Description
There is a deadlock in handle_sigchld() because of logging
--------------------------------------------------------------------
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)
Another one:
Daemon failed to fork PySpark worker: [Errno 35] Resource temporarily unavailable
14/08/07 12:04:37 ERROR Executor: Exception in task 15579.0 in stage 0.0 (TID 15579)
java.lang.IllegalStateException: Python daemon failed to launch worker
at org.apache.spark.api.python.PythonWorkerFactory.createSocket$1(PythonWorkerFactory.scala:71)
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)
14/08/07 12:04:37 WARN TaskSetManager: Lost task 15579.0 in stage 0.0 (TID 15579, localhost): java.lang.IllegalStateException: Python daemon failed to launch worker
org.apache.spark.api.python.PythonWorkerFactory.createSocket$1(PythonWorkerFactory.scala:71)
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)
14/08/07 12:04:37 ERROR TaskSetManager: Task 15579 in stage 0.0 failed 1 times; aborting job
worker 17037 crashed abruptly with exit status 1
14/08/07 12:06:34 ERROR Executor: Exception in task 19607.0 in stage 0.0 (TID 19607)
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)
14/08/07 12:06:34 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)
4/08/07 12:06:34 ERROR Executor: Exception in task 19604.0 in stage 0.0 (TID 19604)
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
14/08/07 12:06:34 WARN PythonWorkerFactory: Assuming that daemon unexpectedly quit, attempting to restart
14/08/07 12:06:34 WARN TaskSetManager: Lost task 19604.0 in stage 0.0 (TID 19604, 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)
14/08/07 12:06:34 ERROR TaskSetManager: Task 19604 in stage 0.0 failed 1 times; aborting job
14/08/07 12:06:34 WARN TaskSetManager: Lost task 19607.0 in stage 0.0 (TID 19607, 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)
14/08/07 13:29:01 WARN PythonWorkerFactory: Assuming that daemon unexpectedly quit, attempting to restart
14/08/07 13:29:01 ERROR Executor: Exception in task 9085.0 in stage 0.0 (TID 9085)
java.io.IOException: Cannot run program "python": error=2, No such file or directory
at java.lang.ProcessBuilder.start(ProcessBuilder.java:1041)
at org.apache.spark.api.python.PythonWorkerFactory.startDaemon(PythonWorkerFactory.scala:149)
at org.apache.spark.api.python.PythonWorkerFactory.liftedTree1$1(PythonWorkerFactory.scala:89)
at org.apache.spark.api.python.PythonWorkerFactory.createThroughDaemon(PythonWorkerFactory.scala:82)
at org.apache.spark.api.python.PythonWorkerFactory.create(PythonWorkerFactory.scala:55)
at org.apache.spark.SparkEnv.createPythonWorker(SparkEnv.scala:101)
at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:66)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:62)
at org.apache.spark.scheduler.Task.run(Task.scala:54)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:199)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.io.IOException: error=2, No such file or directory
at java.lang.UNIXProcess.forkAndExec(Native Method)
at java.lang.UNIXProcess.<init>(UNIXProcess.java:184)
at java.lang.ProcessImpl.start(ProcessImpl.java:130)
at java.lang.ProcessBuilder.start(ProcessBuilder.java:1022)
... 14 more
14/08/07 13:29:01 ERROR Executor: Exception in task 9084.0 in stage 0.0 (TID 9084)
java.io.IOException: Cannot run program "python": error=316, Unknown error: 316
at java.lang.ProcessBuilder.start(ProcessBuilder.java:1041)
at org.apache.spark.api.python.PythonWorkerFactory.startDaemon(PythonWorkerFactory.scala:149)
at org.apache.spark.api.python.PythonWorkerFactory.createThroughDaemon(PythonWorkerFactory.scala:79)
at org.apache.spark.api.python.PythonWorkerFactory.create(PythonWorkerFactory.scala:55)
at org.apache.spark.SparkEnv.createPythonWorker(SparkEnv.scala:101)
at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:66)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:62)
at org.apache.spark.scheduler.Task.run(Task.scala:54)
at org.apache.spark.executor.Executor$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)
Caused by: java.io.IOException: error=316, Unknown error: 316
at java.lang.UNIXProcess.forkAndExec(Native Method)
at java.lang.UNIXProcess.<init>(UNIXProcess.java:184)
at java.lang.ProcessImpl.start(ProcessImpl.java:130)
at java.lang.ProcessBuilder.start(ProcessBuilder.java:1022)
... 13 more
Attachments
Issue Links
- links to