cloud-fan commented on a change in pull request #32450: URL: https://github.com/apache/spark/pull/32450#discussion_r628202988
########## File path: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/Statistics.scala ########## @@ -49,12 +50,15 @@ object Statistics { * @param attributeStats Statistics for Attributes. * @param isRuntime Whether the statistics is inferred from query stage runtime statistics during * adaptive query execution. + * @param mapOutputStatistics the map output statistics from query stage runtime statistics during + * adaptive query execution. */ case class Statistics( sizeInBytes: BigInt, rowCount: Option[BigInt] = None, attributeStats: AttributeMap[ColumnStat] = AttributeMap(Nil), - isRuntime: Boolean = false) { + isRuntime: Boolean = false, + mapOutputStatistics: Option[MapOutputStatistics] = None) { Review comment: > We added a rule in AdaptiveSparkPlanExec to convert SMJ to SHJ according to shuffle stats This looks like a better idea. Do you want to open a PR for it? -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org