[
https://issues.apache.org/jira/browse/HBASE-15082?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15092831#comment-15092831
]
Sean Busbey commented on HBASE-15082:
-------------------------------------
{quote}
The write pipeline changed a load with HBASE-12751. Porting the 'hack' from
branch-1.1 is mostly done as part of this attached patch. I could spend time
distilling and testing just forward porting the 'hack' for a 1.2. Preferred
trying to do the proper 'fix' given HBASE-12751 opens up new vistas allowing
reordering of when edits are sync'd and when they can go to memstore.
{quote}
Now I see my confusion. HBASE-12751 is marked as only 2.0.0, so I wasn't sure
why it'd be relevant. I see that HBASE-14465 backported it to branch-1.
How far away is a fix for the current 1.2 blocker?
> Fix merge of MVCC and SequenceID performance regression
> -------------------------------------------------------
>
> Key: HBASE-15082
> URL: https://issues.apache.org/jira/browse/HBASE-15082
> Project: HBase
> Issue Type: Sub-task
> Components: Performance
> Reporter: stack
> Assignee: stack
> Priority: Critical
> Fix For: 2.0.0, 1.2.0, 1.3.0
>
> Attachments: 15082.patch, 15082v2.patch, 15082v2.txt, 15082v3.txt,
> 15082v4.patch, 15082v5.patch, 15082v6.patch, 15082v7.patch
>
>
> This is general fix for increments (appends, checkAnd*) perf-regression
> identified in the parent issue. HBASE-15031 has a narrow fix for branch-1.1
> and branch-1.0.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
