Huaxin Gao created SPARK-37523:
----------------------------------
Summary: Support optimize skewed partitions in Distribution and
Ordering if numPartitions is not specified
Key: SPARK-37523
URL: https://issues.apache.org/jira/browse/SPARK-37523
Project: Spark
Issue Type: Improvement
Components: SQL
Affects Versions: 3.3.0
Reporter: Huaxin Gao
When doing repartition in distribution and sort, if data source requests for a
specific number of partitions, we should not optimize repartition. However, if
data source does not request for a specific number of partitions, Spark should
optimize repartition and split the skewed partitions if necessary.
--
This message was sent by Atlassian Jira
(v8.20.1#820001)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
