You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Ming Tang (JIRA)" <ji...@apache.org> on 2016/08/23 06:14:21 UTC
[jira] [Commented] (SPARK-11138) Flaky pyspark test:
test_add_py_file
[ https://issues.apache.org/jira/browse/SPARK-11138?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15432209#comment-15432209 ]
Ming Tang commented on SPARK-11138:
-----------------------------------
I got the same error.Here is my unit-tests.log:
..E..........................................................................s............Ivy Default Cache set to: /home/jenkins/.ivy2/cache
The jars for the packages stored in: /home/jenkins/.ivy2/jars
file:/tmp/tmp22Y47d added as a remote repository with the name: repo-1
:: loading settings :: url = jar:file:/home/jenkins/.jenkins/workspace/V100R002C00_Spark_Core_UT/assembly/target/scala-2.10/spark-assembly-1.3.0-hadoop2.7.1.jar!/org/apache/ivy/core/settings/ivysettings.xml
a#mylib added as a dependency
:: resolving dependencies :: org.apache.spark#spark-submit-parent;1.0
confs: [default]
found a#mylib;0.1 in repo-1
:: resolution report :: resolve 318ms :: artifacts dl 7ms
:: modules in use:
a#mylib;0.1 from repo-1 in [default]
---------------------------------------------------------------------
| | modules || artifacts |
| conf | number| search|dwnlded|evicted|| number|dwnlded|
---------------------------------------------------------------------
| default | 1 | 0 | 0 | 0 || 1 | 0 |
---------------------------------------------------------------------
:: retrieving :: org.apache.spark#spark-submit-parent
confs: [default]
0 artifacts copied, 1 already retrieved (0kB/9ms)
.Ivy Default Cache set to: /home/jenkins/.ivy2/cache
The jars for the packages stored in: /home/jenkins/.ivy2/jars
file:/tmp/tmpW_7uje added as a remote repository with the name: repo-1
:: loading settings :: url = jar:file:/home/jenkins/.jenkins/workspace/V100R002C00_Spark_Core_UT/assembly/target/scala-2.10/spark-assembly-1.3.0-hadoop2.7.1.jar!/org/apache/ivy/core/settings/ivysettings.xml
a#mylib added as a dependency
:: resolving dependencies :: org.apache.spark#spark-submit-parent;1.0
confs: [default]
found a#mylib;0.1 in repo-1
:: resolution report :: resolve 249ms :: artifacts dl 5ms
:: modules in use:
a#mylib;0.1 from repo-1 in [default]
---------------------------------------------------------------------
| | modules || artifacts |
| conf | number| search|dwnlded|evicted|| number|dwnlded|
---------------------------------------------------------------------
| default | 1 | 0 | 0 | 0 || 1 | 0 |
---------------------------------------------------------------------
:: retrieving :: org.apache.spark#spark-submit-parent
confs: [default]
0 artifacts copied, 1 already retrieved (0kB/5ms)
..........
======================================================================
ERROR: test_add_py_file (__main__.AddFileTests)
----------------------------------------------------------------------
Traceback (most recent call last):
File "/home/jenkins/.jenkins/workspace/V100R002C00_Spark_Core_UT/python/pyspark/tests.py", line 402, in test_add_py_file
res = self.sc.parallelize(range(2)).map(func).first()
File "pyspark/rdd.py", line 1301, in first
rs = self.take(1)
File "pyspark/rdd.py", line 1283, in take
res = self.context.runJob(self, takeUpToNumLeft, p, True)
File "pyspark/context.py", line 897, in runJob
allowLocal)
File "/home/jenkins/.jenkins/workspace/V100R002C00_Spark_Core_UT/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/.jenkins/workspace/V100R002C00_Spark_Core_UT/python/lib/py4j-0.8.2.1-src.zip/py4j/protocol.py", line 300, in get_return_value
format(target_id, '.', name), value)
py4j.protocol.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 "pyspark/worker.py", line 111, in main
process()
File "pyspark/worker.py", line 106, in process
serializer.dump_stream(func(split_index, iterator), outfile)
File "pyspark/serializers.py", line 263, in dump_stream
vs = list(itertools.islice(iterator, batch))
File "pyspark/rdd.py", line 1279, in takeUpToNumLeft
yield next(iterator)
File "/home/jenkins/.jenkins/workspace/V100R002C00_Spark_Core_UT/python/pyspark/tests.py", line 394, in func
from userlibrary import UserClass
ImportError: cannot import name UserClass
at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRDD.scala:167)
at org.apache.spark.api.python.PythonRunner$$anon$1.<init>(PythonRDD.scala:208)
at org.apache.spark.api.python.PythonRunner.compute(PythonRDD.scala:126)
at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:71)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:244)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:63)
at org.apache.spark.scheduler.Task.run(Task.scala:70)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:222)
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$$failJobAndIndependentStages(DAGScheduler.scala:1285)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1276)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1275)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1275)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:730)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:730)
at scala.Option.foreach(Option.scala:236)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:730)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1469)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1430)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
----------------------------------------------------------------------
Ran 101 tests in 131.779s
FAILED (errors=1, skipped=1)
NOTE: Skipping SciPy tests as it does not seem to be installed
Random listing order was used
Command exited with non-zero status 1
92.22user 4.84system 2:12.50elapsed 73%CPU (0avgtext+0avgdata 340784maxresident)k
1072inputs+92312outputs (0major+727455minor)pagefaults 0swaps
> 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
> Labels: flaky-test
>
> 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-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org