Consider explicit incremental sort for Append and MergeAppend

For an ordered Append or MergeAppend, we need to inject an explicit
sort into any subpath that is not already well enough ordered.
Currently, only explicit full sorts are considered; incremental sorts
are not yet taken into account.

In this patch, for subpaths of an ordered Append or MergeAppend, we
choose to use explicit incremental sort if it is enabled and there are
presorted keys.

The rationale is based on the assumption that incremental sort is
always faster than full sort when there are presorted keys, a premise
that has been applied in various parts of the code.  In addition, the
current cost model tends to favor incremental sort as being cheaper
than full sort in the presence of presorted keys, making it reasonable
not to consider full sort in such cases.

No backpatch as this could result in plan changes.

Author: Richard Guo <guofenglinux@gmail.com>
Reviewed-by: Andrei Lepikhov <lepihov@gmail.com>
Reviewed-by: Robert Haas <robertmhaas@gmail.com>
Discussion: https://postgr.es/m/CAMbWs4_V7a2enTR+T3pOY_YZ-FU8ZsFYym2swOz4jNMqmSgyuw@mail.gmail.com

1 files changed, 58 insertions, 8 deletions

diff --git a/src/backend/optimizer/plan/createplan.c b/src/backend/optimizer/plan/createplan.c
index 0b61aef962c..8a9f1d7a943 100644
--- a/src/backend/optimizer/plan/createplan.c
+++ b/src/backend/optimizer/plan/createplan.c
@@ -1318,6 +1318,7 @@ create_append_plan(PlannerInfo *root, AppendPath *best_path, int flags)
 			Oid		   *sortOperators;
 			Oid		   *collations;
 			bool	   *nullsFirst;
+			int			presorted_keys;
 
 			/*
 			 * Compute sort column info, and adjust subplan's tlist as needed.
@@ -1353,14 +1354,38 @@ create_append_plan(PlannerInfo *root, AppendPath *best_path, int flags)
 						  numsortkeys * sizeof(bool)) == 0);
 
 			/* Now, insert a Sort node if subplan isn't sufficiently ordered */
-			if (!pathkeys_contained_in(pathkeys, subpath->pathkeys))
+			if (!pathkeys_count_contained_in(pathkeys, subpath->pathkeys,
+											 &presorted_keys))
 			{
-				Sort	   *sort = make_sort(subplan, numsortkeys,
+				Plan	   *sort_plan;
+
+				/*
+				 * We choose to use incremental sort if it is enabled and
+				 * there are presorted keys; otherwise we use full sort.
+				 */
+				if (enable_incremental_sort && presorted_keys > 0)
+				{
+					sort_plan = (Plan *)
+						make_incrementalsort(subplan, numsortkeys, presorted_keys,
 											 sortColIdx, sortOperators,
 											 collations, nullsFirst);
 
-				label_sort_with_costsize(root, sort, best_path->limit_tuples);
-				subplan = (Plan *) sort;
+					label_incrementalsort_with_costsize(root,
+														(IncrementalSort *) sort_plan,
+														pathkeys,
+														best_path->limit_tuples);
+				}
+				else
+				{
+					sort_plan = (Plan *) make_sort(subplan, numsortkeys,
+												   sortColIdx, sortOperators,
+												   collations, nullsFirst);
+
+					label_sort_with_costsize(root, (Sort *) sort_plan,
+											 best_path->limit_tuples);
+				}
+
+				subplan = sort_plan;
 			}
 		}
 
@@ -1491,6 +1516,7 @@ create_merge_append_plan(PlannerInfo *root, MergeAppendPath *best_path,
 		Oid		   *sortOperators;
 		Oid		   *collations;
 		bool	   *nullsFirst;
+		int			presorted_keys;
 
 		/* Build the child plan */
 		/* Must insist that all children return the same tlist */
@@ -1525,14 +1551,38 @@ create_merge_append_plan(PlannerInfo *root, MergeAppendPath *best_path,
 					  numsortkeys * sizeof(bool)) == 0);
 
 		/* Now, insert a Sort node if subplan isn't sufficiently ordered */
-		if (!pathkeys_contained_in(pathkeys, subpath->pathkeys))
+		if (!pathkeys_count_contained_in(pathkeys, subpath->pathkeys,
+										 &presorted_keys))
 		{
-			Sort	   *sort = make_sort(subplan, numsortkeys,
+			Plan	   *sort_plan;
+
+			/*
+			 * We choose to use incremental sort if it is enabled and there
+			 * are presorted keys; otherwise we use full sort.
+			 */
+			if (enable_incremental_sort && presorted_keys > 0)
+			{
+				sort_plan = (Plan *)
+					make_incrementalsort(subplan, numsortkeys, presorted_keys,
 										 sortColIdx, sortOperators,
 										 collations, nullsFirst);
 
-			label_sort_with_costsize(root, sort, best_path->limit_tuples);
-			subplan = (Plan *) sort;
+				label_incrementalsort_with_costsize(root,
+													(IncrementalSort *) sort_plan,
+													pathkeys,
+													best_path->limit_tuples);
+			}
+			else
+			{
+				sort_plan = (Plan *) make_sort(subplan, numsortkeys,
+											   sortColIdx, sortOperators,
+											   collations, nullsFirst);
+
+				label_sort_with_costsize(root, (Sort *) sort_plan,
+										 best_path->limit_tuples);
+			}
+
+			subplan = sort_plan;
 		}
 
 		subplans = lappend(subplans, subplan);