naveenp2708 commented on code in PR #57442:
URL: https://github.com/apache/spark/pull/57442#discussion_r3648280640
##########
sql/core/src/test/scala/org/apache/spark/sql/connector/KeyGroupedPartitioningSuite.scala:
##########
@@ -2724,6 +2724,37 @@ class KeyGroupedPartitioningSuite extends
DistributionAndOrderingSuiteBase with
}
}
+ test("SPARK-52246: one-side shuffle with join key tail part of the partition
keys") {
+ val items_partitions = Array(bucket(2, "id"))
+ createTable(items, itemsColumns, items_partitions)
+
+ sql(s"INSERT INTO testcat.ns.$items VALUES " +
+ "(1, 'aa', 40.0, cast('2020-01-01' as timestamp)), " +
+ "(1, 'aa', 30.0, cast('2020-01-02' as timestamp)), " +
+ "(3, 'bb', 10.0, cast('2020-01-01' as timestamp)), " +
+ "(4, 'cc', 15.5, cast('2020-02-01' as timestamp))")
+
+ createTable(purchases, purchasesColumns, Array.empty)
+ sql(s"INSERT INTO testcat.ns.$purchases VALUES " +
+ "(1, 42.0, cast('2020-01-01' as timestamp)), " +
+ "(1, 89.0, cast('2020-01-03' as timestamp)), " +
+ "(3, 19.5, cast('2020-02-01' as timestamp)), " +
+ "(5, 26.0, cast('2023-01-01' as timestamp)), " +
+ "(6, 50.0, cast('2023-02-01' as timestamp))")
+
+ withSQLConf(
+ SQLConf.REQUIRE_ALL_CLUSTER_KEYS_FOR_CO_PARTITION.key -> "false",
Review Comment:
Good catch, thanks @peter-toth . I'd copied the confs straight from the JIRA
repro without checking which ones actually matter. Dropped everything except
V2_BUCKETING_SHUFFLE_ENABLED, same as the SPARK-54439 tests. Still passes on
master and still fails on v4.0.1 without the fix, so nothing lost
--
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]
