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

Posted to issues@ozone.apache.org by "Ethan Rose (Jira)" <ji...@apache.org> on 2023/09/11 16:40:00 UTC

[jira] [Commented] (HDDS-2146) Optimize block write path performance by reducing no of watchForCommit calls

    [ https://issues.apache.org/jira/browse/HDDS-2146?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17763812#comment-17763812 ] 

Ethan Rose commented on HDDS-2146:
----------------------------------

cc Ritesh and [~szetszwo] since this is perf related and may be fixed by streaming.

> Optimize block write path performance by reducing no of watchForCommit calls
> ----------------------------------------------------------------------------
>
>                 Key: HDDS-2146
>                 URL: https://issues.apache.org/jira/browse/HDDS-2146
>             Project: Apache Ozone
>          Issue Type: Improvement
>          Components: Ozone Client
>            Reporter: Shashikant Banerjee
>            Assignee: Shashikant Banerjee
>            Priority: Major
>              Labels: TriagePending
>
> Currently, the watchForCommit calls from client to Ratis server for All replicated semantics happens when the max buffer limit is reached which can potentially be called 4 times as per the default configs for a single full block write. The idea here is inspect and add optimizations to reduce the no of watchForCommit calls.



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

---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@ozone.apache.org
For additional commands, e-mail: issues-help@ozone.apache.org