AngersZhuuuu commented on a change in pull request #26437: [SPARK-29800][SQL]
Rewrite non-correlated subquery use ScalaSubquery to optimize perf
URL: https://github.com/apache/spark/pull/26437#discussion_r363134410
##########
File path: sql/core/src/test/scala/org/apache/spark/sql/CachedTableSuite.scala
##########
@@ -89,10 +89,19 @@ class CachedTableSuite extends QueryTest with SQLTestUtils
with SharedSparkSessi
sum
}
+ private def getNumInMemoryTablesInSubquery(plan: SparkPlan): Int = {
+ plan.expressions.map(_.collect {
+ case sub: ExecSubqueryExpression =>
getNumInMemoryTablesRecursively(sub.plan)
+ }.sum).sum
+ }
+
private def getNumInMemoryTablesRecursively(plan: SparkPlan): Int = {
plan.collect {
- case InMemoryTableScanExec(_, _, relation) =>
- getNumInMemoryTablesRecursively(relation.cachedPlan) + 1
+ case inMemoryTable @ InMemoryTableScanExec(_, _, relation) =>
+ getNumInMemoryTablesRecursively(relation.cachedPlan) +
+ getNumInMemoryTablesInSubquery(inMemoryTable) + 1
+ case p =>
+ getNumInMemoryTablesInSubquery(p)
Review comment:
> Is this change needed for this PR? Looks like not directly related?
https://github.com/apache/spark/pull/26437#discussion_r362758580
----------------------------------------------------------------
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]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
