hbase-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "dhruba borthakur (JIRA)" <j...@apache.org>
Subject [jira] Commented: (HBASE-3504) HLog performance improvement
Date Fri, 04 Feb 2011 07:02:22 GMT

    [ https://issues.apache.org/jira/browse/HBASE-3504?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12990470#comment-12990470
] 

dhruba borthakur commented on HBASE-3504:
-----------------------------------------

One proposal is to make it a ReadWrite lock. The log roller should acquire the lock in Write
mode while the HLog.append() calls could acquire it in Read mode.

On a related note, I see a possible bug in the existing code where the logSyncer thread invokes
HDFS.sync on a writer that has already been closed by the log-roller.This could happen because
the logSyncer thread does not acquire the updateLock while invoking HDFS sync on the writer.

> HLog performance improvement
> ----------------------------
>
>                 Key: HBASE-3504
>                 URL: https://issues.apache.org/jira/browse/HBASE-3504
>             Project: HBase
>          Issue Type: Improvement
>          Components: regionserver
>            Reporter: dhruba borthakur
>            Assignee: dhruba borthakur
>
> The HLog.updateLock protects the rolling of logs with concurrent writes to the HDFS log
file. This is a scalability bottleneck for a workload that comprises mostly of counter-increments.

-- 
This message is automatically generated by JIRA.
-
For more information on JIRA, see: http://www.atlassian.com/software/jira

        

Mime
View raw message