maropu commented on a change in pull request #28804:
URL: https://github.com/apache/spark/pull/28804#discussion_r467465104
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/execution/WholeStageCodegenSuite.scala
##########
@@ -51,6 +52,42 @@ class WholeStageCodegenSuite extends QueryTest with
SharedSparkSession
assert(df.collect() === Array(Row(9, 4.5)))
}
+ test("Avoid spill in partial aggregation" ) {
+ withSQLConf((SQLConf.SKIP_PARTIAL_AGGREGATE_ENABLED.key, "true"),
+ (SQLConf.SKIP_PARTIAL_AGGREGATE_MINROWS.key, "2")) {
+ // Create Dataframes
+ val data = Seq(("James", 1), ("James", 1), ("Phil", 1))
+ val aggDF = data.toDF("name", "values").groupBy("name").sum("values")
+ val partAggNode = aggDF.queryExecution.executedPlan.find {
+ case h: HashAggregateExec =>
+ val modes = h.aggregateExpressions.map(_.mode)
+ modes.nonEmpty && modes.forall(_ == Partial)
+ case _ => false
+ }
+
+ checkAnswer(aggDF, Seq(Row("James", 2), Row("Phil", 1)))
+ assert(partAggNode.isDefined,
+ "No HashAggregate node with partial aggregate expression found")
+ assert(partAggNode.get.metrics("partialAggSkipped").value == data.size,
+ "Partial aggregation got triggered in partial hash aggregate node")
+ }
+ }
+
+ test(s"Distinct: Partial aggregation should happen for" +
+ s" HashAggregate nodes performing partial Aggregate operations " ) {
Review comment:
please remove `s` in the head.
----------------------------------------------------------------
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]
