Change the division of labor between grouping_planner and query_planner

so that the latter estimates the number of groups that grouping will
produce.  This is needed because it is primarily query_planner that
makes the decision between fast-start and fast-finish plans, and in the
original coding it was unable to make more than a crude rule-of-thumb
choice when the query involved grouping.  This revision helps us make
saner choices for queries like SELECT ... GROUP BY ... LIMIT, as in a
recent example from Mark Kirkwood.  Also move the responsibility for
canonicalizing sort_pathkeys and group_pathkeys into query_planner;
this information has to be available anyway to support the first change,
and doing it this way lets us get rid of compare_noncanonical_pathkeys
entirely.

3 files changed, 8 insertions, 7 deletions

diff --git a/src/include/nodes/relation.h b/src/include/nodes/relation.h
index 88e535dc9b9..3b23bfbeb4e 100644
--- a/src/include/nodes/relation.h
+++ b/src/include/nodes/relation.h
@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/nodes/relation.h,v 1.117 2005/07/23 21:05:48 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/nodes/relation.h,v 1.118 2005/08/27 22:13:43 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -101,6 +101,9 @@ typedef struct PlannerInfo
 	List	   *query_pathkeys; /* desired pathkeys for query_planner(),
 								 * and actual pathkeys afterwards */
 
+	List	   *group_pathkeys; /* groupClause pathkeys, if any */
+	List	   *sort_pathkeys;	/* sortClause pathkeys, if any */
+
 	double		tuple_fraction;	/* tuple_fraction passed to query_planner */
 
 	bool		hasJoinRTEs;	/* true if any RTEs are RTE_JOIN kind */
diff --git a/src/include/optimizer/paths.h b/src/include/optimizer/paths.h
index 8f26c8e8f0d..7c8108b000a 100644
--- a/src/include/optimizer/paths.h
+++ b/src/include/optimizer/paths.h
@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/optimizer/paths.h,v 1.86 2005/07/28 20:26:22 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/optimizer/paths.h,v 1.87 2005/08/27 22:13:44 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -102,9 +102,6 @@ extern void generate_implied_equalities(PlannerInfo *root);
 extern List *canonicalize_pathkeys(PlannerInfo *root, List *pathkeys);
 extern PathKeysComparison compare_pathkeys(List *keys1, List *keys2);
 extern bool pathkeys_contained_in(List *keys1, List *keys2);
-extern PathKeysComparison compare_noncanonical_pathkeys(List *keys1,
-							  List *keys2);
-extern bool noncanonical_pathkeys_contained_in(List *keys1, List *keys2);
 extern Path *get_cheapest_path_for_pathkeys(List *paths, List *pathkeys,
 							   CostSelector cost_criterion);
 extern Path *get_cheapest_fractional_path_for_pathkeys(List *paths,
diff --git a/src/include/optimizer/planmain.h b/src/include/optimizer/planmain.h
index 474a14da9a0..652431b894f 100644
--- a/src/include/optimizer/planmain.h
+++ b/src/include/optimizer/planmain.h
@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/optimizer/planmain.h,v 1.87 2005/08/18 17:51:12 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/optimizer/planmain.h,v 1.88 2005/08/27 22:13:44 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -22,7 +22,8 @@
  */
 extern void query_planner(PlannerInfo *root, List *tlist,
 						  double tuple_fraction,
-						  Path **cheapest_path, Path **sorted_path);
+						  Path **cheapest_path, Path **sorted_path,
+						  double *num_groups);
 
 /*
  * prototypes for plan/planagg.c