Marcelo Vanzin created SPARK-11138: -------------------------------------- Summary: Flaky pyspark test: test_add_py_file Key: SPARK-11138 URL: https://issues.apache.org/jira/browse/SPARK-11138 Project: Spark Issue Type: Bug Components: Tests Affects Versions: 1.6.0 Reporter: Marcelo Vanzin
This test fails pretty often when running PR tests. For example: https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/43800/console {noformat} ====================================================================== ERROR: test_add_py_file (__main__.AddFileTests) ---------------------------------------------------------------------- Traceback (most recent call last): File "/home/jenkins/workspace/SparkPullRequestBuilder@2/python/pyspark/tests.py", line 396, in test_add_py_file res = self.sc.parallelize(range(2)).map(func).first() File "/home/jenkins/workspace/SparkPullRequestBuilder@2/python/pyspark/rdd.py", line 1315, in first rs = self.take(1) File "/home/jenkins/workspace/SparkPullRequestBuilder@2/python/pyspark/rdd.py", line 1297, in take res = self.context.runJob(self, takeUpToNumLeft, p) File "/home/jenkins/workspace/SparkPullRequestBuilder@2/python/pyspark/context.py", line 923, in runJob port = self._jvm.PythonRDD.runJob(self._jsc.sc(), mappedRDD._jrdd, partitions) 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 z:org.apache.spark.api.python.PythonRDD.runJob. : org.apache.spark.SparkException: Job aborted due to stage failure: Task 2 in stage 3.0 failed 1 times, most recent failure: Lost task 2.0 in stage 3.0 (TID 7, localhost): org.apache.spark.api.python.PythonException: Traceback (most recent call last): File "/home/jenkins/workspace/SparkPullRequestBuilder@2/python/lib/pyspark.zip/pyspark/worker.py", line 111, in main process() File "/home/jenkins/workspace/SparkPullRequestBuilder@2/python/lib/pyspark.zip/pyspark/worker.py", line 106, in process serializer.dump_stream(func(split_index, iterator), outfile) File "/home/jenkins/workspace/SparkPullRequestBuilder@2/python/lib/pyspark.zip/pyspark/serializers.py", line 263, in dump_stream vs = list(itertools.islice(iterator, batch)) File "/home/jenkins/workspace/SparkPullRequestBuilder@2/python/pyspark/rdd.py", line 1293, in takeUpToNumLeft yield next(iterator) File "/home/jenkins/workspace/SparkPullRequestBuilder@2/python/pyspark/tests.py", line 388, 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$1.<init>(PythonRDD.scala:207) at org.apache.spark.api.python.PythonRunner.compute(PythonRDD.scala:125) at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:70) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297) at org.apache.spark.rdd.RDD.iterator(RDD.scala:264) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66) at org.apache.spark.scheduler.Task.run(Task.scala:88) at org.apache.spark.executor.Executor$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$$failJobAndIndependentStages(DAGScheduler.scala:1427) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1415) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1414) at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47) at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1414) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:793) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:793) at scala.Option.foreach(Option.scala:236) at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:793) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1639) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1598) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1587) at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48) at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:614) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1830) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1843) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1856) at org.apache.spark.api.python.PythonRDD$.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:379) 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:207) 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/SparkPullRequestBuilder@2/python/lib/pyspark.zip/pyspark/worker.py", line 111, in main process() File "/home/jenkins/workspace/SparkPullRequestBuilder@2/python/lib/pyspark.zip/pyspark/worker.py", line 106, in process serializer.dump_stream(func(split_index, iterator), outfile) File "/home/jenkins/workspace/SparkPullRequestBuilder@2/python/lib/pyspark.zip/pyspark/serializers.py", line 263, in dump_stream vs = list(itertools.islice(iterator, batch)) File "/home/jenkins/workspace/SparkPullRequestBuilder@2/python/pyspark/rdd.py", line 1293, in takeUpToNumLeft yield next(iterator) File "/home/jenkins/workspace/SparkPullRequestBuilder@2/python/pyspark/tests.py", line 388, 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$1.<init>(PythonRDD.scala:207) at org.apache.spark.api.python.PythonRunner.compute(PythonRDD.scala:125) at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:70) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297) at org.apache.spark.rdd.RDD.iterator(RDD.scala:264) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66) at org.apache.spark.scheduler.Task.run(Task.scala:88) at org.apache.spark.executor.Executor$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 ---------------------------------------------------------------------- {noformat} /cc [~davies] in case you have some ideas. -- This message was sent by Atlassian JIRA (v6.3.4#6332) --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org