[GitHub] [spark] viirya commented on a change in pull request #35574: [SPARK-38237][SQL][SS] Allow `ClusteredDistribution` to require full clustering keys

[GitBox <gi...@apache.org>]

viirya commented on a change in pull request #35574:
URL: https://github.com/apache/spark/pull/35574#discussion_r814502749



##########
File path: sql/catalyst/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala
##########
@@ -407,6 +407,18 @@ object SQLConf {
       .booleanConf
       .createWithDefault(true)
 
+  val REQUIRE_ALL_CLUSTER_KEYS_FOR_DISTRIBUTION =
+    buildConf("spark.sql.requireAllClusterKeysForDistribution")
+      .internal()
+      .doc("When true, the planner requires all the clustering keys as the partition keys " +
+        "(with same ordering) of the children, to eliminate the shuffle for the operator that " +
+        "requires its children be clustered distributed, such as AGGREGATE and WINDOW node. " +
+        "This is to avoid data kews which can lead to significant performance regression if " +

Review comment:
       typo: kews -> skews




-- 
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: reviews-unsubscribe@spark.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org



---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org