comphead commented on code in PR #1424:
URL: https://github.com/apache/datafusion-comet/pull/1424#discussion_r1963977075
##########
spark/src/main/scala/org/apache/comet/rules/RewriteJoin.scala:
##########
@@ -67,4 +78,21 @@ object RewriteJoin extends JoinSelectionHelper {
}
case _ => plan
}
+
+ def getOptimalBuildSide(join: Join): BuildSide = {
+ val leftSize = join.left.stats.sizeInBytes
+ val rightSize = join.right.stats.sizeInBytes
+ val leftRowCount = join.left.stats.rowCount
+ val rightRowCount = join.right.stats.rowCount
+ if (leftSize == rightSize && rightRowCount.isDefined &&
leftRowCount.isDefined) {
+ if (rightRowCount.get <= leftRowCount.get) {
Review Comment:
That is really awesome to find correct join order, are we sure we can rely
on stats for any query?
--
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.
To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org
For additional commands, e-mail: github-h...@datafusion.apache.org
