Add an at-least-marginally-plausible method of estimating the number

of groups produced by GROUP BY.  This improves the accuracy of planning
estimates for grouped subselects, and is needed to check whether a
hashed aggregation plan risks memory overflow.

3 files changed, 13 insertions, 5 deletions

diff --git a/src/include/nodes/parsenodes.h b/src/include/nodes/parsenodes.h
index cd976cd1a14..92501196f93 100644
--- a/src/include/nodes/parsenodes.h
+++ b/src/include/nodes/parsenodes.h
@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2002, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $Id: parsenodes.h,v 1.215 2002/11/15 03:09:39 momjian Exp $
+ * $Id: parsenodes.h,v 1.216 2002/11/19 23:21:59 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -102,6 +102,7 @@ typedef struct Query
 	List	   *equi_key_list;	/* list of lists of equijoined
 								 * PathKeyItems */
 	List	   *query_pathkeys; /* desired pathkeys for query_planner() */
+	bool		hasJoinRTEs;	/* true if any RTEs are RTE_JOIN kind */
 } Query;
 
 
diff --git a/src/include/optimizer/planmain.h b/src/include/optimizer/planmain.h
index c927d540740..bd4bcddd308 100644
--- a/src/include/optimizer/planmain.h
+++ b/src/include/optimizer/planmain.h
@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2002, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $Id: planmain.h,v 1.61 2002/11/06 00:00:45 tgl Exp $
+ * $Id: planmain.h,v 1.62 2002/11/19 23:22:00 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -35,8 +35,11 @@ extern Sort *make_sort(Query *root, List *tlist,
 extern Sort *make_sort_from_pathkeys(Query *root, List *tlist,
 						Plan *lefttree, List *pathkeys);
 extern Agg *make_agg(List *tlist, List *qual, AggStrategy aggstrategy,
-					 int ngrp, AttrNumber *grpColIdx, Plan *lefttree);
-extern Group *make_group(List *tlist, int ngrp, AttrNumber *grpColIdx,
+					 int ngrp, AttrNumber *grpColIdx,
+					 long numGroups, int numAggs,
+					 Plan *lefttree);
+extern Group *make_group(List *tlist,
+						 int ngrp, AttrNumber *grpColIdx, double numGroups,
 						 Plan *lefttree);
 extern Material *make_material(List *tlist, Plan *lefttree);
 extern Unique *make_unique(List *tlist, Plan *lefttree, List *distinctList);
@@ -54,6 +57,7 @@ extern void build_base_rel_tlists(Query *root, List *tlist);
 extern Relids distribute_quals_to_rels(Query *root, Node *jtnode);
 extern void process_implied_equality(Query *root, Node *item1, Node *item2,
 						 Oid sortop1, Oid sortop2);
+extern bool vars_known_equal(Query *root, Var *var1, Var *var2);
 
 /*
  * prototypes for plan/setrefs.c
diff --git a/src/include/utils/selfuncs.h b/src/include/utils/selfuncs.h
index 8e73e61ffdc..49f3bc7e005 100644
--- a/src/include/utils/selfuncs.h
+++ b/src/include/utils/selfuncs.h
@@ -8,7 +8,7 @@
  * Portions Copyright (c) 1996-2002, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $Id: selfuncs.h,v 1.9 2002/10/19 02:56:16 tgl Exp $
+ * $Id: selfuncs.h,v 1.10 2002/11/19 23:22:00 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -75,6 +75,9 @@ extern void mergejoinscansel(Query *root, Node *clause,
 				 Selectivity *leftscan,
 				 Selectivity *rightscan);
 
+extern double estimate_num_groups(Query *root, List *groupClauses,
+								  double input_rows);
+
 extern Datum btcostestimate(PG_FUNCTION_ARGS);
 extern Datum rtcostestimate(PG_FUNCTION_ARGS);
 extern Datum hashcostestimate(PG_FUNCTION_ARGS);