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 (Created) (JIRA)" <ji...@apache.org> on 2012/02/04 00:53:53 UTC
[jira] [Created] (MAPREDUCE-3805) MR AM not respecting
MaxReduceRampUpLimit
MR AM not respecting MaxReduceRampUpLimit
-----------------------------------------
Key: MAPREDUCE-3805
URL: https://issues.apache.org/jira/browse/MAPREDUCE-3805
Project: Hadoop Map/Reduce
Issue Type: Bug
Components: mr-am, mrv2
Affects Versions: 0.23.0
Reporter: Vinod Kumar Vavilapalli
Fix For: 0.23.1
While running GridMixV3 with high memory reduces, we ran into issues where for jobs with significant number of maps and reduces, when the map progress hits 98-99% but still there are maps pending, reduces get every new container that RM allocates. And the job takes much longer time than with usual reduces.
For addressing precisely these issues, a configurable limit was introduced to limit the reduce ramp up. Unfortunately this limit is not working correctly.
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Assigned] (MAPREDUCE-3805) MR AM not respecting
MaxReduceRampUpLimit
Posted by "Vinod Kumar Vavilapalli (Assigned) (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/MAPREDUCE-3805?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Vinod Kumar Vavilapalli reassigned MAPREDUCE-3805:
--------------------------------------------------
Assignee: Vinod Kumar Vavilapalli
> MR AM not respecting MaxReduceRampUpLimit
> -----------------------------------------
>
> Key: MAPREDUCE-3805
> URL: https://issues.apache.org/jira/browse/MAPREDUCE-3805
> Project: Hadoop Map/Reduce
> Issue Type: Bug
> Components: mr-am, mrv2
> Affects Versions: 0.23.0
> Reporter: Vinod Kumar Vavilapalli
> Assignee: Vinod Kumar Vavilapalli
> Fix For: 0.23.1
>
>
> While running GridMixV3 with high memory reduces, we ran into issues where for jobs with significant number of maps and reduces, when the map progress hits 98-99% but still there are maps pending, reduces get every new container that RM allocates. And the job takes much longer time than with usual reduces.
> For addressing precisely these issues, a configurable limit was introduced to limit the reduce ramp up. Unfortunately this limit is not working correctly.
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Updated] (MAPREDUCE-3805) MR AM not respecting
MaxReduceRampUpLimit
Posted by "Arun C Murthy (Updated) (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/MAPREDUCE-3805?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Arun C Murthy updated MAPREDUCE-3805:
-------------------------------------
Fix Version/s: (was: 0.23.1)
0.24.0
> MR AM not respecting MaxReduceRampUpLimit
> -----------------------------------------
>
> Key: MAPREDUCE-3805
> URL: https://issues.apache.org/jira/browse/MAPREDUCE-3805
> Project: Hadoop Map/Reduce
> Issue Type: Bug
> Components: mr-am, mrv2
> Affects Versions: 0.23.0
> Reporter: Vinod Kumar Vavilapalli
> Assignee: Vinod Kumar Vavilapalli
> Fix For: 0.24.0
>
> Attachments: MAPREDUCE-3805-20120203.txt
>
>
> While running GridMixV3 with high memory reduces, we ran into issues where for jobs with significant number of maps and reduces, when the map progress hits 98-99% but still there are maps pending, reduces get every new container that RM allocates. And the job takes much longer time than with usual reduces.
> For addressing precisely these issues, a configurable limit was introduced to limit the reduce ramp up. Unfortunately this limit is not working correctly.
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Updated] (MAPREDUCE-3805) MR AM not respecting
MaxReduceRampUpLimit
Posted by "Vinod Kumar Vavilapalli (Updated) (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/MAPREDUCE-3805?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Vinod Kumar Vavilapalli updated MAPREDUCE-3805:
-----------------------------------------------
Attachment: MAPREDUCE-3805-20120203.txt
A very raw patch that we were using for GridMix with high ram reduces.
This needs cleanup and tests.
> MR AM not respecting MaxReduceRampUpLimit
> -----------------------------------------
>
> Key: MAPREDUCE-3805
> URL: https://issues.apache.org/jira/browse/MAPREDUCE-3805
> Project: Hadoop Map/Reduce
> Issue Type: Bug
> Components: mr-am, mrv2
> Affects Versions: 0.23.0
> Reporter: Vinod Kumar Vavilapalli
> Assignee: Vinod Kumar Vavilapalli
> Fix For: 0.23.1
>
> Attachments: MAPREDUCE-3805-20120203.txt
>
>
> While running GridMixV3 with high memory reduces, we ran into issues where for jobs with significant number of maps and reduces, when the map progress hits 98-99% but still there are maps pending, reduces get every new container that RM allocates. And the job takes much longer time than with usual reduces.
> For addressing precisely these issues, a configurable limit was introduced to limit the reduce ramp up. Unfortunately this limit is not working correctly.
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira