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

Posted to issues@spark.apache.org by "Holden Karau (Jira)" <ji...@apache.org> on 2021/02/04 17:36:00 UTC

[jira] [Commented] (SPARK-34337) Reject disk blocks when out of disk space

    [ https://issues.apache.org/jira/browse/SPARK-34337?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17279000#comment-17279000 ] 

Holden Karau commented on SPARK-34337:
--------------------------------------

Initially we should allow the user to configure a maximum amount of shuffle blocks to be stored. In the future we can try and use underlying FS info.

> Reject disk blocks when out of disk space
> -----------------------------------------
>
>                 Key: SPARK-34337
>                 URL: https://issues.apache.org/jira/browse/SPARK-34337
>             Project: Spark
>          Issue Type: Improvement
>          Components: Spark Core
>    Affects Versions: 3.2.0, 3.1.1, 3.1.2
>            Reporter: Holden Karau
>            Priority: Major
>
> Now that we have the ability to store shuffle blocks on dis-aggregated storage (when configured) we should add the option to reject storing blocks locally on an executor at a certain disk pressure threshold.



--
This message was sent by Atlassian Jira
(v8.3.4#803005)

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