hbase-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Elliott Clark (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HBASE-15047) Try spin lock for MVCC completion
Date Wed, 30 Dec 2015 03:06:49 GMT

    [ https://issues.apache.org/jira/browse/HBASE-15047?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15074582#comment-15074582
] 

Elliott Clark commented on HBASE-15047:
---------------------------------------

bq.And usually I do not think a simple spin can perform better than standard locking method.

http://askldjd.com/2010/05/16/spin-wait-vs-condition-variable/
http://stackoverflow.com/questions/5869825/when-should-one-use-a-spinlock-instead-of-mutex/5870415#5870415
http://www.alexonlinux.com/pthread-mutex-vs-pthread-spinlock

Spin locking is much faster than requesting the operating system to de-schedule and re-schedule
a thread. 

> Try spin lock for MVCC completion
> ---------------------------------
>
>                 Key: HBASE-15047
>                 URL: https://issues.apache.org/jira/browse/HBASE-15047
>             Project: HBase
>          Issue Type: Bug
>            Reporter: Elliott Clark
>            Assignee: Elliott Clark
>         Attachments: HBASE-15047.patch
>
>
> Waits/Notify is very very expensive since it can cost a thread scheduling. There should
only ever be a few threads ( < Num Cores ) running. So it should be possible to spin and
use compare and swap to update the read point.



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

Mime
View raw message