hadoop-common-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Hemanth Yamijala (JIRA)" <j...@apache.org>
Subject [jira] Updated: (HADOOP-5883) TaskMemoryMonitorThread might shoot down tasks even if their processes momentarily exceed the requested memory
Date Tue, 26 May 2009 15:15:45 GMT

     [ https://issues.apache.org/jira/browse/HADOOP-5883?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]

Hemanth Yamijala updated HADOOP-5883:
-------------------------------------

    Attachment: HADOOP-5883.patch

New patch incorporating Vinod's comments.

> TaskMemoryMonitorThread might shoot down tasks even if their processes momentarily exceed
the requested memory
> --------------------------------------------------------------------------------------------------------------
>
>                 Key: HADOOP-5883
>                 URL: https://issues.apache.org/jira/browse/HADOOP-5883
>             Project: Hadoop Core
>          Issue Type: Bug
>          Components: mapred
>            Reporter: Hemanth Yamijala
>         Attachments: HADOOP-5883.patch, HADOOP-5883.patch, HADOOP-5883.patch
>
>
> Currently the TaskMemoryMonitorThread kills tasks as soon as it detects they are consuming
more memory than the max value specified. There are valid cases (see HADOOP-5059) where if
a program is executed from the task, it might momentarily occupy twice the amount of memory
for a short time. Ideally the monitoring thread should handle this case.

-- 
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