hbase-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Todd Lipcon (JIRA)" <j...@apache.org>
Subject [jira] Commented: (HBASE-2457) RS gets stuck compacting region ad infinitum
Date Fri, 16 Apr 2010 17:46:26 GMT

    [ https://issues.apache.org/jira/browse/HBASE-2457?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12857907#action_12857907
] 

Todd Lipcon commented on HBASE-2457:
------------------------------------

I thought about this a bit on the train this morning (guess this long commute is good for
something!)

The real root of this problem is that we are getting "noop" compactions when we are blocked
on a compaction happening. Rather than changing the compaction algorithm like in stack's patch,
could we simply make it so that it checks whether there are currently flushes blocked on a
compaction, and if that's the case, force one to happen?

> RS gets stuck compacting region ad infinitum
> --------------------------------------------
>
>                 Key: HBASE-2457
>                 URL: https://issues.apache.org/jira/browse/HBASE-2457
>             Project: Hadoop HBase
>          Issue Type: Bug
>    Affects Versions: 0.20.4
>            Reporter: Todd Lipcon
>            Priority: Critical
>         Attachments: log.gz, stack
>
>
> Testing 0.20_pre_durability@934643, I ended up in a state where one region server got
stuck compacting a single region over and over again forever. This was with a special config
with very low flush threshold in order to stress test flush/compact code.

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

        

Mime
View raw message