[
https://issues.apache.org/jira/browse/HBASE-6270?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
stack resolved HBASE-6270.
--------------------------
Resolution: Later
We are better now but still loads of work to do. Better to open specific
issues that come of profiling rather than this generic issue of mine.
> If all data is locally cached, undo locking and context switching so we are
> cpu bound
> -------------------------------------------------------------------------------------
>
> Key: HBASE-6270
> URL: https://issues.apache.org/jira/browse/HBASE-6270
> Project: HBase
> Issue Type: Bug
> Components: Performance
> Reporter: stack
>
> See Dhruba's blog here towards the end where he talks about HBase:
> http://hadoopblog.blogspot.com.es/2012/05/hadoop-and-solid-state-drives.html
> He says that when all data is local and cached, we bind ourselves up with
> locks and context switching, so much so, that we are unable to use all CPU.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
