You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Davies Liu (JIRA)" <ji...@apache.org> on 2014/08/07 07:21:12 UTC
[jira] [Created] (SPARK-2898) Failed to connect to daemon
Davies Liu created SPARK-2898:
---------------------------------
Summary: Failed to connect to daemon
Key: SPARK-2898
URL: https://issues.apache.org/jira/browse/SPARK-2898
Project: Spark
Issue Type: Bug
Affects Versions: 1.1.0
Reporter: Davies Liu
--------------------------------------------------------------------
Java options: -Dspark.storage.memoryFraction=0.66 -Dspark.serializer=org.apache.spark.serializer.JavaSerializer -Dspark.executor.memory=3g -Dspark.locality.wait=60000000
Options: SchedulerThroughputTest --num-tasks=10000 --num-trials=4 --inter-trial-wait=1
--------------------------------------------------------------------
14/08/06 22:09:41 WARN JettyUtils: Failed to create UI on port 4040. Trying again on port 4041. - Failure(java.net.BindException: Address already in use)
worker 50114 crashed abruptly with exit status 1
14/08/06 22:10:37 ERROR Executor: Exception in task 1476.0 in stage 1.0 (TID 11476)
org.apache.spark.SparkException: Python worker exited unexpectedly (crashed)
at org.apache.spark.api.python.PythonRDD$$anon$1.read(PythonRDD.scala:150)
at org.apache.spark.api.python.PythonRDD$$anon$1.<init>(PythonRDD.scala:154)
at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:87)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:62)
at org.apache.spark.scheduler.Task.run(Task.scala:54)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:199)
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)
Caused by: java.io.EOFException
at java.io.DataInputStream.readInt(DataInputStream.java:392)
at org.apache.spark.api.python.PythonRDD$$anon$1.read(PythonRDD.scala:101)
... 10 more
14/08/06 22:10:37 WARN PythonWorkerFactory: Failed to open socket to Python daemon:
java.net.ConnectException: Connection refused
at java.net.PlainSocketImpl.socketConnect(Native Method)
at java.net.AbstractPlainSocketImpl.doConnect(AbstractPlainSocketImpl.java:339)
at java.net.AbstractPlainSocketImpl.connectToAddress(AbstractPlainSocketImpl.java:200)
at java.net.AbstractPlainSocketImpl.connect(AbstractPlainSocketImpl.java:182)
at java.net.SocksSocketImpl.connect(SocksSocketImpl.java:392)
at java.net.Socket.connect(Socket.java:579)
at java.net.Socket.connect(Socket.java:528)
at java.net.Socket.<init>(Socket.java:425)
at java.net.Socket.<init>(Socket.java:241)
at org.apache.spark.api.python.PythonWorkerFactory.createSocket$1(PythonWorkerFactory.scala:68)
at org.apache.spark.api.python.PythonWorkerFactory.liftedTree1$1(PythonWorkerFactory.scala:83)
at org.apache.spark.api.python.PythonWorkerFactory.createThroughDaemon(PythonWorkerFactory.scala:82)
at org.apache.spark.api.python.PythonWorkerFactory.create(PythonWorkerFactory.scala:55)
at org.apache.spark.SparkEnv.createPythonWorker(SparkEnv.scala:101)
at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:66)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:62)
at org.apache.spark.scheduler.Task.run(Task.scala:54)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:199)
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)
14/08/06 22:10:37 ERROR Executor: Exception in task 1478.0 in stage 1.0 (TID 11478)
java.io.EOFException
at java.io.DataInputStream.readInt(DataInputStream.java:392)
at org.apache.spark.api.python.PythonWorkerFactory.createSocket$1(PythonWorkerFactory.scala:69)
at org.apache.spark.api.python.PythonWorkerFactory.liftedTree1$1(PythonWorkerFactory.scala:83)
at org.apache.spark.api.python.PythonWorkerFactory.createThroughDaemon(PythonWorkerFactory.scala:82)
at org.apache.spark.api.python.PythonWorkerFactory.create(PythonWorkerFactory.scala:55)
at org.apache.spark.SparkEnv.createPythonWorker(SparkEnv.scala:101)
at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:66)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:62)
at org.apache.spark.scheduler.Task.run(Task.scala:54)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:199)
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)
14/08/06 22:10:37 WARN PythonWorkerFactory: Assuming that daemon unexpectedly quit, attempting to restart
14/08/06 22:10:37 WARN TaskSetManager: Lost task 1476.0 in stage 1.0 (TID 11476, localhost): org.apache.spark.SparkException: Python worker exited unexpectedly (crashed)
org.apache.spark.api.python.PythonRDD$$anon$1.read(PythonRDD.scala:150)
org.apache.spark.api.python.PythonRDD$$anon$1.<init>(PythonRDD.scala:154)
org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:87)
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:62)
org.apache.spark.scheduler.Task.run(Task.scala:54)
org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:199)
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
java.lang.Thread.run(Thread.java:745)
14/08/06 22:10:37 ERROR TaskSetManager: Task 1476 in stage 1.0 failed 1 times; aborting job
14/08/06 22:10:37 WARN TaskSetManager: Lost task 1478.0 in stage 1.0 (TID 11478, localhost): java.io.EOFException:
java.io.DataInputStream.readInt(DataInputStream.java:392)
org.apache.spark.api.python.PythonWorkerFactory.createSocket$1(PythonWorkerFactory.scala:69)
org.apache.spark.api.python.PythonWorkerFactory.liftedTree1$1(PythonWorkerFactory.scala:83)
org.apache.spark.api.python.PythonWorkerFactory.createThroughDaemon(PythonWorkerFactory.scala:82)
org.apache.spark.api.python.PythonWorkerFactory.create(PythonWorkerFactory.scala:55)
org.apache.spark.SparkEnv.createPythonWorker(SparkEnv.scala:101)
org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:66)
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:62)
org.apache.spark.scheduler.Task.run(Task.scala:54)
org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:199)
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
java.lang.Thread.run(Thread.java:745)
--
This message was sent by Atlassian JIRA
(v6.2#6252)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org