You are viewing a plain text version of this content. The canonical link for it is here.

Posted to common-dev@hadoop.apache.org by "Hairong Kuang (JIRA)" <ji...@apache.org> on 2006/06/01 02:14:32 UTC

[jira] Updated: (HADOOP-265) Abort tasktracker if it can not write to its local directories

     [ http://issues.apache.org/jira/browse/HADOOP-265?page=all ]

Hairong Kuang updated HADOOP-265:
---------------------------------

    Attachment: mapred_disk.patch

In this patch, if a task tracker finds out that any of its local directories becomes not readable or writable, it logs the error. If all of its local directories are not readable/writable, it reports the problem to its job tracker and then aborts. When the job tracker receives the error report, it logs the error. 

A task tracker detects disk problem at startup time and before it starts a new task. A task tracker will not start if all its local directories are not readable or writable. 


> Abort tasktracker if it can not write to its local directories
> --------------------------------------------------------------
>
>          Key: HADOOP-265
>          URL: http://issues.apache.org/jira/browse/HADOOP-265
>      Project: Hadoop
>         Type: Bug

>   Components: mapred
>     Versions: 0.3
>     Reporter: Hairong Kuang
>     Assignee: Hairong Kuang
>      Fix For: 0.3
>  Attachments: mapred_disk.patch
>
> Currently if a task tracker is not able to write to any of its local directories, it continues to run and all the tasks assigned to it fail.
> A task tracker should not start upif it has a problem reading/writing any of its local directories. It should abort if it gets the problem at run time.

-- 
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