[
https://issues.apache.org/jira/browse/HBASE-15971?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15326666#comment-15326666
]
stack commented on HBASE-15971:
-------------------------------
HBASE-11355 "a couple of callQueue related improvements" when applied on
branch-1 actually 3x'd the perf but throughput numbers were super low before it
was applied; we went from 80k to 230k. The following commit dropped the
branch-1 throughput from 180k to 80k:
commit de98955c16d71f2486f54f88c9ca6c88b91a3812
Author: mbertozzi <mbertozzi@unknown>
Date: Wed May 7 21:05:04 2014 +0000
HBASE-10993 Deprioritize long-running scanners
Checking to see if I revert both of the above, does branch-1 perf come back up
to 0.98s.
> Regression: Random Read/WorkloadC slower in 1.x than 0.98
> ---------------------------------------------------------
>
> Key: HBASE-15971
> URL: https://issues.apache.org/jira/browse/HBASE-15971
> Project: HBase
> Issue Type: Sub-task
> Components: rpc
> Reporter: stack
> Assignee: stack
> Priority: Critical
> Attachments: 098.hits.png, 098.png, HBASE-15971.branch-1.001.patch,
> Screen Shot 2016-06-10 at 5.08.24 PM.png, Screen Shot 2016-06-10 at 5.08.26
> PM.png, branch-1.hits.png, branch-1.png,
> flight_recording_10172402220203_28.branch-1.jfr,
> flight_recording_10172402220203_29.09820.0.98.20.jfr, handlers.fp.png,
> hits.fp.png, hits.patched1.0.vs.unpatched1.0.vs.098.png, run_ycsb.sh
>
>
> branch-1 is slower than 0.98 doing YCSB random read/workloadC. It seems to be
> doing about 1/2 the throughput of 0.98.
> In branch-1, we have low handler occupancy compared to 0.98. Hacking in
> reader thread occupancy metric, is about the same in both. In parent issue,
> hacking out the scheduler, I am able to get branch-1 to go 3x faster so will
> dig in here.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
