hadoop-common-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Arun C Murthy (JIRA)" <j...@apache.org>
Subject [jira] Commented: (HADOOP-1798) The counts of currently running maps and reduces isn't maintained correctly when task trackers fail
Date Wed, 29 Aug 2007 11:55:31 GMT

    [ https://issues.apache.org/jira/browse/HADOOP-1798?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel#action_12523550
] 

Arun C Murthy commented on HADOOP-1798:
---------------------------------------

+1

Long term, I'd like to fix updateTaskTrackerStatus to handle this better... thoughts?

> The counts of currently running maps and reduces isn't maintained correctly when task
trackers fail
> ---------------------------------------------------------------------------------------------------
>
>                 Key: HADOOP-1798
>                 URL: https://issues.apache.org/jira/browse/HADOOP-1798
>             Project: Hadoop
>          Issue Type: Bug
>          Components: mapred
>    Affects Versions: 0.13.0
>            Reporter: Owen O'Malley
>            Assignee: Owen O'Malley
>             Fix For: 0.14.1
>
>         Attachments: 1798.patch
>
>
> The code in JobTracker.processHeartbeat removes the task tracker status from trackerStatus
without updating the counts. Eventually the cluster will stop launching tasks.

-- 
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