[jira] [Commented] (HBASE-12040) Performances issues with branch-1 and master

["Devaraj Das (JIRA)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/HBASE-12040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14148043#comment-14148043 ] 

Devaraj Das commented on HBASE-12040:
-------------------------------------

I was looking at the FilterScan test performance regression.. Ran it the way [~jmspaggi] cited in the email thread referenced in the previous comment.
{noformat}
hbase org.apache.hadoop.hbase.PerformanceEvaluation sequentialWrite 1;
echo balancer | bin/hbase shell; sleep 60;
hbase org.apache.hadoop.hbase.PerformanceEvaluation --rows=100 --nomapred filterScan 1
{noformat}

After a couple of runs with various versions of hbase, I think HBASE-11331 has something to do with the regression (although my runs were not enabling that feature). 
I can consistently reproduce the problem on the tip of the 0.98 branch. But if I run the test with the contents of 0.98 as of the commit sha 1cf6c7b2471da2578ee023fec1d89f73e460ee59 (prior to the commit for HBASE-11331), I don't see the issue. I also tried running with the sha 822cbc867c1424da8cfa793c9a2e5f374e5da4bf (this is after a few, mostly unrelated, commits after the commit for HBASE-11331),  and I could reproduce the problem.

[~stack], [~jmspaggi], if you have time, can you please validate this at your end?

> Performances issues with branch-1 and master
> --------------------------------------------
>
>                 Key: HBASE-12040
>                 URL: https://issues.apache.org/jira/browse/HBASE-12040
>             Project: HBase
>          Issue Type: Bug
>    Affects Versions: 0.99.1
>            Reporter: Jean-Marc Spaggiari
>            Assignee: stack
>            Priority: Blocker
>             Fix For: 0.99.1
>
>
> While testing 0.99.0RC1 release performances, compared to 0.98.6, figured that:
> - FilteredScanTest is 100 times slower;
> - RandomReadTest is 1.5 times slower;
> - RandomSeekScanTest is 3.2 times slower;
> - RandomScanWithRange10Test is 1,2 times slower;
> - RandomScanWithRange100Test is 1,3 times slower;
> - RandomScanWithRange1000Test is 4 times slower;
> - SequentialReadTest is 1,7 times slower;
> - SequentialWriteTest is just a bit faster;
> - RandomWriteTest	 is just a bit faster;
> - GaussianRandomReadBenchmark is just a beat slower;
> - SequentialReadBenchmark is 1,1 times slower;
> - SequentialWriteBenchmark is 1,1 times slower;
> - UniformRandomReadBenchmark crashed;
> - UniformRandomSmallScan is 1,3 times slower.



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)