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 2020/03/20 18:52:00 UTC

[jira] [Created] (SPARK-31208) Expose the ability for user to cleanup shuffle files

Holden Karau created SPARK-31208:
------------------------------------

             Summary: Expose the ability for user to cleanup shuffle files
                 Key: SPARK-31208
                 URL: https://issues.apache.org/jira/browse/SPARK-31208
             Project: Spark
          Issue Type: Improvement
          Components: Kubernetes
    Affects Versions: 3.1.0
            Reporter: Holden Karau
            Assignee: Holden Karau


Dynamic scaling on Kubernetes (introduced in Spark 3) depends on only shutting down executors without shuffle files. However Spark does not aggressively clean up shuffle files (see SPARK-5836) and instead depends on JVM GC on the driver to trigger deletes. We already have a mechanism to explicitly clean up shuffle files from the ALS algorithm where we create a lot of quickly orphaned shuffle files. We should expose this as an advanced developer feature to enable people to better clean-up shuffle files improving dynamic scaling of their jobs on Kubernetes.



--
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