Major Description
Should not pushdown LeftSemi/LeftAnti over Aggregate for some cases.
spark.range(50000000L).selectExpr("id % 10000 as a", "id % 10000 as b").write.saveAsTable("t1") spark.range(40000000L).selectExpr("id % 8000 as c", "id % 8000 as d").write.saveAsTable("t2") spark.sql("SELECT distinct a, b FROM t1 INTERSECT SELECT distinct c, d FROM t2").explain
Current:
== Physical Plan ==
AdaptiveSparkPlan isFinalPlan=false
+- HashAggregate(keys=[a#16L, b#17L], functions=[])
+- HashAggregate(keys=[a#16L, b#17L], functions=[])
+- HashAggregate(keys=[a#16L, b#17L], functions=[])
+- Exchange hashpartitioning(a#16L, b#17L, 5), ENSURE_REQUIREMENTS, [id=#72]
+- HashAggregate(keys=[a#16L, b#17L], functions=[])
+- SortMergeJoin [coalesce(a#16L, 0), isnull(a#16L), coalesce(b#17L, 0), isnull(b#17L)], [coalesce(c#18L, 0), isnull(c#18L), coalesce(d#19L, 0), isnull(d#19L)], LeftSemi
:- Sort [coalesce(a#16L, 0) ASC NULLS FIRST, isnull(a#16L) ASC NULLS FIRST, coalesce(b#17L, 0) ASC NULLS FIRST, isnull(b#17L) ASC NULLS FIRST], false, 0
: +- Exchange hashpartitioning(coalesce(a#16L, 0), isnull(a#16L), coalesce(b#17L, 0), isnull(b#17L), 5), ENSURE_REQUIREMENTS, [id=#65]
: +- FileScan parquet default.t1[a#16L,b#17L] Batched: true, DataFilters: [], Format: Parquet, Location: InMemoryFileIndex[file:/Users/yumwang/spark/spark-warehouse/org.apache.spark.sql.Data..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<a:bigint,b:bigint>
+- Sort [coalesce(c#18L, 0) ASC NULLS FIRST, isnull(c#18L) ASC NULLS FIRST, coalesce(d#19L, 0) ASC NULLS FIRST, isnull(d#19L) ASC NULLS FIRST], false, 0
+- Exchange hashpartitioning(coalesce(c#18L, 0), isnull(c#18L), coalesce(d#19L, 0), isnull(d#19L), 5), ENSURE_REQUIREMENTS, [id=#66]
+- HashAggregate(keys=[c#18L, d#19L], functions=[])
+- Exchange hashpartitioning(c#18L, d#19L, 5), ENSURE_REQUIREMENTS, [id=#61]
+- HashAggregate(keys=[c#18L, d#19L], functions=[])
+- FileScan parquet default.t2[c#18L,d#19L] Batched: true, DataFilters: [], Format: Parquet, Location: InMemoryFileIndex[file:/Users/yumwang/spark/spark-warehouse/org.apache.spark.sql.Data..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<c:bigint,d:bigint>
Expected:
== Physical Plan ==
AdaptiveSparkPlan isFinalPlan=false
+- HashAggregate(keys=[a#16L, b#17L], functions=[])
+- Exchange hashpartitioning(a#16L, b#17L, 5), ENSURE_REQUIREMENTS, [id=#74]
+- HashAggregate(keys=[a#16L, b#17L], functions=[])
+- SortMergeJoin [coalesce(a#16L, 0), isnull(a#16L), coalesce(b#17L, 0), isnull(b#17L)], [coalesce(c#18L, 0), isnull(c#18L), coalesce(d#19L, 0), isnull(d#19L)], LeftSemi
:- Sort [coalesce(a#16L, 0) ASC NULLS FIRST, isnull(a#16L) ASC NULLS FIRST, coalesce(b#17L, 0) ASC NULLS FIRST, isnull(b#17L) ASC NULLS FIRST], false, 0
: +- Exchange hashpartitioning(coalesce(a#16L, 0), isnull(a#16L), coalesce(b#17L, 0), isnull(b#17L), 5), ENSURE_REQUIREMENTS, [id=#67]
: +- HashAggregate(keys=[a#16L, b#17L], functions=[])
: +- Exchange hashpartitioning(a#16L, b#17L, 5), ENSURE_REQUIREMENTS, [id=#61]
: +- HashAggregate(keys=[a#16L, b#17L], functions=[])
: +- FileScan parquet default.t1[a#16L,b#17L] Batched: true, DataFilters: [], Format: Parquet, Location: InMemoryFileIndex[file:/Users/yumwang/spark/spark-warehouse/org.apache.spark.sql.Data..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<a:bigint,b:bigint>
+- Sort [coalesce(c#18L, 0) ASC NULLS FIRST, isnull(c#18L) ASC NULLS FIRST, coalesce(d#19L, 0) ASC NULLS FIRST, isnull(d#19L) ASC NULLS FIRST], false, 0
+- Exchange hashpartitioning(coalesce(c#18L, 0), isnull(c#18L), coalesce(d#19L, 0), isnull(d#19L), 5), ENSURE_REQUIREMENTS, [id=#68]
+- HashAggregate(keys=[c#18L, d#19L], functions=[])
+- Exchange hashpartitioning(c#18L, d#19L, 5), ENSURE_REQUIREMENTS, [id=#63]
+- HashAggregate(keys=[c#18L, d#19L], functions=[])
+- FileScan parquet default.t2[c#18L,d#19L] Batched: true, DataFilters: [], Format: Parquet, Location: InMemoryFileIndex[file:/Users/yumwang/spark/spark-warehouse/org.apache.spark.sql.Data..., PartitionFilters: [], PushedFilters: [], ReadSchema: struct<c:bigint,d:bigint>
