hadoop-mapreduce-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Allen Wittenauer (JIRA)" <j...@apache.org>
Subject [jira] Updated: (MAPREDUCE-1180) Detailed histogram of map/reduce slots usage
Date Tue, 03 Nov 2009 18:49:32 GMT

     [ https://issues.apache.org/jira/browse/MAPREDUCE-1180?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]

Allen Wittenauer updated MAPREDUCE-1180:
----------------------------------------

    Attachment: samplechart.png

This is a simple example with a cluster that has 20 map slots.  It is a snapshot of when all
the slots are being used.

> Detailed histogram of map/reduce slots usage
> --------------------------------------------
>
>                 Key: MAPREDUCE-1180
>                 URL: https://issues.apache.org/jira/browse/MAPREDUCE-1180
>             Project: Hadoop Map/Reduce
>          Issue Type: Wish
>            Reporter: Allen Wittenauer
>            Priority: Minor
>         Attachments: samplechart.png
>
>
> People are always looking for ideas of things to implement... so here's one. :)
> I'd like an app that I can throw at a JobHistory directory that would show me detailed
slot usage by job, user, pool, etc, in an area stacked chart format.  This would be very helpful
to determine if a particular job, user, or pool is under/over utilizing the capacity, if we
need more capacity, what time slots have holes, etc.  I'll see if I can create an example
in Excel of what I'm thinking of.

-- 
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