[jira] [Commented] (CASSANDRA-18766) high speculative retries on v4.1.3

["Stefan Miklosovic (Jira)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/CASSANDRA-18766?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17832436#comment-17832436 ] 

Stefan Miklosovic commented on CASSANDRA-18766:
-----------------------------------------------

[~ivnovi] [~nicolas.henneaux] this one is interesting CASSANDRA-18766 It is there from times of 4.1-alpha1 ... What that patch seems to solve is that previously it was sending speculative retries but it should not. But if that ticket introduced the performance regression you see, then it might be actually other way around?

Another possibility is that the patch indeed fixes the discrepancy around units and it started to speculate just right and you see this in your tests as it was not speculating before but it should. 

[~jonmeredith] what do you think?

> high speculative retries on v4.1.3
> ----------------------------------
>
>                 Key: CASSANDRA-18766
>                 URL: https://issues.apache.org/jira/browse/CASSANDRA-18766
>             Project: Cassandra
>          Issue Type: Bug
>          Components: Consistency/Coordination
>            Reporter: Ivans Novikovs
>            Priority: Normal
>             Fix For: 4.1.x
>
>         Attachments: signature.asc
>
>
> There are up to 10+ times higher speculative retries for reads on 4.1.3 comparing to 4.0.7 and 4.1.2 when using QUORUM and default setting of 99p.
> On 4.1.3 after upgrade I see speculative retries for up to 35% of all reads for specific table. Latency for reads is stable around 500 microseconds.
> java 1.8.0_382 is used



--
This message was sent by Atlassian Jira
(v8.20.10#820010)

---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@cassandra.apache.org
For additional commands, e-mail: commits-help@cassandra.apache.org