ulysses-you commented on a change in pull request #31994:
URL: https://github.com/apache/spark/pull/31994#discussion_r603808961
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/execution/adaptive/AdaptiveQueryExecSuite.scala
##########
@@ -1543,4 +1543,27 @@ class AdaptiveQueryExecSuite
assert(materializeLogs(0).startsWith("Materialize query stage
BroadcastQueryStageExec"))
assert(materializeLogs(1).startsWith("Materialize query stage
ShuffleQueryStageExec"))
}
+
+ test("SPARK-34899: Use origin plan if we can not coalesce shuffle
partition") {
+ def check(ds: Dataset[Row], origin: ShuffleOrigin): Unit = {
+ ds.collect()
+ val plan =
ds.queryExecution.executedPlan.asInstanceOf[AdaptiveSparkPlanExec].executedPlan
+ assert(collect(plan) {
+ case c: CustomShuffleReaderExec => c
+ }.isEmpty)
+ assert(collect(plan) {
+ case s: ShuffleExchangeExec if s.shuffleOrigin == origin &&
s.numPartitions == 3 => s
+ }.size == 1)
+ checkAnswer(ds, testData)
+ }
+
+ withSQLConf(SQLConf.ADAPTIVE_EXECUTION_ENABLED.key -> "true",
+ SQLConf.COALESCE_PARTITIONS_ENABLED.key -> "true",
+ SQLConf.ADVISORY_PARTITION_SIZE_IN_BYTES.key -> "10",
+ SQLConf.COALESCE_PARTITIONS_MIN_PARTITION_NUM.key -> "1",
+ SQLConf.SHUFFLE_PARTITIONS.key -> "3") {
+ check(testData.repartition(), REPARTITION)
Review comment:
Just a question, is there a way to estimate the partition size quickly
or just the type of jvm size ? Let's say we have one rows with one int column,
and the map and reduce partition number are 1, then after shuffle the partition
size is always 4.
--
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]
