hadoop-common-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Mahadev konar (JIRA)" <j...@apache.org>
Subject [jira] Updated: (HADOOP-205) the job tracker does not schedule enough map on the cluster
Date Tue, 23 May 2006 04:08:30 GMT
     [ http://issues.apache.org/jira/browse/HADOOP-205?page=all ]

Mahadev konar updated HADOOP-205:

    Attachment: maplaunch.patch

This patch allows map/reduce jobs to be scheduled using the pending load rather than the current
load. Also, I have made changes in the JobInProgress to keep a running count of number of
running/finished maps/reduces.

> the job tracker does not schedule enough map on the cluster
> -----------------------------------------------------------
>          Key: HADOOP-205
>          URL: http://issues.apache.org/jira/browse/HADOOP-205
>      Project: Hadoop
>         Type: Bug

>   Components: mapred
>     Versions: 0.2
>     Reporter: Owen O'Malley
>     Assignee: Owen O'Malley
>      Fix For: 0.4
>  Attachments: maplaunch.patch
> The job tracker during my big sort runs only has 80-120 maps running at a time with 2
tasks/node and 179 nodes and a large queue of map tasks. It seems to be caused by the load
balancing using the current load rather than the required load to run all of the queued tasks.

This message is automatically generated by JIRA.
If you think it was sent incorrectly contact one of the administrators:
For more information on JIRA, see:

View raw message