Mailing-List: contact hadoop-dev-help@lucene.apache.org; run by ezmlm
Precedence: bulk
Reply-To: hadoop-dev@lucene.apache.org
Message-ID: <1135581815.1143142460106.JavaMail.jira@ajax>
Date: Thu, 23 Mar 2006 19:34:20 +0000 (GMT)
From: "Owen O'Malley (JIRA)" <jira@apache.org>
To: hadoop-dev@lucene.apache.org
Subject: [jira] Updated: (HADOOP-98) The JobTracker's count of the number of
 running maps and reduces is wrong
In-Reply-To: <1952812446.1143101653374.JavaMail.jira@ajax>
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: 7bit

     [ http://issues.apache.org/jira/browse/HADOOP-98?page=all ]

Owen O'Malley updated HADOOP-98:
--------------------------------

    Attachment: task-counter.patch

This patch consolidate all of the places where status was put in to or out of the taskTrackers status map, so that
the counts of maps and reduces are maintained consistently. 

I also added the cluster status to the webapp so that you can get a quick view of how busy the cluster is.

> The JobTracker's count of the number of running maps and reduces is wrong
> -------------------------------------------------------------------------
>
>          Key: HADOOP-98
>          URL: http://issues.apache.org/jira/browse/HADOOP-98
>      Project: Hadoop
>         Type: Bug
>   Components: mapred
>     Versions: 0.1
>     Reporter: Owen O'Malley
>     Assignee: Owen O'Malley
>      Fix For: 0.1
>  Attachments: task-counter.patch
>
> When a heatbeat comes in from a task tracker, the job tracker just adds the number of currently running maps and reduces. The jobs from the previous heartbear are never subtracted. This causes the scheduling to misjudge the "loading" levels of the task trackers.

-- 
This message is automatically generated by JIRA.
-
If you think it was sent incorrectly contact one of the administrators:
   http://issues.apache.org/jira/secure/Administrators.jspa
-
For more information on JIRA, see:
   http://www.atlassian.com/software/jira