[
https://issues.apache.org/jira/browse/HBASE-12988?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14615107#comment-14615107
]
Abhishek Singh Chouhan commented on HBASE-12988:
------------------------------------------------
[~lhofhansl] Sorry for the delay, was busy lately. Doing a performance run with
patch today. Will share the numbers tomorrow.
As for the debug messages, i was keeping a track of the time it took for
ReplicationProtbufUtil.replicateWALEntry on the source side, we can maybe have
statements at trace level to track how much time it took for all the threads to
parallely apply edits (we can log just after we get all the futures). On the
sink side i was keeping track of the time taken by replicateEntries(..) and
then to profile further and see which part was taking the most time, was
monitoring how much was being taken to batch into the sink cluster. Should we
add all these at trace level (having these at debug level would be too spammy
IMO).
> [Replication]Parallel apply edits across regions
> ------------------------------------------------
>
> Key: HBASE-12988
> URL: https://issues.apache.org/jira/browse/HBASE-12988
> Project: HBase
> Issue Type: Improvement
> Components: Replication
> Reporter: hongyu bi
> Assignee: Lars Hofhansl
> Attachments: 12988-v2.txt, 12988-v3.txt, 12988-v4.txt, 12988-v5.txt,
> 12988.txt, HBASE-12988-0.98.patch, ParallelReplication-v2.txt
>
>
> we can apply edits to slave cluster in parallel on table-level to speed up
> replication .
> update : per conversation blow , it's better to apply edits on row-level in
> parallel
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
