[
https://issues.apache.org/jira/browse/HBASE-16156?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15360191#comment-15360191
]
Anoop Sam John edited comment on HBASE-16156 at 7/2/16 2:39 PM:
----------------------------------------------------------------
So setting inMemoryFlushInProgress time before. Ya that should be better.
Because we wont make a new thread unwantedly. HBASE-16162 I can fix that way
then.
Thought of checking and changing this locking way as part of more generic item
and just solve this bug. That is why I added the extra check in HBASE-16162
fix.
was (Author: anoop.hbase):
So setting inMemoryFlushInProgress time before. Ya that should be better.
Because we wont make a new thread unwantedly. HBASE-16162 I can fix that way
then.
> In write heavy scenario creating in memory flushes leads to contention
> ----------------------------------------------------------------------
>
> Key: HBASE-16156
> URL: https://issues.apache.org/jira/browse/HBASE-16156
> Project: HBase
> Issue Type: Sub-task
> Affects Versions: 2.0.0
> Reporter: ramkrishna.s.vasudevan
> Assignee: ramkrishna.s.vasudevan
> Fix For: 2.0.0
>
>
> In write heavy cases, the inmemory flushes blocks the write because it takes
> a update lock. Dumps show that it is causing heavy contention and leads to
> memstore filling up and so intern blocks the flush from happening sooner.
> This JIRA is to discuss optimal settings and then make suitable changes.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
