[ https://issues.apache.org/jira/browse/SPARK-3740?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Reynold Xin updated SPARK-3740: ------------------------------- Labels: starter (was: ) > Use a compressed bitmap to track zero sized blocks in > HighlyCompressedMapStatus > ------------------------------------------------------------------------------- > > Key: SPARK-3740 > URL: https://issues.apache.org/jira/browse/SPARK-3740 > Project: Spark > Issue Type: Improvement > Components: Shuffle, Spark Core > Reporter: Reynold Xin > Labels: starter > > HighlyCompressedMapStatus uses a single long to track the average block size. > However, if a stage has a lot of zero sized outputs, this leads to > inefficiency because executors would need to send requests to fetch zero > sized blocks. > We can use a compressed bitmap to track the zero-sized blocks. > See discussion in https://github.com/apache/spark/pull/2470 -- This message was sent by Atlassian JIRA (v6.3.4#6332) --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org