cloud-fan commented on a change in pull request #26516: [SPARK-29893] improve
the local shuffle reader performance by changing the reading task number from 1
to multi.
URL: https://github.com/apache/spark/pull/26516#discussion_r347731045
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/execution/adaptive/AdaptiveQueryExecSuite.scala
##########
@@ -103,6 +103,64 @@ class AdaptiveQueryExecSuite
}
}
+ test("Reuse the parallelism of CoalescedShuffleReaderExec as the tasks" +
+ " of LocalShuffleReaderExec") {
+ withSQLConf(
+ SQLConf.ADAPTIVE_EXECUTION_ENABLED.key -> "true",
+ SQLConf.AUTO_BROADCASTJOIN_THRESHOLD.key -> "80",
+ SQLConf.SHUFFLE_TARGET_POSTSHUFFLE_INPUT_SIZE.key -> "150") {
+ val (plan, adaptivePlan) = runAdaptiveAndVerifyResult(
+ "SELECT * FROM testData join testData2 ON key = a where value = '1'")
+ val smj = findTopLevelSortMergeJoin(plan)
+ assert(smj.size == 1)
+ val bhj = findTopLevelBroadcastHashJoin(adaptivePlan)
+ assert(bhj.size == 1)
+ val localReaders = collect(adaptivePlan) {
+ case reader: LocalShuffleReaderExec => reader
+ }
Review comment:
better to add `assert(localReaders.length == 2)`
----------------------------------------------------------------
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]
