[
https://issues.apache.org/jira/browse/HBASE-8420?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13652160#comment-13652160
]
Jean-Daniel Cryans commented on HBASE-8420:
-------------------------------------------
I think we need a way to keep track of the total size of what's being
pre-fetched, and make sure we can keep it under a certain size. I can totally
see a badly behaving client opening a lot of scanners, pre-fetching enabled,
and then we're stuck with a lot of garbage in memory. Sure, we're going to
clean it in a minute, but I've also seen cases where hundreds of scanners are
created per minute.
Else, this feature is a sure way to get users to DDOS themselves.
> 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,
> trunk-8420_v1.patch, trunk-8420_v2.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
