ulysses-you commented on code in PR #41609:
URL: https://github.com/apache/spark/pull/41609#discussion_r1271643468
##########
sql/core/src/test/scala/org/apache/spark/sql/execution/adaptive/AdaptiveQueryExecSuite.scala:
##########
@@ -2851,6 +2851,68 @@ class AdaptiveQueryExecSuite
val unionDF = aggDf1.union(aggDf2)
checkAnswer(unionDF.select("id").distinct, Seq(Row(null)))
}
+
+ test("SPARK-44065: Optimize BroadcastHashJoin skew when localShuffleReader
is disabled") {
+ withSQLConf(
+ SQLConf.ADAPTIVE_EXECUTION_ENABLED.key -> "true",
+ SQLConf.AUTO_BROADCASTJOIN_THRESHOLD.key -> "-1",
+ SQLConf.ADAPTIVE_AUTO_BROADCASTJOIN_THRESHOLD.key -> "1000",
+ SQLConf.LOCAL_SHUFFLE_READER_ENABLED.key -> "false",
+ SQLConf.SHUFFLE_PARTITIONS.key -> "10",
+ SQLConf.SKEW_JOIN_SKEWED_PARTITION_THRESHOLD.key -> "600",
+ SQLConf.ADVISORY_PARTITION_SIZE_IN_BYTES.key -> "600") {
+ withTempView("skewData", "smallData") {
+ spark
+ .range(0, 1000, 1, 10)
+ .selectExpr("if(id >= 5, 5, id) as key1", "id as value1")
+ .createOrReplaceTempView("skewData1")
+ spark
+ .range(0, 5, 1, 10)
+ .selectExpr("id key2", "id as value2")
+ .createOrReplaceTempView("smallData")
+
+ Seq(true, false).foreach { localShuffleReader =>
+ withSQLConf(SQLConf.LOCAL_SHUFFLE_READER_ENABLED.key ->
localShuffleReader.toString) {
+ val sqlText =
+ s"""
+ |select * from skewData1 a join smallData b on a.key1 = b.key2
+ |""".stripMargin
+ val (_, plan) = runAdaptiveAndVerifyResult(sqlText)
+ val bhjs = findTopLevelBroadcastHashJoin(plan)
+ assert(bhjs.nonEmpty)
+
+ if (localShuffleReader) {
+ val localShuffleReaders = collect(plan) {
+ case c: AQEShuffleReadExec if c.isLocalRead => c
Review Comment:
We should respect `PartialReducerPartitionSpec` in
`OptimizeShuffleWithLocalRead`. Before this pr, `OptimizeShuffleWithLocalRead`
assumes it would not accpet the skewed partition, so we should make it consider
`PartialReducerPartitionSpec`.
--
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]
