An error occurred while calling z:org.apache.spark.api.python.PythonRDD.runJob. : org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 3.0 failed 1 times, most recent failure: Lost task 0.0 in stage 3.0 (TID 5, localhost): org.apache.spark.api.python.PythonException: Traceback (most recent call last): File "/home/jenkins/workspace/spark-branch-1.6-test-sbt-hadoop-2.0/python/lib/pyspark.zip/pyspark/worker.py", line 111, in main process() File "/home/jenkins/workspace/spark-branch-1.6-test-sbt-hadoop-2.0/python/lib/pyspark.zip/pyspark/worker.py", line 106, in process serializer.dump_stream(func(split_index, iterator), outfile) File "/home/jenkins/workspace/spark-branch-1.6-test-sbt-hadoop-2.0/python/lib/pyspark.zip/pyspark/serializers.py", line 263, in dump_stream vs = list(itertools.islice(iterator, batch)) File "/home/jenkins/workspace/spark-branch-1.6-test-sbt-hadoop-2.0/python/pyspark/rdd.py", line 1293, in takeUpToNumLeft yield next(iterator) File "/home/jenkins/workspace/spark-branch-1.6-test-sbt-hadoop-2.0/python/pyspark/tests.py", line 394, in func from userlibrary import UserClass ImportError: cannot import name UserClass at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRDD.scala:166) at org.apache.spark.api.python.PythonRunner$$anon$1.<init>(PythonRDD.scala:207) at org.apache.spark.api.python.PythonRunner.compute(PythonRDD.scala:125) at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:70) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306) at org.apache.spark.rdd.RDD.iterator(RDD.scala:270) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66) at org.apache.spark.scheduler.Task.run(Task.scala:89) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214) 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$$failJobAndIndependentStages(DAGScheduler.scala:1431) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1419) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1418) at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47) at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1418) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799) at scala.Option.foreach(Option.scala:236) at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:799) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1640) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1599) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1588) at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48) at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:620) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1832) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1845) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1858) at org.apache.spark.api.python.PythonRDD$.runJob(PythonRDD.scala:393) at org.apache.spark.api.python.PythonRDD.runJob(PythonRDD.scala) at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57) at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) at java.lang.reflect.Method.invoke(Method.java:606) at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:231) at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:381) at py4j.Gateway.invoke(Gateway.java:259) at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:133) at py4j.commands.CallCommand.execute(CallCommand.java:79) at py4j.GatewayConnection.run(GatewayConnection.java:209) at java.lang.Thread.run(Thread.java:745) Caused by: org.apache.spark.api.python.PythonException: Traceback (most recent call last): File "/home/jenkins/workspace/spark-branch-1.6-test-sbt-hadoop-2.0/python/lib/pyspark.zip/pyspark/worker.py", line 111, in main process() File "/home/jenkins/workspace/spark-branch-1.6-test-sbt-hadoop-2.0/python/lib/pyspark.zip/pyspark/worker.py", line 106, in process serializer.dump_stream(func(split_index, iterator), outfile) File "/home/jenkins/workspace/spark-branch-1.6-test-sbt-hadoop-2.0/python/lib/pyspark.zip/pyspark/serializers.py", line 263, in dump_stream vs = list(itertools.islice(iterator, batch)) File "/home/jenkins/workspace/spark-branch-1.6-test-sbt-hadoop-2.0/python/pyspark/rdd.py", line 1293, in takeUpToNumLeft yield next(iterator) File "/home/jenkins/workspace/spark-branch-1.6-test-sbt-hadoop-2.0/python/pyspark/tests.py", line 394, in func from userlibrary import UserClass ImportError: cannot import name UserClass at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRDD.scala:166) at org.apache.spark.api.python.PythonRunner$$anon$1.<init>(PythonRDD.scala:207) at org.apache.spark.api.python.PythonRunner.compute(PythonRDD.scala:125) at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:70) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306) at org.apache.spark.rdd.RDD.iterator(RDD.scala:270) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66) at org.apache.spark.scheduler.Task.run(Task.scala:89) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) ... 1 more
Traceback (most recent call last):
File "/home/jenkins/workspace/spark-branch-1.6-test-sbt-hadoop-2.0/python/pyspark/tests.py", line 402, in test_add_py_file
res = self.sc.parallelize(range(2)).map(func).first()
File "/home/jenkins/workspace/spark-branch-1.6-test-sbt-hadoop-2.0/python/pyspark/rdd.py", line 1315, in first
rs = self.take(1)
File "/home/jenkins/workspace/spark-branch-1.6-test-sbt-hadoop-2.0/python/pyspark/rdd.py", line 1297, in take
res = self.context.runJob(self, takeUpToNumLeft, p)
File "/home/jenkins/workspace/spark-branch-1.6-test-sbt-hadoop-2.0/python/pyspark/context.py", line 939, in runJob
port = self._jvm.PythonRDD.runJob(self._jsc.sc(), mappedRDD._jrdd, partitions)
File "/home/jenkins/workspace/spark-branch-1.6-test-sbt-hadoop-2.0/python/lib/py4j-0.9-src.zip/py4j/java_gateway.py", line 813, in __call__
answer, self.gateway_client, self.target_id, self.name)
File "/home/jenkins/workspace/spark-branch-1.6-test-sbt-hadoop-2.0/python/lib/py4j-0.9-src.zip/py4j/protocol.py", line 308, in get_return_value
format(target_id, ".", name), value)
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 0 in stage 3.0 failed 1 times, most recent failure: Lost task 0.0 in stage 3.0 (TID 5, localhost): org.apache.spark.api.python.PythonException: Traceback (most recent call last):
File "/home/jenkins/workspace/spark-branch-1.6-test-sbt-hadoop-2.0/python/lib/pyspark.zip/pyspark/worker.py", line 111, in main
process()
File "/home/jenkins/workspace/spark-branch-1.6-test-sbt-hadoop-2.0/python/lib/pyspark.zip/pyspark/worker.py", line 106, in process
serializer.dump_stream(func(split_index, iterator), outfile)
File "/home/jenkins/workspace/spark-branch-1.6-test-sbt-hadoop-2.0/python/lib/pyspark.zip/pyspark/serializers.py", line 263, in dump_stream
vs = list(itertools.islice(iterator, batch))
File "/home/jenkins/workspace/spark-branch-1.6-test-sbt-hadoop-2.0/python/pyspark/rdd.py", line 1293, in takeUpToNumLeft
yield next(iterator)
File "/home/jenkins/workspace/spark-branch-1.6-test-sbt-hadoop-2.0/python/pyspark/tests.py", line 394, in func
from userlibrary import UserClass
ImportError: cannot import name UserClass
at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRDD.scala:166)
at org.apache.spark.api.python.PythonRunner$$anon$1.<init>(PythonRDD.scala:207)
at org.apache.spark.api.python.PythonRunner.compute(PythonRDD.scala:125)
at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:70)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:89)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
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$$failJobAndIndependentStages(DAGScheduler.scala:1431)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1419)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1418)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1418)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799)
at scala.Option.foreach(Option.scala:236)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:799)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1640)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1599)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1588)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:620)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1832)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1845)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1858)
at org.apache.spark.api.python.PythonRDD$.runJob(PythonRDD.scala:393)
at org.apache.spark.api.python.PythonRDD.runJob(PythonRDD.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:231)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:381)
at py4j.Gateway.invoke(Gateway.java:259)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:133)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:209)
at java.lang.Thread.run(Thread.java:745)
Caused by: org.apache.spark.api.python.PythonException: Traceback (most recent call last):
File "/home/jenkins/workspace/spark-branch-1.6-test-sbt-hadoop-2.0/python/lib/pyspark.zip/pyspark/worker.py", line 111, in main
process()
File "/home/jenkins/workspace/spark-branch-1.6-test-sbt-hadoop-2.0/python/lib/pyspark.zip/pyspark/worker.py", line 106, in process
serializer.dump_stream(func(split_index, iterator), outfile)
File "/home/jenkins/workspace/spark-branch-1.6-test-sbt-hadoop-2.0/python/lib/pyspark.zip/pyspark/serializers.py", line 263, in dump_stream
vs = list(itertools.islice(iterator, batch))
File "/home/jenkins/workspace/spark-branch-1.6-test-sbt-hadoop-2.0/python/pyspark/rdd.py", line 1293, in takeUpToNumLeft
yield next(iterator)
File "/home/jenkins/workspace/spark-branch-1.6-test-sbt-hadoop-2.0/python/pyspark/tests.py", line 394, in func
from userlibrary import UserClass
ImportError: cannot import name UserClass
at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRDD.scala:166)
at org.apache.spark.api.python.PythonRunner$$anon$1.<init>(PythonRDD.scala:207)
at org.apache.spark.api.python.PythonRunner.compute(PythonRDD.scala:125)
at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:70)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:89)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
... 1 more