[ https://issues.apache.org/jira/browse/SPARK-37559?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17453971#comment-17453971 ]
Apache Spark commented on SPARK-37559: -------------------------------------- User 'ulysses-you' has created a pull request for this issue: https://github.com/apache/spark/pull/34820 > ShuffledRowRDD get preferred locations order by reduce size > ----------------------------------------------------------- > > Key: SPARK-37559 > URL: https://issues.apache.org/jira/browse/SPARK-37559 > Project: Spark > Issue Type: Improvement > Components: SQL > Affects Versions: 3.3.0 > Reporter: XiDuo You > Priority: Major > > The coalesced partition can contain several reduce partitions. The preferred > locations of the RDD partition should be the biggest reduce partition before > coalesced. So it can get a better data locality and reduce the network > traffic. -- This message was sent by Atlassian Jira (v8.20.1#820001) --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org