[
https://issues.apache.org/jira/browse/HBASE-6870?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13758372#comment-13758372
]
Jonathan Hsieh commented on HBASE-6870:
---------------------------------------
updated the description to make it easier to understand
> HTable#coprocessorExec always scan the whole table
> ---------------------------------------------------
>
> Key: HBASE-6870
> URL: https://issues.apache.org/jira/browse/HBASE-6870
> Project: HBase
> Issue Type: Improvement
> Components: Coprocessors
> Affects Versions: 0.94.1, 0.95.0, 0.95.2
> Reporter: chunhui shen
> Assignee: chunhui shen
> Priority: Critical
> Fix For: 0.98.0, 0.94.8, 0.95.1
>
> Attachments: 6870-v4.txt, hbase-0.94-6870v6.patch,
> hbase-0.95-6870v6.patch, HBASE-6870.patch, HBASE-6870-testPerformance.patch,
> HBASE-6870v2.patch, HBASE-6870v3.patch, hbase-6870v5.patch, hbase-6870v6.patch
>
>
> In current logic, HTable#coprocessorExec always scans the entire META table,
> loading it into memory and then filters the keys to return only those that
> fall in specified range. The version after the patch only scans the portions
> of meta that are in the specified key range, and returns them. Put simply --
> before we did a load-all-then-filter; afterwards we only-scan-what-is-needed.
> The former has low efficiency and greatly impacts the Regionserver carrying
> .META. when there are many coprocessorExec requests.
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira
