cloud-fan commented on a change in pull request #32883:
URL: https://github.com/apache/spark/pull/32883#discussion_r661466362
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/execution/adaptive/AdaptiveQueryExecSuite.scala
##########
@@ -1820,4 +1821,45 @@ class AdaptiveQueryExecSuite
}
}
}
+
+ test("SPARK-35725: Support optimize skewed partitions in
RebalancePartitions") {
+ withTempView("v") {
+ withSQLConf(
+ SQLConf.ADAPTIVE_EXECUTION_ENABLED.key -> "true",
+ SQLConf.COALESCE_PARTITIONS_ENABLED.key -> "true",
+ SQLConf.ADAPTIVE_OPTIMIZE_SKEWS_IN_REBALANCE_PARTITIONS_ENABLED.key ->
"true",
+ SQLConf.AUTO_BROADCASTJOIN_THRESHOLD.key -> "-1",
+ SQLConf.SHUFFLE_PARTITIONS.key -> "5",
+ SQLConf.COALESCE_PARTITIONS_MIN_PARTITION_NUM.key -> "1") {
+
+ spark.sparkContext.parallelize(
+ (1 to 10).map(i => TestData(if (i > 4) 5 else i, i.toString)), 3)
+ .toDF("c1", "c2").createOrReplaceTempView("v")
+
+ def checkPartitionNumber(
+ query: String, skewedPartitionNumber: Int, totalNumber: Int): Unit
= {
+ val (_, adaptive) = runAdaptiveAndVerifyResult(query)
+ val reader = collect(adaptive) {
+ case reader: CustomShuffleReaderExec => reader
+ }
+ assert(reader.size == 1)
+
assert(reader.head.partitionSpecs.count(_.isInstanceOf[PartialReducerPartitionSpec])
==
+ skewedPartitionNumber)
+ assert(reader.head.partitionSpecs.size == totalNumber)
+ }
+
+ withSQLConf(SQLConf.ADVISORY_PARTITION_SIZE_IN_BYTES.key -> "100") {
+ // partition size [0,258,72,72,72]
Review comment:
can we tune the size a little more, so that coalesce also applies?
--
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]
