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 "Vinay Kumar Thota (JIRA)" <ji...@apache.org> on 2011/06/16 12:53:47 UTC

[jira] [Created] (MAPREDUCE-2599) Gridmix system tests are failing due to misconfiguration of task memory in simulated cluster when high ram job emulation enabled.

Gridmix system tests are failing due to misconfiguration of task memory in simulated cluster when high ram job emulation enabled.
---------------------------------------------------------------------------------------------------------------------------------

                 Key: MAPREDUCE-2599
                 URL: https://issues.apache.org/jira/browse/MAPREDUCE-2599
             Project: Hadoop Map/Reduce
          Issue Type: Bug
          Components: contrib/gridmix
            Reporter: Vinay Kumar Thota
            Assignee: Amar Kamat


Gridmix system test are failing due to misconfiguration of task memory in simulated cluster when high ram job emulation enabled.

Girdmix scale the task memory for emulation of high ram jobs based on simulated cluster configuration and it reserved the slots based on scaled memory information of each task. Here, I found an issue, suppose if total reserved slots of either map or reduce exceeds the slot capacity then it hangs the job and failed after timeout.So, Gridmix should show either error message or bailing out before submitting the job in this condition.


--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira