Add COST and ROWS options to CREATE/ALTER FUNCTION, plus underlying pg_proc

columns procost and prorows, to allow simple user adjustment of the estimated
cost of a function call, as well as control of the estimated number of rows
returned by a set-returning function.  We might eventually wish to extend this
to allow function-specific estimation routines, but there seems to be
consensus that we should try a simple constant estimate first.  In particular
this provides a relatively simple way to control the order in which different
WHERE clauses are applied in a plan node, which is a Good Thing in view of the
fact that the recent EquivalenceClass planner rewrite made that much less
predictable than before.

doc/src/sgml/catalogs.sgml

-<!-- $PostgreSQL: pgsql/doc/src/sgml/catalogs.sgml,v 2.142 2007/01/20 23:13:01 tgl Exp $ -->
+<!-- $PostgreSQL: pgsql/doc/src/sgml/catalogs.sgml,v 2.143 2007/01/22 01:35:19 tgl Exp $ -->
 <!--
  Documentation of the system catalogs, directed toward PostgreSQL developers
  -->
@@ -3375,6 +3375,22 @@
       <entry>Implementation language or call interface of this function</entry>
      </row>
 
+     <row>
+      <entry><structfield>procost</structfield></entry>
+      <entry><type>float4</type></entry>
+      <entry></entry>
+      <entry>Estimated execution cost (in units of
+       <xref linkend="guc-cpu-operator-cost">); if <structfield>proretset</>,
+       this is cost per row returned</entry>
+     </row>
+
+     <row>
+      <entry><structfield>prorows</structfield></entry>
+      <entry><type>float4</type></entry>
+      <entry></entry>
+      <entry>Estimated number of result rows (zero if not <structfield>proretset</>)</entry>
+     </row>
+
      <row>
       <entry><structfield>proisagg</structfield></entry>
       <entry><type>bool</type></entry>

doc/src/sgml/ref/alter_function.sgml

 <!--
-$PostgreSQL: pgsql/doc/src/sgml/ref/alter_function.sgml,v 1.12 2006/09/16 00:30:16 momjian Exp $
+$PostgreSQL: pgsql/doc/src/sgml/ref/alter_function.sgml,v 1.13 2007/01/22 01:35:19 tgl Exp $
 PostgreSQL documentation
 -->
 
@@ -34,6 +34,8 @@ where <replaceable class="PARAMETER">action</replaceable> is one of:
     CALLED ON NULL INPUT | RETURNS NULL ON NULL INPUT | STRICT
     IMMUTABLE | STABLE | VOLATILE
     [ EXTERNAL ] SECURITY INVOKER | [ EXTERNAL ] SECURITY DEFINER
+    COST <replaceable class="parameter">execution_cost</replaceable>
+    ROWS <replaceable class="parameter">result_rows</replaceable>
 </synopsis>
  </refsynopsisdiv>
   
@@ -186,6 +188,30 @@ where <replaceable class="PARAMETER">action</replaceable> is one of:
     </listitem>
    </varlistentry>
 
+    <varlistentry>
+     <term><literal>COST</literal> <replaceable class="parameter">execution_cost</replaceable></term>
+
+     <listitem>
+      <para>
+       Change the estimated execution cost of the function.
+       See <xref linkend="sql-createfunction"
+       endterm="sql-createfunction-title"> for more information.
+      </para>
+     </listitem>
+   </varlistentry>
+
+    <varlistentry>
+     <term><literal>ROWS</literal> <replaceable class="parameter">result_rows</replaceable></term>
+
+     <listitem>
+      <para>
+       Change the estimated number of rows returned by a set-returning
+       function.  See <xref linkend="sql-createfunction"
+       endterm="sql-createfunction-title"> for more information.
+      </para>
+     </listitem>
+   </varlistentry>
+
    <varlistentry>
     <term><literal>RESTRICT</literal></term>
 

doc/src/sgml/ref/create_function.sgml

 <!--
-$PostgreSQL: pgsql/doc/src/sgml/ref/create_function.sgml,v 1.70 2006/11/10 20:52:18 tgl Exp $
+$PostgreSQL: pgsql/doc/src/sgml/ref/create_function.sgml,v 1.71 2007/01/22 01:35:19 tgl Exp $
 -->
 
 <refentry id="SQL-CREATEFUNCTION">
@@ -26,6 +26,8 @@ CREATE [ OR REPLACE ] FUNCTION
     | IMMUTABLE | STABLE | VOLATILE
     | CALLED ON NULL INPUT | RETURNS NULL ON NULL INPUT | STRICT
     | [ EXTERNAL ] SECURITY INVOKER | [ EXTERNAL ] SECURITY DEFINER
+    | COST <replaceable class="parameter">execution_cost</replaceable>
+    | ROWS <replaceable class="parameter">result_rows</replaceable>
     | AS '<replaceable class="parameter">definition</replaceable>'
     | AS '<replaceable class="parameter">obj_file</replaceable>', '<replaceable class="parameter">link_symbol</replaceable>'
   } ...
@@ -52,7 +54,7 @@ CREATE [ OR REPLACE ] FUNCTION
   </para>
 
   <para>
-   To update the definition of an existing function, use
+   To replace the current definition of an existing function, use
    <command>CREATE OR REPLACE FUNCTION</command>.  It is not possible
    to change the name or argument types of a function this way (if you
    tried, you would actually be creating a new, distinct function).
@@ -289,6 +291,35 @@ CREATE [ OR REPLACE ] FUNCTION
     </listitem>
    </varlistentry>
 
+    <varlistentry>
+     <term><replaceable class="parameter">execution_cost</replaceable></term>
+
+     <listitem>
+      <para>
+       A positive number giving the estimated execution cost for the function,
+       in units of <xref linkend="guc-cpu-operator-cost">.  If the function
+       returns a set, this is the cost per returned row.  If the cost is
+       not specified, 1 unit is assumed for C-language and internal functions,
+       and 100 units for functions in all other languages.  Larger values
+       cause the planner to try to avoid evaluating the function more often
+       than necessary.
+      </para>
+     </listitem>
+    </varlistentry>
+
+    <varlistentry>
+     <term><replaceable class="parameter">result_rows</replaceable></term>
+
+     <listitem>
+      <para>
+       A positive number giving the estimated number of rows that the planner
+       should expect the function to return.  This is only allowed when the
+       function is declared to return a set.  The default assumption is
+       1000 rows.
+      </para>
+     </listitem>
+    </varlistentry>
+
     <varlistentry>
      <term><replaceable class="parameter">definition</replaceable></term>
 
@@ -400,7 +431,8 @@ CREATE FUNCTION foo(int, out text) ...
 
    <para>
     When repeated <command>CREATE FUNCTION</command> calls refer to
-    the same object file, the file is only loaded once.  To unload and
+    the same object file, the file is only loaded once per session.
+    To unload and
     reload the file (perhaps during development), use the <xref
     linkend="sql-load" endterm="sql-load-title"> command.
    </para>

src/backend/bootstrap/bootstrap.c

@@ -8,7 +8,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/bootstrap/bootstrap.c,v 1.228 2007/01/05 22:19:24 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/backend/bootstrap/bootstrap.c,v 1.229 2007/01/22 01:35:19 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -115,16 +115,18 @@ static const struct typinfo TypInfo[] = {
 	F_BYTEAIN, F_BYTEAOUT},
 	{"char", CHAROID, 0, 1, true, 'c', 'p',
 	F_CHARIN, F_CHAROUT},
-	{"name", NAMEOID, CHAROID, NAMEDATALEN, false, 'i', 'p',
-	F_NAMEIN, F_NAMEOUT},
 	{"int2", INT2OID, 0, 2, true, 's', 'p',
 	F_INT2IN, F_INT2OUT},
 	{"int4", INT4OID, 0, 4, true, 'i', 'p',
 	F_INT4IN, F_INT4OUT},
-	{"regproc", REGPROCOID, 0, 4, true, 'i', 'p',
-	F_REGPROCIN, F_REGPROCOUT},
+	{"float4", FLOAT4OID, 0, 4, false, 'i', 'p',
+	F_FLOAT4IN, F_FLOAT4OUT},
+	{"name", NAMEOID, CHAROID, NAMEDATALEN, false, 'i', 'p',
+	F_NAMEIN, F_NAMEOUT},
 	{"regclass", REGCLASSOID, 0, 4, true, 'i', 'p',
 	F_REGCLASSIN, F_REGCLASSOUT},
+	{"regproc", REGPROCOID, 0, 4, true, 'i', 'p',
+	F_REGPROCIN, F_REGPROCOUT},
 	{"regtype", REGTYPEOID, 0, 4, true, 'i', 'p',
 	F_REGTYPEIN, F_REGTYPEOUT},
 	{"text", TEXTOID, 0, -1, false, 'i', 'x',

src/backend/catalog/pg_aggregate.c

@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/catalog/pg_aggregate.c,v 1.84 2007/01/05 22:19:25 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/backend/catalog/pg_aggregate.c,v 1.85 2007/01/22 01:35:20 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -214,7 +214,9 @@ AggregateCreate(const char *aggName,
 											 numArgs),	/* paramTypes */
 							  PointerGetDatum(NULL),	/* allParamTypes */
 							  PointerGetDatum(NULL),	/* parameterModes */
-							  PointerGetDatum(NULL));	/* parameterNames */
+							  PointerGetDatum(NULL),	/* parameterNames */
+							  1,				/* procost */
+							  0);				/* prorows */
 
 	/*
 	 * Okay to create the pg_aggregate entry.

src/backend/catalog/pg_proc.c

@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/catalog/pg_proc.c,v 1.142 2007/01/05 22:19:25 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/backend/catalog/pg_proc.c,v 1.143 2007/01/22 01:35:20 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -71,7 +71,9 @@ ProcedureCreate(const char *procedureName,
 				oidvector *parameterTypes,
 				Datum allParameterTypes,
 				Datum parameterModes,
-				Datum parameterNames)
+				Datum parameterNames,
+				float4 procost,
+				float4 prorows)
 {
 	Oid			retval;
 	int			parameterCount;
@@ -219,6 +221,8 @@ ProcedureCreate(const char *procedureName,
 	values[Anum_pg_proc_pronamespace - 1] = ObjectIdGetDatum(procNamespace);
 	values[Anum_pg_proc_proowner - 1] = ObjectIdGetDatum(GetUserId());
 	values[Anum_pg_proc_prolang - 1] = ObjectIdGetDatum(languageObjectId);
+	values[Anum_pg_proc_procost - 1] = Float4GetDatum(procost);
+	values[Anum_pg_proc_prorows - 1] = Float4GetDatum(prorows);
 	values[Anum_pg_proc_proisagg - 1] = BoolGetDatum(isAgg);
 	values[Anum_pg_proc_prosecdef - 1] = BoolGetDatum(security_definer);
 	values[Anum_pg_proc_proisstrict - 1] = BoolGetDatum(isStrict);

src/backend/commands/functioncmds.c

@@ -10,7 +10,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/commands/functioncmds.c,v 1.81 2007/01/05 22:19:26 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/backend/commands/functioncmds.c,v 1.82 2007/01/22 01:35:20 tgl Exp $
  *
  * DESCRIPTION
  *	  These routines take the parse tree and pick out the
@@ -273,7 +273,9 @@ static bool
 compute_common_attribute(DefElem *defel,
 						 DefElem **volatility_item,
 						 DefElem **strict_item,
-						 DefElem **security_item)
+						 DefElem **security_item,
+						 DefElem **cost_item,
+						 DefElem **rows_item)
 {
 	if (strcmp(defel->defname, "volatility") == 0)
 	{
@@ -296,6 +298,20 @@ compute_common_attribute(DefElem *defel,
 
 		*security_item = defel;
 	}
+	else if (strcmp(defel->defname, "cost") == 0)
+	{
+		if (*cost_item)
+			goto duplicate_error;
+
+		*cost_item = defel;
+	}
+	else if (strcmp(defel->defname, "rows") == 0)
+	{
+		if (*rows_item)
+			goto duplicate_error;
+
+		*rows_item = defel;
+	}
 	else
 		return false;
 
@@ -337,7 +353,9 @@ compute_attributes_sql_style(List *options,
 							 char **language,
 							 char *volatility_p,
 							 bool *strict_p,
-							 bool *security_definer)
+							 bool *security_definer,
+							 float4 *procost,
+							 float4 *prorows)
 {
 	ListCell   *option;
 	DefElem    *as_item = NULL;
@@ -345,6 +363,8 @@ compute_attributes_sql_style(List *options,
 	DefElem    *volatility_item = NULL;
 	DefElem    *strict_item = NULL;
 	DefElem    *security_item = NULL;
+	DefElem    *cost_item = NULL;
+	DefElem    *rows_item = NULL;
 
 	foreach(option, options)
 	{
@@ -369,7 +389,9 @@ compute_attributes_sql_style(List *options,
 		else if (compute_common_attribute(defel,
 										  &volatility_item,
 										  &strict_item,
-										  &security_item))
+										  &security_item,
+										  &cost_item,
+										  &rows_item))
 		{
 			/* recognized common option */
 			continue;
@@ -407,6 +429,22 @@ compute_attributes_sql_style(List *options,
 		*strict_p = intVal(strict_item->arg);
 	if (security_item)
 		*security_definer = intVal(security_item->arg);
+	if (cost_item)
+	{
+		*procost = defGetNumeric(cost_item);
+		if (*procost <= 0)
+			ereport(ERROR,
+					(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+					 errmsg("COST must be positive")));
+	}
+	if (rows_item)
+	{
+		*prorows = defGetNumeric(rows_item);
+		if (*prorows <= 0)
+			ereport(ERROR,
+					(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+					 errmsg("ROWS must be positive")));
+	}
 }
 
 
@@ -519,6 +557,8 @@ CreateFunction(CreateFunctionStmt *stmt)
 	bool		isStrict,
 				security;
 	char		volatility;
+	float4		procost;
+	float4		prorows;
 	HeapTuple	languageTuple;
 	Form_pg_language languageStruct;
 	List	   *as_clause;
@@ -537,10 +577,14 @@ CreateFunction(CreateFunctionStmt *stmt)
 	isStrict = false;
 	security = false;
 	volatility = PROVOLATILE_VOLATILE;
+	procost = -1;				/* indicates not set */
+	prorows = -1;				/* indicates not set */
 
 	/* override attributes from explicit list */
 	compute_attributes_sql_style(stmt->options,
-				   &as_clause, &language, &volatility, &isStrict, &security);
+								 &as_clause, &language,
+								 &volatility, &isStrict, &security,
+								 &procost, &prorows);
 
 	/* Convert language name to canonical case */
 	languageName = case_translate_language_name(language);
@@ -645,6 +689,32 @@ CreateFunction(CreateFunctionStmt *stmt)
 			prosrc_str = funcname;
 	}
 
+	/*
+	 * Set default values for COST and ROWS depending on other parameters;
+	 * reject ROWS if it's not returnsSet.  NB: pg_dump knows these default
+	 * values, keep it in sync if you change them.
+	 */
+	if (procost < 0)
+	{
+		/* SQL and PL-language functions are assumed more expensive */
+		if (languageOid == INTERNALlanguageId ||
+			languageOid == ClanguageId)
+			procost = 1;
+		else
+			procost = 100;
+	}
+	if (prorows < 0)
+	{
+		if (returnsSet)
+			prorows = 1000;
+		else
+			prorows = 0;		/* dummy value if not returnsSet */
+	}
+	else if (!returnsSet)
+		ereport(ERROR,
+				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+				 errmsg("ROWS is not applicable when function does not return a set")));
+
 	/*
 	 * And now that we have all the parameters, and know we're permitted to do
 	 * so, go ahead and create the function.
@@ -665,7 +735,9 @@ CreateFunction(CreateFunctionStmt *stmt)
 					parameterTypes,
 					PointerGetDatum(allParameterTypes),
 					PointerGetDatum(parameterModes),
-					PointerGetDatum(parameterNames));
+					PointerGetDatum(parameterNames),
+					procost,
+					prorows);
 }
 
 
@@ -1012,6 +1084,8 @@ AlterFunction(AlterFunctionStmt *stmt)
 	DefElem    *volatility_item = NULL;
 	DefElem    *strict_item = NULL;
 	DefElem    *security_def_item = NULL;
+	DefElem    *cost_item = NULL;
+	DefElem    *rows_item = NULL;
 
 	rel = heap_open(ProcedureRelationId, RowExclusiveLock);
 
@@ -1046,7 +1120,9 @@ AlterFunction(AlterFunctionStmt *stmt)
 		if (compute_common_attribute(defel,
 									 &volatility_item,
 									 &strict_item,
-									 &security_def_item) == false)
+									 &security_def_item,
+									 &cost_item,
+									 &rows_item) == false)
 			elog(ERROR, "option \"%s\" not recognized", defel->defname);
 	}
 
@@ -1056,6 +1132,26 @@ AlterFunction(AlterFunctionStmt *stmt)
 		procForm->proisstrict = intVal(strict_item->arg);
 	if (security_def_item)
 		procForm->prosecdef = intVal(security_def_item->arg);
+	if (cost_item)
+	{
+		procForm->procost = defGetNumeric(cost_item);
+		if (procForm->procost <= 0)
+			ereport(ERROR,
+					(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+					 errmsg("COST must be positive")));
+	}
+	if (rows_item)
+	{
+		procForm->prorows = defGetNumeric(rows_item);
+		if (procForm->prorows <= 0)
+			ereport(ERROR,
+					(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+					 errmsg("ROWS must be positive")));
+		if (!procForm->proretset)
+			ereport(ERROR,
+					(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+					 errmsg("ROWS is not applicable when function does not return a set")));
+	}
 
 	/* Do the update */
 	simple_heap_update(rel, &tup->t_self, tup);

src/backend/commands/proclang.c

@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/commands/proclang.c,v 1.70 2007/01/05 22:19:26 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/backend/commands/proclang.c,v 1.71 2007/01/22 01:35:20 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -130,7 +130,9 @@ CreateProceduralLanguage(CreatePLangStmt *stmt)
 										 buildoidvector(funcargtypes, 0),
 										 PointerGetDatum(NULL),
 										 PointerGetDatum(NULL),
-										 PointerGetDatum(NULL));
+										 PointerGetDatum(NULL),
+										 1,
+										 0);
 		}
 
 		/*
@@ -160,7 +162,9 @@ CreateProceduralLanguage(CreatePLangStmt *stmt)
 										 buildoidvector(funcargtypes, 1),
 										 PointerGetDatum(NULL),
 										 PointerGetDatum(NULL),
-										 PointerGetDatum(NULL));
+										 PointerGetDatum(NULL),
+										 1,
+										 0);
 			}
 		}
 		else

src/backend/optimizer/path/costsize.c

@@ -54,7 +54,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/optimizer/path/costsize.c,v 1.175 2007/01/20 20:45:38 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/optimizer/path/costsize.c,v 1.176 2007/01/22 01:35:20 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -68,6 +68,7 @@
 #include "optimizer/clauses.h"
 #include "optimizer/cost.h"
 #include "optimizer/pathnode.h"
+#include "optimizer/planmain.h"
 #include "parser/parsetree.h"
 #include "utils/lsyscache.h"
 #include "utils/selfuncs.h"
@@ -842,17 +843,19 @@ cost_functionscan(Path *path, PlannerInfo *root, RelOptInfo *baserel)
 	Cost		startup_cost = 0;
 	Cost		run_cost = 0;
 	Cost		cpu_per_tuple;
+	RangeTblEntry *rte;
+	QualCost	exprcost;
 
 	/* Should only be applied to base relations that are functions */
 	Assert(baserel->relid > 0);
-	Assert(baserel->rtekind == RTE_FUNCTION);
+	rte = rt_fetch(baserel->relid, root->parse->rtable);
+	Assert(rte->rtekind == RTE_FUNCTION);
 
-	/*
-	 * For now, estimate function's cost at one operator eval per function
-	 * call.  Someday we should revive the function cost estimate columns in
-	 * pg_proc...
-	 */
-	cpu_per_tuple = cpu_operator_cost;
+	/* Estimate costs of executing the function expression */
+	cost_qual_eval_node(&exprcost, rte->funcexpr);
+
+	startup_cost += exprcost.startup;
+	cpu_per_tuple = exprcost.per_tuple;
 
 	/* Add scanning CPU costs */
 	startup_cost += baserel->baserestrictcost.startup;
@@ -1068,6 +1071,10 @@ cost_agg(Path *path, PlannerInfo *root,
 	 * there's roundoff error we might do the wrong thing.  So be sure that
 	 * the computations below form the same intermediate values in the same
 	 * order.
+	 *
+	 * Note: ideally we should use the pg_proc.procost costs of each
+	 * aggregate's component functions, but for now that seems like an
+	 * excessive amount of work.
 	 */
 	if (aggstrategy == AGG_PLAIN)
 	{
@@ -1694,7 +1701,8 @@ cost_hashjoin(HashPath *path, PlannerInfo *root)
  * cost_qual_eval
  *		Estimate the CPU costs of evaluating a WHERE clause.
  *		The input can be either an implicitly-ANDed list of boolean
- *		expressions, or a list of RestrictInfo nodes.
+ *		expressions, or a list of RestrictInfo nodes.  (The latter is
+ *		preferred since it allows caching of the results.)
  *		The result includes both a one-time (startup) component,
  *		and a per-evaluation component.
  */
@@ -1712,25 +1720,56 @@ cost_qual_eval(QualCost *cost, List *quals)
 	{
 		Node	   *qual = (Node *) lfirst(l);
 
+		cost_qual_eval_walker(qual, cost);
+	}
+}
+
+/*
+ * cost_qual_eval_node
+ *		As above, for a single RestrictInfo or expression.
+ */
+void
+cost_qual_eval_node(QualCost *cost, Node *qual)
+{
+	cost->startup = 0;
+	cost->per_tuple = 0;
+	cost_qual_eval_walker(qual, cost);
+}
+
+static bool
+cost_qual_eval_walker(Node *node, QualCost *total)
+{
+	if (node == NULL)
+		return false;
+
 	/*
 	 * RestrictInfo nodes contain an eval_cost field reserved for this
 	 * routine's use, so that it's not necessary to evaluate the qual
 	 * clause's cost more than once.  If the clause's cost hasn't been
 	 * computed yet, the field's startup value will contain -1.
-		 *
-		 * If the RestrictInfo is marked pseudoconstant, it will be tested
-		 * only once, so treat its cost as all startup cost.
 	 */
-		if (qual && IsA(qual, RestrictInfo))
+	if (IsA(node, RestrictInfo))
 	{
-			RestrictInfo *rinfo = (RestrictInfo *) qual;
+		RestrictInfo *rinfo = (RestrictInfo *) node;
 
 		if (rinfo->eval_cost.startup < 0)
 		{
 			rinfo->eval_cost.startup = 0;
 			rinfo->eval_cost.per_tuple = 0;
+			/*
+			 * For an OR clause, recurse into the marked-up tree so that
+			 * we set the eval_cost for contained RestrictInfos too.
+			 */
+			if (rinfo->orclause)
+				cost_qual_eval_walker((Node *) rinfo->orclause,
+									  &rinfo->eval_cost);
+			else
 				cost_qual_eval_walker((Node *) rinfo->clause,
 									  &rinfo->eval_cost);
+			/*
+			 * If the RestrictInfo is marked pseudoconstant, it will be tested
+			 * only once, so treat its cost as all startup cost.
+			 */
 			if (rinfo->pseudoconstant)
 			{
 				/* count one execution during startup */
@@ -1738,37 +1777,41 @@ cost_qual_eval(QualCost *cost, List *quals)
 				rinfo->eval_cost.per_tuple = 0;
 			}
 		}
-			cost->startup += rinfo->eval_cost.startup;
-			cost->per_tuple += rinfo->eval_cost.per_tuple;
-		}
-		else
-		{
-			/* If it's a bare expression, must always do it the hard way */
-			cost_qual_eval_walker(qual, cost);
-		}
-	}
-}
-
-static bool
-cost_qual_eval_walker(Node *node, QualCost *total)
-{
-	if (node == NULL)
+		total->startup += rinfo->eval_cost.startup;
+		total->per_tuple += rinfo->eval_cost.per_tuple;
+		/* do NOT recurse into children */
 		return false;
+	}
 
 	/*
-	 * Our basic strategy is to charge one cpu_operator_cost for each operator
-	 * or function node in the given tree.	Vars and Consts are charged zero,
-	 * and so are boolean operators (AND, OR, NOT). Simplistic, but a lot
-	 * better than no model at all.
+	 * For each operator or function node in the given tree, we charge the
+	 * estimated execution cost given by pg_proc.procost (remember to
+	 * multiply this by cpu_operator_cost).
+	 *
+	 * Vars and Consts are charged zero, and so are boolean operators (AND,
+	 * OR, NOT). Simplistic, but a lot better than no model at all.
 	 *
 	 * Should we try to account for the possibility of short-circuit
-	 * evaluation of AND/OR?
+	 * evaluation of AND/OR?  Probably *not*, because that would make the
+	 * results depend on the clause ordering, and we are not in any position
+	 * to expect that the current ordering of the clauses is the one that's
+	 * going to end up being used.  (Is it worth applying order_qual_clauses
+	 * much earlier in the planning process to fix this?)
 	 */
-	if (IsA(node, FuncExpr) ||
-		IsA(node, OpExpr) ||
+	if (IsA(node, FuncExpr))
+	{
+		total->per_tuple += get_func_cost(((FuncExpr *) node)->funcid) *
+			cpu_operator_cost;
+	}
+	else if (IsA(node, OpExpr) ||
 			 IsA(node, DistinctExpr) ||
 			 IsA(node, NullIfExpr))
-		total->per_tuple += cpu_operator_cost;
+	{
+		/* rely on struct equivalence to treat these all alike */
+		set_opfuncid((OpExpr *) node);
+		total->per_tuple += get_func_cost(((OpExpr *) node)->opfuncid) *
+			cpu_operator_cost;
+	}
 	else if (IsA(node, ScalarArrayOpExpr))
 	{
 		/*
@@ -1778,15 +1821,23 @@ cost_qual_eval_walker(Node *node, QualCost *total)
 		ScalarArrayOpExpr *saop = (ScalarArrayOpExpr *) node;
 		Node	   *arraynode = (Node *) lsecond(saop->args);
 
-		total->per_tuple +=
+		set_sa_opfuncid(saop);
+		total->per_tuple += get_func_cost(saop->opfuncid) *
 			cpu_operator_cost * estimate_array_length(arraynode) * 0.5;
 	}
 	else if (IsA(node, RowCompareExpr))
 	{
 		/* Conservatively assume we will check all the columns */
 		RowCompareExpr *rcexpr = (RowCompareExpr *) node;
+		ListCell   *lc;
 
-		total->per_tuple += cpu_operator_cost * list_length(rcexpr->opnos);
+		foreach(lc, rcexpr->opnos)
+		{
+			Oid		opid = lfirst_oid(lc);
+
+			total->per_tuple += get_func_cost(get_opcode(opid)) *
+				cpu_operator_cost;
+		}
 	}
 	else if (IsA(node, SubLink))
 	{
@@ -1873,6 +1924,7 @@ cost_qual_eval_walker(Node *node, QualCost *total)
 		}
 	}
 
+	/* recurse into children */
 	return expression_tree_walker(node, cost_qual_eval_walker,
 								  (void *) total);
 }
@@ -2172,16 +2224,8 @@ set_function_size_estimates(PlannerInfo *root, RelOptInfo *rel)
 	rte = rt_fetch(rel->relid, root->parse->rtable);
 	Assert(rte->rtekind == RTE_FUNCTION);
 
-	/*
-	 * Estimate number of rows the function itself will return.
-	 *
-	 * XXX no idea how to do this yet; but we can at least check whether
-	 * function returns set or not...
-	 */
-	if (expression_returns_set(rte->funcexpr))
-		rel->tuples = 1000;
-	else
-		rel->tuples = 1;
+	/* Estimate number of rows the function itself will return */
+	rel->tuples = clamp_row_est(expression_returns_set_rows(rte->funcexpr));
 
 	/* Now estimate number of output rows, etc */
 	set_baserel_size_estimates(root, rel);

src/backend/optimizer/plan/setrefs.c

@@ -9,7 +9,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/optimizer/plan/setrefs.c,v 1.127 2007/01/05 22:19:32 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/backend/optimizer/plan/setrefs.c,v 1.128 2007/01/22 01:35:20 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -83,7 +83,6 @@ static Node *replace_vars_with_subplan_refs(Node *node,
 static Node *replace_vars_with_subplan_refs_mutator(Node *node,
 							replace_vars_with_subplan_refs_context *context);
 static bool fix_opfuncids_walker(Node *node, void *context);
-static void set_sa_opfuncid(ScalarArrayOpExpr *opexpr);
 
 
 /*****************************************************************************
@@ -1433,7 +1432,7 @@ set_opfuncid(OpExpr *opexpr)
  * set_sa_opfuncid
  *		As above, for ScalarArrayOpExpr nodes.
  */
-static void
+void
 set_sa_opfuncid(ScalarArrayOpExpr *opexpr)
 {
 	if (opexpr->opfuncid == InvalidOid)

src/backend/optimizer/util/clauses.c

@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/optimizer/util/clauses.c,v 1.230 2007/01/17 17:25:52 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/optimizer/util/clauses.c,v 1.231 2007/01/22 01:35:20 tgl Exp $
  *
  * HISTORY
  *	  AUTHOR			DATE			MAJOR EVENT
@@ -64,6 +64,7 @@ typedef struct
 static bool contain_agg_clause_walker(Node *node, void *context);
 static bool count_agg_clauses_walker(Node *node, AggClauseCounts *counts);
 static bool expression_returns_set_walker(Node *node, void *context);
+static bool expression_returns_set_rows_walker(Node *node, double *count);
 static bool contain_subplans_walker(Node *node, void *context);
 static bool contain_mutable_functions_walker(Node *node, void *context);
 static bool contain_volatile_functions_walker(Node *node, void *context);
@@ -566,6 +567,78 @@ expression_returns_set_walker(Node *node, void *context)
 								  context);
 }
 
+/*
+ * expression_returns_set_rows
+ *	  Estimate the number of rows in a set result.
+ *
+ * We use the product of the rowcount estimates of all the functions in
+ * the given tree.  The result is 1 if there are no set-returning functions.
+ */
+double
+expression_returns_set_rows(Node *clause)
+{
+	double		result = 1;
+
+	(void) expression_returns_set_rows_walker(clause, &result);
+	return result;
+}
+
+static bool
+expression_returns_set_rows_walker(Node *node, double *count)
+{
+	if (node == NULL)
+		return false;
+	if (IsA(node, FuncExpr))
+	{
+		FuncExpr   *expr = (FuncExpr *) node;
+
+		if (expr->funcretset)
+			*count *= get_func_rows(expr->funcid);
+	}
+	if (IsA(node, OpExpr))
+	{
+		OpExpr	   *expr = (OpExpr *) node;
+
+		if (expr->opretset)
+		{
+			set_opfuncid(expr);
+			*count *= get_func_rows(expr->opfuncid);
+		}
+	}
+
+	/* Avoid recursion for some cases that can't return a set */
+	if (IsA(node, Aggref))
+		return false;
+	if (IsA(node, DistinctExpr))
+		return false;
+	if (IsA(node, ScalarArrayOpExpr))
+		return false;
+	if (IsA(node, BoolExpr))
+		return false;
+	if (IsA(node, SubLink))
+		return false;
+	if (IsA(node, SubPlan))
+		return false;
+	if (IsA(node, ArrayExpr))
+		return false;
+	if (IsA(node, RowExpr))
+		return false;
+	if (IsA(node, RowCompareExpr))
+		return false;
+	if (IsA(node, CoalesceExpr))
+		return false;
+	if (IsA(node, MinMaxExpr))
+		return false;
+	if (IsA(node, XmlExpr))
+		return false;
+	if (IsA(node, NullIfExpr))
+		return false;
+
+	return expression_tree_walker(node, expression_returns_set_rows_walker,
+								  (void *) count);
+}
+
+
 /*****************************************************************************
  *		Subplan clause manipulation
  *****************************************************************************/

src/backend/parser/gram.y

@@ -11,7 +11,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/parser/gram.y,v 2.574 2007/01/14 13:11:53 petere Exp $
+ *	  $PostgreSQL: pgsql/src/backend/parser/gram.y,v 2.575 2007/01/22 01:35:21 tgl Exp $
  *
  * HISTORY
  *	  AUTHOR			DATE			MAJOR EVENT
@@ -370,7 +370,7 @@ static Node *makeXmlExpr(XmlExprOp op, char *name, List *named_args, List *args)
 	CHARACTER CHARACTERISTICS CHECK CHECKPOINT CLASS CLOSE
 	CLUSTER COALESCE COLLATE COLUMN COMMENT COMMIT
 	COMMITTED CONCURRENTLY CONNECTION CONSTRAINT CONSTRAINTS
-	CONTENT_P CONVERSION_P CONVERT COPY CREATE CREATEDB
+	CONTENT_P CONVERSION_P CONVERT COPY COST CREATE CREATEDB
 	CREATEROLE CREATEUSER CROSS CSV CURRENT_DATE CURRENT_ROLE CURRENT_TIME
 	CURRENT_TIMESTAMP CURRENT_USER CURSOR CYCLE
 
@@ -3958,6 +3958,14 @@ common_func_opt_item:
 				{
 					$$ = makeDefElem("security", (Node *)makeInteger(FALSE));
 				}
+			| COST NumericOnly
+				{
+					$$ = makeDefElem("cost", (Node *)$2);
+				}
+			| ROWS NumericOnly
+				{
+					$$ = makeDefElem("rows", (Node *)$2);
+				}
 		;
 
 createfunc_opt_item:
@@ -8564,6 +8572,7 @@ unreserved_keyword:
 			| CONTENT_P
 			| CONVERSION_P
 			| COPY
+			| COST
 			| CREATEDB
 			| CREATEROLE
 			| CREATEUSER

src/backend/parser/keywords.c

@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/parser/keywords.c,v 1.181 2007/01/09 02:14:14 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/parser/keywords.c,v 1.182 2007/01/22 01:35:21 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -93,6 +93,7 @@ static const ScanKeyword ScanKeywords[] = {
 	{"conversion", CONVERSION_P},
 	{"convert", CONVERT},
 	{"copy", COPY},
+	{"cost", COST},
 	{"create", CREATE},
 	{"createdb", CREATEDB},
 	{"createrole", CREATEROLE},

src/backend/utils/Gen_fmgrtab.sh

@@ -9,7 +9,7 @@
 #
 #
 # IDENTIFICATION
-#    $PostgreSQL: pgsql/src/backend/utils/Gen_fmgrtab.sh,v 1.34 2007/01/05 22:19:39 momjian Exp $
+#    $PostgreSQL: pgsql/src/backend/utils/Gen_fmgrtab.sh,v 1.35 2007/01/22 01:35:21 tgl Exp $
 #
 #-------------------------------------------------------------------------
 
@@ -72,6 +72,8 @@ trap 'echo "Caught signal." ; cleanup ; exit 1' 1 2 15
 #
 # Generate the file containing raw pg_proc tuple data
 # (but only for "internal" language procedures...).
+# Basically we strip off the DATA macro call, leaving procedure OID as $1
+# and all the pg_proc field values as $2, $3, etc on each line.
 #
 # Note assumption here that prolang == $5 and INTERNALlanguageId == 12.
 #
@@ -202,15 +204,15 @@ FuNkYfMgRtAbStUfF
 # may seem tedious, but avoid the temptation to write a quick x?y:z
 # conditional expression instead.  Not all awks have conditional expressions.
 #
-# Note assumptions here that prosrc == $(NF-2), pronargs == $11,
-# proisstrict == $8, proretset == $9
+# Note assumptions here that prosrc == $(NF-2), pronargs == $13,
+# proisstrict == $10, proretset == $11
 
 $AWK 'BEGIN {
     Bool["t"] = "true"
     Bool["f"] = "false"
 }
 { printf ("  { %d, \"%s\", %d, %s, %s, %s },\n"), \
-	$1, $(NF-2), $11, Bool[$8], Bool[$9], $(NF-2)
+	$1, $(NF-2), $13, Bool[$10], Bool[$11], $(NF-2)
 }' $SORTEDFILE >> "$$-$TABLEFILE"
 
 if [ $? -ne 0 ]; then

src/backend/utils/cache/lsyscache.c

@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/utils/cache/lsyscache.c,v 1.145 2007/01/21 00:57:15 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/utils/cache/lsyscache.c,v 1.146 2007/01/22 01:35:21 tgl Exp $
  *
  * NOTES
  *	  Eventually, the index information should go through here, too.
@@ -1295,6 +1295,48 @@ func_volatile(Oid funcid)
 	return result;
 }
 
+/*
+ * get_func_cost
+ *		Given procedure id, return the function's procost field.
+ */
+float4
+get_func_cost(Oid funcid)
+{
+	HeapTuple	tp;
+	float4		result;
+
+	tp = SearchSysCache(PROCOID,
+						ObjectIdGetDatum(funcid),
+						0, 0, 0);
+	if (!HeapTupleIsValid(tp))
+		elog(ERROR, "cache lookup failed for function %u", funcid);
+
+	result = ((Form_pg_proc) GETSTRUCT(tp))->procost;
+	ReleaseSysCache(tp);
+	return result;
+}
+
+/*
+ * get_func_rows
+ *		Given procedure id, return the function's prorows field.
+ */
+float4
+get_func_rows(Oid funcid)
+{
+	HeapTuple	tp;
+	float4		result;
+
+	tp = SearchSysCache(PROCOID,
+						ObjectIdGetDatum(funcid),
+						0, 0, 0);
+	if (!HeapTupleIsValid(tp))
+		elog(ERROR, "cache lookup failed for function %u", funcid);
+
+	result = ((Form_pg_proc) GETSTRUCT(tp))->prorows;
+	ReleaseSysCache(tp);
+	return result;
+}
+
 /*				---------- RELATION CACHE ----------					 */
 
 /*

src/bin/pg_dump/pg_dump.c

@@ -12,7 +12,7 @@
  *	by PostgreSQL
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/bin/pg_dump/pg_dump.c,v 1.456 2007/01/05 22:19:48 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/bin/pg_dump/pg_dump.c,v 1.457 2007/01/22 01:35:21 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -5837,6 +5837,8 @@ dumpFunc(Archive *fout, FuncInfo *finfo)
 	char	   *provolatile;
 	char	   *proisstrict;
 	char	   *prosecdef;
+	char	   *procost;
+	char	   *prorows;
 	char	   *lanname;
 	char	   *rettypename;
 	int			nallargs;
@@ -5857,12 +5859,25 @@ dumpFunc(Archive *fout, FuncInfo *finfo)
 	selectSourceSchema(finfo->dobj.namespace->dobj.name);
 
 	/* Fetch function-specific details */
-	if (g_fout->remoteVersion >= 80100)
+	if (g_fout->remoteVersion >= 80300)
+	{
+		appendPQExpBuffer(query,
+						  "SELECT proretset, prosrc, probin, "
+						  "proallargtypes, proargmodes, proargnames, "
+						  "provolatile, proisstrict, prosecdef, "
+						  "procost, prorows, "
+						  "(SELECT lanname FROM pg_catalog.pg_language WHERE oid = prolang) as lanname "
+						  "FROM pg_catalog.pg_proc "
+						  "WHERE oid = '%u'::pg_catalog.oid",
+						  finfo->dobj.catId.oid);
+	}
+	else if (g_fout->remoteVersion >= 80100)
 	{
 		appendPQExpBuffer(query,
 						  "SELECT proretset, prosrc, probin, "
 						  "proallargtypes, proargmodes, proargnames, "
 						  "provolatile, proisstrict, prosecdef, "
+						  "0 as procost, 0 as prorows, "
 						  "(SELECT lanname FROM pg_catalog.pg_language WHERE oid = prolang) as lanname "
 						  "FROM pg_catalog.pg_proc "
 						  "WHERE oid = '%u'::pg_catalog.oid",
@@ -5876,6 +5891,7 @@ dumpFunc(Archive *fout, FuncInfo *finfo)
 						  "null as proargmodes, "
 						  "proargnames, "
 						  "provolatile, proisstrict, prosecdef, "
+						  "0 as procost, 0 as prorows, "
 						  "(SELECT lanname FROM pg_catalog.pg_language WHERE oid = prolang) as lanname "
 						  "FROM pg_catalog.pg_proc "
 						  "WHERE oid = '%u'::pg_catalog.oid",
@@ -5889,6 +5905,7 @@ dumpFunc(Archive *fout, FuncInfo *finfo)
 						  "null as proargmodes, "
 						  "null as proargnames, "
 						  "provolatile, proisstrict, prosecdef, "
+						  "0 as procost, 0 as prorows, "
 						  "(SELECT lanname FROM pg_catalog.pg_language WHERE oid = prolang) as lanname "
 						  "FROM pg_catalog.pg_proc "
 						  "WHERE oid = '%u'::pg_catalog.oid",
@@ -5904,6 +5921,7 @@ dumpFunc(Archive *fout, FuncInfo *finfo)
 			 "case when proiscachable then 'i' else 'v' end as provolatile, "
 						  "proisstrict, "
 						  "'f'::boolean as prosecdef, "
+						  "0 as procost, 0 as prorows, "
 		  "(SELECT lanname FROM pg_language WHERE oid = prolang) as lanname "
 						  "FROM pg_proc "
 						  "WHERE oid = '%u'::oid",
@@ -5919,6 +5937,7 @@ dumpFunc(Archive *fout, FuncInfo *finfo)
 			 "case when proiscachable then 'i' else 'v' end as provolatile, "
 						  "'f'::boolean as proisstrict, "
 						  "'f'::boolean as prosecdef, "
+						  "0 as procost, 0 as prorows, "
 		  "(SELECT lanname FROM pg_language WHERE oid = prolang) as lanname "
 						  "FROM pg_proc "
 						  "WHERE oid = '%u'::oid",
@@ -5946,6 +5965,8 @@ dumpFunc(Archive *fout, FuncInfo *finfo)
 	provolatile = PQgetvalue(res, 0, PQfnumber(res, "provolatile"));
 	proisstrict = PQgetvalue(res, 0, PQfnumber(res, "proisstrict"));
 	prosecdef = PQgetvalue(res, 0, PQfnumber(res, "prosecdef"));
+	procost = PQgetvalue(res, 0, PQfnumber(res, "procost"));
+	prorows = PQgetvalue(res, 0, PQfnumber(res, "prorows"));
 	lanname = PQgetvalue(res, 0, PQfnumber(res, "lanname"));
 
 	/*
@@ -6072,6 +6093,30 @@ dumpFunc(Archive *fout, FuncInfo *finfo)
 	if (prosecdef[0] == 't')
 		appendPQExpBuffer(q, " SECURITY DEFINER");
 
+	/*
+	 * COST and ROWS are emitted only if present and not default, so as not to
+	 * break backwards-compatibility of the dump without need.  Keep this code
+	 * in sync with the defaults in functioncmds.c.
+	 */
+	if (strcmp(procost, "0") != 0)
+	{
+		if (strcmp(lanname, "internal") == 0 || strcmp(lanname, "c") == 0)
+		{
+			/* default cost is 1 */
+			if (strcmp(procost, "1") != 0)
+				appendPQExpBuffer(q, " COST %s", procost);
+		}
+		else
+		{
+			/* default cost is 100 */
+			if (strcmp(procost, "100") != 0)
+				appendPQExpBuffer(q, " COST %s", procost);
+		}
+	}
+	if (proretset[0] == 't' &&
+		strcmp(prorows, "0") != 0 && strcmp(prorows, "1000") != 0)
+		appendPQExpBuffer(q, " ROWS %s", prorows);
+
 	appendPQExpBuffer(q, ";\n");
 
 	ArchiveEntry(fout, finfo->dobj.catId, finfo->dobj.dumpId,

src/include/catalog/catversion.h

@@ -37,7 +37,7 @@
  * Portions Copyright (c) 1996-2007, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/catalog/catversion.h,v 1.375 2007/01/20 23:13:01 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/catalog/catversion.h,v 1.376 2007/01/22 01:35:21 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -53,6 +53,6 @@
  */
 
 /*							yyyymmddN */
-#define CATALOG_VERSION_NO	200701203
+#define CATALOG_VERSION_NO	200701211
 
 #endif

src/include/catalog/pg_attribute.h

@@ -8,7 +8,7 @@
  * Portions Copyright (c) 1996-2007, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/catalog/pg_attribute.h,v 1.129 2007/01/09 02:14:15 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/catalog/pg_attribute.h,v 1.130 2007/01/22 01:35:21 tgl Exp $
  *
  * NOTES
  *	  the genbki.sh script reads this file and generates .bki
@@ -290,39 +290,43 @@ DATA(insert ( 1247 tableoid			26 0  4  -7 0 -1 -1 t p i t f f t 0));
 { 1255, {"pronamespace"},		26, -1, 4,	2, 0, -1, -1, true, 'p', 'i', true, false, false, true, 0 }, \
 { 1255, {"proowner"},			26, -1, 4,	3, 0, -1, -1, true, 'p', 'i', true, false, false, true, 0 }, \
 { 1255, {"prolang"},			26, -1, 4,	4, 0, -1, -1, true, 'p', 'i', true, false, false, true, 0 }, \
-{ 1255, {"proisagg"},			16, -1, 1,	5, 0, -1, -1, true, 'p', 'c', true, false, false, true, 0 }, \
-{ 1255, {"prosecdef"},			16, -1, 1,	6, 0, -1, -1, true, 'p', 'c', true, false, false, true, 0 }, \
-{ 1255, {"proisstrict"},		16, -1, 1,	7, 0, -1, -1, true, 'p', 'c', true, false, false, true, 0 }, \
-{ 1255, {"proretset"},			16, -1, 1,	8, 0, -1, -1, true, 'p', 'c', true, false, false, true, 0 }, \
-{ 1255, {"provolatile"},		18, -1, 1,	9, 0, -1, -1, true, 'p', 'c', true, false, false, true, 0 }, \
-{ 1255, {"pronargs"},			21, -1, 2, 10, 0, -1, -1, true, 'p', 's', true, false, false, true, 0 }, \
-{ 1255, {"prorettype"},			26, -1, 4, 11, 0, -1, -1, true, 'p', 'i', true, false, false, true, 0 }, \
-{ 1255, {"proargtypes"},		30, -1, -1, 12, 1, -1, -1, false, 'p', 'i', true, false, false, true, 0 }, \
-{ 1255, {"proallargtypes"},   1028, -1, -1, 13, 1, -1, -1, false, 'x', 'i', false, false, false, true, 0 }, \
-{ 1255, {"proargmodes"},	  1002, -1, -1, 14, 1, -1, -1, false, 'x', 'i', false, false, false, true, 0 }, \
-{ 1255, {"proargnames"},	  1009, -1, -1, 15, 1, -1, -1, false, 'x', 'i', false, false, false, true, 0 }, \
-{ 1255, {"prosrc"},				25, -1, -1, 16, 0, -1, -1, false, 'x', 'i', false, false, false, true, 0 }, \
-{ 1255, {"probin"},				17, -1, -1, 17, 0, -1, -1, false, 'x', 'i', false, false, false, true, 0 }, \
-{ 1255, {"proacl"},			  1034, -1, -1, 18, 1, -1, -1, false, 'x', 'i', false, false, false, true, 0 }
+{ 1255, {"procost"},		   700, -1, 4,	5, 0, -1, -1, false, 'p', 'i', true, false, false, true, 0 }, \
+{ 1255, {"prorows"},		   700, -1, 4,	6, 0, -1, -1, false, 'p', 'i', true, false, false, true, 0 }, \
+{ 1255, {"proisagg"},			16, -1, 1,	7, 0, -1, -1, true, 'p', 'c', true, false, false, true, 0 }, \
+{ 1255, {"prosecdef"},			16, -1, 1,	8, 0, -1, -1, true, 'p', 'c', true, false, false, true, 0 }, \
+{ 1255, {"proisstrict"},		16, -1, 1,	9, 0, -1, -1, true, 'p', 'c', true, false, false, true, 0 }, \
+{ 1255, {"proretset"},			16, -1, 1, 10, 0, -1, -1, true, 'p', 'c', true, false, false, true, 0 }, \
+{ 1255, {"provolatile"},		18, -1, 1, 11, 0, -1, -1, true, 'p', 'c', true, false, false, true, 0 }, \
+{ 1255, {"pronargs"},			21, -1, 2, 12, 0, -1, -1, true, 'p', 's', true, false, false, true, 0 }, \
+{ 1255, {"prorettype"},			26, -1, 4, 13, 0, -1, -1, true, 'p', 'i', true, false, false, true, 0 }, \
+{ 1255, {"proargtypes"},		30, -1, -1, 14, 1, -1, -1, false, 'p', 'i', true, false, false, true, 0 }, \
+{ 1255, {"proallargtypes"},   1028, -1, -1, 15, 1, -1, -1, false, 'x', 'i', false, false, false, true, 0 }, \
+{ 1255, {"proargmodes"},	  1002, -1, -1, 16, 1, -1, -1, false, 'x', 'i', false, false, false, true, 0 }, \
+{ 1255, {"proargnames"},	  1009, -1, -1, 17, 1, -1, -1, false, 'x', 'i', false, false, false, true, 0 }, \
+{ 1255, {"prosrc"},				25, -1, -1, 18, 0, -1, -1, false, 'x', 'i', false, false, false, true, 0 }, \
+{ 1255, {"probin"},				17, -1, -1, 19, 0, -1, -1, false, 'x', 'i', false, false, false, true, 0 }, \
+{ 1255, {"proacl"},			  1034, -1, -1, 20, 1, -1, -1, false, 'x', 'i', false, false, false, true, 0 }
 
 DATA(insert ( 1255 proname			19 -1 NAMEDATALEN	1 0 -1 -1 f p i t f f t 0));
 DATA(insert ( 1255 pronamespace		26 -1 4   2 0 -1 -1 t p i t f f t 0));
 DATA(insert ( 1255 proowner			26 -1 4   3 0 -1 -1 t p i t f f t 0));
 DATA(insert ( 1255 prolang			26 -1 4   4 0 -1 -1 t p i t f f t 0));
-DATA(insert ( 1255 proisagg			16 -1 1   5 0 -1 -1 t p c t f f t 0));
-DATA(insert ( 1255 prosecdef		16 -1 1   6 0 -1 -1 t p c t f f t 0));
-DATA(insert ( 1255 proisstrict		16 -1 1   7 0 -1 -1 t p c t f f t 0));
-DATA(insert ( 1255 proretset		16 -1 1   8 0 -1 -1 t p c t f f t 0));
-DATA(insert ( 1255 provolatile		18 -1 1   9 0 -1 -1 t p c t f f t 0));
-DATA(insert ( 1255 pronargs			21 -1 2  10 0 -1 -1 t p s t f f t 0));
-DATA(insert ( 1255 prorettype		26 -1 4  11 0 -1 -1 t p i t f f t 0));
-DATA(insert ( 1255 proargtypes		30 -1 -1 12 1 -1 -1 f p i t f f t 0));
-DATA(insert ( 1255 proallargtypes 1028 -1 -1 13 1 -1 -1 f x i f f f t 0));
-DATA(insert ( 1255 proargmodes	  1002 -1 -1 14 1 -1 -1 f x i f f f t 0));
-DATA(insert ( 1255 proargnames	  1009 -1 -1 15 1 -1 -1 f x i f f f t 0));
-DATA(insert ( 1255 prosrc			25 -1 -1 16 0 -1 -1 f x i f f f t 0));
-DATA(insert ( 1255 probin			17 -1 -1 17 0 -1 -1 f x i f f f t 0));
-DATA(insert ( 1255 proacl		  1034 -1 -1 18 1 -1 -1 f x i f f f t 0));
+DATA(insert ( 1255 procost		   700 -1 4   5 0 -1 -1 f p i t f f t 0));
+DATA(insert ( 1255 prorows		   700 -1 4   6 0 -1 -1 f p i t f f t 0));
+DATA(insert ( 1255 proisagg			16 -1 1   7 0 -1 -1 t p c t f f t 0));
+DATA(insert ( 1255 prosecdef		16 -1 1   8 0 -1 -1 t p c t f f t 0));
+DATA(insert ( 1255 proisstrict		16 -1 1   9 0 -1 -1 t p c t f f t 0));
+DATA(insert ( 1255 proretset		16 -1 1  10 0 -1 -1 t p c t f f t 0));
+DATA(insert ( 1255 provolatile		18 -1 1  11 0 -1 -1 t p c t f f t 0));
+DATA(insert ( 1255 pronargs			21 -1 2  12 0 -1 -1 t p s t f f t 0));
+DATA(insert ( 1255 prorettype		26 -1 4  13 0 -1 -1 t p i t f f t 0));
+DATA(insert ( 1255 proargtypes		30 -1 -1 14 1 -1 -1 f p i t f f t 0));
+DATA(insert ( 1255 proallargtypes 1028 -1 -1 15 1 -1 -1 f x i f f f t 0));
+DATA(insert ( 1255 proargmodes	  1002 -1 -1 16 1 -1 -1 f x i f f f t 0));
+DATA(insert ( 1255 proargnames	  1009 -1 -1 17 1 -1 -1 f x i f f f t 0));
+DATA(insert ( 1255 prosrc			25 -1 -1 18 0 -1 -1 f x i f f f t 0));
+DATA(insert ( 1255 probin			17 -1 -1 19 0 -1 -1 f x i f f f t 0));
+DATA(insert ( 1255 proacl		  1034 -1 -1 20 1 -1 -1 f x i f f f t 0));
 DATA(insert ( 1255 ctid				27 0  6  -1 0 -1 -1 f p s t f f t 0));
 DATA(insert ( 1255 oid				26 0  4  -2 0 -1 -1 t p i t f f t 0));
 DATA(insert ( 1255 xmin				28 0  4  -3 0 -1 -1 t p i t f f t 0));

src/include/catalog/pg_class.h

@@ -8,7 +8,7 @@
  * Portions Copyright (c) 1996-2007, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/catalog/pg_class.h,v 1.99 2007/01/05 22:19:52 momjian Exp $
+ * $PostgreSQL: pgsql/src/include/catalog/pg_class.h,v 1.100 2007/01/22 01:35:22 tgl Exp $
  *
  * NOTES
  *	  the genbki.sh script reads this file and generates .bki
@@ -136,7 +136,7 @@ DATA(insert OID = 1247 (  pg_type		PGNSP 71 PGUID 0 1247 0 0 0 0 0 f f r 25 0 0
 DESCR("");
 DATA(insert OID = 1249 (  pg_attribute	PGNSP 75 PGUID 0 1249 0 0 0 0 0 f f r 17 0 0 0 0 0 f f f f 3 _null_ _null_ ));
 DESCR("");
-DATA(insert OID = 1255 (  pg_proc		PGNSP 81 PGUID 0 1255 0 0 0 0 0 f f r 18 0 0 0 0 0 t f f f 3 _null_ _null_ ));
+DATA(insert OID = 1255 (  pg_proc		PGNSP 81 PGUID 0 1255 0 0 0 0 0 f f r 20 0 0 0 0 0 t f f f 3 _null_ _null_ ));
 DESCR("");
 DATA(insert OID = 1259 (  pg_class		PGNSP 83 PGUID 0 1259 0 0 0 0 0 f f r 27 0 0 0 0 0 t f f f 3 _null_ _null_ ));
 DESCR("");

src/include/optimizer/clauses.h

@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2007, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/optimizer/clauses.h,v 1.85 2007/01/05 22:19:56 momjian Exp $
+ * $PostgreSQL: pgsql/src/include/optimizer/clauses.h,v 1.86 2007/01/22 01:35:22 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -51,6 +51,7 @@ extern bool contain_agg_clause(Node *clause);
 extern void count_agg_clauses(Node *clause, AggClauseCounts *counts);
 
 extern bool expression_returns_set(Node *clause);
+extern double expression_returns_set_rows(Node *clause);
 
 extern bool contain_subplans(Node *clause);
 

src/include/optimizer/cost.h

@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2007, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/optimizer/cost.h,v 1.83 2007/01/05 22:19:56 momjian Exp $
+ * $PostgreSQL: pgsql/src/include/optimizer/cost.h,v 1.84 2007/01/22 01:35:22 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -89,6 +89,7 @@ extern void cost_nestloop(NestPath *path, PlannerInfo *root);
 extern void cost_mergejoin(MergePath *path, PlannerInfo *root);
 extern void cost_hashjoin(HashPath *path, PlannerInfo *root);
 extern void cost_qual_eval(QualCost *cost, List *quals);
+extern void cost_qual_eval_node(QualCost *cost, Node *qual);
 extern void set_baserel_size_estimates(PlannerInfo *root, RelOptInfo *rel);
 extern void set_joinrel_size_estimates(PlannerInfo *root, RelOptInfo *rel,
 						   RelOptInfo *outer_rel,

src/include/optimizer/planmain.h

@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2007, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/optimizer/planmain.h,v 1.98 2007/01/20 20:45:40 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/optimizer/planmain.h,v 1.99 2007/01/22 01:35:22 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -97,5 +97,6 @@ extern List *set_returning_clause_references(List *rlist,
 								Index resultRelation);
 extern void fix_opfuncids(Node *node);
 extern void set_opfuncid(OpExpr *opexpr);
+extern void set_sa_opfuncid(ScalarArrayOpExpr *opexpr);
 
 #endif   /* PLANMAIN_H */

src/include/utils/lsyscache.h

@@ -6,7 +6,7 @@
  * Portions Copyright (c) 1996-2007, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/utils/lsyscache.h,v 1.114 2007/01/21 00:57:15 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/utils/lsyscache.h,v 1.115 2007/01/22 01:35:22 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -76,6 +76,8 @@ extern Oid	get_func_signature(Oid funcid, Oid **argtypes, int *nargs);
 extern bool get_func_retset(Oid funcid);
 extern bool func_strict(Oid funcid);
 extern char func_volatile(Oid funcid);
+extern float4 get_func_cost(Oid funcid);
+extern float4 get_func_rows(Oid funcid);
 extern Oid	get_relname_relid(const char *relname, Oid relnamespace);
 extern char *get_rel_name(Oid relid);
 extern Oid	get_rel_namespace(Oid relid);

src/test/regress/expected/opr_sanity.out

@@ -46,7 +46,9 @@ WHERE p1.prolang = 0 OR p1.prorettype = 0 OR
        p1.pronargs < 0 OR
        array_lower(p1.proargtypes, 1) != 0 OR
        array_upper(p1.proargtypes, 1) != p1.pronargs-1 OR
-       0::oid = ANY (p1.proargtypes);
+       0::oid = ANY (p1.proargtypes) OR
+       procost <= 0 OR
+       CASE WHEN proretset THEN prorows <= 0 ELSE prorows != 0 END;
  oid | proname 
 -----+---------
 (0 rows)

src/test/regress/sql/opr_sanity.sql

@@ -53,7 +53,9 @@ WHERE p1.prolang = 0 OR p1.prorettype = 0 OR
        p1.pronargs < 0 OR
        array_lower(p1.proargtypes, 1) != 0 OR
        array_upper(p1.proargtypes, 1) != p1.pronargs-1 OR
-       0::oid = ANY (p1.proargtypes);
+       0::oid = ANY (p1.proargtypes) OR
+       procost <= 0 OR
+       CASE WHEN proretset THEN prorows <= 0 ELSE prorows != 0 END;
 
 -- Look for conflicting proc definitions (same names and input datatypes).
 -- (This test should be dead code now that we have the unique index