You are viewing a plain text version of this content. The canonical link for it is here.

Posted to dev@hbase.apache.org by "Jean-Daniel Cryans (JIRA)" <ji...@apache.org> on 2008/12/06 18:27:44 UTC

[jira] Updated: (HBASE-1049) Backport HBASE-998 to branch 0.18

     [ https://issues.apache.org/jira/browse/HBASE-1049?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Jean-Daniel Cryans updated HBASE-1049:
--------------------------------------

    Attachment: hbase-1049.patch

Backport patch.

> Backport HBASE-998 to branch 0.18
> ---------------------------------
>
>                 Key: HBASE-1049
>                 URL: https://issues.apache.org/jira/browse/HBASE-1049
>             Project: Hadoop HBase
>          Issue Type: Improvement
>    Affects Versions: 0.18.1
>            Reporter: Jean-Daniel Cryans
>            Assignee: Jean-Daniel Cryans
>             Fix For: 0.18.2
>
>         Attachments: hbase-1049.patch
>
>
> Without HBASE-998, any cluster with hundreds of regions will suffer from inefficient getClosestRowBefore in META. For example, during a modest upload job in a 400 regions cluster with 34 reducers, creating a HTable could take more than 600 seconds and tasks were failing for that reason.

-- 
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.