[
https://issues.apache.org/jira/browse/HBASE-16890?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16258963#comment-16258963
]
ramkrishna.s.vasudevan commented on HBASE-16890:
------------------------------------------------
bq.No. But I like the numbers you are getting. Can you paste config. and
command you ran so can repro? Thanks
Sure. Will do it.
{code}
./hbase org.apache.hadoop.hbase.PerformanceEvaluation --nomapred --size=25
--presplit=20 --writeToWAL=true --bloomFilter=ROW --inmemoryCompaction=NONE
randomWrite 50
{code}
This is what we tried. So before doing async WAL need to change the config to
write with AsyncWAL.
{code}
<property>
<name>hbase.wal.provider</name>
<value>asyncfs</value>
</property>
{code}
bq.Personally I think YCSB result is more persuasive. Could we help get some
number here?
Sure. If [~chancelq] does not have time I can try it with YCSB not an issue.
But one good thing is that previously even for this small load there was a
difference in performance with Async.
[~carp84]
What is your feedback with AsyncWAL and its perf in case you have already tried
in your prod cluster? That will be a good take away here rather than small
tests.
> Analyze the performance of AsyncWAL and fix the same
> ----------------------------------------------------
>
> Key: HBASE-16890
> URL: https://issues.apache.org/jira/browse/HBASE-16890
> Project: HBase
> Issue Type: Sub-task
> Components: wal
> Affects Versions: 2.0.0
> Reporter: ramkrishna.s.vasudevan
> Assignee: ramkrishna.s.vasudevan
> Priority: Blocker
> Fix For: 2.0.0-beta-1
>
> Attachments: AsyncWAL_disruptor.patch, AsyncWAL_disruptor_1
> (2).patch, AsyncWAL_disruptor_3.patch, AsyncWAL_disruptor_3.patch,
> AsyncWAL_disruptor_4.patch, AsyncWAL_disruptor_6.patch,
> HBASE-16890-rc-v2.patch, HBASE-16890-rc-v3.patch,
> HBASE-16890-remove-contention-v1.patch, HBASE-16890-remove-contention.patch,
> Screen Shot 2016-10-25 at 7.34.47 PM.png, Screen Shot 2016-10-25 at 7.39.07
> PM.png, Screen Shot 2016-10-25 at 7.39.48 PM.png, Screen Shot 2016-11-04 at
> 5.21.27 PM.png, Screen Shot 2016-11-04 at 5.30.18 PM.png, async.svg,
> classic.svg, contention.png, contention_defaultWAL.png
>
>
> Tests reveal that AsyncWAL under load in single node cluster performs slower
> than the Default WAL. This task is to analyze and see if we could fix it.
> See some discussions in the tail of JIRA HBASE-15536.
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
