hbase-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Cosmin Lehene (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HBASE-6270) If all data is locally cached, undo locking and context switching so we are cpu bound
Date Wed, 07 Jan 2015 22:12:36 GMT

    [ https://issues.apache.org/jira/browse/HBASE-6270?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14268366#comment-14268366
] 

Cosmin Lehene commented on HBASE-6270:
--------------------------------------

[~saint.ack@gmail.com], this seems a potentially interesting one. Would it worh a refresh?

> 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)

Mime
View raw message