You are viewing a plain text version of this content. The canonical link for it is here.

Posted to issues@tez.apache.org by "Jason Lowe (JIRA)" <ji...@apache.org> on 2016/02/11 20:31:18 UTC

[jira] [Updated] (TEZ-3114) Shuffle OOM due to EventMetaData flood

     [ https://issues.apache.org/jira/browse/TEZ-3114?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Jason Lowe updated TEZ-3114:
----------------------------
    Attachment: TEZ-3114.001.patch

Here's a patch I threw together that I think should put some back pressure on the number of events a task will allow to accumulate.  Haven't had a chance to test it on the problematic job nor write a unit test for it.

> Shuffle OOM due to EventMetaData flood
> --------------------------------------
>
>                 Key: TEZ-3114
>                 URL: https://issues.apache.org/jira/browse/TEZ-3114
>             Project: Apache Tez
>          Issue Type: Bug
>    Affects Versions: 0.7.0
>            Reporter: Jason Lowe
>         Attachments: TEZ-3114.001.patch
>
>
> A task encountered an OOM during shuffle, and investigation of the heap dump showed a lot of memory being consumed by almost 3.5 million EventMetaData objects.  Auto-parallelism had reduced the number of tasks in the vertex to 1 and there were 2000 upstream tasks to shuffle.



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