[
https://issues.apache.org/jira/browse/HBASE-12335?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14183865#comment-14183865
]
Nick Dimiduk commented on HBASE-12335:
--------------------------------------
bq. Do replicas have a better 99th percentile in your testing?
Usually, but not always. Will need to dig deeper into logs on a failed run. You
can see some recent results in
https://docs.google.com/spreadsheets/d/1oapgHAtliDlH73rNH-BTme4ETxkpADFRabtvP9dZ2o0/edit?usp=sharing
.
[~enis] also suggested adding meta server skipping in
RestartRsHoldingTableAction. Will come back to this for another round. Will
give that a go as well.
> IntegrationTestRegionReplicaPerf is flaky
> -----------------------------------------
>
> Key: HBASE-12335
> URL: https://issues.apache.org/jira/browse/HBASE-12335
> Project: HBase
> Issue Type: Test
> Components: test
> Affects Versions: 0.99.0, 2.0.0
> Reporter: Nick Dimiduk
> Assignee: Nick Dimiduk
> Fix For: 2.0.0, 0.99.2
>
> Attachments: HBASE-12335.00-0.99.patch, HBASE-12335.00.patch,
> HBASE-12335.00.patch, HBASE-12335.00.patch
>
>
> I find that this test often fails; the assertion that running with read
> replicas should complete faster than without is usually false. I need to
> investigate further as to why this is the case and how we should tune it.
> In the mean time, I'd like to change the test to assert instead on the
> average of the stdev across all the test runs in each category. Meaning,
> enabling this feature should reduce the overall latency variance experienced
> by the client.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
