Allow partitionwise joins in more cases.

Previously, the partitionwise join technique only allowed partitionwise
join when input partitioned tables had exactly the same partition
bounds.  This commit extends the technique to some cases when the tables
have different partition bounds, by using an advanced partition-matching
algorithm introduced by this commit.  For both the input partitioned
tables, the algorithm checks whether every partition of one input
partitioned table only matches one partition of the other input
partitioned table at most, and vice versa.  In such a case the join
between the tables can be broken down into joins between the matching
partitions, so the algorithm produces the pairs of the matching
partitions, plus the partition bounds for the join relation, to allow
partitionwise join for computing the join.  Currently, the algorithm
works for list-partitioned and range-partitioned tables, but not
hash-partitioned tables.  See comments in partition_bounds_merge().

Ashutosh Bapat and Etsuro Fujita, most of regression tests by Rajkumar
Raghuwanshi, some of the tests by Mark Dilger and Amul Sul, reviewed by
Dmitry Dolgov and Amul Sul, with additional review at various points by
Ashutosh Bapat, Mark Dilger, Robert Haas, Antonin Houska, Amit Langote,
Justin Pryzby, and Tomas Vondra

Discussion: https://postgr.es/m/CAFjFpRdjQvaUEV5DJX3TW6pU5eq54NCkadtxHX2JiJG_GvbrCA@mail.gmail.com

1 files changed, 15 insertions, 30 deletions

diff --git a/src/backend/optimizer/util/relnode.c b/src/backend/optimizer/util/relnode.c
index af1fb486488..cbb1ee3b337 100644
--- a/src/backend/optimizer/util/relnode.c
+++ b/src/backend/optimizer/util/relnode.c
@@ -249,10 +249,12 @@ build_simple_rel(PlannerInfo *root, int relid, RelOptInfo *parent)
 	rel->has_eclass_joins = false;
 	rel->consider_partitionwise_join = false;	/* might get changed later */
 	rel->part_scheme = NULL;
-	rel->nparts = 0;
+	rel->nparts = -1;
 	rel->boundinfo = NULL;
+	rel->partbounds_merged = false;
 	rel->partition_qual = NIL;
 	rel->part_rels = NULL;
+	rel->all_partrels = NULL;
 	rel->partexprs = NULL;
 	rel->nullable_partexprs = NULL;
 	rel->partitioned_child_rels = NIL;
@@ -662,10 +664,12 @@ build_join_rel(PlannerInfo *root,
 	joinrel->consider_partitionwise_join = false;	/* might get changed later */
 	joinrel->top_parent_relids = NULL;
 	joinrel->part_scheme = NULL;
-	joinrel->nparts = 0;
+	joinrel->nparts = -1;
 	joinrel->boundinfo = NULL;
+	joinrel->partbounds_merged = false;
 	joinrel->partition_qual = NIL;
 	joinrel->part_rels = NULL;
+	joinrel->all_partrels = NULL;
 	joinrel->partexprs = NULL;
 	joinrel->nullable_partexprs = NULL;
 	joinrel->partitioned_child_rels = NIL;
@@ -838,10 +842,12 @@ build_child_join_rel(PlannerInfo *root, RelOptInfo *outer_rel,
 	joinrel->consider_partitionwise_join = false;	/* might get changed later */
 	joinrel->top_parent_relids = NULL;
 	joinrel->part_scheme = NULL;
-	joinrel->nparts = 0;
+	joinrel->nparts = -1;
 	joinrel->boundinfo = NULL;
+	joinrel->partbounds_merged = false;
 	joinrel->partition_qual = NIL;
 	joinrel->part_rels = NULL;
+	joinrel->all_partrels = NULL;
 	joinrel->partexprs = NULL;
 	joinrel->nullable_partexprs = NULL;
 	joinrel->partitioned_child_rels = NIL;
@@ -1645,7 +1651,7 @@ build_joinrel_partition_info(RelOptInfo *joinrel, RelOptInfo *outer_rel,
 	 * of the way the query planner deduces implied equalities and reorders
 	 * the joins.  Please see optimizer/README for details.
 	 */
-	if (!IS_PARTITIONED_REL(outer_rel) || !IS_PARTITIONED_REL(inner_rel) ||
+	if (outer_rel->part_scheme == NULL || inner_rel->part_scheme == NULL ||
 		!outer_rel->consider_partitionwise_join ||
 		!inner_rel->consider_partitionwise_join ||
 		outer_rel->part_scheme != inner_rel->part_scheme ||
@@ -1658,24 +1664,6 @@ build_joinrel_partition_info(RelOptInfo *joinrel, RelOptInfo *outer_rel,
 
 	part_scheme = outer_rel->part_scheme;
 
-	Assert(REL_HAS_ALL_PART_PROPS(outer_rel) &&
-		   REL_HAS_ALL_PART_PROPS(inner_rel));
-
-	/*
-	 * For now, our partition matching algorithm can match partitions only
-	 * when the partition bounds of the joining relations are exactly same.
-	 * So, bail out otherwise.
-	 */
-	if (outer_rel->nparts != inner_rel->nparts ||
-		!partition_bounds_equal(part_scheme->partnatts,
-								part_scheme->parttyplen,
-								part_scheme->parttypbyval,
-								outer_rel->boundinfo, inner_rel->boundinfo))
-	{
-		Assert(!IS_PARTITIONED_REL(joinrel));
-		return;
-	}
-
 	/*
 	 * This function will be called only once for each joinrel, hence it
 	 * should not have partitioning fields filled yet.
@@ -1685,18 +1673,15 @@ build_joinrel_partition_info(RelOptInfo *joinrel, RelOptInfo *outer_rel,
 		   !joinrel->boundinfo);
 
 	/*
-	 * Join relation is partitioned using the same partitioning scheme as the
-	 * joining relations and has same bounds.
+	 * If the join relation is partitioned, it uses the same partitioning
+	 * scheme as the joining relations.
+	 *
+	 * Note: we calculate the partition bounds, number of partitions, and
+	 * child-join relations of the join relation in try_partitionwise_join().
 	 */
 	joinrel->part_scheme = part_scheme;
-	joinrel->boundinfo = outer_rel->boundinfo;
-	joinrel->nparts = outer_rel->nparts;
 	set_joinrel_partition_key_exprs(joinrel, outer_rel, inner_rel, jointype);
 
-	/* part_rels[] will be filled later, but allocate it now */
-	joinrel->part_rels =
-		(RelOptInfo **) palloc0(sizeof(RelOptInfo *) * joinrel->nparts);
-
 	/*
 	 * Set the consider_partitionwise_join flag.
 	 */