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 "Vinod Kumar Vavilapalli (JIRA)" <ji...@apache.org> on 2014/02/26 00:49:25 UTC
[jira] [Updated] (MAPREDUCE-5517) enabling uber mode with 0 reducer
still requires mapreduce.reduce.memory.mb to be less than
yarn.app.mapreduce.am.resource.mb
[ https://issues.apache.org/jira/browse/MAPREDUCE-5517?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Vinod Kumar Vavilapalli updated MAPREDUCE-5517:
-----------------------------------------------
Status: Open (was: Patch Available)
Few more nits:
- Fix lines longer than 80 chars
- Make the same changes w.r.t cpu configuration too?
- The conditional code has become a bit complex. Rewrite using simple if..else statements? Also create local variables for values of MAP_MEMORY_MB etc instead of repeated config lookups?
> enabling uber mode with 0 reducer still requires mapreduce.reduce.memory.mb to be less than yarn.app.mapreduce.am.resource.mb
> -----------------------------------------------------------------------------------------------------------------------------
>
> Key: MAPREDUCE-5517
> URL: https://issues.apache.org/jira/browse/MAPREDUCE-5517
> Project: Hadoop Map/Reduce
> Issue Type: Bug
> Affects Versions: 2.0.5-alpha
> Reporter: Siqi Li
> Assignee: Siqi Li
> Priority: Minor
> Attachments: MAPREDUCE_5517_v3.patch.txt, MAPREDUCE_5517_v4.patch.txt
>
>
> Since there is no reducer, the memory allocated to reducer is irrelevant to enable uber mode of a job
--
This message was sent by Atlassian JIRA
(v6.1.5#6160)