LantaoJin commented on a change in pull request #28961:
URL: https://github.com/apache/spark/pull/28961#discussion_r449330214
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/OptimizeSkewedJoin.scala
##########
@@ -236,6 +236,10 @@ case class OptimizeSkewedJoin(conf: SQLConf) extends
Rule[SparkPlan] {
} {
leftSidePartitions += leftSidePartition
rightSidePartitions += rightSidePartition
+ if (leftSidePartitions.length >
conf.getConf(SQLConf.SKEW_JOIN_MAX_PARTITION_SPLITS)) {
+ throw new SparkException(s"Too many partition splits produced in
handling data skew." +
+ s" The threshold is
${conf.getConf(SQLConf.SKEW_JOIN_MAX_PARTITION_SPLITS)}")
+ }
Review comment:
How about it now?
----------------------------------------------------------------
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:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
