[
https://issues.apache.org/jira/browse/HBASE-11964?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14132208#comment-14132208
]
Andrew Purtell commented on HBASE-11964:
----------------------------------------
I think what we want is for node failover work to be better distributed around
the cluster, rather than have one regionserver potentially win the lock when
taking over for failed regionservers much more often than other peers in the
cluster, causing really uneven distribution of replication work.
The patch on this issue actually doesn't get to the core issue (yet) I think.
It might be useful to propose alternate changes here, or we can just resolve
this as Later.
Ping [~lhofhansl], [~jesse_yates]
> Improve replication source thread handling
> ------------------------------------------
>
> Key: HBASE-11964
> URL: https://issues.apache.org/jira/browse/HBASE-11964
> Project: HBase
> Issue Type: Sub-task
> Reporter: Andrew Purtell
> Assignee: Andrew Purtell
> Fix For: 2.0.0, 0.98.7, 0.94.24, 0.99.1
>
> Attachments: HBASE-11964-0.98.patch, HBASE-11964.patch
>
>
> Improve replication source thread handling. Limit parallelism when
> transferring queues. Ensure replication sources terminate properly.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
