You are viewing a plain text version of this content. The canonical link for it is here.
Posted to mapreduce-issues@hadoop.apache.org by "Jason Lowe (JIRA)" <ji...@apache.org> on 2015/09/10 17:58:47 UTC
[jira] [Moved] (MAPREDUCE-6474) Nodemanager ShuffleHandler can
possible exhaust file descriptors
[ https://issues.apache.org/jira/browse/MAPREDUCE-6474?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Jason Lowe moved YARN-2410 to MAPREDUCE-6474:
---------------------------------------------
Affects Version/s: (was: 2.5.0)
2.5.0
Target Version/s: 2.7.2 (was: 2.7.2)
Component/s: (was: nodemanager)
nodemanager
mrv2
Key: MAPREDUCE-6474 (was: YARN-2410)
Project: Hadoop Map/Reduce (was: Hadoop YARN)
> Nodemanager ShuffleHandler can possible exhaust file descriptors
> ----------------------------------------------------------------
>
> Key: MAPREDUCE-6474
> URL: https://issues.apache.org/jira/browse/MAPREDUCE-6474
> Project: Hadoop Map/Reduce
> Issue Type: Bug
> Components: mrv2, nodemanager
> Affects Versions: 2.5.0
> Reporter: Nathan Roberts
> Assignee: Kuhu Shukla
> Attachments: YARN-2410-v1.patch, YARN-2410-v10.patch, YARN-2410-v11.patch, YARN-2410-v2.patch, YARN-2410-v3.patch, YARN-2410-v4.patch, YARN-2410-v5.patch, YARN-2410-v6.patch, YARN-2410-v7.patch, YARN-2410-v8.patch, YARN-2410-v9.patch
>
>
> The async nature of the shufflehandler can cause it to open a huge number of
> file descriptors, when it runs out it crashes.
> Scenario:
> Job with 6K reduces, slow start set to 0.95, about 40 map outputs per node.
> Let's say all 6K reduces hit a node at about same time asking for their
> outputs. Each reducer will ask for all 40 map outputs over a single socket in a
> single request (not necessarily all 40 at once, but with coalescing it is
> likely to be a large number).
> sendMapOutput() will open the file for random reading and then perform an async transfer of the particular portion of this file(). This will theoretically
> happen 6000*40=240000 times which will run the NM out of file descriptors and cause it to crash.
> The algorithm should be refactored a little to not open the fds until they're
> actually needed.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)