You are viewing a plain text version of this content. The canonical link for it is here.

Posted to commits@cassandra.apache.org by "Jonathan Ellis (JIRA)" <ji...@apache.org> on 2014/12/03 18:48:13 UTC

[jira] [Commented] (CASSANDRA-8415) Reduce maxHintsInProgress

    [ https://issues.apache.org/jira/browse/CASSANDRA-8415?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14233239#comment-14233239 ] 

Jonathan Ellis commented on CASSANDRA-8415:
-------------------------------------------

Patch to cut it to 128*cores from 1024*cores.  Part of me wants to throw this in 2.0.12 as well, but I don't want to go too far the other direction either and we're basically taking an educated guess still.

> Reduce maxHintsInProgress
> -------------------------
>
>                 Key: CASSANDRA-8415
>                 URL: https://issues.apache.org/jira/browse/CASSANDRA-8415
>             Project: Cassandra
>          Issue Type: Improvement
>          Components: Core
>            Reporter: Jonathan Ellis
>            Assignee: Jonathan Ellis
>             Fix For: 2.1.3
>
>         Attachments: 8415.txt
>
>
> We have lots of evidence at this point that load shedding isn't kicking in fast enough to stop people from knocking nodes over.  A major contributor is writing hints for dropped mutations on the coordinator.  Reducing maxHintsInProgress will result in OverloadedException being thrown sooner.



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