ulysses-you commented on a change in pull request #32084:
URL: https://github.com/apache/spark/pull/32084#discussion_r612105702
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/execution/adaptive/AdaptiveQueryExecSuite.scala
##########
@@ -1575,4 +1575,86 @@ class AdaptiveQueryExecSuite
checkNoCoalescePartitions(df.sort($"key"), ENSURE_REQUIREMENTS)
}
}
+
+ test("SPARK-34980: Support coalesce partition through union") {
+ def checkResultPartition(
+ df: Dataset[Row], unionNumber: Int, shuffleReaderNumber: Int,
partitionNumber: Int): Unit = {
+ df.collect()
+ assert(collect(df.queryExecution.executedPlan) {
+ case u: UnionExec => u
+ }.size == unionNumber)
+ assert(
+ collect(df.queryExecution.executedPlan) {
+ case s: CustomShuffleReaderExec => s
+ }.size === shuffleReaderNumber)
+ assert(df.rdd.partitions.length === partitionNumber)
+ }
+
+ Seq(true, false).foreach { combineUnionEnabled =>
+ val combineUnionConfig = if (combineUnionEnabled) {
+ "" -> ""
+ } else {
+ SQLConf.OPTIMIZER_EXCLUDED_RULES.key ->
+ "org.apache.spark.sql.catalyst.optimizer.CombineUnions"
+ }
+ withSQLConf(SQLConf.ADAPTIVE_EXECUTION_ENABLED.key -> "true",
Review comment:
@maropu add the test that without rule `CombineUnions`. After this, the
plan can introduce the nested `Union`.
--
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]
