[
https://issues.apache.org/jira/browse/HBASE-8420?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Jimmy Xiang updated HBASE-8420:
-------------------------------
Release Note:
By default, prefetching is enabled in the trunk version (0.95.2 and 0.98). To
disable it, users have to set prefetching off in the Scan object.
This patch introduced a configuration
hbase.hregionserver.prefetcher.resultsize.max to control how much data we can
prefetch. By default, it is 256MB. If there is already more than that much
data prefetched, no new prefetching will be scheduled until some prefetched
results are retrieved by clients, so there is room again for new prefetching.
Hadoop Flags: Reviewed
> Port HBASE-6874 Implement prefetching for scanners from 0.89-fb
> -----------------------------------------------------------------
>
> Key: HBASE-8420
> URL: https://issues.apache.org/jira/browse/HBASE-8420
> Project: HBase
> Issue Type: Improvement
> Reporter: Jimmy Xiang
> Assignee: Jimmy Xiang
> Attachments: 0.94-8420_v1.patch, 0.94-8420_v2.patch,
> 0.94-8420_v6.1.patch, trunk-8420_v1.patch, trunk-8420_v2.patch,
> trunk-8420_v3.patch, trunk-8420_v4.patch, trunk-8420_v5.1.patch,
> trunk-8420_v5.patch, trunk-8420_v6.1.patch, trunk-8420_v6.patch
>
>
> This should help scanner performance. We should have it in trunk.
--
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
