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

Posted to issues@spark.apache.org by "Hyukjin Kwon (Jira)" <ji...@apache.org> on 2021/12/15 00:31:00 UTC

[jira] [Created] (SPARK-37649) Switch default index to distributed-sequence by default in pandas API on Spark

Hyukjin Kwon created SPARK-37649:
------------------------------------

             Summary: Switch default index to distributed-sequence by default in pandas API on Spark
                 Key: SPARK-37649
                 URL: https://issues.apache.org/jira/browse/SPARK-37649
             Project: Spark
          Issue Type: Improvement
          Components: PySpark
    Affects Versions: 3.3.0
            Reporter: Hyukjin Kwon


pandas API on Spark currently sets {{compute.default_index_type}} to {{sequence}} which relies on sending all data to one executor that easily causes OOM.

We should better switch to {{distributed-sequence}} type that truly distributes the data.



--
This message was sent by Atlassian Jira
(v8.20.1#820001)

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