Github user cloud-fan commented on a diff in the pull request: https://github.com/apache/spark/pull/21529#discussion_r194830241 --- Diff: sql/core/src/test/scala/org/apache/spark/sql/execution/PlannerSuite.scala --- @@ -679,6 +679,17 @@ class PlannerSuite extends SharedSQLContext { } assert(rangeExecInZeroPartition.head.outputPartitioning == UnknownPartitioning(0)) } + + test("SPARK-24495: EnsureRequirements can return wrong plan when reusing the same key in join") { + withSQLConf(("spark.sql.shuffle.partitions", "1"), + ("spark.sql.constraintPropagation.enabled", "false"), + ("spark.sql.autoBroadcastJoinThreshold", "-1")) { + val df1 = spark.range(100).repartition(2, $"id", $"id") --- End diff -- a simpler way `spark.range(0, 100, 1, numPartitions = 2)`
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org