Simplify LATERAL-related calculations within add_paths_to_joinrel().

tglsfdc · tglsfdc · commit 7145d35c1727 · 2015-12-09T18:54:25.000-05:00
While convincing myself that commit 7e19db0 would solve both of the problems recently reported by Andreas Seltenreich, I realized that add_paths_to_joinrel's handling of LATERAL restrictions could be made noticeably simpler and faster if we were to retain the minimum possible parameterization for each joinrel (that is, the set of relids supplying unsatisfied lateral references in it). We already retain that for baserels, in RelOptInfo.lateral_relids, so we can use that field for joinrels too. This is a back-port of commit edca44b. I originally intended not to back-patch that, but additional hacking in this area turns out to be needed, making it necessary not optional to compute lateral_relids for joinrels. In preparation for those fixes, sync the relevant code with HEAD as much as practical. (I did not risk rearranging fields of RelOptInfo in released branches, however.)
diff --git a/src/backend/optimizer/path/joinpath.c b/src/backend/optimizer/path/joinpath.c
@@ -29,19 +29,19 @@ static void sort_inner_and_outer(PlannerInfo *root, RelOptInfo *joinrel,
 					 RelOptInfo *outerrel, RelOptInfo *innerrel,
 					 List *restrictlist, List *mergeclause_list,
 					 JoinType jointype, SpecialJoinInfo *sjinfo,
-					 Relids param_source_rels, Relids extra_lateral_rels);
+					 Relids param_source_rels);
 static void match_unsorted_outer(PlannerInfo *root, RelOptInfo *joinrel,
 					 RelOptInfo *outerrel, RelOptInfo *innerrel,
 					 List *restrictlist, List *mergeclause_list,
 					 JoinType jointype, SpecialJoinInfo *sjinfo,
 					 SemiAntiJoinFactors *semifactors,
-					 Relids param_source_rels, Relids extra_lateral_rels);
+					 Relids param_source_rels);
 static void hash_inner_and_outer(PlannerInfo *root, RelOptInfo *joinrel,
 					 RelOptInfo *outerrel, RelOptInfo *innerrel,
 					 List *restrictlist,
 					 JoinType jointype, SpecialJoinInfo *sjinfo,
 					 SemiAntiJoinFactors *semifactors,
-					 Relids param_source_rels, Relids extra_lateral_rels);
+					 Relids param_source_rels);
 static List *select_mergejoin_clauses(PlannerInfo *root,
 						 RelOptInfo *joinrel,
 						 RelOptInfo *outerrel,
@@ -87,7 +87,6 @@ add_paths_to_joinrel(PlannerInfo *root,
 	bool		mergejoin_allowed = true;
 	SemiAntiJoinFactors semifactors;
 	Relids		param_source_rels = NULL;
-	Relids		extra_lateral_rels = NULL;
 	ListCell   *lc;
 
 	/*
@@ -153,59 +152,14 @@ add_paths_to_joinrel(PlannerInfo *root,
 	}
 
 	/*
-	 * However, when a LATERAL subquery is involved, we have to be a bit
-	 * laxer, because there will simply not be any paths for the joinrel that
-	 * aren't parameterized by whatever the subquery is parameterized by,
-	 * unless its parameterization is resolved within the joinrel.  Hence, add
-	 * to param_source_rels anything that is laterally referenced in either
-	 * input and is not in the join already.
+	 * However, when a LATERAL subquery is involved, there will simply not be
+	 * any paths for the joinrel that aren't parameterized by whatever the
+	 * subquery is parameterized by, unless its parameterization is resolved
+	 * within the joinrel.  So we might as well allow additional dependencies
+	 * on whatever residual lateral dependencies the joinrel will have.
 	 */
-	foreach(lc, root->lateral_info_list)
-	{
-		LateralJoinInfo *ljinfo = (LateralJoinInfo *) lfirst(lc);
-
-		if (bms_is_subset(ljinfo->lateral_rhs, joinrel->relids))
-			param_source_rels = bms_join(param_source_rels,
-										 bms_difference(ljinfo->lateral_lhs,
-														joinrel->relids));
-	}
-
-	/*
-	 * Another issue created by LATERAL references is that PlaceHolderVars
-	 * that need to be computed at this join level might contain lateral
-	 * references to rels not in the join, meaning that the paths for the join
-	 * would need to be marked as parameterized by those rels, independently
-	 * of all other considerations.  Set extra_lateral_rels to the set of such
-	 * rels.  This will not affect our decisions as to which paths to
-	 * generate; we merely add these rels to their required_outer sets.
-	 */
-	foreach(lc, root->placeholder_list)
-	{
-		PlaceHolderInfo *phinfo = (PlaceHolderInfo *) lfirst(lc);
-
-		/* PHVs without lateral refs can be skipped over quickly */
-		if (phinfo->ph_lateral == NULL)
-			continue;
-		/* Is it due to be evaluated at this join, and not in either input? */
-		if (bms_is_subset(phinfo->ph_eval_at, joinrel->relids) &&
-			!bms_is_subset(phinfo->ph_eval_at, outerrel->relids) &&
-			!bms_is_subset(phinfo->ph_eval_at, innerrel->relids))
-		{
-			/* Yes, remember its lateral rels */
-			extra_lateral_rels = bms_add_members(extra_lateral_rels,
-												 phinfo->ph_lateral);
-		}
-	}
-
-	/*
-	 * Make sure extra_lateral_rels doesn't list anything within the join, and
-	 * that it's NULL if empty.  (This allows us to use bms_add_members to add
-	 * it to required_outer below, while preserving the property that
-	 * required_outer is exactly NULL if empty.)
-	 */
-	extra_lateral_rels = bms_del_members(extra_lateral_rels, joinrel->relids);
-	if (bms_is_empty(extra_lateral_rels))
-		extra_lateral_rels = NULL;
+	param_source_rels = bms_add_members(param_source_rels,
+										joinrel->lateral_relids);
 
 	/*
 	 * 1. Consider mergejoin paths where both relations must be explicitly
@@ -215,7 +169,7 @@ add_paths_to_joinrel(PlannerInfo *root,
 		sort_inner_and_outer(root, joinrel, outerrel, innerrel,
 							 restrictlist, mergeclause_list, jointype,
 							 sjinfo,
-							 param_source_rels, extra_lateral_rels);
+							 param_source_rels);
 
 	/*
 	 * 2. Consider paths where the outer relation need not be explicitly
@@ -228,7 +182,7 @@ add_paths_to_joinrel(PlannerInfo *root,
 		match_unsorted_outer(root, joinrel, outerrel, innerrel,
 							 restrictlist, mergeclause_list, jointype,
 							 sjinfo, &semifactors,
-							 param_source_rels, extra_lateral_rels);
+							 param_source_rels);
 
 #ifdef NOT_USED
 
@@ -247,7 +201,7 @@ add_paths_to_joinrel(PlannerInfo *root,
 		match_unsorted_inner(root, joinrel, outerrel, innerrel,
 							 restrictlist, mergeclause_list, jointype,
 							 sjinfo, &semifactors,
-							 param_source_rels, extra_lateral_rels);
+							 param_source_rels);
 #endif
 
 	/*
@@ -259,7 +213,7 @@ add_paths_to_joinrel(PlannerInfo *root,
 		hash_inner_and_outer(root, joinrel, outerrel, innerrel,
 							 restrictlist, jointype,
 							 sjinfo, &semifactors,
-							 param_source_rels, extra_lateral_rels);
+							 param_source_rels);
 }
 
 /*
@@ -353,7 +307,6 @@ try_nestloop_path(PlannerInfo *root,
 				  SpecialJoinInfo *sjinfo,
 				  SemiAntiJoinFactors *semifactors,
 				  Relids param_source_rels,
-				  Relids extra_lateral_rels,
 				  Path *outer_path,
 				  Path *inner_path,
 				  List *restrict_clauses,
@@ -382,9 +335,13 @@ try_nestloop_path(PlannerInfo *root,
 
 	/*
 	 * Independently of that, add parameterization needed for any
-	 * PlaceHolderVars that need to be computed at the join.
+	 * PlaceHolderVars that need to be computed at the join.  We can handle
+	 * that just by adding joinrel->lateral_relids; that might include some
+	 * rels that are already in required_outer, but no harm done.  (Note that
+	 * lateral_relids is exactly NULL if empty, so this will not break the
+	 * property that required_outer is too.)
 	 */
-	required_outer = bms_add_members(required_outer, extra_lateral_rels);
+	required_outer = bms_add_members(required_outer, joinrel->lateral_relids);
 
 	/*
 	 * Do a precheck to quickly eliminate obviously-inferior paths.  We
@@ -434,7 +391,6 @@ try_mergejoin_path(PlannerInfo *root,
 				   JoinType jointype,
 				   SpecialJoinInfo *sjinfo,
 				   Relids param_source_rels,
-				   Relids extra_lateral_rels,
 				   Path *outer_path,
 				   Path *inner_path,
 				   List *restrict_clauses,
@@ -464,7 +420,7 @@ try_mergejoin_path(PlannerInfo *root,
 	 * Independently of that, add parameterization needed for any
 	 * PlaceHolderVars that need to be computed at the join.
 	 */
-	required_outer = bms_add_members(required_outer, extra_lateral_rels);
+	required_outer = bms_add_members(required_outer, joinrel->lateral_relids);
 
 	/*
 	 * If the given paths are already well enough ordered, we can skip doing
@@ -523,7 +479,6 @@ try_hashjoin_path(PlannerInfo *root,
 				  SpecialJoinInfo *sjinfo,
 				  SemiAntiJoinFactors *semifactors,
 				  Relids param_source_rels,
-				  Relids extra_lateral_rels,
 				  Path *outer_path,
 				  Path *inner_path,
 				  List *restrict_clauses,
@@ -550,7 +505,7 @@ try_hashjoin_path(PlannerInfo *root,
 	 * Independently of that, add parameterization needed for any
 	 * PlaceHolderVars that need to be computed at the join.
 	 */
-	required_outer = bms_add_members(required_outer, extra_lateral_rels);
+	required_outer = bms_add_members(required_outer, joinrel->lateral_relids);
 
 	/*
 	 * See comments in try_nestloop_path().  Also note that hashjoin paths
@@ -630,7 +585,6 @@ clause_sides_match_join(RestrictInfo *rinfo, RelOptInfo *outerrel,
  * 'jointype' is the type of join to do
  * 'sjinfo' is extra info about the join for selectivity estimation
  * 'param_source_rels' are OK targets for parameterization of result paths
- * 'extra_lateral_rels' are additional parameterization for result paths
  */
 static void
 sort_inner_and_outer(PlannerInfo *root,
@@ -641,8 +595,7 @@ sort_inner_and_outer(PlannerInfo *root,
 					 List *mergeclause_list,
 					 JoinType jointype,
 					 SpecialJoinInfo *sjinfo,
-					 Relids param_source_rels,
-					 Relids extra_lateral_rels)
+					 Relids param_source_rels)
 {
 	Path	   *outer_path;
 	Path	   *inner_path;
@@ -772,7 +725,6 @@ sort_inner_and_outer(PlannerInfo *root,
 						   jointype,
 						   sjinfo,
 						   param_source_rels,
-						   extra_lateral_rels,
 						   outer_path,
 						   inner_path,
 						   restrictlist,
@@ -818,7 +770,6 @@ sort_inner_and_outer(PlannerInfo *root,
  * 'sjinfo' is extra info about the join for selectivity estimation
  * 'semifactors' contains valid data if jointype is SEMI or ANTI
  * 'param_source_rels' are OK targets for parameterization of result paths
- * 'extra_lateral_rels' are additional parameterization for result paths
  */
 static void
 match_unsorted_outer(PlannerInfo *root,
@@ -830,8 +781,7 @@ match_unsorted_outer(PlannerInfo *root,
 					 JoinType jointype,
 					 SpecialJoinInfo *sjinfo,
 					 SemiAntiJoinFactors *semifactors,
-					 Relids param_source_rels,
-					 Relids extra_lateral_rels)
+					 Relids param_source_rels)
 {
 	JoinType	save_jointype = jointype;
 	bool		nestjoinOK;
@@ -961,7 +911,6 @@ match_unsorted_outer(PlannerInfo *root,
 							  sjinfo,
 							  semifactors,
 							  param_source_rels,
-							  extra_lateral_rels,
 							  outerpath,
 							  inner_cheapest_total,
 							  restrictlist,
@@ -987,7 +936,6 @@ match_unsorted_outer(PlannerInfo *root,
 								  sjinfo,
 								  semifactors,
 								  param_source_rels,
-								  extra_lateral_rels,
 								  outerpath,
 								  innerpath,
 								  restrictlist,
@@ -1002,7 +950,6 @@ match_unsorted_outer(PlannerInfo *root,
 								  sjinfo,
 								  semifactors,
 								  param_source_rels,
-								  extra_lateral_rels,
 								  outerpath,
 								  matpath,
 								  restrictlist,
@@ -1058,7 +1005,6 @@ match_unsorted_outer(PlannerInfo *root,
 						   jointype,
 						   sjinfo,
 						   param_source_rels,
-						   extra_lateral_rels,
 						   outerpath,
 						   inner_cheapest_total,
 						   restrictlist,
@@ -1157,7 +1103,6 @@ match_unsorted_outer(PlannerInfo *root,
 								   jointype,
 								   sjinfo,
 								   param_source_rels,
-								   extra_lateral_rels,
 								   outerpath,
 								   innerpath,
 								   restrictlist,
@@ -1203,7 +1148,6 @@ match_unsorted_outer(PlannerInfo *root,
 									   jointype,
 									   sjinfo,
 									   param_source_rels,
-									   extra_lateral_rels,
 									   outerpath,
 									   innerpath,
 									   restrictlist,
@@ -1238,7 +1182,6 @@ match_unsorted_outer(PlannerInfo *root,
  * 'sjinfo' is extra info about the join for selectivity estimation
  * 'semifactors' contains valid data if jointype is SEMI or ANTI
  * 'param_source_rels' are OK targets for parameterization of result paths
- * 'extra_lateral_rels' are additional parameterization for result paths
  */
 static void
 hash_inner_and_outer(PlannerInfo *root,
@@ -1249,8 +1192,7 @@ hash_inner_and_outer(PlannerInfo *root,
 					 JoinType jointype,
 					 SpecialJoinInfo *sjinfo,
 					 SemiAntiJoinFactors *semifactors,
-					 Relids param_source_rels,
-					 Relids extra_lateral_rels)
+					 Relids param_source_rels)
 {
 	bool		isouterjoin = IS_OUTER_JOIN(jointype);
 	List	   *hashclauses;
@@ -1324,7 +1266,6 @@ hash_inner_and_outer(PlannerInfo *root,
 							  sjinfo,
 							  semifactors,
 							  param_source_rels,
-							  extra_lateral_rels,
 							  cheapest_total_outer,
 							  cheapest_total_inner,
 							  restrictlist,
@@ -1344,7 +1285,6 @@ hash_inner_and_outer(PlannerInfo *root,
 							  sjinfo,
 							  semifactors,
 							  param_source_rels,
-							  extra_lateral_rels,
 							  cheapest_total_outer,
 							  cheapest_total_inner,
 							  restrictlist,
@@ -1357,7 +1297,6 @@ hash_inner_and_outer(PlannerInfo *root,
 								  sjinfo,
 								  semifactors,
 								  param_source_rels,
-								  extra_lateral_rels,
 								  cheapest_startup_outer,
 								  cheapest_total_inner,
 								  restrictlist,
@@ -1382,7 +1321,6 @@ hash_inner_and_outer(PlannerInfo *root,
 								  sjinfo,
 								  semifactors,
 								  param_source_rels,
-								  extra_lateral_rels,
 								  cheapest_startup_outer,
 								  cheapest_total_inner,
 								  restrictlist,
@@ -1420,7 +1358,6 @@ hash_inner_and_outer(PlannerInfo *root,
 									  sjinfo,
 									  semifactors,
 									  param_source_rels,
-									  extra_lateral_rels,
 									  outerpath,
 									  innerpath,
 									  restrictlist,
diff --git a/src/backend/optimizer/util/relnode.c b/src/backend/optimizer/util/relnode.c
@@ -376,7 +376,7 @@ build_join_rel(PlannerInfo *root,
 	joinrel->attr_needed = NULL;
 	joinrel->attr_widths = NULL;
 	joinrel->lateral_vars = NIL;
-	joinrel->lateral_relids = NULL;
+	joinrel->lateral_relids = min_join_parameterization(root, joinrel->relids);
 	joinrel->lateral_referencers = NULL;
 	joinrel->indexlist = NIL;
 	joinrel->pages = 0;
diff --git a/src/include/nodes/relation.h b/src/include/nodes/relation.h
@@ -349,7 +349,7 @@ typedef struct PlannerInfo
  *		lateral_vars - lateral cross-references of rel, if any (list of
  *					   Vars and PlaceHolderVars)
  *		lateral_relids - required outer rels for LATERAL, as a Relids set
- *						 (for child rels this can be more than lateral_vars)
+ *			(this is now used for join rels too, but we won't move it till 9.5)
  *		lateral_referencers - relids of rels that reference this one laterally
  *		indexlist - list of IndexOptInfo nodes for relation's indexes
  *					(always NIL if it's not a table)
@@ -368,7 +368,7 @@ typedef struct PlannerInfo
  *		and fdw_private are filled during initial path creation.
  *
  *		For otherrels that are appendrel members, these fields are filled
- *		in just as for a baserel.
+ *		in just as for a baserel, except we don't bother with lateral_vars.
  *
  * The presence of the remaining fields depends on the restrictions
  * and joins that the relation participates in:
