You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@apex.apache.org by "Timothy Farkas (JIRA)" <ji...@apache.org> on 2016/04/01 21:22:25 UTC

[jira] [Updated] (APEXCORE-415) Reducing Dag Checkpoint Window Count Causes Async Checkpoint Errors

     [ https://issues.apache.org/jira/browse/APEXCORE-415?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Timothy Farkas updated APEXCORE-415:
------------------------------------
    Description: 
Application that reproduces the issue is here

https://github.com/ilooner/streamcodec-bug/tree/asyncCheckpointBug

java.lang.RuntimeException: java.util.concurrent.ExecutionException: java.lang.RuntimeException: java.io.FileNotFoundException: /disk6/ndevyarn/nm/usercache/tim/appcache/application_1456485348783_3429/container_1456485348783_3429_01_000019/tmp/chkp3241218411712328004/1/6268662011559673861 (No such file or directory)
	at com.datatorrent.netlet.util.DTThrowable.wrapIfChecked(DTThrowable.java:59)
	at com.datatorrent.stram.engine.Node.reportStats(Node.java:465)
	at com.datatorrent.stram.engine.InputNode.run(InputNode.java:156)
	at com.datatorrent.stram.engine.StreamingContainer$2.run(StreamingContainer.java:1388)
Caused by: java.util.concurrent.ExecutionException: java.lang.RuntimeException: java.io.FileNotFoundException: /disk6/ndevyarn/nm/usercache/tim/appcache/application_1456485348783_3429/container_1456485348783_3429_01_000019/tmp/chkp3241218411712328004/1/6268662011559673861 (No such file or directory)
	at java.util.concurrent.FutureTask.report(FutureTask.java:122)
	at java.util.concurrent.FutureTask.get(FutureTask.java:188)
	at com.datatorrent.stram.engine.Node.reportStats(Node.java:458)
	... 2 more
Caused by: java.lang.RuntimeException: java.io.FileNotFoundException: /disk6/ndevyarn/nm/usercache/tim/appcache/application_1456485348783_3429/container_1456485348783_3429_01_000019/tmp/chkp3241218411712328004/1/6268662011559673861 (No such file or directory)
	at com.datatorrent.netlet.util.DTThrowable.wrapIfChecked(DTThrowable.java:50)
	at com.datatorrent.netlet.util.DTThrowable.rethrow(DTThrowable.java:31)
	at com.datatorrent.common.util.AsyncFSStorageAgent.copyToHDFS(AsyncFSStorageAgent.java:126)
	at com.datatorrent.stram.engine.Node$CheckpointHandler.call(Node.java:684)
	at com.datatorrent.stram.engine.Node$CheckpointHandler.call(Node.java:673)
	at java.util.concurrent.FutureTask.run(FutureTask.java:262)
	at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
	at java.util.concurrent.FutureTask.run(FutureTask.java:262)
	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.FileNotFoundException: /disk6/ndevyarn/nm/usercache/tim/appcache/application_1456485348783_3429/container_1456485348783_3429_01_000019/tmp/chkp3241218411712328004/1/6268662011559673861 (No such file or directory)
	at java.io.FileInputStream.open(Native Method)
	at java.io.FileInputStream.<init>(FileInputStream.java:146)
	at com.datatorrent.common.util.AsyncFSStorageAgent.copyToHDFS(AsyncFSStorageAgent.java:117)
	... 8 more

  was:
java.lang.RuntimeException: java.util.concurrent.ExecutionException: java.lang.RuntimeException: java.io.FileNotFoundException: /disk6/ndevyarn/nm/usercache/tim/appcache/application_1456485348783_3429/container_1456485348783_3429_01_000019/tmp/chkp3241218411712328004/1/6268662011559673861 (No such file or directory)
	at com.datatorrent.netlet.util.DTThrowable.wrapIfChecked(DTThrowable.java:59)
	at com.datatorrent.stram.engine.Node.reportStats(Node.java:465)
	at com.datatorrent.stram.engine.InputNode.run(InputNode.java:156)
	at com.datatorrent.stram.engine.StreamingContainer$2.run(StreamingContainer.java:1388)
Caused by: java.util.concurrent.ExecutionException: java.lang.RuntimeException: java.io.FileNotFoundException: /disk6/ndevyarn/nm/usercache/tim/appcache/application_1456485348783_3429/container_1456485348783_3429_01_000019/tmp/chkp3241218411712328004/1/6268662011559673861 (No such file or directory)
	at java.util.concurrent.FutureTask.report(FutureTask.java:122)
	at java.util.concurrent.FutureTask.get(FutureTask.java:188)
	at com.datatorrent.stram.engine.Node.reportStats(Node.java:458)
	... 2 more
Caused by: java.lang.RuntimeException: java.io.FileNotFoundException: /disk6/ndevyarn/nm/usercache/tim/appcache/application_1456485348783_3429/container_1456485348783_3429_01_000019/tmp/chkp3241218411712328004/1/6268662011559673861 (No such file or directory)
	at com.datatorrent.netlet.util.DTThrowable.wrapIfChecked(DTThrowable.java:50)
	at com.datatorrent.netlet.util.DTThrowable.rethrow(DTThrowable.java:31)
	at com.datatorrent.common.util.AsyncFSStorageAgent.copyToHDFS(AsyncFSStorageAgent.java:126)
	at com.datatorrent.stram.engine.Node$CheckpointHandler.call(Node.java:684)
	at com.datatorrent.stram.engine.Node$CheckpointHandler.call(Node.java:673)
	at java.util.concurrent.FutureTask.run(FutureTask.java:262)
	at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
	at java.util.concurrent.FutureTask.run(FutureTask.java:262)
	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.FileNotFoundException: /disk6/ndevyarn/nm/usercache/tim/appcache/application_1456485348783_3429/container_1456485348783_3429_01_000019/tmp/chkp3241218411712328004/1/6268662011559673861 (No such file or directory)
	at java.io.FileInputStream.open(Native Method)
	at java.io.FileInputStream.<init>(FileInputStream.java:146)
	at com.datatorrent.common.util.AsyncFSStorageAgent.copyToHDFS(AsyncFSStorageAgent.java:117)
	... 8 more


> Reducing Dag Checkpoint Window Count Causes Async Checkpoint Errors
> -------------------------------------------------------------------
>
>                 Key: APEXCORE-415
>                 URL: https://issues.apache.org/jira/browse/APEXCORE-415
>             Project: Apache Apex Core
>          Issue Type: Bug
>            Reporter: Timothy Farkas
>            Assignee: Timothy Farkas
>
> Application that reproduces the issue is here
> https://github.com/ilooner/streamcodec-bug/tree/asyncCheckpointBug
> java.lang.RuntimeException: java.util.concurrent.ExecutionException: java.lang.RuntimeException: java.io.FileNotFoundException: /disk6/ndevyarn/nm/usercache/tim/appcache/application_1456485348783_3429/container_1456485348783_3429_01_000019/tmp/chkp3241218411712328004/1/6268662011559673861 (No such file or directory)
> 	at com.datatorrent.netlet.util.DTThrowable.wrapIfChecked(DTThrowable.java:59)
> 	at com.datatorrent.stram.engine.Node.reportStats(Node.java:465)
> 	at com.datatorrent.stram.engine.InputNode.run(InputNode.java:156)
> 	at com.datatorrent.stram.engine.StreamingContainer$2.run(StreamingContainer.java:1388)
> Caused by: java.util.concurrent.ExecutionException: java.lang.RuntimeException: java.io.FileNotFoundException: /disk6/ndevyarn/nm/usercache/tim/appcache/application_1456485348783_3429/container_1456485348783_3429_01_000019/tmp/chkp3241218411712328004/1/6268662011559673861 (No such file or directory)
> 	at java.util.concurrent.FutureTask.report(FutureTask.java:122)
> 	at java.util.concurrent.FutureTask.get(FutureTask.java:188)
> 	at com.datatorrent.stram.engine.Node.reportStats(Node.java:458)
> 	... 2 more
> Caused by: java.lang.RuntimeException: java.io.FileNotFoundException: /disk6/ndevyarn/nm/usercache/tim/appcache/application_1456485348783_3429/container_1456485348783_3429_01_000019/tmp/chkp3241218411712328004/1/6268662011559673861 (No such file or directory)
> 	at com.datatorrent.netlet.util.DTThrowable.wrapIfChecked(DTThrowable.java:50)
> 	at com.datatorrent.netlet.util.DTThrowable.rethrow(DTThrowable.java:31)
> 	at com.datatorrent.common.util.AsyncFSStorageAgent.copyToHDFS(AsyncFSStorageAgent.java:126)
> 	at com.datatorrent.stram.engine.Node$CheckpointHandler.call(Node.java:684)
> 	at com.datatorrent.stram.engine.Node$CheckpointHandler.call(Node.java:673)
> 	at java.util.concurrent.FutureTask.run(FutureTask.java:262)
> 	at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
> 	at java.util.concurrent.FutureTask.run(FutureTask.java:262)
> 	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.FileNotFoundException: /disk6/ndevyarn/nm/usercache/tim/appcache/application_1456485348783_3429/container_1456485348783_3429_01_000019/tmp/chkp3241218411712328004/1/6268662011559673861 (No such file or directory)
> 	at java.io.FileInputStream.open(Native Method)
> 	at java.io.FileInputStream.<init>(FileInputStream.java:146)
> 	at com.datatorrent.common.util.AsyncFSStorageAgent.copyToHDFS(AsyncFSStorageAgent.java:117)
> 	... 8 more



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)