Reset API of clause_selectivity()

Discussion: https://postgr.es/m/CAKJS1f9yurJQW9pdnzL+rmOtsp2vOytkpXKGnMFJEO-qz5O5eA@mail.gmail.com

8 files changed, 74 insertions, 60 deletions

diff --git a/contrib/file_fdw/file_fdw.c b/contrib/file_fdw/file_fdw.c
index 7414c16128..277639f6e9 100644
--- a/contrib/file_fdw/file_fdw.c
+++ b/contrib/file_fdw/file_fdw.c
@@ -1013,7 +1013,6 @@ estimate_size(PlannerInfo *root, RelOptInfo *baserel,
 							   baserel->baserestrictinfo,
 							   0,
 							   JOIN_INNER,
-							   NULL,
 							   NULL);
 
 	nrows = clamp_row_est(nrows);
diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c
index a73d1a0bed..2851869932 100644
--- a/contrib/postgres_fdw/postgres_fdw.c
+++ b/contrib/postgres_fdw/postgres_fdw.c
@@ -591,7 +591,6 @@ postgresGetForeignRelSize(PlannerInfo *root,
 													 fpinfo->local_conds,
 													 baserel->relid,
 													 JOIN_INNER,
-													 NULL,
 													 NULL);
 
 	cost_qual_eval(&fpinfo->local_conds_cost, fpinfo->local_conds, root);
@@ -2573,7 +2572,6 @@ estimate_path_cost_size(PlannerInfo *root,
 										   local_param_join_conds,
 										   foreignrel->relid,
 										   JOIN_INNER,
-										   NULL,
 										   NULL);
 		local_sel *= fpinfo->local_conds_sel;
 
@@ -4457,7 +4455,6 @@ postgresGetForeignJoinPaths(PlannerInfo *root,
 													 fpinfo->local_conds,
 													 0,
 													 JOIN_INNER,
-													 NULL,
 													 NULL);
 	cost_qual_eval(&fpinfo->local_conds_cost, fpinfo->local_conds, root);
 
@@ -4468,7 +4465,7 @@ postgresGetForeignJoinPaths(PlannerInfo *root,
 	if (!fpinfo->use_remote_estimate)
 		fpinfo->joinclause_sel = clauselist_selectivity(root, fpinfo->joinclauses,
 														0, fpinfo->jointype,
-														extra->sjinfo, NULL);
+														extra->sjinfo);
 
 	/* Estimate costs for bare join relation */
 	estimate_path_cost_size(root, joinrel, NIL, NIL, &rows,
diff --git a/src/backend/optimizer/path/clausesel.c b/src/backend/optimizer/path/clausesel.c
index 1ba578130e..614c1d127c 100644
--- a/src/backend/optimizer/path/clausesel.c
+++ b/src/backend/optimizer/path/clausesel.c
@@ -41,7 +41,8 @@ typedef struct RangeQueryClause
 
 static void addRangeClause(RangeQueryClause **rqlist, Node *clause,
 			   bool varonleft, bool isLTsel, Selectivity s2);
-
+static RelOptInfo *find_relation_from_clauses(PlannerInfo *root,
+											  List *clauses);
 
 /****************************************************************************
  *		ROUTINES TO COMPUTE SELECTIVITIES
@@ -101,14 +102,14 @@ clauselist_selectivity(PlannerInfo *root,
 					   List *clauses,
 					   int varRelid,
 					   JoinType jointype,
-					   SpecialJoinInfo *sjinfo,
-					   RelOptInfo *rel)
+					   SpecialJoinInfo *sjinfo)
 {
 	Selectivity s1 = 1.0;
 	RangeQueryClause *rqlist = NULL;
 	ListCell   *l;
 	Bitmapset  *estimatedclauses = NULL;
 	int			listidx;
+	RelOptInfo *rel;
 
 	/*
 	 * If there's exactly one clause, then extended statistics is futile at
@@ -117,7 +118,14 @@ clauselist_selectivity(PlannerInfo *root,
 	 */
 	if (list_length(clauses) == 1)
 		return clause_selectivity(root, (Node *) linitial(clauses),
-								  varRelid, jointype, sjinfo, rel);
+								  varRelid, jointype, sjinfo);
+
+	/*
+	 * Determine if these clauses reference a single relation. If so we might
+	 * like to try applying any extended statistics which exist on it.
+	 * Called many time during joins, so must return NULL quickly if not.
+	 */
+	rel = find_relation_from_clauses(root, clauses);
 
 	/*
 	 * When a relation of RTE_RELATION is given as 'rel', we'll try to
@@ -164,7 +172,7 @@ clauselist_selectivity(PlannerInfo *root,
 			continue;
 
 		/* Always compute the selectivity using clause_selectivity */
-		s2 = clause_selectivity(root, clause, varRelid, jointype, sjinfo, rel);
+		s2 = clause_selectivity(root, clause, varRelid, jointype, sjinfo);
 
 		/*
 		 * Check for being passed a RestrictInfo.
@@ -418,6 +426,39 @@ addRangeClause(RangeQueryClause **rqlist, Node *clause,
 }
 
 /*
+ * find_relation_from_clauses
+ *		Process each clause in 'clauses' and determine if all clauses
+ *		reference only a single relation. If so return that relation,
+ *		otherwise return NULL.
+ */
+static RelOptInfo *
+find_relation_from_clauses(PlannerInfo *root, List *clauses)
+{
+	ListCell *l;
+	int relid;
+	int lastrelid = 0;
+
+	foreach(l, clauses)
+	{
+		RestrictInfo *rinfo = (RestrictInfo *) lfirst(l);
+
+		if (bms_get_singleton_member(rinfo->clause_relids, &relid))
+		{
+			if (lastrelid != 0 && relid != lastrelid)
+				return NULL;		/* relation not the same as last one */
+			lastrelid = relid;
+		}
+		else
+			return NULL;			/* multiple relations in clause */
+	}
+
+	if (lastrelid != 0)
+		return find_base_rel(root, lastrelid);
+
+	return NULL;			/* no clauses */
+}
+
+/*
  * bms_is_subset_singleton
  *
  * Same result as bms_is_subset(s, bms_make_singleton(x)),
@@ -529,8 +570,7 @@ clause_selectivity(PlannerInfo *root,
 				   Node *clause,
 				   int varRelid,
 				   JoinType jointype,
-				   SpecialJoinInfo *sjinfo,
-				   RelOptInfo *rel)
+				   SpecialJoinInfo *sjinfo)
 {
 	Selectivity s1 = 0.5;		/* default for any unhandled clause type */
 	RestrictInfo *rinfo = NULL;
@@ -650,8 +690,7 @@ clause_selectivity(PlannerInfo *root,
 								  (Node *) get_notclausearg((Expr *) clause),
 									  varRelid,
 									  jointype,
-									  sjinfo,
-									  rel);
+									  sjinfo);
 	}
 	else if (and_clause(clause))
 	{
@@ -660,8 +699,7 @@ clause_selectivity(PlannerInfo *root,
 									((BoolExpr *) clause)->args,
 									varRelid,
 									jointype,
-									sjinfo,
-									rel);
+									sjinfo);
 	}
 	else if (or_clause(clause))
 	{
@@ -680,8 +718,7 @@ clause_selectivity(PlannerInfo *root,
 												(Node *) lfirst(arg),
 												varRelid,
 												jointype,
-												sjinfo,
-												rel);
+												sjinfo);
 
 			s1 = s1 + s2 - s1 * s2;
 		}
@@ -774,8 +811,7 @@ clause_selectivity(PlannerInfo *root,
 								(Node *) ((RelabelType *) clause)->arg,
 								varRelid,
 								jointype,
-								sjinfo,
-								rel);
+								sjinfo);
 	}
 	else if (IsA(clause, CoerceToDomain))
 	{
@@ -784,8 +820,7 @@ clause_selectivity(PlannerInfo *root,
 								(Node *) ((CoerceToDomain *) clause)->arg,
 								varRelid,
 								jointype,
-								sjinfo,
-								rel);
+								sjinfo);
 	}
 	else
 	{
diff --git a/src/backend/optimizer/path/costsize.c b/src/backend/optimizer/path/costsize.c
index bf0fb56ab0..ed07e2f655 100644
--- a/src/backend/optimizer/path/costsize.c
+++ b/src/backend/optimizer/path/costsize.c
@@ -3750,8 +3750,7 @@ compute_semi_anti_join_factors(PlannerInfo *root,
 									joinquals,
 									0,
 									jointype,
-									sjinfo,
-									NULL);
+									sjinfo);
 
 	/*
 	 * Also get the normal inner-join selectivity of the join clauses.
@@ -3774,8 +3773,7 @@ compute_semi_anti_join_factors(PlannerInfo *root,
 									joinquals,
 									0,
 									JOIN_INNER,
-									&norm_sjinfo,
-									NULL);
+									&norm_sjinfo);
 
 	/* Avoid leaking a lot of ListCells */
 	if (jointype == JOIN_ANTI)
@@ -3942,7 +3940,7 @@ approx_tuple_count(PlannerInfo *root, JoinPath *path, List *quals)
 		Node	   *qual = (Node *) lfirst(l);
 
 		/* Note that clause_selectivity will be able to cache its result */
-		selec *= clause_selectivity(root, qual, 0, JOIN_INNER, &sjinfo, NULL);
+		selec *= clause_selectivity(root, qual, 0, JOIN_INNER, &sjinfo);
 	}
 
 	/* Apply it to the input relation sizes */
@@ -3978,8 +3976,7 @@ set_baserel_size_estimates(PlannerInfo *root, RelOptInfo *rel)
 							   rel->baserestrictinfo,
 							   0,
 							   JOIN_INNER,
-							   NULL,
-							   rel);
+							   NULL);
 
 	rel->rows = clamp_row_est(nrows);
 
@@ -4016,8 +4013,7 @@ get_parameterized_baserel_size(PlannerInfo *root, RelOptInfo *rel,
 							   allclauses,
 							   rel->relid,		/* do not use 0! */
 							   JOIN_INNER,
-							   NULL,
-							   rel);
+							   NULL);
 	nrows = clamp_row_est(nrows);
 	/* For safety, make sure result is not more than the base estimate */
 	if (nrows > rel->rows)
@@ -4183,14 +4179,12 @@ calc_joinrel_size_estimate(PlannerInfo *root,
 										joinquals,
 										0,
 										jointype,
-										sjinfo,
-										NULL);
+										sjinfo);
 		pselec = clauselist_selectivity(root,
 										pushedquals,
 										0,
 										jointype,
-										sjinfo,
-										NULL);
+										sjinfo);
 
 		/* Avoid leaking a lot of ListCells */
 		list_free(joinquals);
@@ -4202,8 +4196,7 @@ calc_joinrel_size_estimate(PlannerInfo *root,
 										restrictlist,
 										0,
 										jointype,
-										sjinfo,
-										NULL);
+										sjinfo);
 		pselec = 0.0;			/* not used, keep compiler quiet */
 	}
 
@@ -4498,7 +4491,7 @@ get_foreign_key_join_selectivity(PlannerInfo *root,
 				Selectivity csel;
 
 				csel = clause_selectivity(root, (Node *) rinfo,
-										  0, jointype, sjinfo, NULL);
+										  0, jointype, sjinfo);
 				thisfksel = Min(thisfksel, csel);
 			}
 			fkselec *= thisfksel;
diff --git a/src/backend/optimizer/util/orclauses.c b/src/backend/optimizer/util/orclauses.c
index 735697d2f3..9cbcaedb75 100644
--- a/src/backend/optimizer/util/orclauses.c
+++ b/src/backend/optimizer/util/orclauses.c
@@ -280,7 +280,7 @@ consider_new_or_clause(PlannerInfo *root, RelOptInfo *rel,
 	 * saving work later.)
 	 */
 	or_selec = clause_selectivity(root, (Node *) or_rinfo,
-								  0, JOIN_INNER, NULL, rel);
+								  0, JOIN_INNER, NULL);
 
 	/*
 	 * The clause is only worth adding to the query if it rejects a useful
@@ -344,7 +344,7 @@ consider_new_or_clause(PlannerInfo *root, RelOptInfo *rel,
 
 		/* Compute inner-join size */
 		orig_selec = clause_selectivity(root, (Node *) join_or_rinfo,
-										0, JOIN_INNER, &sjinfo, NULL);
+										0, JOIN_INNER, &sjinfo);
 
 		/* And hack cached selectivity so join size remains the same */
 		join_or_rinfo->norm_selec = orig_selec / or_selec;
diff --git a/src/backend/statistics/dependencies.c b/src/backend/statistics/dependencies.c
index 159ddb8723..1a90e4b715 100644
--- a/src/backend/statistics/dependencies.c
+++ b/src/backend/statistics/dependencies.c
@@ -1050,8 +1050,8 @@ dependencies_clauselist_selectivity(PlannerInfo *root,
 			{
 				clause = (Node *) lfirst(l);
 
-				s2 = clause_selectivity(root, clause, varRelid, jointype, sjinfo,
-										NULL);	/* don't try to use ext stats */
+				s2 = clause_selectivity(root, clause, varRelid, jointype,
+										sjinfo);
 
 				/* mark this one as done, so we don't touch it again. */
 				*estimatedclauses = bms_add_member(*estimatedclauses, listidx);
diff --git a/src/backend/utils/adt/selfuncs.c b/src/backend/utils/adt/selfuncs.c
index b6893e22bf..51c50eff50 100644
--- a/src/backend/utils/adt/selfuncs.c
+++ b/src/backend/utils/adt/selfuncs.c
@@ -1634,17 +1634,13 @@ booltestsel(PlannerInfo *root, BoolTestType booltesttype, Node *arg,
 			case IS_NOT_FALSE:
 				selec = (double) clause_selectivity(root, arg,
 													varRelid,
-													jointype,
-													sjinfo,
-													NULL);
+													jointype, sjinfo);
 				break;
 			case IS_FALSE:
 			case IS_NOT_TRUE:
 				selec = 1.0 - (double) clause_selectivity(root, arg,
 														  varRelid,
-														  jointype,
-														  sjinfo,
-														  NULL);
+														  jointype, sjinfo);
 				break;
 			default:
 				elog(ERROR, "unrecognized booltesttype: %d",
@@ -6441,8 +6437,7 @@ genericcostestimate(PlannerInfo *root,
 	indexSelectivity = clauselist_selectivity(root, selectivityQuals,
 											  index->rel->relid,
 											  JOIN_INNER,
-											  NULL,
-											  index->rel);
+											  NULL);
 
 	/*
 	 * If caller didn't give us an estimate, estimate the number of index
@@ -6763,8 +6758,7 @@ btcostestimate(PlannerInfo *root, IndexPath *path, double loop_count,
 		btreeSelectivity = clauselist_selectivity(root, selectivityQuals,
 												  index->rel->relid,
 												  JOIN_INNER,
-												  NULL,
-												  index->rel);
+												  NULL);
 		numIndexTuples = btreeSelectivity * index->rel->tuples;
 
 		/*
@@ -7523,8 +7517,7 @@ gincostestimate(PlannerInfo *root, IndexPath *path, double loop_count,
 	*indexSelectivity = clauselist_selectivity(root, selectivityQuals,
 											   index->rel->relid,
 											   JOIN_INNER,
-											   NULL,
-											   index->rel);
+											   NULL);
 
 	/* fetch estimated page cost for tablespace containing index */
 	get_tablespace_page_costs(index->reltablespace,
@@ -7854,8 +7847,7 @@ brincostestimate(PlannerInfo *root, IndexPath *path, double loop_count,
 
 	qualSelectivity = clauselist_selectivity(root, indexQuals,
 											 baserel->relid,
-											 JOIN_INNER, NULL,
-											 baserel);
+											 JOIN_INNER, NULL);
 
 	/* work out the actual number of ranges in the index */
 	indexRanges = Max(ceil((double) baserel->pages / statsData.pagesPerRange),
diff --git a/src/include/optimizer/cost.h b/src/include/optimizer/cost.h
index 81a84b5494..6909359bcf 100644
--- a/src/include/optimizer/cost.h
+++ b/src/include/optimizer/cost.h
@@ -203,14 +203,12 @@ extern Selectivity clauselist_selectivity(PlannerInfo *root,
 					   List *clauses,
 					   int varRelid,
 					   JoinType jointype,
-					   SpecialJoinInfo *sjinfo,
-					   RelOptInfo *rel);
+					   SpecialJoinInfo *sjinfo);
 extern Selectivity clause_selectivity(PlannerInfo *root,
 				   Node *clause,
 				   int varRelid,
 				   JoinType jointype,
-				   SpecialJoinInfo *sjinfo,
-				   RelOptInfo *rel);
+				   SpecialJoinInfo *sjinfo);
 extern void cost_gather_merge(GatherMergePath *path, PlannerInfo *root,
 							  RelOptInfo *rel, ParamPathInfo *param_info,
 							  Cost input_startup_cost, Cost input_total_cost,