[jira] Updated: (MAPREDUCE-2155) RaidNode should optionally dispatch map reduce jobs to fix corrupt blocks (instead of fixing locally)

["Patrick Kling (JIRA)" <ji...@apache.org>]

     [ https://issues.apache.org/jira/browse/MAPREDUCE-2155?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Patrick Kling updated MAPREDUCE-2155:
-------------------------------------

    Attachment: MAPREDUCE-2155.patch

This change adds a new implementation of the raid block fixer that uses map reduce jobs to fix missing/corrupt blocks, which allows us to fix a large number of blocks quickly. The user can specify via a configuration variable whether the old (local) or the new implementation should be used.

> RaidNode should optionally dispatch map reduce jobs to fix corrupt blocks (instead of fixing locally)
> -----------------------------------------------------------------------------------------------------
>
>                 Key: MAPREDUCE-2155
>                 URL: https://issues.apache.org/jira/browse/MAPREDUCE-2155
>             Project: Hadoop Map/Reduce
>          Issue Type: Improvement
>            Reporter: Patrick Kling
>         Attachments: MAPREDUCE-2155.patch
>
>
> Recomputing blocks based on parity information is expensive. Rather than doing this locally at the RaidNode, we should run map reduce jobs. This will allow us to quickly fix a large number of corrupt or missing blocks.

-- 
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.