cloud-fan commented on code in PR #37014:
URL: https://github.com/apache/spark/pull/37014#discussion_r916504512
##########
sql/core/src/test/scala/org/apache/spark/sql/execution/adaptive/AdaptiveQueryExecSuite.scala:
##########
@@ -2602,6 +2602,59 @@ class AdaptiveQueryExecSuite
assert(findTopLevelBroadcastNestedLoopJoin(adaptivePlan).size == 1)
}
}
+
+ test("SPARK-39624 Support coalesce partition through CartesianProduct") {
+ def checkResultPartition(
+ df: Dataset[Row],
+ numShuffleReader: Int,
+ numPartition: Int): Unit = {
+ df.collect()
+ assert(collect(df.queryExecution.executedPlan) {
+ case r: AQEShuffleReadExec => r
+ }.size === numShuffleReader)
+ assert(df.rdd.partitions.length === numPartition)
+ }
+ withSQLConf(SQLConf.ADAPTIVE_EXECUTION_ENABLED.key -> "true",
+ SQLConf.COALESCE_PARTITIONS_ENABLED.key -> "true",
+ SQLConf.ADVISORY_PARTITION_SIZE_IN_BYTES.key -> "1048576",
+ SQLConf.COALESCE_PARTITIONS_MIN_PARTITION_NUM.key -> "1",
+ SQLConf.SHUFFLE_PARTITIONS.key -> "10") {
+ withTempView("t1", "t2", "t3") {
+ spark.sparkContext.parallelize((1 to 10).map(i => TestData(i,
i.toString)), 2)
+ .toDF().createOrReplaceTempView("t1")
+ spark.sparkContext.parallelize((1 to 10).map(i => TestData(i,
i.toString)), 4)
+ .toDF().createOrReplaceTempView("t2")
+ spark.sparkContext.parallelize((1 to 10).map(i => TestData(i,
i.toString)), 4)
+ .toDF().createOrReplaceTempView("t3")
+ // positive test that could be coalesced
+ checkResultPartition(
+ sql("""
+ |SELECT * FROM
+ |(SELECT * FROM t3) t3
Review Comment:
why can't we use `t3` directly?
##########
sql/core/src/test/scala/org/apache/spark/sql/execution/adaptive/AdaptiveQueryExecSuite.scala:
##########
@@ -2602,6 +2602,59 @@ class AdaptiveQueryExecSuite
assert(findTopLevelBroadcastNestedLoopJoin(adaptivePlan).size == 1)
}
}
+
+ test("SPARK-39624 Support coalesce partition through CartesianProduct") {
+ def checkResultPartition(
+ df: Dataset[Row],
+ numShuffleReader: Int,
+ numPartition: Int): Unit = {
+ df.collect()
+ assert(collect(df.queryExecution.executedPlan) {
+ case r: AQEShuffleReadExec => r
+ }.size === numShuffleReader)
+ assert(df.rdd.partitions.length === numPartition)
+ }
+ withSQLConf(SQLConf.ADAPTIVE_EXECUTION_ENABLED.key -> "true",
+ SQLConf.COALESCE_PARTITIONS_ENABLED.key -> "true",
+ SQLConf.ADVISORY_PARTITION_SIZE_IN_BYTES.key -> "1048576",
+ SQLConf.COALESCE_PARTITIONS_MIN_PARTITION_NUM.key -> "1",
+ SQLConf.SHUFFLE_PARTITIONS.key -> "10") {
+ withTempView("t1", "t2", "t3") {
+ spark.sparkContext.parallelize((1 to 10).map(i => TestData(i,
i.toString)), 2)
+ .toDF().createOrReplaceTempView("t1")
+ spark.sparkContext.parallelize((1 to 10).map(i => TestData(i,
i.toString)), 4)
+ .toDF().createOrReplaceTempView("t2")
+ spark.sparkContext.parallelize((1 to 10).map(i => TestData(i,
i.toString)), 4)
+ .toDF().createOrReplaceTempView("t3")
+ // positive test that could be coalesced
+ checkResultPartition(
+ sql("""
+ |SELECT * FROM
+ |(SELECT * FROM t3) t3
+ |join (
+ |SELECT t1.key, t2.value FROM
+ |(SELECT * FROM t1 ) t1
Review Comment:
ditto
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
