0002-Use-default-restriction-for-number-of-groups.txt

From d5fd0f8f981d9e457320c1007f21f2b9b74aab9e Mon Sep 17 00:00:00 2001
From: Andrey Lepikhov <a.lepikhov@postgrespro.ru>
Date: Thu, 10 Feb 2022 13:51:51 +0500
Subject: [PATCH 2/2] Use default restriction for number of groups.

---
 src/backend/optimizer/path/costsize.c | 22 +++++++---------------
 1 file changed, 7 insertions(+), 15 deletions(-)

diff --git a/src/backend/optimizer/path/costsize.c b/src/backend/optimizer/path/costsize.c
index 68a32740d7..b9e975df10 100644
--- a/src/backend/optimizer/path/costsize.c
+++ b/src/backend/optimizer/path/costsize.c
@@ -1756,8 +1756,8 @@ cost_recursive_union(Path *runion, Path *nrterm, Path *rterm)
 
 /*
  * is_fake_var
- *		Workaround for generate_append_tlist() which generates fake Vars with
- *		varno == 0, that will cause a fail of estimate_num_group() call
+ *		Workaround for generate_append_tlist() which generates fake Vars for the
+ *		case of "varno 0", that will cause a fail of estimate_num_group() call
  *
  * XXX Ummm, why would estimate_num_group fail with this?
  */
@@ -1978,21 +1978,13 @@ compute_cpu_sort_cost(PlannerInfo *root, List *pathkeys, int nPresortedKeys,
 													  tuplesPerPrevGroup, NULL, NULL,
 													  &cache_varinfos,
 													  list_length(pathkeyExprs) - 1);
-		else if (tuples > 4.0)
+		else
 			/*
-			 * Use geometric mean as estimation if there is no any stats.
-			 * Don't use DEFAULT_NUM_DISTINCT because it used for only one
-			 * column while here we try to estimate number of groups over
-			 * set of columns.
-			 *
-			 * XXX Perhaps this should use DEFAULT_NUM_DISTINCT at least to
-			 * limit the calculated values, somehow?
-			 *
-			 * XXX What's the logic of the following formula?
+			 * In case of full uncertainity use default defensive approach. It
+			 * means that any permutations of such vars are equivalent.
+			 * Also, see comments for the cost_incremental_sort routine.
 			 */
-			nGroups = ceil(2.0 + sqrt(tuples) * (i + 1) / list_length(pathkeys));
-		else
-			nGroups = tuples;
+			nGroups = Min(tuplesPerPrevGroup, DEFAULT_NUM_DISTINCT);
 
 		/*
 		 * Presorted keys aren't participated in comparison but still checked
-- 
2.25.1