You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@hbase.apache.org by "stack (JIRA)" <ji...@apache.org> on 2013/09/23 18:55:02 UTC
[jira] [Updated] (HBASE-4231) Flush regions in multiple threads
[ https://issues.apache.org/jira/browse/HBASE-4231?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
stack updated HBASE-4231:
-------------------------
Fix Version/s: (was: 0.95.0)
> Flush regions in multiple threads
> ---------------------------------
>
> Key: HBASE-4231
> URL: https://issues.apache.org/jira/browse/HBASE-4231
> Project: HBase
> Issue Type: Improvement
> Components: regionserver
> Affects Versions: 0.94.0
> Reporter: Todd Lipcon
>
> As servers get beefier, it makes less and less sense to have only a single thread do flushes at a time. In watching an insert-only benchmark run, HBase isn't currently disk, network, or CPU-bound -- it seems it's bound only by the rate at which flushes and compactions get processed. Increasing the threading a bit here should increase total disk/network throughput utilization.
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira