chukwa-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Eric Yang (JIRA)" <j...@apache.org>
Subject [jira] Updated: (CHUKWA-78) Track map reduce cluster usage through through job history and jobconf
Date Wed, 08 Apr 2009 04:23:12 GMT

     [ https://issues.apache.org/jira/browse/CHUKWA-78?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]

Eric Yang updated CHUKWA-78:
----------------------------

    Attachment: CHUKWA-78.patch

After job conf and job tracker data is loaded to the database, the database partition should
down sample and roll up the jobs/tasks data to bigger partitions.

> Track map reduce cluster usage through through job history and jobconf
> ----------------------------------------------------------------------
>
>                 Key: CHUKWA-78
>                 URL: https://issues.apache.org/jira/browse/CHUKWA-78
>             Project: Hadoop Chukwa
>          Issue Type: New Feature
>          Components: data collection, Data Processors
>         Environment: Redhat 5.1, Java 6
>            Reporter: Eric Yang
>            Assignee: Eric Yang
>            Priority: Blocker
>         Attachments: CHUKWA-78.patch
>
>
> Job history data and jobconf contains valuable information to determine the usage of
the map reduce job cluster.  The request feature is to create the following components:
> - ChukwaJobTrackerInstrumentation API to stream job history and jobconf file to Chukwa.
> - parsers to collect job data.
> - MDL dictionary to load key/value pair for Job data to database.
> - Usage report of the cluster base on user, and job queues.

-- 
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