cloud-fan commented on a change in pull request #26434: [SPARK-29544] [SQL]
optimize skewed partition based on data size
URL: https://github.com/apache/spark/pull/26434#discussion_r358060612
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/execution/adaptive/AdaptiveQueryExecSuite.scala
##########
@@ -552,4 +577,155 @@ class AdaptiveQueryExecSuite
spark.sparkContext.removeSparkListener(listener)
}
}
+
+ test("adaptive skew join both in left and right for inner join ") {
+ withSQLConf(
+ SQLConf.ADAPTIVE_EXECUTION_ENABLED.key -> "true",
+ SQLConf.AUTO_BROADCASTJOIN_THRESHOLD.key -> "-1",
+ SQLConf.ADAPTIVE_EXECUTION_SKEWED_PARTITION_FACTOR.key -> "1",
+ SQLConf.ADAPTIVE_EXECUTION_SKEWED_PARTITION_SIZE_THRESHOLD.key -> "100",
+ SQLConf.SHUFFLE_TARGET_POSTSHUFFLE_INPUT_SIZE.key -> "2000") {
+ val (plan, adaptivePlan) = runAdaptiveAndVerifyResult(
+ "SELECT * FROM skewData1 join skewData2 ON key1 = key2")
+ val smj = findTopLevelSortMergeJoin(plan)
+ assert(smj.size == 1)
+ // left stats: [4403, 0, 1927, 1927, 1927]
Review comment:
I'm a little surprised that partition 1 is skewed. Isn't `key1` uniformly
distributed?
----------------------------------------------------------------
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:
us...@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
