hadoop-mapreduce-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Vinod K V (JIRA)" <j...@apache.org>
Subject [jira] Resolved: (MAPREDUCE-515) CapacityTaskScheduler.MapSchedulingMgr.killTasksFromJob() will not work as expected
Date Mon, 09 Nov 2009 09:34:48 GMT

     [ https://issues.apache.org/jira/browse/MAPREDUCE-515?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]

Vinod K V resolved MAPREDUCE-515.
---------------------------------

    Resolution: Invalid

Preemption is removed after HADOOP-5726. This issue is no longer valid.

> CapacityTaskScheduler.MapSchedulingMgr.killTasksFromJob() will not work as expected
> -----------------------------------------------------------------------------------
>
>                 Key: MAPREDUCE-515
>                 URL: https://issues.apache.org/jira/browse/MAPREDUCE-515
>             Project: Hadoop Map/Reduce
>          Issue Type: Bug
>            Reporter: Amar Kamat
>
> Once capacity-scheduler decides on killing tasks, it selects running-jobs from the queue
and issues {{killTasksFromJob()}}. The order in which it kills is as follows
> - non-local maps
> - local maps
> _Killing non-local maps :_
> The code here uses {{JobInProgress.getNonLocalRunningMaps()}}. HADOOP-2119 introduced
this for handling cases like _random-writer_. Hence this api will return an empty structure
if there are reducers in the job. Hence the code fails to serve its purpose. 

-- 
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.


Mime
View raw message