[
https://issues.apache.org/jira/browse/HBASE-12988?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Lars Hofhansl updated HBASE-12988:
----------------------------------
Attachment: ParallelReplication-v2.txt
Here's a simple patch. Only so that we can perf test this, to see whether we'll
see any improvement.
* doesn't do any grouping by table or row, so with badly times compaction on
the sink, deleted data can resurface
* fixed max parallelization, should better be scaled to the number of sink
region servers available (i.e. 10% of selected servers, or something)
As I said, just for testing so that we can see what we can expect as
improvement at best.
> [Replication]Parallel apply edits on row-level
> ----------------------------------------------
>
> Key: HBASE-12988
> URL: https://issues.apache.org/jira/browse/HBASE-12988
> Project: HBase
> Issue Type: Improvement
> Components: Replication
> Reporter: hongyu bi
> Assignee: hongyu bi
> Attachments: 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)
