 20) as f:
IOError: [Errno 2] No such file or directory: '/tmp/spark-4a8c591e-9192-4198-a608-c7daa3a5d494/tmpuzsAVM'
at org.apache.spark.api.python.PythonRDD$$anon$1.read(PythonRDD.scala:137)
at org.apache.spark.api.python.PythonRDD$$anon$1.<init>(PythonRDD.scala:174)
at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:96)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:263)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:230)
at org.apache.spark.rdd.UnionRDD.compute(UnionRDD.scala:87)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:263)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:230)
at org.apache.spark.api.python.PythonRDD$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$$anonfun$run$1.apply(PythonRDD.scala:204)
at org.apache.spark.util.Utils$.logUncaughtExceptions(Utils.scala:1468)
at org.apache.spark.api.python.PythonRDD$WriterThread.run(PythonRDD.scala:203)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$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$2.applyOrElse(DAGScheduler.scala:1420)
at akka.actor.ActorCell.receiveMessage(ActorCell.scala:498)
at akka.actor.ActorCell.invoke(ActorCell.scala:456)
at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:237)
at akka.dispatch.Mailbox.run(Mailbox.scala:219)
at akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(AbstractDispatcher.scala:386)
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)
In case you're wondering
>>> b.take(10)
[(16744491, 1),
(16203827, 1),
(16695357, 1),
(16958298, 1),
(16400458, 1),
(16810060, 1),
(11452497, 1),
(14803033, 1),
(15630426, 1),
(14917736, 1)]
So maybe (I thought) there's some weird number in there that overflows or something, and collecting and re-parallelizing "fixes" the problem. This next bit of code proves this assumption wrong.
>>> a=sc.parallelize([(16646160,1)])
>>> b=stuff.map(lambda x:(16646160,1))
>>> #b=sc.parallelize(b.collect())
>>> a.join(b).take(10)
It still breaks. (Here again including the comment line fixes the problem.)
So I'm apparently looking at some sort of spark/pyspark bug. Spark 1.2.0. Any idea?