[
https://issues.apache.org/jira/browse/HBASE-8635?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13673337#comment-13673337
]
Elliott Clark commented on HBASE-8635:
--------------------------------------
bq.Prefetching, however, should help all the time
Get based work loads will be hurt pretty significantly, as the block cache will
be smaller due to the unused reserved space for pre-fetching.
Honestly the whole on server pre-fetching scares me, and I would prefer to see
usage before dedicated large amounts of ram to it by default. Maybe by then
we'll have autotuning (T-Pain style)
> Define prefetcher.resultsize.max as percentage
> ----------------------------------------------
>
> Key: HBASE-8635
> URL: https://issues.apache.org/jira/browse/HBASE-8635
> Project: HBase
> Issue Type: Improvement
> Reporter: Ted Yu
> Assignee: Jimmy Xiang
> Priority: Minor
> Attachments: trunk-8635.patch
>
>
> Currently "hbase.hregionserver.prefetcher.resultsize.max" defines global
> limit for prefetching.
> The default value is 256MB.
> It would be more flexible to define this measure as a percentage of the heap.
--
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
