You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@hbase.apache.org by "Andrew Purtell (JIRA)" <ji...@apache.org> on 2008/10/09 21:24:45 UTC

[jira] Created: (HBASE-917) filesystem intensive operations such as compaction should be load aware

filesystem intensive operations such as compaction should be load aware
-----------------------------------------------------------------------

                 Key: HBASE-917
                 URL: https://issues.apache.org/jira/browse/HBASE-917
             Project: Hadoop HBase
          Issue Type: Improvement
          Components: regionserver
            Reporter: Andrew Purtell


If the underlying filesystem is already severely stressed, running intensive operations such as compaction is asking for trouble. Ideally, such actions should be deferred until load is observed to lessen. 

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


[jira] Commented: (HBASE-917) filesystem intensive operations such as compaction should be load aware

Posted by "Billy Pearson (JIRA)" <ji...@apache.org>.
    [ https://issues.apache.org/jira/browse/HBASE-917?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12638513#action_12638513 ] 

Billy Pearson commented on HBASE-917:
-------------------------------------

I see my compaction stop now during a long insert jobs that is loading the server vary heavy.
I thank it related to HBASE-616 but I do not get any messages from in the logs as we see from HBASE-616
Once insert load slows the next memcache flush starts a compaction.

> filesystem intensive operations such as compaction should be load aware
> -----------------------------------------------------------------------
>
>                 Key: HBASE-917
>                 URL: https://issues.apache.org/jira/browse/HBASE-917
>             Project: Hadoop HBase
>          Issue Type: Improvement
>          Components: regionserver
>            Reporter: Andrew Purtell
>
> If the underlying filesystem is already severely stressed, running intensive operations such as compaction is asking for trouble. Ideally, such actions should be deferred until load is observed to lessen. 

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