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

Posted to mapreduce-dev@hadoop.apache.org by "Ravi Gummadi (Created) (JIRA)" <ji...@apache.org> on 2012/01/25 10:28:40 UTC

[jira] [Created] (MAPREDUCE-3722) [Gridmix] Use high-RAM jobs' behavior/info in cluster overloading logic in STRESS mode

[Gridmix] Use high-RAM jobs' behavior/info in cluster overloading logic in STRESS mode
--------------------------------------------------------------------------------------

                 Key: MAPREDUCE-3722
                 URL: https://issues.apache.org/jira/browse/MAPREDUCE-3722
             Project: Hadoop Map/Reduce
          Issue Type: Improvement
          Components: contrib/gridmix
            Reporter: Ravi Gummadi


Currently, Gridmix in STRESS mode calculates the existing load on the cluster to decide on whether to load further or not. The number of map/reduce tasks of all jobs are considered in this calculation as "each task taking single slot". But with high RAM jobs, this is not true and so needs to fix this computation.

--
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