diff --git a/doc/src/sgml/libpq++.sgml b/doc/src/sgml/libpq++.sgml
index d259206c88227318029f6fd5405cc4936aa06b3b..65cc873e2803b1a7e1daa8989d5882acca7e8ab5 100644
--- a/doc/src/sgml/libpq++.sgml
+++ b/doc/src/sgml/libpq++.sgml
@@ -164,24 +164,6 @@
sets the default mode for the genetic optimizer.
</para>
</listitem>
- <listitem>
- <para>
- <envar>PGRPLANS</envar>
- sets the default mode to allow or disable right-sided plans in the optimizer.
- </para>
- </listitem>
- <listitem>
- <para>
- <envar>PGCOSTHEAP</envar>
- sets the default cost for heap searches for the optimizer.
- </para>
- </listitem>
- <listitem>
- <para>
- <envar>PGCOSTINDEX</envar>
- sets the default cost for indexed searches for the optimizer.
- </para>
- </listitem>
</itemizedlist>
</para>
diff --git a/doc/src/sgml/libpq.sgml b/doc/src/sgml/libpq.sgml
index 2e02618c62e955461add106d0e4f1e7f942f63a8..506d98002c586a4559300cfc4517d245c8b8c5f4 100644
--- a/doc/src/sgml/libpq.sgml
+++ b/doc/src/sgml/libpq.sgml
@@ -1900,24 +1900,6 @@ behavior for every Postgres session:
sets the default mode for the genetic optimizer.
</para>
</listitem>
-<listitem>
-<para>
-<envar>PGRPLANS</envar>
-sets the default mode to allow or disable right-sided plans in the optimizer.
-</para>
-</listitem>
-<listitem>
-<para>
-<envar>PGCOSTHEAP</envar>
-sets the default cost for heap searches for the optimizer.
-</para>
-</listitem>
-<listitem>
-<para>
-<envar>PGCOSTINDEX</envar>
-sets the default cost for indexed searches for the optimizer.
-</para>
-</listitem>
</itemizedlist>
</para>
diff --git a/doc/src/sgml/ref/set.sgml b/doc/src/sgml/ref/set.sgml
index 51177570649c6f300dc5860e43aec18bfa8a137b..2c32c76ff035b3bfc9328fa07a257f537411928a 100644
--- a/doc/src/sgml/ref/set.sgml
+++ b/doc/src/sgml/ref/set.sgml
@@ -1,5 +1,5 @@
<!--
-$Header: /cvsroot/pgsql/doc/src/sgml/ref/set.sgml,v 1.28 1999/07/22 15:09:15 thomas Exp $
+$Header: /cvsroot/pgsql/doc/src/sgml/ref/set.sgml,v 1.29 2000/02/15 20:49:07 tgl Exp $
Postgres documentation
-->
@@ -50,7 +50,8 @@ SET TRANSACTION ISOLATION LEVEL { READ COMMITTED | SERIALIZABLE }
<term><replaceable class="PARAMETER">value</replaceable></term>
<listitem>
<para>
- New value of parameter.
+ New value of parameter. The word <term>DEFAULT</term> can be
+ written to specify resetting the parameter to its default value.
</para>
</listitem>
</varlistentry>
@@ -78,20 +79,12 @@ SET TRANSACTION ISOLATION LEVEL { READ COMMITTED | SERIALIZABLE }
</para>
</listitem>
</varlistentry>
-
- <varlistentry>
- <term>DEFAULT</term>
- <listitem>
- <para>
- Sets the multi-byte client encoding to the default value.
- </para>
- </listitem>
- </varlistentry>
</variablelist>
</para>
<para>
- This is only enabled if multi-byte was specified to configure.
+ This option is only available if MULTIBYTE support was enabled
+ during the configure step of building Postgres.
</para>
</listitem>
</varlistentry>
@@ -176,6 +169,9 @@ SET TRANSACTION ISOLATION LEVEL { READ COMMITTED | SERIALIZABLE }
<simplelist>
<member>
Setting the <envar>PGDATESTYLE</envar> environment variable.
+ If PGDATESTYLE is set in the frontend environment of a client
+ based on libpq, libpq will automatically set DATESTYLE to the
+ value of PGDATESTYLE during connection startup.
</member>
<member>
Running postmaster using the option <option>-o -e</option> to set
@@ -218,19 +214,12 @@ SET TRANSACTION ISOLATION LEVEL { READ COMMITTED | SERIALIZABLE }
</para>
</listitem>
</varlistentry>
-
- <varlistentry>
- <term>DEFAULT</term>
- <listitem>
- <para>
- Sets the multi-byte server encoding.
- </para>
- </listitem>
- </varlistentry>
</variablelist>
</para>
+
<para>
- This is only enabled if multi-byte was specified to configure.
+ This option is only available if MULTIBYTE support was enabled
+ during the configure step of building Postgres.
</para>
</listitem>
</varlistentry>
@@ -286,16 +275,17 @@ SET TRANSACTION ISOLATION LEVEL { READ COMMITTED | SERIALIZABLE }
If an invalid time zone is specified, the time zone
becomes GMT (on most systems anyway).
</para>
- <para>
- A frontend which uses libpq may be initialized by setting the PGTZ
- environment variable.
- </para>
<para>
The second syntax shown above, allows one to set the timezone
with a syntax similar to SQL92 <command>SET TIME ZONE</command>.
The LOCAL keyword is just an alternate form
of DEFAULT for SQL92 compatibility.
</para>
+ <para>
+ If the PGTZ environment variable is set in the frontend
+ environment of a client based on libpq, libpq will automatically
+ set TIMEZONE to the value of PGTZ during connection startup.
+ </para>
</listitem>
</varlistentry>
@@ -349,133 +339,381 @@ SET TRANSACTION ISOLATION LEVEL { READ COMMITTED | SERIALIZABLE }
<variablelist>
<varlistentry>
- <term>COST_HEAP</term>
+ <term>RANDOM_PAGE_COST</term>
<listitem>
<para>
- Sets the default cost of a heap scan for use by the optimizer.
+ Sets the optimizer's estimate of the cost of a nonsequentially
+ fetched disk page. This is measured as a multiple of the cost
+ of a sequential page fetch.
<variablelist>
<varlistentry>
- <term><replaceable class="parameter">float4</replaceable></term>
+ <term><replaceable class="parameter">float8</replaceable></term>
<listitem>
<para>
- Set the cost of a heap scan to the specified floating point value.
+ Set the cost of a random page access
+ to the specified floating-point value.
</para>
</listitem>
</varlistentry>
-
+ </variablelist>
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term>CPU_TUPLE_COST</term>
+ <listitem>
+ <para>
+ Sets the optimizer's estimate of the cost of processing each
+ tuple during a query. This is measured as a fraction of the cost
+ of a sequential page fetch.
+
+ <variablelist>
<varlistentry>
- <term>DEFAULT</term>
+ <term><replaceable class="parameter">float8</replaceable></term>
<listitem>
<para>
- Sets the cost of a heap scan to the default value.
+ Set the cost of per-tuple CPU processing
+ to the specified floating-point value.
</para>
</listitem>
</varlistentry>
</variablelist>
</para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term>CPU_INDEX_TUPLE_COST</term>
+ <listitem>
<para>
- The frontend may be initialized by setting the PGCOSTHEAP
- environment variable.
+ Sets the optimizer's estimate of the cost of processing each
+ index tuple during an index scan. This is measured as a fraction
+ of the cost of a sequential page fetch.
+
+ <variablelist>
+ <varlistentry>
+ <term><replaceable class="parameter">float8</replaceable></term>
+ <listitem>
+ <para>
+ Set the cost of per-index-tuple CPU processing
+ to the specified floating-point value.
+ </para>
+ </listitem>
+ </varlistentry>
+ </variablelist>
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term>CPU_OPERATOR_COST</term>
+ <listitem>
+ <para>
+ Sets the optimizer's estimate of the cost of processing each
+ operator in a WHERE clause. This is measured as a fraction
+ of the cost of a sequential page fetch.
+
+ <variablelist>
+ <varlistentry>
+ <term><replaceable class="parameter">float8</replaceable></term>
+ <listitem>
+ <para>
+ Set the cost of per-operator CPU processing
+ to the specified floating-point value.
+ </para>
+ </listitem>
+ </varlistentry>
+ </variablelist>
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term>EFFECTIVE_CACHE_SIZE</term>
+ <listitem>
+ <para>
+ Sets the optimizer's assumption about the effective size of the
+ disk cache (that is, the portion of the kernel's disk cache that
+ will be used for Postgres data files). This is measured in disk
+ pages, which are normally 8Kb apiece.
+
+ <variablelist>
+ <varlistentry>
+ <term><replaceable class="parameter">float8</replaceable></term>
+ <listitem>
+ <para>
+ Set the assumed cache size
+ to the specified floating-point value.
+ </para>
+ </listitem>
+ </varlistentry>
+ </variablelist>
</para>
</listitem>
</varlistentry>
<varlistentry>
- <term>COST_INDEX</term>
+ <term>ENABLE_SEQSCAN</term>
<listitem>
<para>
- Sets the default cost of an index scan for use by the optimizer.
+ Enables or disables the planner's use of sequential scan plan types.
+ (It's not possible to suppress sequential scans entirely, but turning
+ this variable OFF discourages the planner from using one if there is
+ any other method available.)
- <variablelist>
+ <variablelist>
<varlistentry>
- <term><replaceable class="parameter">float4</replaceable></term>
+ <term>ON</term>
<listitem>
<para>
- Set the cost of an index scan to the specified floating point value.
+ enables use of sequential scans (default setting).
</para>
</listitem>
</varlistentry>
-
+
<varlistentry>
- <term>DEFAULT</term>
+ <term>OFF</term>
<listitem>
<para>
- Sets the cost of an index scan to the default value.
+ disables use of sequential scans.
</para>
</listitem>
</varlistentry>
</variablelist>
</para>
+ </listitem>
+ </varlistentry>
+ <varlistentry>
+ <term>ENABLE_INDEXSCAN</term>
+ <listitem>
<para>
- The frontend may be initialized by setting the PGCOSTINDEX
- environment variable.
+ Enables or disables the planner's use of index scan plan types.
+
+ <variablelist>
+ <varlistentry>
+ <term>ON</term>
+ <listitem>
+ <para>
+ enables use of index scans (default setting).
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term>OFF</term>
+ <listitem>
+ <para>
+ disables use of index scans.
+ </para>
+ </listitem>
+ </varlistentry>
+ </variablelist>
</para>
</listitem>
</varlistentry>
<varlistentry>
- <term>GEQO</term>
+ <term>ENABLE_TIDSCAN</term>
<listitem>
<para>
- Sets the threshold for using the genetic optimizer algorithm.
+ Enables or disables the planner's use of TID scan plan types.
<variablelist>
<varlistentry>
<term>ON</term>
<listitem>
<para>
- enables the genetic optimizer algorithm
- for statements with 6 or more tables.
+ enables use of TID scans (default setting).
</para>
</listitem>
</varlistentry>
+
+ <varlistentry>
+ <term>OFF</term>
+ <listitem>
+ <para>
+ disables use of TID scans.
+ </para>
+ </listitem>
+ </varlistentry>
+ </variablelist>
+ </para>
+ </listitem>
+ </varlistentry>
+ <varlistentry>
+ <term>ENABLE_SORT</term>
+ <listitem>
+ <para>
+ Enables or disables the planner's use of explicit sort steps.
+ (It's not possible to suppress explicit sorts entirely, but turning
+ this variable OFF discourages the planner from using one if there is
+ any other method available.)
+
+ <variablelist>
<varlistentry>
- <term>ON=<replaceable class="parameter">#</replaceable></term>
+ <term>ON</term>
<listitem>
<para>
- Takes an integer argument to enable the genetic optimizer algorithm
- for statements with <replaceable class="parameter">#</replaceable>
- or more tables in the query.
+ enables use of sorts (default setting).
</para>
</listitem>
</varlistentry>
+
+ <varlistentry>
+ <term>OFF</term>
+ <listitem>
+ <para>
+ disables use of sorts.
+ </para>
+ </listitem>
+ </varlistentry>
+ </variablelist>
+ </para>
+ </listitem>
+ </varlistentry>
+ <varlistentry>
+ <term>ENABLE_NESTLOOP</term>
+ <listitem>
+ <para>
+ Enables or disables the planner's use of nested-loop join plans.
+ (It's not possible to suppress nested-loop joins entirely, but turning
+ this variable OFF discourages the planner from using one if there is
+ any other method available.)
+
+ <variablelist>
+ <varlistentry>
+ <term>ON</term>
+ <listitem>
+ <para>
+ enables use of nested-loop joins (default setting).
+ </para>
+ </listitem>
+ </varlistentry>
+
<varlistentry>
<term>OFF</term>
<listitem>
<para>
- disables the genetic optimizer algorithm.
+ disables use of nested-loop joins.
+ </para>
+ </listitem>
+ </varlistentry>
+ </variablelist>
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term>ENABLE_MERGEJOIN</term>
+ <listitem>
+ <para>
+ Enables or disables the planner's use of mergejoin plans.
+
+ <variablelist>
+ <varlistentry>
+ <term>ON</term>
+ <listitem>
+ <para>
+ enables use of merge joins (default setting).
</para>
</listitem>
</varlistentry>
+
<varlistentry>
- <term>DEFAULT</term>
+ <term>OFF</term>
+ <listitem>
+ <para>
+ disables use of merge joins.
+ </para>
+ </listitem>
+ </varlistentry>
+ </variablelist>
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term>ENABLE_HASHJOIN</term>
+ <listitem>
+ <para>
+ Enables or disables the planner's use of hashjoin plans.
+
+ <variablelist>
+ <varlistentry>
+ <term>ON</term>
<listitem>
<para>
- Equivalent to specifying <command>SET GEQO='ON'</command>
+ enables use of hash joins (default setting).
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term>OFF</term>
+ <listitem>
+ <para>
+ disables use of hash joins.
</para>
</listitem>
</varlistentry>
</variablelist>
</para>
+ </listitem>
+ </varlistentry>
+ <varlistentry>
+ <term>GEQO</term>
+ <listitem>
<para>
- This algorithm is on by default, which used GEQO for
- statements of eleven or more tables.
- (See the chapter on GEQO in the Programmer's Guide
- for more information).
+ Sets the threshold for using the genetic optimizer algorithm.
+
+ <variablelist>
+ <varlistentry>
+ <term>ON</term>
+ <listitem>
+ <para>
+ enables the genetic optimizer algorithm
+ for statements with 11 or more tables.
+ (This is also the DEFAULT setting.)
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term>ON=<replaceable class="parameter">#</replaceable></term>
+ <listitem>
+ <para>
+ Takes an integer argument to enable the genetic optimizer algorithm
+ for statements with <replaceable class="parameter">#</replaceable>
+ or more tables in the query.
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term>OFF</term>
+ <listitem>
+ <para>
+ disables the genetic optimizer algorithm.
+ </para>
+ </listitem>
+ </varlistentry>
+ </variablelist>
</para>
+
<para>
- The frontend may be initialized by setting PGGEQO
- environment variable.
+ See the chapter on GEQO in the Programmer's Guide
+ for more information about query optimization.
</para>
<para>
- It may be useful when joining big relations with
- small ones. This algorithm is off by default.
- It's not used by GEQO anyway.
+ If the PGGEQO environment variable is set in the frontend
+ environment of a client based on libpq, libpq will automatically
+ set GEQO to the value of PGGEQO during connection startup.
</para>
</listitem>
</varlistentry>
@@ -484,10 +722,16 @@ SET TRANSACTION ISOLATION LEVEL { READ COMMITTED | SERIALIZABLE }
<term>KSQO</term>
<listitem>
<para>
- <firstterm>Key Set Query Optimizer</firstterm> forces the query optimizer
- to optimize repetative OR clauses such as generated by
- <productname>MicroSoft Access</productname>:
-
+ <firstterm>Key Set Query Optimizer</firstterm> causes the query
+ planner to convert queries whose WHERE clause contains many
+ OR'ed AND clauses (such as "WHERE (a=1 AND b=2) OR (a=2 AND b=3) ...")
+ into a UNION query. This method can be faster than the default
+ implementation, but it doesn't necessarily give exactly the same
+ results, since UNION implicitly adds a SELECT DISTINCT clause to
+ eliminate identical output rows. KSQO is commonly used when
+ working with products like <productname>MicroSoft
+ Access</productname>, which tend to generate queries of this form.
+
<variablelist>
<varlistentry>
<term>ON</term>
@@ -502,7 +746,7 @@ SET TRANSACTION ISOLATION LEVEL { READ COMMITTED | SERIALIZABLE }
<term>OFF</term>
<listitem>
<para>
- disables this optimization.
+ disables this optimization (default setting).
</para>
</listitem>
</varlistentry>
@@ -519,13 +763,9 @@ SET TRANSACTION ISOLATION LEVEL { READ COMMITTED | SERIALIZABLE }
</para>
<para>
- It may be useful when joining big relations with
- small ones. This algorithm is off by default.
- It's not used by GEQO anyway.
- </para>
- <para>
- The frontend may be initialized by setting the PGKSQO
- environment variable.
+ The KSQO algorithm used to be absolutely essential for queries
+ with many OR'ed AND clauses, but in Postgres 7.0 and later
+ the standard planner handles these queries fairly successfully.
</para>
</listitem>
</varlistentry>
diff --git a/doc/src/sgml/ref/show.sgml b/doc/src/sgml/ref/show.sgml
index 14b43d823447eeba6376b0d60e8601313e77982e..39fbde16ae0c3434ca5b46327e15493cdff8a38d 100644
--- a/doc/src/sgml/ref/show.sgml
+++ b/doc/src/sgml/ref/show.sgml
@@ -1,5 +1,5 @@
<!--
-$Header: /cvsroot/pgsql/doc/src/sgml/ref/show.sgml,v 1.7 1999/07/22 15:09:15 thomas Exp $
+$Header: /cvsroot/pgsql/doc/src/sgml/ref/show.sgml,v 1.8 2000/02/15 20:49:07 tgl Exp $
Postgres documentation
-->
@@ -106,14 +106,14 @@ SHOW VARIABLE
Description
</title>
<para>
- <command>SHOW</command> will display the current
- configuration parameters for
- variable during a session.
+ <command>SHOW</command> will display the current setting of a
+ run-time parameter during a session.
</para>
<para>
- The session can be configured using <command>SET</command> statement,
- and values
- can be restored to the defaults using <command>RESET</command> statement.
+ These variables can be set using the <command>SET</command> statement,
+ and
+ can be restored to the default values using the <command>RESET</command>
+ statement.
Parameters and values are case-insensitive.
</para>
@@ -125,13 +125,12 @@ SHOW VARIABLE
Notes
</title>
<para>
- The <command>SHOW</command> is a <productname>Postgres</productname>
+ <command>SHOW</command> is a <productname>Postgres</productname>
language extension.
</para>
<para>
Refer to <command>SET</command>/<command>RESET</command>
to set/reset variable values.
- See also <command>SET TIME ZONE</command>.
</para>
</refsect2>
</refsect1>
diff --git a/src/backend/commands/explain.c b/src/backend/commands/explain.c
index 2b152b2fe5b0e7df8c90563035a1486ef343023e..2a38a349d6073999b40bfe939939bdb23ec619a9 100644
--- a/src/backend/commands/explain.c
+++ b/src/backend/commands/explain.c
@@ -5,7 +5,7 @@
* Portions Copyright (c) 1996-2000, PostgreSQL, Inc
* Portions Copyright (c) 1994-5, Regents of the University of California
*
- * $Id: explain.c,v 1.53 2000/02/15 03:36:39 thomas Exp $
+ * $Header: /cvsroot/pgsql/src/backend/commands/explain.c,v 1.54 2000/02/15 20:49:08 tgl Exp $
*
*/
@@ -217,39 +217,24 @@ explain_outNode(StringInfo str, Plan *plan, int indent, ExplainState *es)
{
relation = RelationIdGetRelation(lfirsti(l));
Assert(relation);
- if (++i > 1)
- appendStringInfo(str, ", ");
- appendStringInfo(str,
+ appendStringInfo(str, "%s%s",
+ (++i > 1) ? ", " : "",
stringStringInfo(RelationGetRelationName(relation)));
/* drop relcache refcount from RelationIdGetRelation */
RelationDecrementReferenceCount(relation);
}
+ /* FALL THRU */
case T_SeqScan:
+ case T_TidScan:
if (((Scan *) plan)->scanrelid > 0)
{
RangeTblEntry *rte = nth(((Scan *) plan)->scanrelid - 1, es->rtable);
- appendStringInfo(str, " on ");
- if (strcmp(rte->ref->relname, rte->relname) != 0)
- {
- appendStringInfo(str, "%s ",
- stringStringInfo(rte->relname));
- }
- appendStringInfo(str, stringStringInfo(rte->ref->relname));
- }
- break;
- case T_TidScan:
- if (((TidScan *) plan)->scan.scanrelid > 0)
- {
- RangeTblEntry *rte = nth(((TidScan *) plan)->scan.scanrelid - 1, es->rtable);
-
- appendStringInfo(str, " on ");
- if (strcmp(rte->ref->relname, rte->relname) != 0)
- {
- appendStringInfo(str, "%s ",
- stringStringInfo(rte->relname));
- }
- appendStringInfo(str, stringStringInfo(rte->ref->relname));
+ appendStringInfo(str, " on %s",
+ stringStringInfo(rte->relname));
+ if (rte->ref && strcmp(rte->ref->relname, rte->relname) != 0)
+ appendStringInfo(str, " %s",
+ stringStringInfo(rte->ref->relname));
}
break;
default:
@@ -257,8 +242,9 @@ explain_outNode(StringInfo str, Plan *plan, int indent, ExplainState *es)
}
if (es->printCost)
{
- appendStringInfo(str, " (cost=%.2f rows=%.0f width=%d)",
- plan->cost, plan->plan_rows, plan->plan_width);
+ appendStringInfo(str, " (cost=%.2f..%.2f rows=%.0f width=%d)",
+ plan->startup_cost, plan->total_cost,
+ plan->plan_rows, plan->plan_width);
}
appendStringInfo(str, "\n");
diff --git a/src/backend/commands/variable.c b/src/backend/commands/variable.c
index 52c4ed3552a1149254673abd6dea97f05c1d26aa..718a62a118d98d79413ceb1fc5acfb4e889f1f82 100644
--- a/src/backend/commands/variable.c
+++ b/src/backend/commands/variable.c
@@ -1,15 +1,24 @@
-/*
- * Routines for handling of 'SET var TO',
- * 'SHOW var' and 'RESET var' statements.
+/*-------------------------------------------------------------------------
+ *
+ * variable.c
+ * Routines for handling of 'SET var TO',
+ * 'SHOW var' and 'RESET var' statements.
+ *
+ * Portions Copyright (c) 1996-2000, PostgreSQL, Inc
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
*
- * $Id: variable.c,v 1.28 2000/01/22 23:50:10 tgl Exp $
+ * IDENTIFICATION
+ * $Header: /cvsroot/pgsql/src/backend/commands/variable.c,v 1.29 2000/02/15 20:49:08 tgl Exp $
*
+ *-------------------------------------------------------------------------
*/
#include <ctype.h>
#include <time.h>
#include "postgres.h"
+
#include "access/xact.h"
#include "catalog/pg_shadow.h"
#include "commands/variable.h"
@@ -24,18 +33,53 @@
#include "mb/pg_wchar.h"
#endif
+
+/* XXX should be in a header file */
+extern bool _use_keyset_query_optimizer;
+
+
static bool show_date(void);
static bool reset_date(void);
static bool parse_date(const char *);
static bool show_timezone(void);
static bool reset_timezone(void);
static bool parse_timezone(const char *);
-static bool show_cost_heap(void);
-static bool reset_cost_heap(void);
-static bool parse_cost_heap(const char *);
-static bool show_cost_index(void);
-static bool reset_cost_index(void);
-static bool parse_cost_index(const char *);
+static bool show_effective_cache_size(void);
+static bool reset_effective_cache_size(void);
+static bool parse_effective_cache_size(const char *);
+static bool show_random_page_cost(void);
+static bool reset_random_page_cost(void);
+static bool parse_random_page_cost(const char *);
+static bool show_cpu_tuple_cost(void);
+static bool reset_cpu_tuple_cost(void);
+static bool parse_cpu_tuple_cost(const char *);
+static bool show_cpu_index_tuple_cost(void);
+static bool reset_cpu_index_tuple_cost(void);
+static bool parse_cpu_index_tuple_cost(const char *);
+static bool show_cpu_operator_cost(void);
+static bool reset_cpu_operator_cost(void);
+static bool parse_cpu_operator_cost(const char *);
+static bool reset_enable_seqscan(void);
+static bool show_enable_seqscan(void);
+static bool parse_enable_seqscan(const char *);
+static bool reset_enable_indexscan(void);
+static bool show_enable_indexscan(void);
+static bool parse_enable_indexscan(const char *);
+static bool reset_enable_tidscan(void);
+static bool show_enable_tidscan(void);
+static bool parse_enable_tidscan(const char *);
+static bool reset_enable_sort(void);
+static bool show_enable_sort(void);
+static bool parse_enable_sort(const char *);
+static bool reset_enable_nestloop(void);
+static bool show_enable_nestloop(void);
+static bool parse_enable_nestloop(const char *);
+static bool reset_enable_mergejoin(void);
+static bool show_enable_mergejoin(void);
+static bool parse_enable_mergejoin(const char *);
+static bool reset_enable_hashjoin(void);
+static bool show_enable_hashjoin(void);
+static bool parse_enable_hashjoin(const char *);
static bool reset_geqo(void);
static bool show_geqo(void);
static bool parse_geqo(const char *);
@@ -46,8 +90,6 @@ static bool show_XactIsoLevel(void);
static bool reset_XactIsoLevel(void);
static bool parse_XactIsoLevel(const char *);
-extern bool _use_keyset_query_optimizer;
-
/*
*
* Get_Token
@@ -153,6 +195,204 @@ get_token(char **tok, char **val, const char *str)
return str;
}
+/*
+ * Generic parse routine for boolean ON/OFF variables
+ */
+static bool
+parse_boolean_var(const char *value,
+ bool *variable, const char *varname, bool defaultval)
+{
+ if (value == NULL)
+ {
+ *variable = defaultval;
+ return TRUE;
+ }
+
+ if (strcasecmp(value, "on") == 0)
+ *variable = true;
+ else if (strcasecmp(value, "off") == 0)
+ *variable = false;
+ else
+ elog(ERROR, "Bad value for %s (%s)", varname, value);
+
+ return TRUE;
+}
+
+/*
+ * ENABLE_SEQSCAN
+ */
+static bool
+parse_enable_seqscan(const char *value)
+{
+ return parse_boolean_var(value, &enable_seqscan,
+ "ENABLE_SEQSCAN", true);
+}
+
+static bool
+show_enable_seqscan()
+{
+ elog(NOTICE, "ENABLE_SEQSCAN is %s",
+ enable_seqscan ? "ON" : "OFF");
+ return TRUE;
+}
+
+static bool
+reset_enable_seqscan()
+{
+ enable_seqscan = true;
+ return TRUE;
+}
+
+/*
+ * ENABLE_INDEXSCAN
+ */
+static bool
+parse_enable_indexscan(const char *value)
+{
+ return parse_boolean_var(value, &enable_indexscan,
+ "ENABLE_INDEXSCAN", true);
+}
+
+static bool
+show_enable_indexscan()
+{
+ elog(NOTICE, "ENABLE_INDEXSCAN is %s",
+ enable_indexscan ? "ON" : "OFF");
+ return TRUE;
+}
+
+static bool
+reset_enable_indexscan()
+{
+ enable_indexscan = true;
+ return TRUE;
+}
+
+/*
+ * ENABLE_TIDSCAN
+ */
+static bool
+parse_enable_tidscan(const char *value)
+{
+ return parse_boolean_var(value, &enable_tidscan,
+ "ENABLE_TIDSCAN", true);
+}
+
+static bool
+show_enable_tidscan()
+{
+ elog(NOTICE, "ENABLE_TIDSCAN is %s",
+ enable_tidscan ? "ON" : "OFF");
+ return TRUE;
+}
+
+static bool
+reset_enable_tidscan()
+{
+ enable_tidscan = true;
+ return TRUE;
+}
+
+/*
+ * ENABLE_SORT
+ */
+static bool
+parse_enable_sort(const char *value)
+{
+ return parse_boolean_var(value, &enable_sort,
+ "ENABLE_SORT", true);
+}
+
+static bool
+show_enable_sort()
+{
+ elog(NOTICE, "ENABLE_SORT is %s",
+ enable_sort ? "ON" : "OFF");
+ return TRUE;
+}
+
+static bool
+reset_enable_sort()
+{
+ enable_sort = true;
+ return TRUE;
+}
+
+/*
+ * ENABLE_NESTLOOP
+ */
+static bool
+parse_enable_nestloop(const char *value)
+{
+ return parse_boolean_var(value, &enable_nestloop,
+ "ENABLE_NESTLOOP", true);
+}
+
+static bool
+show_enable_nestloop()
+{
+ elog(NOTICE, "ENABLE_NESTLOOP is %s",
+ enable_nestloop ? "ON" : "OFF");
+ return TRUE;
+}
+
+static bool
+reset_enable_nestloop()
+{
+ enable_nestloop = true;
+ return TRUE;
+}
+
+/*
+ * ENABLE_MERGEJOIN
+ */
+static bool
+parse_enable_mergejoin(const char *value)
+{
+ return parse_boolean_var(value, &enable_mergejoin,
+ "ENABLE_MERGEJOIN", true);
+}
+
+static bool
+show_enable_mergejoin()
+{
+ elog(NOTICE, "ENABLE_MERGEJOIN is %s",
+ enable_mergejoin ? "ON" : "OFF");
+ return TRUE;
+}
+
+static bool
+reset_enable_mergejoin()
+{
+ enable_mergejoin = true;
+ return TRUE;
+}
+
+/*
+ * ENABLE_HASHJOIN
+ */
+static bool
+parse_enable_hashjoin(const char *value)
+{
+ return parse_boolean_var(value, &enable_hashjoin,
+ "ENABLE_HASHJOIN", true);
+}
+
+static bool
+show_enable_hashjoin()
+{
+ elog(NOTICE, "ENABLE_HASHJOIN is %s",
+ enable_hashjoin ? "ON" : "OFF");
+ return TRUE;
+}
+
+static bool
+reset_enable_hashjoin()
+{
+ enable_hashjoin = true;
+ return TRUE;
+}
+
/*
*
* GEQO
@@ -208,7 +448,6 @@ parse_geqo(const char *value)
static bool
show_geqo()
{
-
if (enable_geqo)
elog(NOTICE, "GEQO is ON beginning with %d relations", geqo_rels);
else
@@ -219,7 +458,6 @@ show_geqo()
static bool
reset_geqo(void)
{
-
#ifdef GEQO
enable_geqo = true;
#else
@@ -230,76 +468,173 @@ reset_geqo(void)
}
/*
- *
- * COST_HEAP
- *
+ * EFFECTIVE_CACHE_SIZE
*/
static bool
-parse_cost_heap(const char *value)
+parse_effective_cache_size(const char *value)
{
float64 res;
if (value == NULL)
{
- reset_cost_heap();
+ reset_effective_cache_size();
return TRUE;
}
res = float8in((char *) value);
- cpu_page_weight = *res;
+ effective_cache_size = *res;
return TRUE;
}
static bool
-show_cost_heap()
+show_effective_cache_size()
{
+ elog(NOTICE, "EFFECTIVE_CACHE_SIZE is %g (%dK pages)",
+ effective_cache_size, BLCKSZ/1024);
+ return TRUE;
+}
- elog(NOTICE, "COST_HEAP is %f", cpu_page_weight);
+static bool
+reset_effective_cache_size()
+{
+ effective_cache_size = DEFAULT_EFFECTIVE_CACHE_SIZE;
return TRUE;
}
+/*
+ * RANDOM_PAGE_COST
+ */
static bool
-reset_cost_heap()
+parse_random_page_cost(const char *value)
{
- cpu_page_weight = CPU_PAGE_WEIGHT;
+ float64 res;
+
+ if (value == NULL)
+ {
+ reset_random_page_cost();
+ return TRUE;
+ }
+
+ res = float8in((char *) value);
+ random_page_cost = *res;
+
+ return TRUE;
+}
+
+static bool
+show_random_page_cost()
+{
+ elog(NOTICE, "RANDOM_PAGE_COST is %g", random_page_cost);
+ return TRUE;
+}
+
+static bool
+reset_random_page_cost()
+{
+ random_page_cost = DEFAULT_RANDOM_PAGE_COST;
return TRUE;
}
/*
- *
- * COST_INDEX
- *
+ * CPU_TUPLE_COST
*/
static bool
-parse_cost_index(const char *value)
+parse_cpu_tuple_cost(const char *value)
{
float64 res;
if (value == NULL)
{
- reset_cost_index();
+ reset_cpu_tuple_cost();
return TRUE;
}
res = float8in((char *) value);
- cpu_index_page_weight = *res;
+ cpu_tuple_cost = *res;
return TRUE;
}
static bool
-show_cost_index()
+show_cpu_tuple_cost()
{
+ elog(NOTICE, "CPU_TUPLE_COST is %g", cpu_tuple_cost);
+ return TRUE;
+}
- elog(NOTICE, "COST_INDEX is %f", cpu_index_page_weight);
+static bool
+reset_cpu_tuple_cost()
+{
+ cpu_tuple_cost = DEFAULT_CPU_TUPLE_COST;
return TRUE;
}
+/*
+ * CPU_INDEX_TUPLE_COST
+ */
static bool
-reset_cost_index()
+parse_cpu_index_tuple_cost(const char *value)
{
- cpu_index_page_weight = CPU_INDEX_PAGE_WEIGHT;
+ float64 res;
+
+ if (value == NULL)
+ {
+ reset_cpu_index_tuple_cost();
+ return TRUE;
+ }
+
+ res = float8in((char *) value);
+ cpu_index_tuple_cost = *res;
+
+ return TRUE;
+}
+
+static bool
+show_cpu_index_tuple_cost()
+{
+ elog(NOTICE, "CPU_INDEX_TUPLE_COST is %g", cpu_index_tuple_cost);
+ return TRUE;
+}
+
+static bool
+reset_cpu_index_tuple_cost()
+{
+ cpu_index_tuple_cost = DEFAULT_CPU_INDEX_TUPLE_COST;
+ return TRUE;
+}
+
+/*
+ * CPU_OPERATOR_COST
+ */
+static bool
+parse_cpu_operator_cost(const char *value)
+{
+ float64 res;
+
+ if (value == NULL)
+ {
+ reset_cpu_operator_cost();
+ return TRUE;
+ }
+
+ res = float8in((char *) value);
+ cpu_operator_cost = *res;
+
+ return TRUE;
+}
+
+static bool
+show_cpu_operator_cost()
+{
+ elog(NOTICE, "CPU_OPERATOR_COST is %g", cpu_operator_cost);
+ return TRUE;
+}
+
+static bool
+reset_cpu_operator_cost()
+{
+ cpu_operator_cost = DEFAULT_CPU_OPERATOR_COST;
return TRUE;
}
@@ -527,6 +862,89 @@ reset_timezone()
return TRUE;
} /* reset_timezone() */
+/*-----------------------------------------------------------------------
+KSQO code will one day be unnecessary when the optimizer makes use of
+indexes when multiple ORs are specified in the where clause.
+See optimizer/prep/prepkeyset.c for more on this.
+ daveh@insightdist.com 6/16/98
+-----------------------------------------------------------------------*/
+static bool
+parse_ksqo(const char *value)
+{
+ return parse_boolean_var(value, &_use_keyset_query_optimizer,
+ "KSQO", false);
+}
+
+static bool
+show_ksqo()
+{
+ elog(NOTICE, "KSQO is %s",
+ _use_keyset_query_optimizer ? "ON" : "OFF");
+ return TRUE;
+}
+
+static bool
+reset_ksqo()
+{
+ _use_keyset_query_optimizer = false;
+ return TRUE;
+}
+
+/* SET TRANSACTION */
+
+static bool
+parse_XactIsoLevel(const char *value)
+{
+
+ if (value == NULL)
+ {
+ reset_XactIsoLevel();
+ return TRUE;
+ }
+
+ if (SerializableSnapshot != NULL)
+ {
+ elog(ERROR, "SET TRANSACTION ISOLATION LEVEL must be called before any query");
+ return TRUE;
+ }
+
+
+ if (strcasecmp(value, "SERIALIZABLE") == 0)
+ XactIsoLevel = XACT_SERIALIZABLE;
+ else if (strcasecmp(value, "COMMITTED") == 0)
+ XactIsoLevel = XACT_READ_COMMITTED;
+ else
+ elog(ERROR, "Bad TRANSACTION ISOLATION LEVEL (%s)", value);
+
+ return TRUE;
+}
+
+static bool
+show_XactIsoLevel()
+{
+
+ if (XactIsoLevel == XACT_SERIALIZABLE)
+ elog(NOTICE, "TRANSACTION ISOLATION LEVEL is SERIALIZABLE");
+ else
+ elog(NOTICE, "TRANSACTION ISOLATION LEVEL is READ COMMITTED");
+ return TRUE;
+}
+
+static bool
+reset_XactIsoLevel()
+{
+
+ if (SerializableSnapshot != NULL)
+ {
+ elog(ERROR, "SET TRANSACTION ISOLATION LEVEL must be called before any query");
+ return TRUE;
+ }
+
+ XactIsoLevel = DefaultXactIsoLevel;
+
+ return TRUE;
+}
+
/*
* Pg_options
*/
@@ -557,6 +975,7 @@ reset_pg_options(void)
return (TRUE);
}
+
/*-----------------------------------------------------------------------*/
struct VariableParsers
@@ -575,10 +994,52 @@ struct VariableParsers
"timezone", parse_timezone, show_timezone, reset_timezone
},
{
- "cost_heap", parse_cost_heap, show_cost_heap, reset_cost_heap
+ "effective_cache_size", parse_effective_cache_size,
+ show_effective_cache_size, reset_effective_cache_size
+ },
+ {
+ "random_page_cost", parse_random_page_cost,
+ show_random_page_cost, reset_random_page_cost
+ },
+ {
+ "cpu_tuple_cost", parse_cpu_tuple_cost,
+ show_cpu_tuple_cost, reset_cpu_tuple_cost
+ },
+ {
+ "cpu_index_tuple_cost", parse_cpu_index_tuple_cost,
+ show_cpu_index_tuple_cost, reset_cpu_index_tuple_cost
+ },
+ {
+ "cpu_operator_cost", parse_cpu_operator_cost,
+ show_cpu_operator_cost, reset_cpu_operator_cost
+ },
+ {
+ "enable_seqscan", parse_enable_seqscan,
+ show_enable_seqscan, reset_enable_seqscan
+ },
+ {
+ "enable_indexscan", parse_enable_indexscan,
+ show_enable_indexscan, reset_enable_indexscan
+ },
+ {
+ "enable_tidscan", parse_enable_tidscan,
+ show_enable_tidscan, reset_enable_tidscan
+ },
+ {
+ "enable_sort", parse_enable_sort,
+ show_enable_sort, reset_enable_sort
},
{
- "cost_index", parse_cost_index, show_cost_index, reset_cost_index
+ "enable_nestloop", parse_enable_nestloop,
+ show_enable_nestloop, reset_enable_nestloop
+ },
+ {
+ "enable_mergejoin", parse_enable_mergejoin,
+ show_enable_mergejoin, reset_enable_mergejoin
+ },
+ {
+ "enable_hashjoin", parse_enable_hashjoin,
+ show_enable_hashjoin, reset_enable_hashjoin
},
{
"geqo", parse_geqo, show_geqo, reset_geqo
@@ -655,102 +1116,3 @@ ResetPGVariable(const char *name)
return TRUE;
}
-
-
-/*-----------------------------------------------------------------------
-KSQO code will one day be unnecessary when the optimizer makes use of
-indexes when multiple ORs are specified in the where clause.
-See optimizer/prep/prepkeyset.c for more on this.
- daveh@insightdist.com 6/16/98
------------------------------------------------------------------------*/
-static bool
-parse_ksqo(const char *value)
-{
- if (value == NULL)
- {
- reset_ksqo();
- return TRUE;
- }
-
- if (strcasecmp(value, "on") == 0)
- _use_keyset_query_optimizer = true;
- else if (strcasecmp(value, "off") == 0)
- _use_keyset_query_optimizer = false;
- else
- elog(ERROR, "Bad value for Key Set Query Optimizer (%s)", value);
-
- return TRUE;
-}
-
-static bool
-show_ksqo()
-{
-
- if (_use_keyset_query_optimizer)
- elog(NOTICE, "Key Set Query Optimizer is ON");
- else
- elog(NOTICE, "Key Set Query Optimizer is OFF");
- return TRUE;
-}
-
-static bool
-reset_ksqo()
-{
- _use_keyset_query_optimizer = false;
- return TRUE;
-}
-
-/* SET TRANSACTION */
-
-static bool
-parse_XactIsoLevel(const char *value)
-{
-
- if (value == NULL)
- {
- reset_XactIsoLevel();
- return TRUE;
- }
-
- if (SerializableSnapshot != NULL)
- {
- elog(ERROR, "SET TRANSACTION ISOLATION LEVEL must be called before any query");
- return TRUE;
- }
-
-
- if (strcasecmp(value, "SERIALIZABLE") == 0)
- XactIsoLevel = XACT_SERIALIZABLE;
- else if (strcasecmp(value, "COMMITTED") == 0)
- XactIsoLevel = XACT_READ_COMMITTED;
- else
- elog(ERROR, "Bad TRANSACTION ISOLATION LEVEL (%s)", value);
-
- return TRUE;
-}
-
-static bool
-show_XactIsoLevel()
-{
-
- if (XactIsoLevel == XACT_SERIALIZABLE)
- elog(NOTICE, "TRANSACTION ISOLATION LEVEL is SERIALIZABLE");
- else
- elog(NOTICE, "TRANSACTION ISOLATION LEVEL is READ COMMITTED");
- return TRUE;
-}
-
-static bool
-reset_XactIsoLevel()
-{
-
- if (SerializableSnapshot != NULL)
- {
- elog(ERROR, "SET TRANSACTION ISOLATION LEVEL must be called before any query");
- return TRUE;
- }
-
- XactIsoLevel = DefaultXactIsoLevel;
-
- return TRUE;
-}
diff --git a/src/backend/nodes/copyfuncs.c b/src/backend/nodes/copyfuncs.c
index adf0c7f1987c2ffe8dd28542ead1f778336c60f0..5bf01e227228c4d55e9f93a0de964054d06b4c58 100644
--- a/src/backend/nodes/copyfuncs.c
+++ b/src/backend/nodes/copyfuncs.c
@@ -8,7 +8,7 @@
*
*
* IDENTIFICATION
- * $Header: /cvsroot/pgsql/src/backend/nodes/copyfuncs.c,v 1.105 2000/02/15 03:37:08 thomas Exp $
+ * $Header: /cvsroot/pgsql/src/backend/nodes/copyfuncs.c,v 1.106 2000/02/15 20:49:09 tgl Exp $
*
*-------------------------------------------------------------------------
*/
@@ -75,7 +75,8 @@ listCopy(List *list)
static void
CopyPlanFields(Plan *from, Plan *newnode)
{
- newnode->cost = from->cost;
+ newnode->startup_cost = from->startup_cost;
+ newnode->total_cost = from->total_cost;
newnode->plan_rows = from->plan_rows;
newnode->plan_width = from->plan_width;
/* state is NOT copied */
@@ -981,8 +982,9 @@ _copyRelOptInfo(RelOptInfo *from)
Node_Copy(from, newnode, targetlist);
Node_Copy(from, newnode, pathlist);
- /* XXX cheapestpath should point to a member of pathlist? */
- Node_Copy(from, newnode, cheapestpath);
+ /* XXX cheapest-path fields should point to members of pathlist? */
+ Node_Copy(from, newnode, cheapest_startup_path);
+ Node_Copy(from, newnode, cheapest_total_path);
newnode->pruneable = from->pruneable;
newnode->indexed = from->indexed;
@@ -990,6 +992,7 @@ _copyRelOptInfo(RelOptInfo *from)
newnode->tuples = from->tuples;
Node_Copy(from, newnode, baserestrictinfo);
+ newnode->baserestrictcost = from->baserestrictcost;
Node_Copy(from, newnode, joininfo);
Node_Copy(from, newnode, innerjoin);
@@ -1045,6 +1048,7 @@ _copyIndexOptInfo(IndexOptInfo *from)
newnode->amcostestimate = from->amcostestimate;
newnode->indproc = from->indproc;
Node_Copy(from, newnode, indpred);
+ newnode->lossy = from->lossy;
return newnode;
}
@@ -1066,7 +1070,8 @@ CopyPathFields(Path *from, Path *newnode)
*/
newnode->parent = from->parent;
- newnode->path_cost = from->path_cost;
+ newnode->startup_cost = from->startup_cost;
+ newnode->total_cost = from->total_cost;
newnode->pathtype = from->pathtype;
@@ -1108,6 +1113,7 @@ _copyIndexPath(IndexPath *from)
*/
newnode->indexid = listCopy(from->indexid);
Node_Copy(from, newnode, indexqual);
+ newnode->indexscandir = from->indexscandir;
newnode->joinrelids = listCopy(from->joinrelids);
return newnode;
@@ -1339,8 +1345,7 @@ _copyRangeTblEntry(RangeTblEntry *from)
if (from->relname)
newnode->relname = pstrdup(from->relname);
- if (from->ref)
- Node_Copy(from, newnode, ref);
+ Node_Copy(from, newnode, ref);
newnode->relid = from->relid;
newnode->inh = from->inh;
newnode->inFromCl = from->inFromCl;
@@ -1449,8 +1454,10 @@ _copyQuery(Query *from)
Node_Copy(from, newnode, limitOffset);
Node_Copy(from, newnode, limitCount);
- /* we do not copy the planner internal fields: base_rel_list,
- * join_rel_list, query_pathkeys. Not entirely clear if this is right?
+ /*
+ * We do not copy the planner internal fields: base_rel_list,
+ * join_rel_list, equi_key_list, query_pathkeys.
+ * Not entirely clear if this is right?
*/
return newnode;
diff --git a/src/backend/nodes/equalfuncs.c b/src/backend/nodes/equalfuncs.c
index 3ddc8d6c98a518cc43c91cdd4fb1c321e98e2217..fadc282d1add86fcb5aa8255e80f65cf443af725 100644
--- a/src/backend/nodes/equalfuncs.c
+++ b/src/backend/nodes/equalfuncs.c
@@ -8,7 +8,7 @@
*
*
* IDENTIFICATION
- * $Header: /cvsroot/pgsql/src/backend/nodes/equalfuncs.c,v 1.60 2000/02/15 03:37:08 thomas Exp $
+ * $Header: /cvsroot/pgsql/src/backend/nodes/equalfuncs.c,v 1.61 2000/02/15 20:49:09 tgl Exp $
*
*-------------------------------------------------------------------------
*/
@@ -100,10 +100,10 @@ _equalAttr(Attr *a, Attr *b)
{
if (!strcmp(a->relname, b->relname))
return false;
- if (length(a->attrs) != length(b->attrs))
+ if (!equal(a->attrs, b->attrs))
return false;
- return equal(a->attrs, b->attrs);
+ return true;
}
static bool
@@ -342,8 +342,8 @@ _equalPath(Path *a, Path *b)
return false;
if (!equal(a->parent, b->parent))
return false;
- /* do not check path_cost, since it may not be set yet, and being
- * a float there are roundoff error issues anyway...
+ /* do not check path costs, since they may not be set yet, and being
+ * float values there are roundoff error issues anyway...
*/
if (!equal(a->pathkeys, b->pathkeys))
return false;
@@ -359,6 +359,8 @@ _equalIndexPath(IndexPath *a, IndexPath *b)
return false;
if (!equal(a->indexqual, b->indexqual))
return false;
+ if (a->indexscandir != b->indexscandir)
+ return false;
if (!equali(a->joinrelids, b->joinrelids))
return false;
return true;
@@ -625,8 +627,9 @@ _equalQuery(Query *a, Query *b)
/*
* We do not check the internal-to-the-planner fields: base_rel_list,
- * join_rel_list, query_pathkeys. They might not be set yet, and
- * in any case they should be derivable from the other fields.
+ * join_rel_list, equi_key_list, query_pathkeys.
+ * They might not be set yet, and in any case they should be derivable
+ * from the other fields.
*/
return true;
}
@@ -644,16 +647,8 @@ _equalRangeTblEntry(RangeTblEntry *a, RangeTblEntry *b)
if (a->relname != b->relname)
return false;
}
- if (a->ref && b->ref)
- {
- if (! equal(a->ref, b->ref))
- return false;
- }
- else
- {
- if (a->ref != b->ref)
- return false;
- }
+ if (!equal(a->ref, b->ref))
+ return false;
if (a->relid != b->relid)
return false;
if (a->inh != b->inh)
@@ -784,6 +779,9 @@ equal(void *a, void *b)
case T_Stream:
retval = _equalStream(a, b);
break;
+ case T_Attr:
+ retval = _equalAttr(a, b);
+ break;
case T_Var:
retval = _equalVar(a, b);
break;
@@ -856,9 +854,6 @@ equal(void *a, void *b)
case T_EState:
retval = _equalEState(a, b);
break;
- case T_Attr:
- retval = _equalAttr(a, b);
- break;
case T_Integer:
case T_String:
case T_Float:
diff --git a/src/backend/nodes/freefuncs.c b/src/backend/nodes/freefuncs.c
index 690da02de85f5ec10190b924a83102f2793d40a2..8eed80e61ab42d4835136ac4259514d0424b0936 100644
--- a/src/backend/nodes/freefuncs.c
+++ b/src/backend/nodes/freefuncs.c
@@ -8,7 +8,7 @@
*
*
* IDENTIFICATION
- * $Header: /cvsroot/pgsql/src/backend/nodes/Attic/freefuncs.c,v 1.35 2000/02/15 03:37:08 thomas Exp $
+ * $Header: /cvsroot/pgsql/src/backend/nodes/Attic/freefuncs.c,v 1.36 2000/02/15 20:49:09 tgl Exp $
*
*-------------------------------------------------------------------------
*/
@@ -730,10 +730,11 @@ _freeRelOptInfo(RelOptInfo *node)
freeObject(node->targetlist);
freeObject(node->pathlist);
- /* XXX is this right? cheapestpath will typically be a pointer into
- * pathlist, won't it?
+ /* XXX is this right? cheapest-path fields will typically be pointers
+ * into pathlist, not separate structs...
*/
- freeObject(node->cheapestpath);
+ freeObject(node->cheapest_startup_path);
+ freeObject(node->cheapest_total_path);
freeObject(node->baserestrictinfo);
freeObject(node->joininfo);
@@ -1013,8 +1014,7 @@ _freeRangeTblEntry(RangeTblEntry *node)
{
if (node->relname)
pfree(node->relname);
- if (node->ref)
- freeObject(node->ref);
+ freeObject(node->ref);
pfree(node);
}
@@ -1024,8 +1024,7 @@ _freeAttr(Attr *node)
{
if (node->relname)
pfree(node->relname);
- if (node->attrs)
- freeObject(node->attrs);
+ freeObject(node->attrs);
pfree(node);
}
@@ -1346,10 +1345,3 @@ freeObject(void *node)
break;
}
}
-
-
-
-
-
-
-
diff --git a/src/backend/nodes/outfuncs.c b/src/backend/nodes/outfuncs.c
index e4c35cc277fb9a4850e8b0ad2fbe69db9b4b3f2e..c40ca9ff9cbdf1e1a8afc969dbbde086477824cc 100644
--- a/src/backend/nodes/outfuncs.c
+++ b/src/backend/nodes/outfuncs.c
@@ -6,7 +6,7 @@
* Portions Copyright (c) 1996-2000, PostgreSQL, Inc
* Portions Copyright (c) 1994, Regents of the University of California
*
- * $Header: /cvsroot/pgsql/src/backend/nodes/outfuncs.c,v 1.107 2000/02/15 03:37:09 thomas Exp $
+ * $Header: /cvsroot/pgsql/src/backend/nodes/outfuncs.c,v 1.108 2000/02/15 20:49:09 tgl Exp $
*
* NOTES
* Every (plan) node in POSTGRES has an associated "out" routine which
@@ -321,8 +321,9 @@ static void
_outPlanInfo(StringInfo str, Plan *node)
{
appendStringInfo(str,
- ":cost %g :rows %.0f :width %d :state %s :qptargetlist ",
- node->cost,
+ ":startup_cost %.2f :total_cost %.2f :rows %.0f :width %d :state %s :qptargetlist ",
+ node->startup_cost,
+ node->total_cost,
node->plan_rows,
node->plan_width,
node->state ? "not-NULL" : "<>");
@@ -908,15 +909,13 @@ _outRelOptInfo(StringInfo str, RelOptInfo *node)
appendStringInfo(str, " :pathlist ");
_outNode(str, node->pathlist);
- /*
- * Not sure if these are nodes or not. They're declared as struct
- * Path *. Since i don't know, i'll just print the addresses for now.
- * This can be changed later, if necessary.
- */
+ appendStringInfo(str, " :cheapest_startup_path ");
+ _outNode(str, node->cheapest_startup_path);
+ appendStringInfo(str, " :cheapest_total_path ");
+ _outNode(str, node->cheapest_total_path);
appendStringInfo(str,
- " :cheapestpath @ 0x%x :pruneable %s :baserestrictinfo ",
- (int) node->cheapestpath,
+ " :pruneable %s :baserestrictinfo ",
node->pruneable ? "true" : "false");
_outNode(str, node->baserestrictinfo);
@@ -977,9 +976,11 @@ _outRowMark(StringInfo str, RowMark *node)
static void
_outPath(StringInfo str, Path *node)
{
- appendStringInfo(str, " PATH :pathtype %d :cost %.2f :pathkeys ",
+ appendStringInfo(str,
+ " PATH :pathtype %d :startup_cost %.2f :total_cost %.2f :pathkeys ",
node->pathtype,
- node->path_cost);
+ node->startup_cost,
+ node->total_cost);
_outNode(str, node->pathkeys);
}
@@ -990,9 +991,10 @@ static void
_outIndexPath(StringInfo str, IndexPath *node)
{
appendStringInfo(str,
- " INDEXPATH :pathtype %d :cost %.2f :pathkeys ",
+ " INDEXPATH :pathtype %d :startup_cost %.2f :total_cost %.2f :pathkeys ",
node->path.pathtype,
- node->path.path_cost);
+ node->path.startup_cost,
+ node->path.total_cost);
_outNode(str, node->path.pathkeys);
appendStringInfo(str, " :indexid ");
@@ -1001,7 +1003,8 @@ _outIndexPath(StringInfo str, IndexPath *node)
appendStringInfo(str, " :indexqual ");
_outNode(str, node->indexqual);
- appendStringInfo(str, " :joinrelids ");
+ appendStringInfo(str, " :indexscandir %d :joinrelids ",
+ (int) node->indexscandir);
_outIntList(str, node->joinrelids);
}
@@ -1012,9 +1015,10 @@ static void
_outTidPath(StringInfo str, TidPath *node)
{
appendStringInfo(str,
- " TIDPATH :pathtype %d :cost %.2f :pathkeys ",
+ " TIDPATH :pathtype %d :startup_cost %.2f :total_cost %.2f :pathkeys ",
node->path.pathtype,
- node->path.path_cost);
+ node->path.startup_cost,
+ node->path.total_cost);
_outNode(str, node->path.pathkeys);
appendStringInfo(str, " :tideval ");
@@ -1031,9 +1035,10 @@ static void
_outNestPath(StringInfo str, NestPath *node)
{
appendStringInfo(str,
- " NESTPATH :pathtype %d :cost %.2f :pathkeys ",
+ " NESTPATH :pathtype %d :startup_cost %.2f :total_cost %.2f :pathkeys ",
node->path.pathtype,
- node->path.path_cost);
+ node->path.startup_cost,
+ node->path.total_cost);
_outNode(str, node->path.pathkeys);
appendStringInfo(str, " :outerjoinpath ");
_outNode(str, node->outerjoinpath);
@@ -1050,9 +1055,10 @@ static void
_outMergePath(StringInfo str, MergePath *node)
{
appendStringInfo(str,
- " MERGEPATH :pathtype %d :cost %.2f :pathkeys ",
+ " MERGEPATH :pathtype %d :startup_cost %.2f :total_cost %.2f :pathkeys ",
node->jpath.path.pathtype,
- node->jpath.path.path_cost);
+ node->jpath.path.startup_cost,
+ node->jpath.path.total_cost);
_outNode(str, node->jpath.path.pathkeys);
appendStringInfo(str, " :outerjoinpath ");
_outNode(str, node->jpath.outerjoinpath);
@@ -1078,9 +1084,10 @@ static void
_outHashPath(StringInfo str, HashPath *node)
{
appendStringInfo(str,
- " HASHPATH :pathtype %d :cost %.2f :pathkeys ",
+ " HASHPATH :pathtype %d :startup_cost %.2f :total_cost %.2f :pathkeys ",
node->jpath.path.pathtype,
- node->jpath.path.path_cost);
+ node->jpath.path.startup_cost,
+ node->jpath.path.total_cost);
_outNode(str, node->jpath.path.pathkeys);
appendStringInfo(str, " :outerjoinpath ");
_outNode(str, node->jpath.outerjoinpath);
@@ -1364,7 +1371,7 @@ _outNode(StringInfo str, void *obj)
return;
}
- if (nodeTag(obj) == T_List)
+ if (IsA(obj, List))
{
List *l;
@@ -1377,6 +1384,11 @@ _outNode(StringInfo str, void *obj)
}
appendStringInfoChar(str, ')');
}
+ else if (IsA_Value(obj))
+ {
+ /* nodeRead does not want to see { } around these! */
+ _outValue(str, obj);
+ }
else
{
appendStringInfoChar(str, '{');
@@ -1550,11 +1562,6 @@ _outNode(StringInfo str, void *obj)
case T_Stream:
_outStream(str, obj);
break;
- case T_Integer:
- case T_String:
- case T_Float:
- _outValue(str, obj);
- break;
case T_A_Expr:
_outAExpr(str, obj);
break;
diff --git a/src/backend/nodes/print.c b/src/backend/nodes/print.c
index a84b829950f5140d7991a3ab54deaae34434c576..248991c0928623d1e224c11159cb1d12dfa960bf 100644
--- a/src/backend/nodes/print.c
+++ b/src/backend/nodes/print.c
@@ -8,7 +8,7 @@
*
*
* IDENTIFICATION
- * $Header: /cvsroot/pgsql/src/backend/nodes/print.c,v 1.36 2000/02/15 03:37:09 thomas Exp $
+ * $Header: /cvsroot/pgsql/src/backend/nodes/print.c,v 1.37 2000/02/15 20:49:12 tgl Exp $
*
* HISTORY
* AUTHOR DATE MAJOR EVENT
@@ -175,9 +175,8 @@ print_expr(Node *expr, List *rtable)
{
rt = rt_fetch(var->varno, rtable);
relname = rt->relname;
- if (rt->ref)
- if (rt->ref->relname)
- relname = rt->relname; /* table renamed */
+ if (rt->ref && rt->ref->relname)
+ relname = rt->ref->relname; /* table renamed */
attname = get_attname(rt->relid, var->varattno);
}
break;
@@ -366,8 +365,9 @@ print_plan_recursive(Plan *p, Query *parsetree, int indentLevel, char *label)
return;
for (i = 0; i < indentLevel; i++)
printf(" ");
- printf("%s%s :c=%.4f :r=%.0f :w=%d ", label, plannode_type(p),
- p->cost, p->plan_rows, p->plan_width);
+ printf("%s%s :c=%.2f..%.2f :r=%.0f :w=%d ", label, plannode_type(p),
+ p->startup_cost, p->total_cost,
+ p->plan_rows, p->plan_width);
if (IsA(p, Scan) ||IsA(p, SeqScan))
{
RangeTblEntry *rte;
diff --git a/src/backend/nodes/readfuncs.c b/src/backend/nodes/readfuncs.c
index 7d56b603b85c1766676a8520a3ad8a2d7ff963e7..7d1e0b4cccf22ca551325c917bd9dce570baf099 100644
--- a/src/backend/nodes/readfuncs.c
+++ b/src/backend/nodes/readfuncs.c
@@ -8,7 +8,7 @@
*
*
* IDENTIFICATION
- * $Header: /cvsroot/pgsql/src/backend/nodes/readfuncs.c,v 1.83 2000/02/15 03:37:09 thomas Exp $
+ * $Header: /cvsroot/pgsql/src/backend/nodes/readfuncs.c,v 1.84 2000/02/15 20:49:12 tgl Exp $
*
* NOTES
* Most of the read functions for plan nodes are tested. (In fact, they
@@ -217,9 +217,13 @@ _getPlan(Plan *node)
char *token;
int length;
- token = lsptok(NULL, &length); /* first token is :cost */
+ token = lsptok(NULL, &length); /* first token is :startup_cost */
token = lsptok(NULL, &length); /* next is the actual cost */
- node->cost = (Cost) atof(token);
+ node->startup_cost = (Cost) atof(token);
+
+ token = lsptok(NULL, &length); /* skip the :total_cost */
+ token = lsptok(NULL, &length); /* next is the actual cost */
+ node->total_cost = (Cost) atof(token);
token = lsptok(NULL, &length); /* skip the :rows */
token = lsptok(NULL, &length); /* get the plan_rows */
@@ -520,7 +524,6 @@ _readIndexScan()
token = lsptok(NULL, &length); /* eat :indxorderdir */
token = lsptok(NULL, &length); /* get indxorderdir */
-
local_node->indxorderdir = atoi(token);
return local_node;
@@ -1275,18 +1278,15 @@ _readRelOptInfo()
token = lsptok(NULL, &length); /* get :pathlist */
local_node->pathlist = nodeRead(true); /* now read it */
- /*
- * Not sure if these are nodes or not. They're declared as struct
- * Path *. Since i don't know, i'll just print the addresses for now.
- * This can be changed later, if necessary.
- */
-
- token = lsptok(NULL, &length); /* get :cheapestpath */
- token = lsptok(NULL, &length); /* get @ */
- token = lsptok(NULL, &length); /* now read it */
+ token = lsptok(NULL, &length); /* get :cheapest_startup_path */
+ local_node->cheapest_startup_path = nodeRead(true); /* now read it */
- sscanf(token, "%x", (unsigned int *) &local_node->cheapestpath);
+ token = lsptok(NULL, &length); /* get :cheapest_total_path */
+ local_node->cheapest_total_path = nodeRead(true); /* now read it */
+ token = lsptok(NULL, &length); /* eat :pruneable */
+ token = lsptok(NULL, &length); /* get :pruneable */
+ local_node->pruneable = (token[0] == 't') ? true : false;
token = lsptok(NULL, &length); /* get :baserestrictinfo */
local_node->baserestrictinfo = nodeRead(true); /* now read it */
@@ -1322,29 +1322,6 @@ _readTargetEntry()
return local_node;
}
-static List *
-_readList()
-{
- List *local_node = NULL;
- char *token;
- int length;
-
- token = lsptok(NULL, &length); /* eat "(" */
- token = lsptok(NULL, &length); /* get "{" */
- while (strncmp(token, "{", length) == 0)
- {
- nconc(local_node, nodeRead(true));
-
- token = lsptok(NULL, &length); /* eat ")" */
- if (strncmp(token, "}", length) != 0)
- elog(ERROR, "badly formatted attribute list"
- " in planstring \"%.10s\"...\n", token);
- token = lsptok(NULL, &length); /* "{" or ")" */
- }
-
- return local_node;
-}
-
static Attr *
_readAttr()
{
@@ -1356,13 +1333,10 @@ _readAttr()
token = lsptok(NULL, &length); /* eat :relname */
token = lsptok(NULL, &length); /* get relname */
- if (length == 0)
- local_node->relname = pstrdup("");
- else
- local_node->relname = debackslash(token, length);
+ local_node->relname = debackslash(token, length);
token = lsptok(NULL, &length); /* eat :attrs */
- local_node->attrs = _readList();
+ local_node->attrs = nodeRead(true); /* now read it */
return local_node;
}
@@ -1388,7 +1362,7 @@ _readRangeTblEntry()
local_node->relname = debackslash(token, length);
token = lsptok(NULL, &length); /* eat :ref */
- local_node->ref = nodeRead(true);
+ local_node->ref = nodeRead(true); /* now read it */
token = lsptok(NULL, &length); /* eat :relid */
token = lsptok(NULL, &length); /* get :relid */
@@ -1450,9 +1424,13 @@ _readPath()
token = lsptok(NULL, &length); /* now read it */
local_node->pathtype = atol(token);
- token = lsptok(NULL, &length); /* get :cost */
+ token = lsptok(NULL, &length); /* get :startup_cost */
+ token = lsptok(NULL, &length); /* now read it */
+ local_node->startup_cost = (Cost) atof(token);
+
+ token = lsptok(NULL, &length); /* get :total_cost */
token = lsptok(NULL, &length); /* now read it */
- local_node->path_cost = (Cost) atof(token);
+ local_node->total_cost = (Cost) atof(token);
token = lsptok(NULL, &length); /* get :pathkeys */
local_node->pathkeys = nodeRead(true); /* now read it */
@@ -1479,9 +1457,13 @@ _readIndexPath()
token = lsptok(NULL, &length); /* now read it */
local_node->path.pathtype = atol(token);
- token = lsptok(NULL, &length); /* get :cost */
+ token = lsptok(NULL, &length); /* get :startup_cost */
token = lsptok(NULL, &length); /* now read it */
- local_node->path.path_cost = (Cost) atof(token);
+ local_node->path.startup_cost = (Cost) atof(token);
+
+ token = lsptok(NULL, &length); /* get :total_cost */
+ token = lsptok(NULL, &length); /* now read it */
+ local_node->path.total_cost = (Cost) atof(token);
token = lsptok(NULL, &length); /* get :pathkeys */
local_node->path.pathkeys = nodeRead(true); /* now read it */
@@ -1492,6 +1474,10 @@ _readIndexPath()
token = lsptok(NULL, &length); /* get :indexqual */
local_node->indexqual = nodeRead(true); /* now read it */
+ token = lsptok(NULL, &length); /* get :indexscandir */
+ token = lsptok(NULL, &length); /* now read it */
+ local_node->indexscandir = (ScanDirection) atoi(token);
+
token = lsptok(NULL, &length); /* get :joinrelids */
local_node->joinrelids = toIntList(nodeRead(true));
@@ -1517,9 +1503,13 @@ _readTidPath()
token = lsptok(NULL, &length); /* now read it */
local_node->path.pathtype = atol(token);
- token = lsptok(NULL, &length); /* get :cost */
+ token = lsptok(NULL, &length); /* get :startup_cost */
token = lsptok(NULL, &length); /* now read it */
- local_node->path.path_cost = (Cost) atof(token);
+ local_node->path.startup_cost = (Cost) atof(token);
+
+ token = lsptok(NULL, &length); /* get :total_cost */
+ token = lsptok(NULL, &length); /* now read it */
+ local_node->path.total_cost = (Cost) atof(token);
token = lsptok(NULL, &length); /* get :pathkeys */
local_node->path.pathkeys = nodeRead(true); /* now read it */
@@ -1552,9 +1542,13 @@ _readNestPath()
token = lsptok(NULL, &length); /* now read it */
local_node->path.pathtype = atol(token);
- token = lsptok(NULL, &length); /* get :cost */
+ token = lsptok(NULL, &length); /* get :startup_cost */
+ token = lsptok(NULL, &length); /* now read it */
+ local_node->path.startup_cost = (Cost) atof(token);
+
+ token = lsptok(NULL, &length); /* get :total_cost */
token = lsptok(NULL, &length); /* now read it */
- local_node->path.path_cost = (Cost) atof(token);
+ local_node->path.total_cost = (Cost) atof(token);
token = lsptok(NULL, &length); /* get :pathkeys */
local_node->path.pathkeys = nodeRead(true); /* now read it */
@@ -1588,13 +1582,15 @@ _readMergePath()
token = lsptok(NULL, &length); /* get :pathtype */
token = lsptok(NULL, &length); /* now read it */
-
local_node->jpath.path.pathtype = atol(token);
- token = lsptok(NULL, &length); /* get :cost */
+ token = lsptok(NULL, &length); /* get :startup_cost */
token = lsptok(NULL, &length); /* now read it */
+ local_node->jpath.path.startup_cost = (Cost) atof(token);
- local_node->jpath.path.path_cost = (Cost) atof(token);
+ token = lsptok(NULL, &length); /* get :total_cost */
+ token = lsptok(NULL, &length); /* now read it */
+ local_node->jpath.path.total_cost = (Cost) atof(token);
token = lsptok(NULL, &length); /* get :pathkeys */
local_node->jpath.path.pathkeys = nodeRead(true); /* now read it */
@@ -1637,13 +1633,15 @@ _readHashPath()
token = lsptok(NULL, &length); /* get :pathtype */
token = lsptok(NULL, &length); /* now read it */
-
local_node->jpath.path.pathtype = atol(token);
- token = lsptok(NULL, &length); /* get :cost */
+ token = lsptok(NULL, &length); /* get :startup_cost */
token = lsptok(NULL, &length); /* now read it */
+ local_node->jpath.path.startup_cost = (Cost) atof(token);
- local_node->jpath.path.path_cost = (Cost) atof(token);
+ token = lsptok(NULL, &length); /* get :total_cost */
+ token = lsptok(NULL, &length); /* now read it */
+ local_node->jpath.path.total_cost = (Cost) atof(token);
token = lsptok(NULL, &length); /* get :pathkeys */
local_node->jpath.path.pathkeys = nodeRead(true); /* now read it */
@@ -1886,14 +1884,6 @@ parsePlanString(void)
return_value = _readCaseWhen();
else if (length == 7 && strncmp(token, "ROWMARK", length) == 0)
return_value = _readRowMark();
-#if 0
- else if (length == 1 && strncmp(token, "{", length) == 0)
- {
- /* raw list (of strings?) found in Attr structure - thomas 2000-02-09 */
- return_value = nodeRead(true);
- token = lsptok(NULL, &length); /* eat trailing brace */
- }
-#endif
else
elog(ERROR, "badly formatted planstring \"%.10s\"...\n", token);
diff --git a/src/backend/optimizer/README b/src/backend/optimizer/README
index bbc1204395a8555fbe0f30b10b4fcf56f1386b2b..6ca70a91f1d3d931780a4b7028da85e0cdb64758 100644
--- a/src/backend/optimizer/README
+++ b/src/backend/optimizer/README
@@ -122,7 +122,7 @@ among other choices. Although the jointree scanning code produces these
potential join combinations one at a time, all the ways to produce the
same set of joined base rels will share the same RelOptInfo, so the paths
produced from different join combinations that produce equivalent joinrels
-will compete in add_pathlist.
+will compete in add_path.
Once we have built the final join rel, we use either the cheapest path
for it or the cheapest path with the desired ordering (if that's cheaper
diff --git a/src/backend/optimizer/geqo/geqo_eval.c b/src/backend/optimizer/geqo/geqo_eval.c
index 614ca47c84d5c8f37b99e65c301646469e47d5c9..1c70e4bcd8d274d591cafe67f96774912052a6e7 100644
--- a/src/backend/optimizer/geqo/geqo_eval.c
+++ b/src/backend/optimizer/geqo/geqo_eval.c
@@ -6,7 +6,7 @@
* Portions Copyright (c) 1996-2000, PostgreSQL, Inc
* Portions Copyright (c) 1994, Regents of the University of California
*
- * $Id: geqo_eval.c,v 1.47 2000/02/07 04:40:58 tgl Exp $
+ * $Id: geqo_eval.c,v 1.48 2000/02/15 20:49:14 tgl Exp $
*
*-------------------------------------------------------------------------
*/
@@ -96,8 +96,13 @@ geqo_eval(Query *root, Gene *tour, int num_gene)
/* construct the best path for the given combination of relations */
joinrel = gimme_tree(root, tour, 0, num_gene, NULL);
- /* compute fitness */
- fitness = joinrel->cheapestpath->path_cost;
+ /*
+ * compute fitness
+ *
+ * XXX geqo does not currently support optimization for partial
+ * result retrieval --- how to fix?
+ */
+ fitness = joinrel->cheapest_total_path->total_cost;
/* restore join_rel_list */
root->join_rel_list = savelist;
@@ -155,8 +160,8 @@ gimme_tree(Query *root, Gene *tour, int rel_count, int num_gene, RelOptInfo *old
rel_count++;
Assert(length(new_rel->relids) == rel_count);
- /* Find and save the cheapest path for this rel */
- set_cheapest(new_rel, new_rel->pathlist);
+ /* Find and save the cheapest paths for this rel */
+ set_cheapest(new_rel);
return gimme_tree(root, tour, rel_count, num_gene, new_rel);
}
diff --git a/src/backend/optimizer/geqo/geqo_misc.c b/src/backend/optimizer/geqo/geqo_misc.c
index 849c739f2ddd64c0b811289a460bf7bc929a44ff..01ced310e1b48d4dc9e2c8865670224cb5590b59 100644
--- a/src/backend/optimizer/geqo/geqo_misc.c
+++ b/src/backend/optimizer/geqo/geqo_misc.c
@@ -6,7 +6,7 @@
* Portions Copyright (c) 1996-2000, PostgreSQL, Inc
* Portions Copyright (c) 1994, Regents of the University of California
*
- * $Id: geqo_misc.c,v 1.27 2000/02/07 04:40:58 tgl Exp $
+ * $Id: geqo_misc.c,v 1.28 2000/02/15 20:49:14 tgl Exp $
*
*-------------------------------------------------------------------------
*/
@@ -179,8 +179,9 @@ geqo_print_path(Query *root, Path *path, int indent)
if (join)
{
jp = (JoinPath *) path;
- printf("%s rows=%.0f cost=%f\n",
- ptype, path->parent->rows, path->path_cost);
+ printf("%s rows=%.0f cost=%.2f..%.2f\n",
+ ptype, path->parent->rows,
+ path->startup_cost, path->total_cost);
switch (nodeTag(path))
{
case T_MergePath:
@@ -215,8 +216,9 @@ geqo_print_path(Query *root, Path *path, int indent)
{
int relid = lfirsti(path->parent->relids);
- printf("%s(%d) rows=%.0f cost=%f\n",
- ptype, relid, path->parent->rows, path->path_cost);
+ printf("%s(%d) rows=%.0f cost=%.2f..%.2f\n",
+ ptype, relid, path->parent->rows,
+ path->startup_cost, path->total_cost);
if (IsA(path, IndexPath))
{
@@ -241,6 +243,9 @@ geqo_print_rel(Query *root, RelOptInfo *rel)
foreach(l, rel->pathlist)
geqo_print_path(root, lfirst(l), 1);
- printf("\tcheapest path:\n");
- geqo_print_path(root, rel->cheapestpath, 1);
+ printf("\tcheapest startup path:\n");
+ geqo_print_path(root, rel->cheapest_startup_path, 1);
+
+ printf("\tcheapest total path:\n");
+ geqo_print_path(root, rel->cheapest_total_path, 1);
}
diff --git a/src/backend/optimizer/path/allpaths.c b/src/backend/optimizer/path/allpaths.c
index 52c30f7d01dd3210fed2127b033a89dd2a04f3c3..572ef00d2e8f2f6b61c215edb25c675cd4d41c76 100644
--- a/src/backend/optimizer/path/allpaths.c
+++ b/src/backend/optimizer/path/allpaths.c
@@ -8,7 +8,7 @@
*
*
* IDENTIFICATION
- * $Header: /cvsroot/pgsql/src/backend/optimizer/path/allpaths.c,v 1.58 2000/02/07 04:40:59 tgl Exp $
+ * $Header: /cvsroot/pgsql/src/backend/optimizer/path/allpaths.c,v 1.59 2000/02/15 20:49:16 tgl Exp $
*
*-------------------------------------------------------------------------
*/
@@ -100,7 +100,7 @@ set_base_rel_pathlist(Query *root)
/*
* Generate paths and add them to the rel's pathlist.
*
- * add_path/add_pathlist will discard any paths that are dominated
+ * Note: add_path() will discard any paths that are dominated
* by another available path, keeping only those paths that are
* superior along at least one dimension of cost or sortedness.
*/
@@ -109,24 +109,21 @@ set_base_rel_pathlist(Query *root)
add_path(rel, create_seqscan_path(rel));
/* Consider TID scans */
- add_pathlist(rel, create_tidscan_paths(root, rel));
+ create_tidscan_paths(root, rel);
/* Consider index paths for both simple and OR index clauses */
- add_pathlist(rel, create_index_paths(root,
- rel,
- indices,
- rel->baserestrictinfo,
- rel->joininfo));
+ create_index_paths(root, rel, indices,
+ rel->baserestrictinfo,
+ rel->joininfo);
/* Note: create_or_index_paths depends on create_index_paths
* to have marked OR restriction clauses with relevant indices;
- * this is why it doesn't need to be given the full list of indices.
+ * this is why it doesn't need to be given the list of indices.
*/
- add_pathlist(rel, create_or_index_paths(root, rel,
- rel->baserestrictinfo));
+ create_or_index_paths(root, rel, rel->baserestrictinfo);
/* Now find the cheapest of the paths for this rel */
- set_cheapest(rel, rel->pathlist);
+ set_cheapest(rel);
}
}
@@ -196,8 +193,8 @@ make_one_rel_by_joins(Query *root, int levels_needed)
xfunc_trypullup(rel);
#endif
- /* Find and save the cheapest path for this rel */
- set_cheapest(rel, rel->pathlist);
+ /* Find and save the cheapest paths for this rel */
+ set_cheapest(rel);
#ifdef OPTIMIZER_DEBUG
debug_print_rel(root, rel);
@@ -279,15 +276,26 @@ print_path(Query *root, Path *path, int indent)
if (join)
{
jp = (JoinPath *) path;
- printf("%s rows=%.0f cost=%f\n",
- ptype, path->parent->rows, path->path_cost);
+
+ printf("%s rows=%.0f cost=%.2f..%.2f\n",
+ ptype, path->parent->rows,
+ path->startup_cost, path->total_cost);
+
+ if (path->pathkeys)
+ {
+ for (i = 0; i < indent; i++)
+ printf("\t");
+ printf(" pathkeys=");
+ print_pathkeys(path->pathkeys, root->rtable);
+ }
+
switch (nodeTag(path))
{
case T_MergePath:
case T_HashPath:
- for (i = 0; i < indent + 1; i++)
+ for (i = 0; i < indent; i++)
printf("\t");
- printf(" clauses=(");
+ printf(" clauses=(");
print_joinclauses(root, jp->joinrestrictinfo);
printf(")\n");
@@ -297,9 +305,9 @@ print_path(Query *root, Path *path, int indent)
if (mp->outersortkeys || mp->innersortkeys)
{
- for (i = 0; i < indent + 1; i++)
+ for (i = 0; i < indent; i++)
printf("\t");
- printf(" sortouter=%d sortinner=%d\n",
+ printf(" sortouter=%d sortinner=%d\n",
((mp->outersortkeys) ? 1 : 0),
((mp->innersortkeys) ? 1 : 0));
}
@@ -315,11 +323,14 @@ print_path(Query *root, Path *path, int indent)
{
int relid = lfirsti(path->parent->relids);
- printf("%s(%d) rows=%.0f cost=%f\n",
- ptype, relid, path->parent->rows, path->path_cost);
+ printf("%s(%d) rows=%.0f cost=%.2f..%.2f\n",
+ ptype, relid, path->parent->rows,
+ path->startup_cost, path->total_cost);
- if (IsA(path, IndexPath))
+ if (path->pathkeys)
{
+ for (i = 0; i < indent; i++)
+ printf("\t");
printf(" pathkeys=");
print_pathkeys(path->pathkeys, root->rtable);
}
@@ -339,8 +350,10 @@ debug_print_rel(Query *root, RelOptInfo *rel)
printf("\tpath list:\n");
foreach(l, rel->pathlist)
print_path(root, lfirst(l), 1);
- printf("\tcheapest path:\n");
- print_path(root, rel->cheapestpath, 1);
+ printf("\tcheapest startup path:\n");
+ print_path(root, rel->cheapest_startup_path, 1);
+ printf("\tcheapest total path:\n");
+ print_path(root, rel->cheapest_total_path, 1);
}
#endif /* OPTIMIZER_DEBUG */
diff --git a/src/backend/optimizer/path/costsize.c b/src/backend/optimizer/path/costsize.c
index 7c8d4b63c07f5e5bfd470a41abb8078dda962f9a..c14692d5b97edfe9bbe1ff69ba83a14a92b3f7ea 100644
--- a/src/backend/optimizer/path/costsize.c
+++ b/src/backend/optimizer/path/costsize.c
@@ -3,23 +3,46 @@
* costsize.c
* Routines to compute (and set) relation sizes and path costs
*
- * Path costs are measured in units of disk accesses: one page fetch
- * has cost 1. The other primitive unit is the CPU time required to
- * process one tuple, which we set at "cpu_page_weight" of a page
- * fetch. Obviously, the CPU time per tuple depends on the query
- * involved, but the relative CPU and disk speeds of a given platform
- * are so variable that we are lucky if we can get useful numbers
- * at all. cpu_page_weight is user-settable, in case a particular
- * user is clueful enough to have a better-than-default estimate
- * of the ratio for his platform. There is also cpu_index_page_weight,
- * the cost to process a tuple of an index during an index scan.
+ * Path costs are measured in units of disk accesses: one sequential page
+ * fetch has cost 1. All else is scaled relative to a page fetch, using
+ * the scaling parameters
+ *
+ * random_page_cost Cost of a non-sequential page fetch
+ * cpu_tuple_cost Cost of typical CPU time to process a tuple
+ * cpu_index_tuple_cost Cost of typical CPU time to process an index tuple
+ * cpu_operator_cost Cost of CPU time to process a typical WHERE operator
+ *
+ * We also use a rough estimate "effective_cache_size" of the number of
+ * disk pages in Postgres + OS-level disk cache. (We can't simply use
+ * NBuffers for this purpose because that would ignore the effects of
+ * the kernel's disk cache.)
+ *
+ * Obviously, taking constants for these values is an oversimplification,
+ * but it's tough enough to get any useful estimates even at this level of
+ * detail. Note that all of these parameters are user-settable, in case
+ * the default values are drastically off for a particular platform.
+ *
+ * We compute two separate costs for each path:
+ * total_cost: total estimated cost to fetch all tuples
+ * startup_cost: cost that is expended before first tuple is fetched
+ * In some scenarios, such as when there is a LIMIT or we are implementing
+ * an EXISTS(...) sub-select, it is not necessary to fetch all tuples of the
+ * path's result. A caller can estimate the cost of fetching a partial
+ * result by interpolating between startup_cost and total_cost. In detail:
+ * actual_cost = startup_cost +
+ * (total_cost - startup_cost) * tuples_to_fetch / path->parent->rows;
+ * Note that a relation's rows count (and, by extension, a Plan's plan_rows)
+ * are set without regard to any LIMIT, so that this equation works properly.
+ * (Also, these routines guarantee not to set the rows count to zero, so there
+ * will be no zero divide.) RelOptInfos, Paths, and Plans themselves never
+ * account for LIMIT.
*
*
* Portions Copyright (c) 1996-2000, PostgreSQL, Inc
* Portions Copyright (c) 1994, Regents of the University of California
*
* IDENTIFICATION
- * $Header: /cvsroot/pgsql/src/backend/optimizer/path/costsize.c,v 1.51 2000/02/07 04:40:59 tgl Exp $
+ * $Header: /cvsroot/pgsql/src/backend/optimizer/path/costsize.c,v 1.52 2000/02/15 20:49:16 tgl Exp $
*
*-------------------------------------------------------------------------
*/
@@ -27,26 +50,25 @@
#include "postgres.h"
#include <math.h>
-#ifdef HAVE_LIMITS_H
-#include <limits.h>
-#ifndef MAXINT
-#define MAXINT INT_MAX
-#endif
-#else
-#ifdef HAVE_VALUES_H
-#include <values.h>
-#endif
-#endif
#include "miscadmin.h"
+#include "nodes/plannodes.h"
+#include "optimizer/clauses.h"
#include "optimizer/cost.h"
#include "optimizer/internal.h"
#include "optimizer/tlist.h"
#include "utils/lsyscache.h"
-Cost cpu_page_weight = CPU_PAGE_WEIGHT;
-Cost cpu_index_page_weight = CPU_INDEX_PAGE_WEIGHT;
+#define LOG2(x) (log(x) / 0.693147180559945)
+#define LOG6(x) (log(x) / 1.79175946922805)
+
+
+double effective_cache_size = DEFAULT_EFFECTIVE_CACHE_SIZE;
+Cost random_page_cost = DEFAULT_RANDOM_PAGE_COST;
+Cost cpu_tuple_cost = DEFAULT_CPU_TUPLE_COST;
+Cost cpu_index_tuple_cost = DEFAULT_CPU_INDEX_TUPLE_COST;
+Cost cpu_operator_cost = DEFAULT_CPU_OPERATOR_COST;
Cost disable_cost = 100000000.0;
@@ -59,53 +81,114 @@ bool enable_mergejoin = true;
bool enable_hashjoin = true;
+static bool cost_qual_eval_walker(Node *node, Cost *total);
static void set_rel_width(Query *root, RelOptInfo *rel);
static int compute_attribute_width(TargetEntry *tlistentry);
static double relation_byte_size(double tuples, int width);
static double page_size(double tuples, int width);
-static double base_log(double x, double b);
/*
* cost_seqscan
* Determines and returns the cost of scanning a relation sequentially.
- * If the relation is a temporary to be materialized from a query
- * embedded within a data field (determined by 'relid' containing an
- * attribute reference), then a predetermined constant is returned (we
- * have NO IDEA how big the result of a POSTQUEL procedure is going to
- * be).
- *
- * disk = p
- * cpu = CPU-PAGE-WEIGHT * t
+ *
+ * If the relation is a temporary to be materialized from a query
+ * embedded within a data field (determined by 'relid' containing an
+ * attribute reference), then a predetermined constant is returned (we
+ * have NO IDEA how big the result of a POSTQUEL procedure is going to be).
+ *
+ * Note: for historical reasons, this routine and the others in this module
+ * use the passed result Path only to store their startup_cost and total_cost
+ * results into. All the input data they need is passed as separate
+ * parameters, even though much of it could be extracted from the result Path.
*/
-Cost
-cost_seqscan(RelOptInfo *baserel)
+void
+cost_seqscan(Path *path, RelOptInfo *baserel)
{
- Cost temp = 0;
+ Cost startup_cost = 0;
+ Cost run_cost = 0;
+ Cost cpu_per_tuple;
/* Should only be applied to base relations */
Assert(length(baserel->relids) == 1);
if (!enable_seqscan)
- temp += disable_cost;
+ startup_cost += disable_cost;
+ /* disk costs */
if (lfirsti(baserel->relids) < 0)
{
/*
* cost of sequentially scanning a materialized temporary relation
*/
- temp += _NONAME_SCAN_COST_;
+ run_cost += _NONAME_SCAN_COST_;
}
else
{
- temp += baserel->pages;
- temp += cpu_page_weight * baserel->tuples;
+ /*
+ * The cost of reading a page sequentially is 1.0, by definition.
+ * Note that the Unix kernel will typically do some amount of
+ * read-ahead optimization, so that this cost is less than the true
+ * cost of reading a page from disk. We ignore that issue here,
+ * but must take it into account when estimating the cost of
+ * non-sequential accesses!
+ */
+ run_cost += baserel->pages; /* sequential fetches with cost 1.0 */
}
- Assert(temp >= 0);
- return temp;
+ /* CPU costs */
+ cpu_per_tuple = cpu_tuple_cost + baserel->baserestrictcost;
+ run_cost += cpu_per_tuple * baserel->tuples;
+
+ path->startup_cost = startup_cost;
+ path->total_cost = startup_cost + run_cost;
}
+/*
+ * cost_nonsequential_access
+ * Estimate the cost of accessing one page at random from a relation
+ * (or sort temp file) of the given size in pages.
+ *
+ * The simplistic model that the cost is random_page_cost is what we want
+ * to use for large relations; but for small ones that is a serious
+ * overestimate because of the effects of caching. This routine tries to
+ * account for that.
+ *
+ * Unfortunately we don't have any good way of estimating the effective cache
+ * size we are working with --- we know that Postgres itself has NBuffers
+ * internal buffers, but the size of the kernel's disk cache is uncertain,
+ * and how much of it we get to use is even less certain. We punt the problem
+ * for now by assuming we are given an effective_cache_size parameter.
+ *
+ * Given a guesstimated cache size, we estimate the actual I/O cost per page
+ * with the entirely ad-hoc equations:
+ * for rel_size <= effective_cache_size:
+ * 1 + (random_page_cost/2-1) * (rel_size/effective_cache_size) ** 2
+ * for rel_size >= effective_cache_size:
+ * random_page_cost * (1 - (effective_cache_size/rel_size)/2)
+ * These give the right asymptotic behavior (=> 1.0 as rel_size becomes
+ * small, => random_page_cost as it becomes large) and meet in the middle
+ * with the estimate that the cache is about 50% effective for a relation
+ * of the same size as effective_cache_size. (XXX this is probably all
+ * wrong, but I haven't been able to find any theory about how effective
+ * a disk cache should be presumed to be.)
+ */
+static Cost
+cost_nonsequential_access(double relpages)
+{
+ double relsize;
+
+ /* don't crash on bad input data */
+ if (relpages <= 0.0 || effective_cache_size <= 0.0)
+ return random_page_cost;
+
+ relsize = relpages / effective_cache_size;
+
+ if (relsize >= 1.0)
+ return random_page_cost * (1.0 - 0.5 / relsize);
+ else
+ return 1.0 + (random_page_cost * 0.5 - 1.0) * relsize * relsize;
+}
/*
* cost_index
@@ -126,25 +209,28 @@ cost_seqscan(RelOptInfo *baserel)
* tuples, but they won't reduce the number of tuples we have to fetch from
* the table, so they don't reduce the scan cost.
*/
-Cost
-cost_index(Query *root,
+void
+cost_index(Path *path, Query *root,
RelOptInfo *baserel,
IndexOptInfo *index,
List *indexQuals,
bool is_injoin)
{
- Cost temp = 0;
- Cost indexAccessCost;
+ Cost startup_cost = 0;
+ Cost run_cost = 0;
+ Cost cpu_per_tuple;
+ Cost indexStartupCost;
+ Cost indexTotalCost;
Selectivity indexSelectivity;
- double reltuples;
- double relpages;
+ double tuples_fetched;
+ double pages_fetched;
/* Should only be applied to base relations */
Assert(IsA(baserel, RelOptInfo) && IsA(index, IndexOptInfo));
Assert(length(baserel->relids) == 1);
if (!enable_indexscan && !is_injoin)
- temp += disable_cost;
+ startup_cost += disable_cost;
/*
* Call index-access-method-specific code to estimate the processing
@@ -152,31 +238,21 @@ cost_index(Query *root,
* (ie, the fraction of main-table tuples we will have to retrieve).
*/
fmgr(index->amcostestimate, root, baserel, index, indexQuals,
- &indexAccessCost, &indexSelectivity);
+ &indexStartupCost, &indexTotalCost, &indexSelectivity);
/* all costs for touching index itself included here */
- temp += indexAccessCost;
+ startup_cost += indexStartupCost;
+ run_cost += indexTotalCost - indexStartupCost;
- /*--------------------
- * Estimate number of main-table tuples and pages touched.
- *
- * Worst case is that each tuple the index tells us to fetch comes
- * from a different base-rel page, in which case the I/O cost would be
- * 'reltuples' pages. In practice we can expect the number of page
- * fetches to be reduced by the buffer cache, because more than one
- * tuple can be retrieved per page fetched. Currently, we estimate
- * the number of pages to be retrieved as
- * MIN(reltuples, relpages)
- * This amounts to assuming that the buffer cache is perfectly efficient
- * and never ends up reading the same page twice within one scan, which
- * of course is too optimistic. On the other hand, we are assuming that
- * the target tuples are perfectly uniformly distributed across the
- * relation's pages, which is too pessimistic --- any nonuniformity of
- * distribution will reduce the number of pages we have to fetch.
- * So, we guess-and-hope that these sources of error will more or less
- * balance out.
+ /*
+ * Estimate number of main-table tuples and pages fetched.
*
- * XXX need to add a penalty for nonsequential page fetches.
+ * If the number of tuples is much smaller than the number of pages in
+ * the relation, each tuple will cost a separate nonsequential fetch.
+ * If it is comparable or larger, then probably we will be able to avoid
+ * some fetches. We use a growth rate of log(#tuples/#pages + 1) ---
+ * probably totally bogus, but intuitively it gives the right shape of
+ * curve at least.
*
* XXX if the relation has recently been "clustered" using this index,
* then in fact the target tuples will be highly nonuniformly distributed,
@@ -184,54 +260,77 @@ cost_index(Query *root,
* have no way to know whether the relation has been clustered, nor how
* much it's been modified since the last clustering, so we ignore this
* effect. Would be nice to do better someday.
- *--------------------
*/
- reltuples = indexSelectivity * baserel->tuples;
+ tuples_fetched = indexSelectivity * baserel->tuples;
- relpages = reltuples;
- if (baserel->pages > 0 && baserel->pages < relpages)
- relpages = baserel->pages;
+ if (tuples_fetched > 0 && baserel->pages > 0)
+ pages_fetched = baserel->pages *
+ log(tuples_fetched / baserel->pages + 1.0);
+ else
+ pages_fetched = tuples_fetched;
+
+ /*
+ * Now estimate one nonsequential access per page fetched,
+ * plus appropriate CPU costs per tuple.
+ */
/* disk costs for main table */
- temp += relpages;
+ run_cost += pages_fetched * cost_nonsequential_access(baserel->pages);
- /* CPU costs for heap tuples */
- temp += cpu_page_weight * reltuples;
+ /* CPU costs */
+ cpu_per_tuple = cpu_tuple_cost + baserel->baserestrictcost;
+ /*
+ * Assume that the indexquals will be removed from the list of
+ * restriction clauses that we actually have to evaluate as qpquals.
+ * This is not completely right, but it's close.
+ * For a lossy index, however, we will have to recheck all the quals.
+ */
+ if (! index->lossy)
+ cpu_per_tuple -= cost_qual_eval(indexQuals);
- Assert(temp >= 0);
- return temp;
+ run_cost += cpu_per_tuple * tuples_fetched;
+
+ path->startup_cost = startup_cost;
+ path->total_cost = startup_cost + run_cost;
}
/*
* cost_tidscan
* Determines and returns the cost of scanning a relation using tid-s.
- *
- * disk = number of tids
- * cpu = CPU-PAGE-WEIGHT * number_of_tids
*/
-Cost
-cost_tidscan(RelOptInfo *baserel, List *tideval)
+void
+cost_tidscan(Path *path, RelOptInfo *baserel, List *tideval)
{
- Cost temp = 0;
+ Cost startup_cost = 0;
+ Cost run_cost = 0;
+ Cost cpu_per_tuple;
+ int ntuples = length(tideval);
if (!enable_tidscan)
- temp += disable_cost;
+ startup_cost += disable_cost;
- temp += (1.0 + cpu_page_weight) * length(tideval);
+ /* disk costs --- assume each tuple on a different page */
+ run_cost += random_page_cost * ntuples;
- return temp;
+ /* CPU costs */
+ cpu_per_tuple = cpu_tuple_cost + baserel->baserestrictcost;
+ run_cost += cpu_per_tuple * ntuples;
+
+ path->startup_cost = startup_cost;
+ path->total_cost = startup_cost + run_cost;
}
/*
* cost_sort
* Determines and returns the cost of sorting a relation.
*
+ * The cost of supplying the input data is NOT included; the caller should
+ * add that cost to both startup and total costs returned from this routine!
+ *
* If the total volume of data to sort is less than SortMem, we will do
* an in-memory sort, which requires no I/O and about t*log2(t) tuple
- * comparisons for t tuples. We use cpu_index_page_weight as the cost
- * of a tuple comparison (is this reasonable, or do we need another
- * basic parameter?).
+ * comparisons for t tuples.
*
* If the total volume exceeds SortMem, we switch to a tape-style merge
* algorithm. There will still be about t*log2(t) tuple comparisons in
@@ -240,8 +339,14 @@ cost_tidscan(RelOptInfo *baserel, List *tideval)
* number of initial runs formed (log6 because tuplesort.c uses six-tape
* merging). Since the average initial run should be about twice SortMem,
* we have
- * disk = 2 * p * ceil(log6(p / (2*SortMem)))
- * cpu = CPU-INDEX-PAGE-WEIGHT * t * log2(t)
+ * disk traffic = 2 * relsize * ceil(log6(p / (2*SortMem)))
+ * cpu = comparison_cost * t * log2(t)
+ *
+ * The disk traffic is assumed to be half sequential and half random
+ * accesses (XXX can't we refine that guess?)
+ *
+ * We charge two operator evals per tuple comparison, which should be in
+ * the right ballpark in most cases.
*
* 'pathkeys' is a list of sort keys
* 'tuples' is the number of tuples in the relation
@@ -252,15 +357,16 @@ cost_tidscan(RelOptInfo *baserel, List *tideval)
* currently do anything with pathkeys anyway, that doesn't matter...
* but if it ever does, it should react gracefully to lack of key data.
*/
-Cost
-cost_sort(List *pathkeys, double tuples, int width)
+void
+cost_sort(Path *path, List *pathkeys, double tuples, int width)
{
- Cost temp = 0;
+ Cost startup_cost = 0;
+ Cost run_cost = 0;
double nbytes = relation_byte_size(tuples, width);
long sortmembytes = SortMem * 1024L;
if (!enable_sort)
- temp += disable_cost;
+ startup_cost += disable_cost;
/*
* We want to be sure the cost of a sort is never estimated as zero,
@@ -270,42 +376,39 @@ cost_sort(List *pathkeys, double tuples, int width)
if (tuples < 2.0)
tuples = 2.0;
- temp += cpu_index_page_weight * tuples * base_log(tuples, 2.0);
+ /*
+ * CPU costs
+ *
+ * Assume about two operator evals per tuple comparison
+ * and N log2 N comparisons
+ */
+ startup_cost += 2.0 * cpu_operator_cost * tuples * LOG2(tuples);
+ /* disk costs */
if (nbytes > sortmembytes)
{
double npages = ceil(nbytes / BLCKSZ);
double nruns = nbytes / (sortmembytes * 2);
- double log_runs = ceil(base_log(nruns, 6.0));
+ double log_runs = ceil(LOG6(nruns));
+ double npageaccesses;
if (log_runs < 1.0)
log_runs = 1.0;
- temp += 2 * npages * log_runs;
+ npageaccesses = 2.0 * npages * log_runs;
+ /* Assume half are sequential (cost 1), half are not */
+ startup_cost += npageaccesses *
+ (1.0 + cost_nonsequential_access(npages)) * 0.5;
}
- Assert(temp > 0);
- return temp;
-}
-
-
-/*
- * cost_result
- * Determines and returns the cost of writing a relation of 'tuples'
- * tuples of 'width' bytes out to a result relation.
- */
-#ifdef NOT_USED
-Cost
-cost_result(double tuples, int width)
-{
- Cost temp = 0;
-
- temp += page_size(tuples, width);
- temp += cpu_page_weight * tuples;
- Assert(temp >= 0);
- return temp;
+ /*
+ * Note: should we bother to assign a nonzero run_cost to reflect the
+ * overhead of extracting tuples from the sort result? Probably not
+ * worth worrying about.
+ */
+ path->startup_cost = startup_cost;
+ path->total_cost = startup_cost + run_cost;
}
-#endif
/*
* cost_nestloop
@@ -314,23 +417,45 @@ cost_result(double tuples, int width)
*
* 'outer_path' is the path for the outer relation
* 'inner_path' is the path for the inner relation
+ * 'restrictlist' are the RestrictInfo nodes to be applied at the join
* 'is_indexjoin' is true if we are using an indexscan for the inner relation
+ * (not currently needed here; the indexscan adjusts its cost...)
*/
-Cost
-cost_nestloop(Path *outer_path,
+void
+cost_nestloop(Path *path,
+ Path *outer_path,
Path *inner_path,
+ List *restrictlist,
bool is_indexjoin)
{
- Cost temp = 0;
+ Cost startup_cost = 0;
+ Cost run_cost = 0;
+ Cost cpu_per_tuple;
+ double ntuples;
if (!enable_nestloop)
- temp += disable_cost;
+ startup_cost += disable_cost;
+
+ /* cost of source data */
+ /*
+ * NOTE: we assume that the inner path's startup_cost is paid once, not
+ * over again on each restart. This is certainly correct if the inner
+ * path is materialized. Are there any cases where it is wrong?
+ */
+ startup_cost += outer_path->startup_cost + inner_path->startup_cost;
+ run_cost += outer_path->total_cost - outer_path->startup_cost;
+ run_cost += outer_path->parent->rows *
+ (inner_path->total_cost - inner_path->startup_cost);
- temp += outer_path->path_cost;
- temp += outer_path->parent->rows * inner_path->path_cost;
+ /* number of tuples processed (not number emitted!) */
+ ntuples = outer_path->parent->rows * inner_path->parent->rows;
- Assert(temp >= 0);
- return temp;
+ /* CPU costs */
+ cpu_per_tuple = cpu_tuple_cost + cost_qual_eval(restrictlist);
+ run_cost += cpu_per_tuple * ntuples;
+
+ path->startup_cost = startup_cost;
+ path->total_cost = startup_cost + run_cost;
}
/*
@@ -340,33 +465,66 @@ cost_nestloop(Path *outer_path,
*
* 'outer_path' is the path for the outer relation
* 'inner_path' is the path for the inner relation
+ * 'restrictlist' are the RestrictInfo nodes to be applied at the join
* 'outersortkeys' and 'innersortkeys' are lists of the keys to be used
* to sort the outer and inner relations, or NIL if no explicit
* sort is needed because the source path is already ordered
*/
-Cost
-cost_mergejoin(Path *outer_path,
+void
+cost_mergejoin(Path *path,
+ Path *outer_path,
Path *inner_path,
+ List *restrictlist,
List *outersortkeys,
List *innersortkeys)
{
- Cost temp = 0;
+ Cost startup_cost = 0;
+ Cost run_cost = 0;
+ Cost cpu_per_tuple;
+ double ntuples;
+ Path sort_path; /* dummy for result of cost_sort */
if (!enable_mergejoin)
- temp += disable_cost;
+ startup_cost += disable_cost;
/* cost of source data */
- temp += outer_path->path_cost + inner_path->path_cost;
-
- if (outersortkeys) /* do we need to sort? */
- temp += cost_sort(outersortkeys,
- outer_path->parent->rows,
- outer_path->parent->width);
+ /*
+ * Note we are assuming that each source tuple is fetched just once,
+ * which is not right in the presence of equal keys. If we had a way of
+ * estimating the proportion of equal keys, we could apply a correction
+ * factor...
+ */
+ if (outersortkeys) /* do we need to sort outer? */
+ {
+ startup_cost += outer_path->total_cost;
+ cost_sort(&sort_path,
+ outersortkeys,
+ outer_path->parent->rows,
+ outer_path->parent->width);
+ startup_cost += sort_path.startup_cost;
+ run_cost += sort_path.total_cost - sort_path.startup_cost;
+ }
+ else
+ {
+ startup_cost += outer_path->startup_cost;
+ run_cost += outer_path->total_cost - outer_path->startup_cost;
+ }
- if (innersortkeys) /* do we need to sort? */
- temp += cost_sort(innersortkeys,
- inner_path->parent->rows,
- inner_path->parent->width);
+ if (innersortkeys) /* do we need to sort inner? */
+ {
+ startup_cost += inner_path->total_cost;
+ cost_sort(&sort_path,
+ innersortkeys,
+ inner_path->parent->rows,
+ inner_path->parent->width);
+ startup_cost += sort_path.startup_cost;
+ run_cost += sort_path.total_cost - sort_path.startup_cost;
+ }
+ else
+ {
+ startup_cost += inner_path->startup_cost;
+ run_cost += inner_path->total_cost - inner_path->startup_cost;
+ }
/*
* Estimate the number of tuples to be processed in the mergejoin itself
@@ -374,11 +532,14 @@ cost_mergejoin(Path *outer_path,
* underestimate if there are many equal-keyed tuples in either relation,
* but we have no good way of estimating that...
*/
- temp += cpu_page_weight * (outer_path->parent->rows +
- inner_path->parent->rows);
+ ntuples = outer_path->parent->rows + inner_path->parent->rows;
- Assert(temp >= 0);
- return temp;
+ /* CPU costs */
+ cpu_per_tuple = cpu_tuple_cost + cost_qual_eval(restrictlist);
+ run_cost += cpu_per_tuple * ntuples;
+
+ path->startup_cost = startup_cost;
+ path->total_cost = startup_cost + run_cost;
}
/*
@@ -388,15 +549,21 @@ cost_mergejoin(Path *outer_path,
*
* 'outer_path' is the path for the outer relation
* 'inner_path' is the path for the inner relation
+ * 'restrictlist' are the RestrictInfo nodes to be applied at the join
* 'innerdisbursion' is an estimate of the disbursion statistic
* for the inner hash key.
*/
-Cost
-cost_hashjoin(Path *outer_path,
+void
+cost_hashjoin(Path *path,
+ Path *outer_path,
Path *inner_path,
+ List *restrictlist,
Selectivity innerdisbursion)
{
- Cost temp = 0;
+ Cost startup_cost = 0;
+ Cost run_cost = 0;
+ Cost cpu_per_tuple;
+ double ntuples;
double outerbytes = relation_byte_size(outer_path->parent->rows,
outer_path->parent->width);
double innerbytes = relation_byte_size(inner_path->parent->rows,
@@ -404,48 +571,169 @@ cost_hashjoin(Path *outer_path,
long hashtablebytes = SortMem * 1024L;
if (!enable_hashjoin)
- temp += disable_cost;
+ startup_cost += disable_cost;
/* cost of source data */
- temp += outer_path->path_cost + inner_path->path_cost;
+ startup_cost += outer_path->startup_cost;
+ run_cost += outer_path->total_cost - outer_path->startup_cost;
+ startup_cost += inner_path->total_cost;
- /* cost of computing hash function: must do it once per tuple */
- temp += cpu_page_weight * (outer_path->parent->rows +
- inner_path->parent->rows);
+ /* cost of computing hash function: must do it once per input tuple */
+ startup_cost += cpu_operator_cost * inner_path->parent->rows;
+ run_cost += cpu_operator_cost * outer_path->parent->rows;
/* the number of tuple comparisons needed is the number of outer
* tuples times the typical hash bucket size, which we estimate
- * conservatively as the inner disbursion times the inner tuple
- * count. The cost per comparison is set at cpu_index_page_weight;
- * is that reasonable, or do we need another basic parameter?
+ * conservatively as the inner disbursion times the inner tuple count.
*/
- temp += cpu_index_page_weight * outer_path->parent->rows *
+ run_cost += cpu_operator_cost * outer_path->parent->rows *
(inner_path->parent->rows * innerdisbursion);
+ /*
+ * Estimate the number of tuples that get through the hashing filter
+ * as one per tuple in the two source relations. This could be a drastic
+ * underestimate if there are many equal-keyed tuples in either relation,
+ * but we have no good way of estimating that...
+ */
+ ntuples = outer_path->parent->rows + inner_path->parent->rows;
+
+ /* CPU costs */
+ cpu_per_tuple = cpu_tuple_cost + cost_qual_eval(restrictlist);
+ run_cost += cpu_per_tuple * ntuples;
+
/*
* if inner relation is too big then we will need to "batch" the join,
* which implies writing and reading most of the tuples to disk an
- * extra time. Charge one cost unit per page of I/O.
+ * extra time. Charge one cost unit per page of I/O (correct since
+ * it should be nice and sequential...). Writing the inner rel counts
+ * as startup cost, all the rest as run cost.
*/
if (innerbytes > hashtablebytes)
- temp += 2 * (page_size(outer_path->parent->rows,
- outer_path->parent->width) +
- page_size(inner_path->parent->rows,
- inner_path->parent->width));
+ {
+ double outerpages = page_size(outer_path->parent->rows,
+ outer_path->parent->width);
+ double innerpages = page_size(inner_path->parent->rows,
+ inner_path->parent->width);
+
+ startup_cost += innerpages;
+ run_cost += innerpages + 2 * outerpages;
+ }
/*
* Bias against putting larger relation on inside. We don't want
* an absolute prohibition, though, since larger relation might have
* better disbursion --- and we can't trust the size estimates
- * unreservedly, anyway.
+ * unreservedly, anyway. Instead, inflate the startup cost by
+ * the square root of the size ratio. (Why square root? No real good
+ * reason, but it seems reasonable...)
+ */
+ if (innerbytes > outerbytes && outerbytes > 0)
+ {
+ startup_cost *= sqrt(innerbytes / outerbytes);
+ }
+
+ path->startup_cost = startup_cost;
+ path->total_cost = startup_cost + run_cost;
+}
+
+
+/*
+ * cost_qual_eval
+ * Estimate the CPU cost of evaluating a WHERE clause (once).
+ * The input can be either an implicitly-ANDed list of boolean
+ * expressions, or a list of RestrictInfo nodes.
+ */
+Cost
+cost_qual_eval(List *quals)
+{
+ Cost total = 0;
+
+ cost_qual_eval_walker((Node *) quals, &total);
+ return total;
+}
+
+static bool
+cost_qual_eval_walker(Node *node, Cost *total)
+{
+ if (node == NULL)
+ 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.
+ *
+ * Should we try to account for the possibility of short-circuit
+ * evaluation of AND/OR?
*/
- if (innerbytes > outerbytes)
- temp *= 1.1; /* is this an OK fudge factor? */
+ if (IsA(node, Expr))
+ {
+ Expr *expr = (Expr *) node;
+
+ switch (expr->opType)
+ {
+ case OP_EXPR:
+ case FUNC_EXPR:
+ *total += cpu_operator_cost;
+ break;
+ case OR_EXPR:
+ case AND_EXPR:
+ case NOT_EXPR:
+ break;
+ case SUBPLAN_EXPR:
+ /*
+ * A subplan node in an expression indicates that the subplan
+ * will be executed on each evaluation, so charge accordingly.
+ * (We assume that sub-selects that can be executed as
+ * InitPlans have already been removed from the expression.)
+ *
+ * NOTE: this logic should agree with make_subplan in
+ * subselect.c.
+ */
+ {
+ SubPlan *subplan = (SubPlan *) expr->oper;
+ Plan *plan = subplan->plan;
+ Cost subcost;
+
+ if (subplan->sublink->subLinkType == EXISTS_SUBLINK)
+ {
+ /* we only need to fetch 1 tuple */
+ subcost = plan->startup_cost +
+ (plan->total_cost - plan->startup_cost) / plan->plan_rows;
+ }
+ else if (subplan->sublink->subLinkType == EXPR_SUBLINK)
+ {
+ /* assume we need all tuples */
+ subcost = plan->total_cost;
+ }
+ else
+ {
+ /* assume we need 50% of the tuples */
+ subcost = plan->startup_cost +
+ 0.50 * (plan->total_cost - plan->startup_cost);
+ }
+ *total += subcost;
+ }
+ break;
+ }
+ /* fall through to examine args of Expr node */
+ }
+ /*
+ * expression_tree_walker doesn't know what to do with RestrictInfo nodes,
+ * but we just want to recurse through them.
+ */
+ if (IsA(node, RestrictInfo))
+ {
+ RestrictInfo *restrictinfo = (RestrictInfo *) node;
- Assert(temp >= 0);
- return temp;
+ return cost_qual_eval_walker((Node *) restrictinfo->clause, total);
+ }
+ /* Otherwise, recurse. */
+ return expression_tree_walker(node, cost_qual_eval_walker,
+ (void *) total);
}
+
/*
* set_baserel_size_estimates
* Set the size estimates for the given base relation.
@@ -457,6 +745,7 @@ cost_hashjoin(Path *outer_path,
* rows: the estimated number of output tuples (after applying
* restriction clauses).
* width: the estimated average output tuple width in bytes.
+ * baserestrictcost: estimated cost of evaluating baserestrictinfo clauses.
*/
void
set_baserel_size_estimates(Query *root, RelOptInfo *rel)
@@ -468,7 +757,14 @@ set_baserel_size_estimates(Query *root, RelOptInfo *rel)
restrictlist_selectivity(root,
rel->baserestrictinfo,
lfirsti(rel->relids));
- Assert(rel->rows >= 0);
+ /*
+ * Force estimate to be at least one row, to make explain output look
+ * better and to avoid possible divide-by-zero when interpolating cost.
+ */
+ if (rel->rows < 1.0)
+ rel->rows = 1.0;
+
+ rel->baserestrictcost = cost_qual_eval(rel->baserestrictinfo);
set_rel_width(root, rel);
}
@@ -513,7 +809,12 @@ set_joinrel_size_estimates(Query *root, RelOptInfo *rel,
restrictlist,
0);
- Assert(temp >= 0);
+ /*
+ * Force estimate to be at least one row, to make explain output look
+ * better and to avoid possible divide-by-zero when interpolating cost.
+ */
+ if (temp < 1.0)
+ temp = 1.0;
rel->rows = temp;
/*
@@ -582,9 +883,3 @@ page_size(double tuples, int width)
{
return ceil(relation_byte_size(tuples, width) / BLCKSZ);
}
-
-static double
-base_log(double x, double b)
-{
- return log(x) / log(b);
-}
diff --git a/src/backend/optimizer/path/indxpath.c b/src/backend/optimizer/path/indxpath.c
index 4c2b0109bc02421b1b64b59f3d2b3ba2f2315818..edb16ce0d6d26620d9cfc9cba5393ad31f51b341 100644
--- a/src/backend/optimizer/path/indxpath.c
+++ b/src/backend/optimizer/path/indxpath.c
@@ -9,7 +9,7 @@
*
*
* IDENTIFICATION
- * $Header: /cvsroot/pgsql/src/backend/optimizer/path/indxpath.c,v 1.79 2000/02/05 18:26:09 tgl Exp $
+ * $Header: /cvsroot/pgsql/src/backend/optimizer/path/indxpath.c,v 1.80 2000/02/15 20:49:16 tgl Exp $
*
*-------------------------------------------------------------------------
*/
@@ -83,7 +83,8 @@ static List *index_innerjoin(Query *root, RelOptInfo *rel, IndexOptInfo *index,
static bool useful_for_mergejoin(RelOptInfo *rel, IndexOptInfo *index,
List *joininfo_list);
static bool useful_for_ordering(Query *root, RelOptInfo *rel,
- IndexOptInfo *index);
+ IndexOptInfo *index,
+ ScanDirection scandir);
static bool match_index_to_operand(int indexkey, Var *operand,
RelOptInfo *rel, IndexOptInfo *index);
static bool function_index_operand(Expr *funcOpnd, RelOptInfo *rel,
@@ -106,6 +107,8 @@ static bool string_lessthan(const char * str1, const char * str2,
/*
* create_index_paths()
* Generate all interesting index paths for the given relation.
+ * Candidate paths are added to the rel's pathlist (using add_path).
+ * Additional IndexPath nodes may also be added to rel's innerjoin list.
*
* To be considered for an index scan, an index must match one or more
* restriction clauses or join clauses from the query's qual condition,
@@ -120,29 +123,26 @@ static bool string_lessthan(const char * str1, const char * str2,
* in its join clauses. In that context, values for the other rels'
* attributes are available and fixed during any one scan of the indexpath.
*
- * This routine's return value is a list of plain IndexPaths for each
- * index the routine deems potentially interesting for the current query
+ * An IndexPath is generated and submitted to add_path() for each index
+ * this routine deems potentially interesting for the current query
* (at most one IndexPath per index on the given relation). An innerjoin
* path is also generated for each interesting combination of outer join
- * relations. The innerjoin paths are *not* in the return list, but are
- * appended to the "innerjoin" list of the relation itself.
+ * relations. The innerjoin paths are *not* passed to add_path(), but are
+ * appended to the "innerjoin" list of the relation for later consideration
+ * in nested-loop joins.
*
* 'rel' is the relation for which we want to generate index paths
* 'indices' is a list of available indexes for 'rel'
* 'restrictinfo_list' is a list of restrictinfo nodes for 'rel'
* 'joininfo_list' is a list of joininfo nodes for 'rel'
- *
- * Returns a list of IndexPath access path descriptors. Additional
- * IndexPath nodes may also be added to the rel->innerjoin list.
*/
-List *
+void
create_index_paths(Query *root,
RelOptInfo *rel,
List *indices,
List *restrictinfo_list,
List *joininfo_list)
{
- List *retval = NIL;
List *ilist;
foreach(ilist, indices)
@@ -189,9 +189,9 @@ create_index_paths(Query *root,
restrictinfo_list);
if (restrictclauses != NIL)
- retval = lappend(retval,
- create_index_path(root, rel, index,
- restrictclauses));
+ add_path(rel, (Path *) create_index_path(root, rel, index,
+ restrictclauses,
+ NoMovementScanDirection));
/*
* 3. If this index can be used for a mergejoin, then create an
@@ -205,10 +205,22 @@ create_index_paths(Query *root,
if (restrictclauses == NIL)
{
if (useful_for_mergejoin(rel, index, joininfo_list) ||
- useful_for_ordering(root, rel, index))
- retval = lappend(retval,
- create_index_path(root, rel, index, NIL));
+ useful_for_ordering(root, rel, index, ForwardScanDirection))
+ add_path(rel, (Path *)
+ create_index_path(root, rel, index,
+ NIL,
+ ForwardScanDirection));
}
+ /*
+ * Currently, backwards scan is never considered except for the case
+ * of matching a query result ordering. Possibly should consider
+ * it in other places?
+ */
+ if (useful_for_ordering(root, rel, index, BackwardScanDirection))
+ add_path(rel, (Path *)
+ create_index_path(root, rel, index,
+ NIL,
+ BackwardScanDirection));
/*
* 4. Create an innerjoin index path for each combination of
@@ -231,8 +243,6 @@ create_index_paths(Query *root,
joinouterrelids));
}
}
-
- return retval;
}
@@ -892,39 +902,26 @@ useful_for_mergejoin(RelOptInfo *rel,
* Determine whether the given index can produce an ordering matching
* the order that is wanted for the query result.
*
- * We check to see whether either forward or backward scan direction can
- * match the specified pathkeys.
- *
* 'rel' is the relation for which 'index' is defined
+ * 'scandir' is the contemplated scan direction
*/
static bool
useful_for_ordering(Query *root,
RelOptInfo *rel,
- IndexOptInfo *index)
+ IndexOptInfo *index,
+ ScanDirection scandir)
{
List *index_pathkeys;
if (root->query_pathkeys == NIL)
return false; /* no special ordering requested */
- index_pathkeys = build_index_pathkeys(root, rel, index);
+ index_pathkeys = build_index_pathkeys(root, rel, index, scandir);
if (index_pathkeys == NIL)
return false; /* unordered index */
- if (pathkeys_contained_in(root->query_pathkeys, index_pathkeys))
- return true;
-
- /* caution: commute_pathkeys destructively modifies its argument;
- * safe because we just built the index_pathkeys for local use here.
- */
- if (commute_pathkeys(index_pathkeys))
- {
- if (pathkeys_contained_in(root->query_pathkeys, index_pathkeys))
- return true; /* useful as a reverse-order path */
- }
-
- return false;
+ return pathkeys_contained_in(root->query_pathkeys, index_pathkeys);
}
/****************************************************************************
@@ -1433,7 +1430,12 @@ index_innerjoin(Query *root, RelOptInfo *rel, IndexOptInfo *index,
pathnode->path.pathtype = T_IndexScan;
pathnode->path.parent = rel;
- pathnode->path.pathkeys = build_index_pathkeys(root, rel, index);
+ /*
+ * There's no point in marking the path with any pathkeys, since
+ * it will only ever be used as the inner path of a nestloop,
+ * and so its ordering does not matter.
+ */
+ pathnode->path.pathkeys = NIL;
indexquals = get_actual_clauses(clausegroup);
/* expand special operators to indexquals the executor can handle */
@@ -1446,11 +1448,13 @@ index_innerjoin(Query *root, RelOptInfo *rel, IndexOptInfo *index,
pathnode->indexid = lconsi(index->indexoid, NIL);
pathnode->indexqual = lcons(indexquals, NIL);
+ /* We don't actually care what order the index scans in ... */
+ pathnode->indexscandir = NoMovementScanDirection;
+
/* joinrelids saves the rels needed on the outer side of the join */
pathnode->joinrelids = lfirst(outerrelids_list);
- pathnode->path.path_cost = cost_index(root, rel, index, indexquals,
- true);
+ cost_index(&pathnode->path, root, rel, index, indexquals, true);
path_list = lappend(path_list, pathnode);
outerrelids_list = lnext(outerrelids_list);
diff --git a/src/backend/optimizer/path/joinpath.c b/src/backend/optimizer/path/joinpath.c
index f8912a1a5477b3e48131da8e74f871b3f8eb6cbc..091e2e40c7922a9e249f234c7de2e9077b5d6aac 100644
--- a/src/backend/optimizer/path/joinpath.c
+++ b/src/backend/optimizer/path/joinpath.c
@@ -8,7 +8,7 @@
*
*
* IDENTIFICATION
- * $Header: /cvsroot/pgsql/src/backend/optimizer/path/joinpath.c,v 1.51 2000/02/07 04:40:59 tgl Exp $
+ * $Header: /cvsroot/pgsql/src/backend/optimizer/path/joinpath.c,v 1.52 2000/02/15 20:49:17 tgl Exp $
*
*-------------------------------------------------------------------------
*/
@@ -27,24 +27,21 @@
#include "parser/parsetree.h"
#include "utils/lsyscache.h"
+static void sort_inner_and_outer(Query *root, RelOptInfo *joinrel,
+ RelOptInfo *outerrel, RelOptInfo *innerrel,
+ List *restrictlist, List *mergeclause_list);
+static void match_unsorted_outer(Query *root, RelOptInfo *joinrel,
+ RelOptInfo *outerrel, RelOptInfo *innerrel,
+ List *restrictlist, List *mergeclause_list);
+#ifdef NOT_USED
+static void match_unsorted_inner(Query *root, RelOptInfo *joinrel,
+ RelOptInfo *outerrel, RelOptInfo *innerrel,
+ List *restrictlist, List *mergeclause_list);
+#endif
+static void hash_inner_and_outer(Query *root, RelOptInfo *joinrel,
+ RelOptInfo *outerrel, RelOptInfo *innerrel,
+ List *restrictlist);
static Path *best_innerjoin(List *join_paths, List *outer_relid);
-static List *sort_inner_and_outer(RelOptInfo *joinrel,
- RelOptInfo *outerrel,
- RelOptInfo *innerrel,
- List *restrictlist,
- List *mergeclause_list);
-static List *match_unsorted_outer(RelOptInfo *joinrel, RelOptInfo *outerrel,
- RelOptInfo *innerrel, List *restrictlist,
- List *outerpath_list, Path *cheapest_inner,
- Path *best_innerjoin,
- List *mergeclause_list);
-static List *match_unsorted_inner(RelOptInfo *joinrel, RelOptInfo *outerrel,
- RelOptInfo *innerrel, List *restrictlist,
- List *innerpath_list,
- List *mergeclause_list);
-static List *hash_inner_and_outer(Query *root, RelOptInfo *joinrel,
- RelOptInfo *outerrel, RelOptInfo *innerrel,
- List *restrictlist);
static Selectivity estimate_disbursion(Query *root, Var *var);
static List *select_mergejoin_clauses(RelOptInfo *joinrel,
RelOptInfo *outerrel,
@@ -70,14 +67,8 @@ add_paths_to_joinrel(Query *root,
RelOptInfo *innerrel,
List *restrictlist)
{
- Path *bestinnerjoin;
List *mergeclause_list = NIL;
- /*
- * Get the best inner join for match_unsorted_outer().
- */
- bestinnerjoin = best_innerjoin(innerrel->innerjoin, outerrel->relids);
-
/*
* Find potential mergejoin clauses.
*/
@@ -91,84 +82,41 @@ add_paths_to_joinrel(Query *root,
* 1. Consider mergejoin paths where both relations must be
* explicitly sorted.
*/
- add_pathlist(joinrel, sort_inner_and_outer(joinrel,
- outerrel,
- innerrel,
- restrictlist,
- mergeclause_list));
+ sort_inner_and_outer(root, joinrel, outerrel, innerrel,
+ restrictlist, mergeclause_list);
/*
* 2. Consider paths where the outer relation need not be
* explicitly sorted. This includes both nestloops and
* mergejoins where the outer path is already ordered.
*/
- add_pathlist(joinrel, match_unsorted_outer(joinrel,
- outerrel,
- innerrel,
- restrictlist,
- outerrel->pathlist,
- innerrel->cheapestpath,
- bestinnerjoin,
- mergeclause_list));
+ match_unsorted_outer(root, joinrel, outerrel, innerrel,
+ restrictlist, mergeclause_list);
+#ifdef NOT_USED
/*
* 3. Consider paths where the inner relation need not be
* explicitly sorted. This includes mergejoins only
* (nestloops were already built in match_unsorted_outer).
+ *
+ * Diked out as redundant 2/13/2000 -- tgl. There isn't any
+ * really significant difference between the inner and outer
+ * side of a mergejoin, so match_unsorted_inner creates no paths
+ * that aren't equivalent to those made by match_unsorted_outer
+ * when add_paths_to_joinrel() is invoked with the two rels given
+ * in the other order.
*/
- add_pathlist(joinrel, match_unsorted_inner(joinrel,
- outerrel,
- innerrel,
- restrictlist,
- innerrel->pathlist,
- mergeclause_list));
+ match_unsorted_inner(root, joinrel, outerrel, innerrel,
+ restrictlist, mergeclause_list);
+#endif
/*
* 4. Consider paths where both outer and inner relations must be
* hashed before being joined.
*/
if (enable_hashjoin)
- add_pathlist(joinrel, hash_inner_and_outer(root,
- joinrel,
- outerrel,
- innerrel,
- restrictlist));
-}
-
-/*
- * best_innerjoin
- * Find the cheapest index path that has already been identified by
- * indexable_joinclauses() as being a possible inner path for the given
- * outer relation(s) in a nestloop join.
- *
- * 'join_paths' is a list of potential inner indexscan join paths
- * 'outer_relids' is the relid list of the outer join relation
- *
- * Returns the pathnode of the best path, or NULL if there's no
- * usable path.
- */
-static Path *
-best_innerjoin(List *join_paths, Relids outer_relids)
-{
- Path *cheapest = (Path *) NULL;
- List *join_path;
-
- foreach(join_path, join_paths)
- {
- Path *path = (Path *) lfirst(join_path);
-
- Assert(IsA(path, IndexPath));
-
- /* path->joinrelids is the set of base rels that must be part of
- * outer_relids in order to use this inner path, because those
- * rels are used in the index join quals of this inner path.
- */
- if (is_subseti(((IndexPath *) path)->joinrelids, outer_relids) &&
- (cheapest == NULL ||
- path_is_cheaper(path, cheapest)))
- cheapest = path;
- }
- return cheapest;
+ hash_inner_and_outer(root, joinrel, outerrel, innerrel,
+ restrictlist);
}
/*
@@ -183,17 +131,15 @@ best_innerjoin(List *join_paths, Relids outer_relids)
* clauses that apply to this join
* 'mergeclause_list' is a list of RestrictInfo nodes for available
* mergejoin clauses in this join
- *
- * Returns a list of mergejoin paths.
*/
-static List *
-sort_inner_and_outer(RelOptInfo *joinrel,
+static void
+sort_inner_and_outer(Query *root,
+ RelOptInfo *joinrel,
RelOptInfo *outerrel,
RelOptInfo *innerrel,
List *restrictlist,
List *mergeclause_list)
{
- List *path_list = NIL;
List *i;
/*
@@ -223,7 +169,6 @@ sort_inner_and_outer(RelOptInfo *joinrel,
List *outerkeys;
List *innerkeys;
List *merge_pathkeys;
- MergePath *path_node;
/* Make a mergeclause list with this guy first. */
curclause_list = lcons(restrictinfo,
@@ -231,31 +176,37 @@ sort_inner_and_outer(RelOptInfo *joinrel,
listCopy(mergeclause_list)));
/* Build sort pathkeys for both sides.
*
- * Note: it's possible that the cheapest path will already be
- * sorted properly --- create_mergejoin_path will detect that case
- * and suppress an explicit sort step.
+ * Note: it's possible that the cheapest paths will already be
+ * sorted properly. create_mergejoin_path will detect that case
+ * and suppress an explicit sort step, so we needn't do so here.
*/
- outerkeys = make_pathkeys_for_mergeclauses(curclause_list,
+ outerkeys = make_pathkeys_for_mergeclauses(root,
+ curclause_list,
outerrel->targetlist);
- innerkeys = make_pathkeys_for_mergeclauses(curclause_list,
+ innerkeys = make_pathkeys_for_mergeclauses(root,
+ curclause_list,
innerrel->targetlist);
/* Build pathkeys representing output sort order. */
merge_pathkeys = build_join_pathkeys(outerkeys,
joinrel->targetlist,
- curclause_list);
- /* And now we can make the path. */
- path_node = create_mergejoin_path(joinrel,
- outerrel->cheapestpath,
- innerrel->cheapestpath,
- restrictlist,
- merge_pathkeys,
- get_actual_clauses(curclause_list),
- outerkeys,
- innerkeys);
+ root->equi_key_list);
- path_list = lappend(path_list, path_node);
+ /*
+ * And now we can make the path. We only consider the cheapest-
+ * total-cost input paths, since we are assuming here that a sort
+ * is required. We will consider cheapest-startup-cost input paths
+ * later, and only if they don't need a sort.
+ */
+ add_path(joinrel, (Path *)
+ create_mergejoin_path(joinrel,
+ outerrel->cheapest_total_path,
+ innerrel->cheapest_total_path,
+ restrictlist,
+ merge_pathkeys,
+ get_actual_clauses(curclause_list),
+ outerkeys,
+ innerkeys));
}
- return path_list;
}
/*
@@ -266,74 +217,56 @@ sort_inner_and_outer(RelOptInfo *joinrel,
* only outer paths that are already ordered well enough for merging).
*
* We always generate a nestloop path for each available outer path.
- * If an indexscan inner path exists that is compatible with this outer rel
- * and cheaper than the cheapest general-purpose inner path, then we use
- * the indexscan inner path; else we use the cheapest general-purpose inner.
+ * In fact we may generate as many as three: one on the cheapest-total-cost
+ * inner path, one on the cheapest-startup-cost inner path (if different),
+ * and one on the best inner-indexscan path (if any).
*
* We also consider mergejoins if mergejoin clauses are available. We have
- * two ways to generate the inner path for a mergejoin: use the cheapest
- * inner path (sorting it if it's not suitably ordered already), or using an
- * inner path that is already suitably ordered for the merge. If the
- * cheapest inner path is suitably ordered, then by definition it's the one
- * to use. Otherwise, we look for ordered paths that are cheaper than the
- * cheapest inner + sort costs. If we have several mergeclauses, it could be
- * that there is no inner path (or only a very expensive one) for the full
- * list of mergeclauses, but better paths exist if we truncate the
- * mergeclause list (thereby discarding some sort key requirements). So, we
- * consider truncations of the mergeclause list as well as the full list.
- * In any case, we find the cheapest suitable path and generate a single
- * output mergejoin path. (Since all the possible mergejoins will have
- * identical output pathkeys, there is no need to keep any but the cheapest.)
+ * two ways to generate the inner path for a mergejoin: sort the cheapest
+ * inner path, or use an inner path that is already suitably ordered for the
+ * merge. If we have several mergeclauses, it could be that there is no inner
+ * path (or only a very expensive one) for the full list of mergeclauses, but
+ * better paths exist if we truncate the mergeclause list (thereby discarding
+ * some sort key requirements). So, we consider truncations of the
+ * mergeclause list as well as the full list. (Ideally we'd consider all
+ * subsets of the mergeclause list, but that seems way too expensive.)
*
* 'joinrel' is the join relation
* 'outerrel' is the outer join relation
* 'innerrel' is the inner join relation
* 'restrictlist' contains all of the RestrictInfo nodes for restriction
* clauses that apply to this join
- * 'outerpath_list' is the list of possible outer paths
- * 'cheapest_inner' is the cheapest inner path
- * 'best_innerjoin' is the best inner index path (if any)
* 'mergeclause_list' is a list of RestrictInfo nodes for available
* mergejoin clauses in this join
- *
- * Returns a list of possible join path nodes.
*/
-static List *
-match_unsorted_outer(RelOptInfo *joinrel,
+static void
+match_unsorted_outer(Query *root,
+ RelOptInfo *joinrel,
RelOptInfo *outerrel,
RelOptInfo *innerrel,
List *restrictlist,
- List *outerpath_list,
- Path *cheapest_inner,
- Path *best_innerjoin,
List *mergeclause_list)
{
- List *path_list = NIL;
- Path *nestinnerpath;
+ Path *bestinnerjoin;
List *i;
/*
- * We only use the best innerjoin indexpath if it is cheaper
- * than the cheapest general-purpose inner path.
+ * Get the best innerjoin indexpath (if any) for this outer rel.
+ * It's the same for all outer paths.
*/
- if (best_innerjoin &&
- path_is_cheaper(best_innerjoin, cheapest_inner))
- nestinnerpath = best_innerjoin;
- else
- nestinnerpath = cheapest_inner;
+ bestinnerjoin = best_innerjoin(innerrel->innerjoin, outerrel->relids);
- foreach(i, outerpath_list)
+ foreach(i, outerrel->pathlist)
{
Path *outerpath = (Path *) lfirst(i);
- List *mergeclauses;
List *merge_pathkeys;
+ List *mergeclauses;
List *innersortkeys;
- Path *mergeinnerpath;
- int mergeclausecount;
+ List *trialsortkeys;
+ Path *cheapest_startup_inner;
+ Path *cheapest_total_inner;
+ int clausecnt;
- /* Look for useful mergeclauses (if any) */
- mergeclauses = find_mergeclauses_for_pathkeys(outerpath->pathkeys,
- mergeclause_list);
/*
* The result will have this sort order (even if it is implemented
* as a nestloop, and even if some of the mergeclauses are implemented
@@ -341,91 +274,137 @@ match_unsorted_outer(RelOptInfo *joinrel,
*/
merge_pathkeys = build_join_pathkeys(outerpath->pathkeys,
joinrel->targetlist,
- mergeclauses);
+ root->equi_key_list);
+
+ /*
+ * Always consider a nestloop join with this outer and cheapest-
+ * total-cost inner. Consider nestloops using the cheapest-
+ * startup-cost inner as well, and the best innerjoin indexpath.
+ */
+ add_path(joinrel, (Path *)
+ create_nestloop_path(joinrel,
+ outerpath,
+ innerrel->cheapest_total_path,
+ restrictlist,
+ merge_pathkeys));
+ if (innerrel->cheapest_startup_path != innerrel->cheapest_total_path)
+ add_path(joinrel, (Path *)
+ create_nestloop_path(joinrel,
+ outerpath,
+ innerrel->cheapest_startup_path,
+ restrictlist,
+ merge_pathkeys));
+ if (bestinnerjoin != NULL)
+ add_path(joinrel, (Path *)
+ create_nestloop_path(joinrel,
+ outerpath,
+ bestinnerjoin,
+ restrictlist,
+ merge_pathkeys));
- /* Always consider a nestloop join with this outer and best inner. */
- path_list = lappend(path_list,
- create_nestloop_path(joinrel,
- outerpath,
- nestinnerpath,
- restrictlist,
- merge_pathkeys));
+ /* Look for useful mergeclauses (if any) */
+ mergeclauses = find_mergeclauses_for_pathkeys(outerpath->pathkeys,
+ mergeclause_list);
/* Done with this outer path if no chance for a mergejoin */
if (mergeclauses == NIL)
continue;
/* Compute the required ordering of the inner path */
- innersortkeys = make_pathkeys_for_mergeclauses(mergeclauses,
+ innersortkeys = make_pathkeys_for_mergeclauses(root,
+ mergeclauses,
innerrel->targetlist);
- /* Set up on the assumption that we will use the cheapest_inner */
- mergeinnerpath = cheapest_inner;
- mergeclausecount = length(mergeclauses);
-
- /* If the cheapest_inner doesn't need to be sorted, it is the winner
- * by definition.
+ /*
+ * Generate a mergejoin on the basis of sorting the cheapest inner.
+ * Since a sort will be needed, only cheapest total cost matters.
*/
- if (pathkeys_contained_in(innersortkeys,
- cheapest_inner->pathkeys))
- {
- /* cheapest_inner is the winner */
- innersortkeys = NIL; /* we do not need to sort it... */
- }
- else
- {
- /* look for a presorted path that's cheaper */
- List *trialsortkeys = listCopy(innersortkeys);
- Cost cheapest_cost;
- int clausecount;
+ add_path(joinrel, (Path *)
+ create_mergejoin_path(joinrel,
+ outerpath,
+ innerrel->cheapest_total_path,
+ restrictlist,
+ merge_pathkeys,
+ get_actual_clauses(mergeclauses),
+ NIL,
+ innersortkeys));
- cheapest_cost = cheapest_inner->path_cost +
- cost_sort(innersortkeys, innerrel->rows, innerrel->width);
+ /*
+ * Look for presorted inner paths that satisfy the mergeclause list
+ * or any truncation thereof. Here, we consider both cheap startup
+ * cost and cheap total cost.
+ */
+ trialsortkeys = listCopy(innersortkeys); /* modifiable copy */
+ cheapest_startup_inner = NULL;
+ cheapest_total_inner = NULL;
- for (clausecount = mergeclausecount;
- clausecount > 0;
- clausecount--)
+ for (clausecnt = length(mergeclauses); clausecnt > 0; clausecnt--)
+ {
+ Path *innerpath;
+
+ /* Look for an inner path ordered well enough to merge with
+ * the first 'clausecnt' mergeclauses. NB: trialsortkeys list
+ * is modified destructively, which is why we made a copy...
+ */
+ trialsortkeys = ltruncate(clausecnt, trialsortkeys);
+ innerpath = get_cheapest_path_for_pathkeys(innerrel->pathlist,
+ trialsortkeys,
+ TOTAL_COST);
+ if (innerpath != NULL &&
+ (cheapest_total_inner == NULL ||
+ compare_path_costs(innerpath, cheapest_total_inner,
+ TOTAL_COST) < 0))
{
- Path *trialinnerpath;
-
- /* Look for an inner path ordered well enough to merge with
- * the first 'clausecount' mergeclauses. NB: trialsortkeys
- * is modified destructively, which is why we made a copy...
- */
- trialinnerpath =
- get_cheapest_path_for_pathkeys(innerrel->pathlist,
- ltruncate(clausecount,
- trialsortkeys),
- false);
- if (trialinnerpath != NULL &&
- trialinnerpath->path_cost < cheapest_cost)
+ /* Found a cheap (or even-cheaper) sorted path */
+ List *newclauses;
+
+ newclauses = ltruncate(clausecnt,
+ get_actual_clauses(mergeclauses));
+ add_path(joinrel, (Path *)
+ create_mergejoin_path(joinrel,
+ outerpath,
+ innerpath,
+ restrictlist,
+ merge_pathkeys,
+ newclauses,
+ NIL,
+ NIL));
+ cheapest_total_inner = innerpath;
+ }
+ /* Same on the basis of cheapest startup cost ... */
+ innerpath = get_cheapest_path_for_pathkeys(innerrel->pathlist,
+ trialsortkeys,
+ STARTUP_COST);
+ if (innerpath != NULL &&
+ (cheapest_startup_inner == NULL ||
+ compare_path_costs(innerpath, cheapest_startup_inner,
+ STARTUP_COST) < 0))
+ {
+ /* Found a cheap (or even-cheaper) sorted path */
+ if (innerpath != cheapest_total_inner)
{
- /* Found a cheaper (or even-cheaper) sorted path */
- cheapest_cost = trialinnerpath->path_cost;
- mergeinnerpath = trialinnerpath;
- mergeclausecount = clausecount;
- innersortkeys = NIL; /* we will not need to sort it... */
+ List *newclauses;
+
+ newclauses = ltruncate(clausecnt,
+ get_actual_clauses(mergeclauses));
+ add_path(joinrel, (Path *)
+ create_mergejoin_path(joinrel,
+ outerpath,
+ innerpath,
+ restrictlist,
+ merge_pathkeys,
+ newclauses,
+ NIL,
+ NIL));
}
+ cheapest_startup_inner = innerpath;
}
}
-
- /* Finally, we can build the mergejoin path */
- mergeclauses = ltruncate(mergeclausecount,
- get_actual_clauses(mergeclauses));
- path_list = lappend(path_list,
- create_mergejoin_path(joinrel,
- outerpath,
- mergeinnerpath,
- restrictlist,
- merge_pathkeys,
- mergeclauses,
- NIL,
- innersortkeys));
}
-
- return path_list;
}
+#ifdef NOT_USED
+
/*
* match_unsorted_inner
* Generate mergejoin paths that use an explicit sort of the outer path
@@ -436,86 +415,105 @@ match_unsorted_outer(RelOptInfo *joinrel,
* 'innerrel' is the inner join relation
* 'restrictlist' contains all of the RestrictInfo nodes for restriction
* clauses that apply to this join
- * 'innerpath_list' is the list of possible inner join paths
* 'mergeclause_list' is a list of RestrictInfo nodes for available
* mergejoin clauses in this join
- *
- * Returns a list of possible merge paths.
*/
-static List *
-match_unsorted_inner(RelOptInfo *joinrel,
+static void
+match_unsorted_inner(Query *root,
+ RelOptInfo *joinrel,
RelOptInfo *outerrel,
RelOptInfo *innerrel,
List *restrictlist,
- List *innerpath_list,
List *mergeclause_list)
{
- List *path_list = NIL;
List *i;
- foreach(i, innerpath_list)
+ foreach(i, innerrel->pathlist)
{
Path *innerpath = (Path *) lfirst(i);
List *mergeclauses;
+ List *outersortkeys;
+ List *merge_pathkeys;
+ Path *totalouterpath;
+ Path *startupouterpath;
/* Look for useful mergeclauses (if any) */
mergeclauses = find_mergeclauses_for_pathkeys(innerpath->pathkeys,
mergeclause_list);
+ if (mergeclauses == NIL)
+ continue;
- if (mergeclauses)
- {
- List *outersortkeys;
- Path *mergeouterpath;
- List *merge_pathkeys;
-
- /* Compute the required ordering of the outer path */
- outersortkeys =
- make_pathkeys_for_mergeclauses(mergeclauses,
- outerrel->targetlist);
-
- /* Look for an outer path already ordered well enough to merge */
- mergeouterpath =
- get_cheapest_path_for_pathkeys(outerrel->pathlist,
- outersortkeys,
- false);
-
- /* Should we use the mergeouter, or sort the cheapest outer? */
- if (mergeouterpath != NULL &&
- mergeouterpath->path_cost <=
- (outerrel->cheapestpath->path_cost +
- cost_sort(outersortkeys, outerrel->rows, outerrel->width)))
- {
- /* Use mergeouterpath */
- outersortkeys = NIL; /* no explicit sort step */
- }
- else
- {
- /* Use outerrel->cheapestpath, with the outersortkeys */
- mergeouterpath = outerrel->cheapestpath;
- }
+ /* Compute the required ordering of the outer path */
+ outersortkeys = make_pathkeys_for_mergeclauses(root,
+ mergeclauses,
+ outerrel->targetlist);
+
+ /*
+ * Generate a mergejoin on the basis of sorting the cheapest outer.
+ * Since a sort will be needed, only cheapest total cost matters.
+ */
+ merge_pathkeys = build_join_pathkeys(outersortkeys,
+ joinrel->targetlist,
+ root->equi_key_list);
+ add_path(joinrel, (Path *)
+ create_mergejoin_path(joinrel,
+ outerrel->cheapest_total_path,
+ innerpath,
+ restrictlist,
+ merge_pathkeys,
+ get_actual_clauses(mergeclauses),
+ outersortkeys,
+ NIL));
+ /*
+ * Now generate mergejoins based on already-sufficiently-ordered
+ * outer paths. There's likely to be some redundancy here with paths
+ * already generated by merge_unsorted_outer ... but since
+ * merge_unsorted_outer doesn't consider all permutations of the
+ * mergeclause list, it may fail to notice that this particular
+ * innerpath could have been used with this outerpath.
+ */
+ totalouterpath = get_cheapest_path_for_pathkeys(outerrel->pathlist,
+ outersortkeys,
+ TOTAL_COST);
+ if (totalouterpath == NULL)
+ continue; /* there won't be a startup-cost path either */
- /* Compute pathkeys the result will have */
- merge_pathkeys = build_join_pathkeys(
- outersortkeys ? outersortkeys : mergeouterpath->pathkeys,
- joinrel->targetlist,
- mergeclauses);
-
- mergeclauses = get_actual_clauses(mergeclauses);
- path_list = lappend(path_list,
- create_mergejoin_path(joinrel,
- mergeouterpath,
- innerpath,
- restrictlist,
- merge_pathkeys,
- mergeclauses,
- outersortkeys,
- NIL));
+ merge_pathkeys = build_join_pathkeys(totalouterpath->pathkeys,
+ joinrel->targetlist,
+ root->equi_key_list);
+ add_path(joinrel, (Path *)
+ create_mergejoin_path(joinrel,
+ totalouterpath,
+ innerpath,
+ restrictlist,
+ merge_pathkeys,
+ get_actual_clauses(mergeclauses),
+ NIL,
+ NIL));
+
+ startupouterpath = get_cheapest_path_for_pathkeys(outerrel->pathlist,
+ outersortkeys,
+ STARTUP_COST);
+ if (startupouterpath != NULL && startupouterpath != totalouterpath)
+ {
+ merge_pathkeys = build_join_pathkeys(startupouterpath->pathkeys,
+ joinrel->targetlist,
+ root->equi_key_list);
+ add_path(joinrel, (Path *)
+ create_mergejoin_path(joinrel,
+ startupouterpath,
+ innerpath,
+ restrictlist,
+ merge_pathkeys,
+ get_actual_clauses(mergeclauses),
+ NIL,
+ NIL));
}
}
-
- return path_list;
}
+#endif
+
/*
* hash_inner_and_outer
* Create hashjoin join paths by explicitly hashing both the outer and
@@ -526,17 +524,14 @@ match_unsorted_inner(RelOptInfo *joinrel,
* 'innerrel' is the inner join relation
* 'restrictlist' contains all of the RestrictInfo nodes for restriction
* clauses that apply to this join
- *
- * Returns a list of hashjoin paths.
*/
-static List *
+static void
hash_inner_and_outer(Query *root,
RelOptInfo *joinrel,
RelOptInfo *outerrel,
RelOptInfo *innerrel,
List *restrictlist)
{
- List *hpath_list = NIL;
Relids outerrelids = outerrel->relids;
Relids innerrelids = innerrel->relids;
List *i;
@@ -558,7 +553,6 @@ hash_inner_and_outer(Query *root,
*right,
*inner;
Selectivity innerdisbursion;
- HashPath *hash_path;
if (restrictinfo->hashjoinoperator == InvalidOid)
continue; /* not hashjoinable */
@@ -581,17 +575,66 @@ hash_inner_and_outer(Query *root,
/* estimate disbursion of inner var for costing purposes */
innerdisbursion = estimate_disbursion(root, inner);
- hash_path = create_hashjoin_path(joinrel,
- outerrel->cheapestpath,
- innerrel->cheapestpath,
- restrictlist,
- lcons(clause, NIL),
- innerdisbursion);
-
- hpath_list = lappend(hpath_list, hash_path);
+ /*
+ * We consider both the cheapest-total-cost and cheapest-startup-cost
+ * outer paths. There's no need to consider any but the cheapest-
+ * total-cost inner path, however.
+ */
+ add_path(joinrel, (Path *)
+ create_hashjoin_path(joinrel,
+ outerrel->cheapest_total_path,
+ innerrel->cheapest_total_path,
+ restrictlist,
+ lcons(clause, NIL),
+ innerdisbursion));
+ if (outerrel->cheapest_startup_path != outerrel->cheapest_total_path)
+ add_path(joinrel, (Path *)
+ create_hashjoin_path(joinrel,
+ outerrel->cheapest_startup_path,
+ innerrel->cheapest_total_path,
+ restrictlist,
+ lcons(clause, NIL),
+ innerdisbursion));
}
+}
+
+/*
+ * best_innerjoin
+ * Find the cheapest index path that has already been identified by
+ * indexable_joinclauses() as being a possible inner path for the given
+ * outer relation(s) in a nestloop join.
+ *
+ * We compare indexpaths on total_cost only, assuming that they will all have
+ * zero or negligible startup_cost. We might have to think harder someday...
+ *
+ * 'join_paths' is a list of potential inner indexscan join paths
+ * 'outer_relids' is the relid list of the outer join relation
+ *
+ * Returns the pathnode of the best path, or NULL if there's no
+ * usable path.
+ */
+static Path *
+best_innerjoin(List *join_paths, Relids outer_relids)
+{
+ Path *cheapest = (Path *) NULL;
+ List *join_path;
+
+ foreach(join_path, join_paths)
+ {
+ Path *path = (Path *) lfirst(join_path);
+
+ Assert(IsA(path, IndexPath));
- return hpath_list;
+ /* path->joinrelids is the set of base rels that must be part of
+ * outer_relids in order to use this inner path, because those
+ * rels are used in the index join quals of this inner path.
+ */
+ if (is_subseti(((IndexPath *) path)->joinrelids, outer_relids) &&
+ (cheapest == NULL ||
+ compare_path_costs(path, cheapest, TOTAL_COST) < 0))
+ cheapest = path;
+ }
+ return cheapest;
}
/*
diff --git a/src/backend/optimizer/path/orindxpath.c b/src/backend/optimizer/path/orindxpath.c
index 9eb0484fc2fa1bc8cd88f8faba8224562d433445..6226100cfc791304a022691b5dc36c7737a82846 100644
--- a/src/backend/optimizer/path/orindxpath.c
+++ b/src/backend/optimizer/path/orindxpath.c
@@ -8,7 +8,7 @@
*
*
* IDENTIFICATION
- * $Header: /cvsroot/pgsql/src/backend/optimizer/path/orindxpath.c,v 1.36 2000/02/05 18:26:09 tgl Exp $
+ * $Header: /cvsroot/pgsql/src/backend/optimizer/path/orindxpath.c,v 1.37 2000/02/15 20:49:17 tgl Exp $
*
*-------------------------------------------------------------------------
*/
@@ -19,6 +19,7 @@
#include "optimizer/clauses.h"
#include "optimizer/cost.h"
#include "optimizer/internal.h"
+#include "optimizer/pathnode.h"
#include "optimizer/paths.h"
#include "optimizer/plancat.h"
#include "optimizer/restrictinfo.h"
@@ -27,14 +28,13 @@
static void best_or_subclause_indices(Query *root, RelOptInfo *rel,
List *subclauses, List *indices,
- List **indexquals,
- List **indexids,
- Cost *cost);
+ IndexPath *pathnode);
static void best_or_subclause_index(Query *root, RelOptInfo *rel,
Expr *subclause, List *indices,
List **retIndexQual,
Oid *retIndexid,
- Cost *retCost);
+ Cost *retStartupCost,
+ Cost *retTotalCost);
/*
@@ -45,14 +45,13 @@ static void best_or_subclause_index(Query *root, RelOptInfo *rel,
* 'rel' is the relation entry for which the paths are to be created
* 'clauses' is the list of available restriction clause nodes
*
- * Returns a list of index path nodes.
- *
+ * Returns nothing, but adds paths to rel->pathlist via add_path().
*/
-List *
+void
create_or_index_paths(Query *root,
- RelOptInfo *rel, List *clauses)
+ RelOptInfo *rel,
+ List *clauses)
{
- List *path_list = NIL;
List *clist;
foreach(clist, clauses)
@@ -86,17 +85,6 @@ create_or_index_paths(Query *root,
* best available index for each subclause.
*/
IndexPath *pathnode = makeNode(IndexPath);
- List *indexquals;
- List *indexids;
- Cost cost;
-
- best_or_subclause_indices(root,
- rel,
- clausenode->clause->args,
- clausenode->subclauseindices,
- &indexquals,
- &indexids,
- &cost);
pathnode->path.pathtype = T_IndexScan;
pathnode->path.parent = rel;
@@ -108,17 +96,21 @@ create_or_index_paths(Query *root,
*/
pathnode->path.pathkeys = NIL;
- pathnode->indexid = indexids;
- pathnode->indexqual = indexquals;
+ /* We don't actually care what order the index scans in ... */
+ pathnode->indexscandir = NoMovementScanDirection;
+
pathnode->joinrelids = NIL; /* no join clauses here */
- pathnode->path.path_cost = cost;
- path_list = lappend(path_list, pathnode);
+ best_or_subclause_indices(root,
+ rel,
+ clausenode->clause->args,
+ clausenode->subclauseindices,
+ pathnode);
+
+ add_path(rel, (Path *) pathnode);
}
}
}
-
- return path_list;
}
/*
@@ -128,53 +120,68 @@ create_or_index_paths(Query *root,
* indices. The cost is the sum of the individual index costs, since
* the executor will perform a scan for each subclause of the 'or'.
*
- * This routine also creates the indexquals and indexids lists that will
- * be needed by the executor. The indexquals list has one entry for each
+ * This routine also creates the indexqual and indexid lists that will
+ * be needed by the executor. The indexqual list has one entry for each
* scan of the base rel, which is a sublist of indexqual conditions to
* apply in that scan. The implicit semantics are AND across each sublist
* of quals, and OR across the toplevel list (note that the executor
- * takes care not to return any single tuple more than once). The indexids
- * list gives the index to be used in each scan.
+ * takes care not to return any single tuple more than once). The indexid
+ * list gives the OID of the index to be used in each scan.
*
* 'rel' is the node of the relation on which the indexes are defined
* 'subclauses' are the subclauses of the 'or' clause
* 'indices' is a list of sublists of the IndexOptInfo nodes that matched
* each subclause of the 'or' clause
- * '*indexquals' gets the constructed indexquals for the path (a list
+ * 'pathnode' is the IndexPath node being built.
+ *
+ * Results are returned by setting these fields of the passed pathnode:
+ * 'indexqual' gets the constructed indexquals for the path (a list
* of sublists of clauses, one sublist per scan of the base rel)
- * '*indexids' gets a list of the index OIDs for each scan of the rel
- * '*cost' gets the total cost of the path
+ * 'indexid' gets a list of the index OIDs for each scan of the rel
+ * 'startup_cost' and 'total_cost' get the complete path costs.
+ *
+ * 'startup_cost' is the startup cost for the first index scan only;
+ * startup costs for later scans will be paid later on, so they just
+ * get reflected in total_cost.
+ *
+ * NOTE: we choose each scan on the basis of its total cost, ignoring startup
+ * cost. This is reasonable as long as all index types have zero or small
+ * startup cost, but we might have to work harder if any index types with
+ * nontrivial startup cost are ever invented.
*/
static void
best_or_subclause_indices(Query *root,
RelOptInfo *rel,
List *subclauses,
List *indices,
- List **indexquals, /* return value */
- List **indexids, /* return value */
- Cost *cost) /* return value */
+ IndexPath *pathnode)
{
List *slist;
- *indexquals = NIL;
- *indexids = NIL;
- *cost = (Cost) 0.0;
+ pathnode->indexqual = NIL;
+ pathnode->indexid = NIL;
+ pathnode->path.startup_cost = 0;
+ pathnode->path.total_cost = 0;
foreach(slist, subclauses)
{
Expr *subclause = lfirst(slist);
List *best_indexqual;
Oid best_indexid;
- Cost best_cost;
+ Cost best_startup_cost;
+ Cost best_total_cost;
best_or_subclause_index(root, rel, subclause, lfirst(indices),
- &best_indexqual, &best_indexid, &best_cost);
+ &best_indexqual, &best_indexid,
+ &best_startup_cost, &best_total_cost);
Assert(best_indexid != InvalidOid);
- *indexquals = lappend(*indexquals, best_indexqual);
- *indexids = lappendi(*indexids, best_indexid);
- *cost += best_cost;
+ pathnode->indexqual = lappend(pathnode->indexqual, best_indexqual);
+ pathnode->indexid = lappendi(pathnode->indexid, best_indexid);
+ if (slist == subclauses) /* first scan? */
+ pathnode->path.startup_cost = best_startup_cost;
+ pathnode->path.total_cost += best_total_cost;
indices = lnext(indices);
}
@@ -182,16 +189,17 @@ best_or_subclause_indices(Query *root,
/*
* best_or_subclause_index
- * Determines which is the best index to be used with a subclause of
- * an 'or' clause by estimating the cost of using each index and selecting
- * the least expensive.
+ * Determines which is the best index to be used with a subclause of an
+ * 'or' clause by estimating the cost of using each index and selecting
+ * the least expensive (considering total cost only, for now).
*
* 'rel' is the node of the relation on which the index is defined
* 'subclause' is the OR subclause being considered
* 'indices' is a list of IndexOptInfo nodes that match the subclause
* '*retIndexQual' gets a list of the indexqual conditions for the best index
* '*retIndexid' gets the OID of the best index
- * '*retCost' gets the cost of a scan with that index
+ * '*retStartupCost' gets the startup cost of a scan with that index
+ * '*retTotalCost' gets the total cost of a scan with that index
*/
static void
best_or_subclause_index(Query *root,
@@ -200,7 +208,8 @@ best_or_subclause_index(Query *root,
List *indices,
List **retIndexQual, /* return value */
Oid *retIndexid, /* return value */
- Cost *retCost) /* return value */
+ Cost *retStartupCost, /* return value */
+ Cost *retTotalCost) /* return value */
{
bool first_time = true;
List *ilist;
@@ -208,27 +217,28 @@ best_or_subclause_index(Query *root,
/* if we don't match anything, return zeros */
*retIndexQual = NIL;
*retIndexid = InvalidOid;
- *retCost = 0.0;
+ *retStartupCost = 0;
+ *retTotalCost = 0;
foreach(ilist, indices)
{
IndexOptInfo *index = (IndexOptInfo *) lfirst(ilist);
List *indexqual;
- Cost subcost;
+ Path subclause_path;
Assert(IsA(index, IndexOptInfo));
/* Convert this 'or' subclause to an indexqual list */
indexqual = extract_or_indexqual_conditions(rel, index, subclause);
- subcost = cost_index(root, rel, index, indexqual,
- false);
+ cost_index(&subclause_path, root, rel, index, indexqual, false);
- if (first_time || subcost < *retCost)
+ if (first_time || subclause_path.total_cost < *retTotalCost)
{
*retIndexQual = indexqual;
*retIndexid = index->indexoid;
- *retCost = subcost;
+ *retStartupCost = subclause_path.startup_cost;
+ *retTotalCost = subclause_path.total_cost;
first_time = false;
}
}
diff --git a/src/backend/optimizer/path/pathkeys.c b/src/backend/optimizer/path/pathkeys.c
index 5aeda1e154e157df2e5d291b0a29b8865d850420..b578e33f5c850a6cde157b8b98aace14c75dfcc7 100644
--- a/src/backend/optimizer/path/pathkeys.c
+++ b/src/backend/optimizer/path/pathkeys.c
@@ -8,7 +8,7 @@
*
*
* IDENTIFICATION
- * $Header: /cvsroot/pgsql/src/backend/optimizer/path/pathkeys.c,v 1.18 2000/01/26 05:56:34 momjian Exp $
+ * $Header: /cvsroot/pgsql/src/backend/optimizer/path/pathkeys.c,v 1.19 2000/02/15 20:49:17 tgl Exp $
*
*-------------------------------------------------------------------------
*/
@@ -17,6 +17,7 @@
#include "nodes/makefuncs.h"
#include "optimizer/clauses.h"
#include "optimizer/joininfo.h"
+#include "optimizer/pathnode.h"
#include "optimizer/paths.h"
#include "optimizer/tlist.h"
#include "optimizer/var.h"
@@ -25,9 +26,9 @@
#include "utils/lsyscache.h"
static PathKeyItem *makePathKeyItem(Node *key, Oid sortop);
-static Var *find_indexkey_var(int indexkey, List *tlist);
-static List *build_join_pathkey(List *pathkeys, List *join_rel_tlist,
- List *joinclauses);
+static List *make_canonical_pathkey(Query *root, PathKeyItem *item);
+static Var *find_indexkey_var(Query *root, RelOptInfo *rel,
+ AttrNumber varattno);
/*--------------------
@@ -50,50 +51,122 @@ static List *build_join_pathkey(List *pathkeys, List *join_rel_tlist,
* Note that a multi-pass indexscan (OR clause scan) has NIL pathkeys since
* we can say nothing about the overall order of its result. Also, an
* indexscan on an unordered type of index generates NIL pathkeys. However,
- * we can always create a pathkey by doing an explicit sort.
- *
- * Multi-relation RelOptInfo Path's are more complicated. Mergejoins are
- * only performed with equijoins ("="). Because of this, the resulting
- * multi-relation path actually has more than one primary key. For example,
- * a mergejoin using a clause "tab1.col1 = tab2.col1" would generate pathkeys
- * of ( (tab1.col1/sortop1 tab2.col1/sortop2) ), indicating that the major
- * sort order of the Path can be taken to be *either* tab1.col1 or tab2.col1.
- * They are equal, so they are both primary sort keys. This allows future
- * joins to use either var as a pre-sorted key to prevent upper Mergejoins
- * from having to re-sort the Path. This is why pathkeys is a List of Lists.
- *
- * Note that while the order of the top list is meaningful (primary vs.
- * secondary sort key), the order of each sublist is arbitrary. No code
- * working with pathkeys should generate a result that depends on the order
- * of a pathkey sublist.
+ * we can always create a pathkey by doing an explicit sort. The pathkeys
+ * for a sort plan's output just represent the sort key fields and the
+ * ordering operators used.
+ *
+ * Things get more interesting when we consider joins. Suppose we do a
+ * mergejoin between A and B using the mergeclause A.X = B.Y. The output
+ * of the mergejoin is sorted by X --- but it is also sorted by Y. We
+ * represent this fact by listing both keys in a single pathkey sublist:
+ * ( (A.X/xsortop B.Y/ysortop) ). This pathkey asserts that the major
+ * sort order of the Path can be taken to be *either* A.X or B.Y.
+ * They are equal, so they are both primary sort keys. By doing this,
+ * we allow future joins to use either var as a pre-sorted key, so upper
+ * Mergejoins may be able to avoid having to re-sort the Path. This is
+ * why pathkeys is a List of Lists.
*
* We keep a sortop associated with each PathKeyItem because cross-data-type
- * mergejoins are possible; for example int4=int8 is mergejoinable. In this
- * case we need to remember that the left var is ordered by int4lt while
- * the right var is ordered by int8lt. So the different members of each
- * sublist could have different sortops.
- *
- * When producing the pathkeys for a merge or nestloop join, we can keep
- * all of the keys of the outer path, since the ordering of the outer path
- * will be preserved in the result. We add to each pathkey sublist any inner
- * vars that are equijoined to any of the outer vars in the sublist. In the
- * nestloop case we have to be careful to consider only equijoin operators;
- * the nestloop's join clauses might include non-equijoin operators.
- * (Currently, we do this by considering only mergejoinable operators while
- * making the pathkeys, since we have no separate marking for operators that
- * are equijoins but aren't mergejoinable.)
+ * mergejoins are possible; for example int4 = int8 is mergejoinable.
+ * In this case we need to remember that the left var is ordered by int4lt
+ * while the right var is ordered by int8lt. So the different members of
+ * each sublist could have different sortops.
+ *
+ * Note that while the order of the top list is meaningful (primary vs.
+ * secondary sort key), the order of each sublist is arbitrary. Each sublist
+ * should be regarded as a set of equivalent keys, with no significance
+ * to the list order.
+ *
+ * With a little further thought, it becomes apparent that pathkeys for
+ * joins need not only come from mergejoins. For example, if we do a
+ * nestloop join between outer relation A and inner relation B, then any
+ * pathkeys relevant to A are still valid for the join result: we have
+ * not altered the order of the tuples from A. Even more interesting,
+ * if there was a mergeclause (more formally, an "equijoin clause") A.X=B.Y,
+ * and A.X was a pathkey for the outer relation A, then we can assert that
+ * B.Y is a pathkey for the join result; X was ordered before and still is,
+ * and the joined values of Y are equal to the joined values of X, so Y
+ * must now be ordered too. This is true even though we used no mergejoin.
+ *
+ * More generally, whenever we have an equijoin clause A.X = B.Y and a
+ * pathkey A.X, we can add B.Y to that pathkey if B is part of the joined
+ * relation the pathkey is for, *no matter how we formed the join*.
+ *
+ * In short, then: when producing the pathkeys for a merge or nestloop join,
+ * we can keep all of the keys of the outer path, since the ordering of the
+ * outer path will be preserved in the result. Furthermore, we can add to
+ * each pathkey sublist any inner vars that are equijoined to any of the
+ * outer vars in the sublist; this works regardless of whether we are
+ * implementing the join using that equijoin clause as a mergeclause,
+ * or merely enforcing the clause after-the-fact as a qpqual filter.
*
* Although Hashjoins also work only with equijoin operators, it is *not*
* safe to consider the output of a Hashjoin to be sorted in any particular
* order --- not even the outer path's order. This is true because the
* executor might have to split the join into multiple batches. Therefore
- * a Hashjoin is always given NIL pathkeys.
+ * a Hashjoin is always given NIL pathkeys. (Also, we need to use only
+ * mergejoinable operators when deducing which inner vars are now sorted,
+ * because a mergejoin operator tells us which left- and right-datatype
+ * sortops can be considered equivalent, whereas a hashjoin operator
+ * doesn't imply anything about sort order.)
*
* Pathkeys are also useful to represent an ordering that we wish to achieve,
* since they are easily compared to the pathkeys of a potential candidate
* path. So, SortClause lists are turned into pathkeys lists for use inside
* the optimizer.
*
+ * OK, now for how it *really* works:
+ *
+ * We did implement pathkeys just as described above, and found that the
+ * planner spent a huge amount of time comparing pathkeys, because the
+ * representation of pathkeys as unordered lists made it expensive to decide
+ * whether two were equal or not. So, we've modified the representation
+ * as described next.
+ *
+ * If we scan the WHERE clause for equijoin clauses (mergejoinable clauses)
+ * during planner startup, we can construct lists of equivalent pathkey items
+ * for the query. There could be more than two items per equivalence set;
+ * for example, WHERE A.X = B.Y AND B.Y = C.Z AND D.R = E.S creates the
+ * equivalence sets { A.X B.Y C.Z } and { D.R E.S } (plus associated sortops).
+ * Any pathkey item that belongs to an equivalence set implies that all the
+ * other items in its set apply to the relation too, or at least all the ones
+ * that are for fields present in the relation. (Some of the items in the
+ * set might be for as-yet-unjoined relations.) Furthermore, any multi-item
+ * pathkey sublist that appears at any stage of planning the query *must* be
+ * a subset of one or another of these equivalence sets; there's no way we'd
+ * have put two items in the same pathkey sublist unless they were equijoined
+ * in WHERE.
+ *
+ * Now suppose that we allow a pathkey sublist to contain pathkey items for
+ * vars that are not yet part of the pathkey's relation. This introduces
+ * no logical difficulty, because such items can easily be seen to be
+ * irrelevant; we just mandate that they be ignored. But having allowed
+ * this, we can declare (by fiat) that any multiple-item pathkey sublist
+ * must be equal() to the appropriate equivalence set. In effect, whenever
+ * we make a pathkey sublist that mentions any var appearing in an
+ * equivalence set, we instantly add all the other vars equivalenced to it,
+ * whether they appear yet in the pathkey's relation or not. And we also
+ * mandate that the pathkey sublist appear in the same order as the
+ * equivalence set it comes from. (In practice, we simply return a pointer
+ * to the relevant equivalence set without building any new sublist at all.)
+ * This makes comparing pathkeys very simple and fast, and saves a lot of
+ * work and memory space for pathkey construction as well.
+ *
+ * Note that pathkey sublists having just one item still exist, and are
+ * not expected to be equal() to any equivalence set. This occurs when
+ * we describe a sort order that involves a var that's not mentioned in
+ * any equijoin clause of the WHERE. We could add singleton sets containing
+ * such vars to the query's list of equivalence sets, but there's little
+ * point in doing so.
+ *
+ * By the way, it's OK and even useful for us to build equivalence sets
+ * that mention multiple vars from the same relation. For example, if
+ * we have WHERE A.X = A.Y and we are scanning A using an index on X,
+ * we can legitimately conclude that the path is sorted by Y as well;
+ * and this could be handy if Y is the variable used in other join clauses
+ * or ORDER BY. So, any WHERE clause with a mergejoinable operator can
+ * contribute to an equivalence set, even if it's not a join clause.
+ *
* -- bjm & tgl
*--------------------
*/
@@ -113,6 +186,129 @@ makePathKeyItem(Node *key, Oid sortop)
return item;
}
+/*
+ * add_equijoined_keys
+ * The given clause has a mergejoinable operator, so its two sides
+ * can be considered equal after restriction clause application; in
+ * particular, any pathkey mentioning one side (with the correct sortop)
+ * can be expanded to include the other as well. Record the vars and
+ * associated sortops in the query's equi_key_list for future use.
+ *
+ * The query's equi_key_list field points to a list of sublists of PathKeyItem
+ * nodes, where each sublist is a set of two or more vars+sortops that have
+ * been identified as logically equivalent (and, therefore, we may consider
+ * any two in a set to be equal). As described above, we will subsequently
+ * use direct pointers to one of these sublists to represent any pathkey
+ * that involves an equijoined variable.
+ *
+ * This code would actually work fine with expressions more complex than
+ * a single Var, but currently it won't see any because check_mergejoinable
+ * won't accept such clauses as mergejoinable.
+ */
+void
+add_equijoined_keys(Query *root, RestrictInfo *restrictinfo)
+{
+ Expr *clause = restrictinfo->clause;
+ PathKeyItem *item1 = makePathKeyItem((Node *) get_leftop(clause),
+ restrictinfo->left_sortop);
+ PathKeyItem *item2 = makePathKeyItem((Node *) get_rightop(clause),
+ restrictinfo->right_sortop);
+ List *newset,
+ *cursetlink;
+
+ /* We might see a clause X=X; don't make a single-element list from it */
+ if (equal(item1, item2))
+ return;
+ /*
+ * Our plan is to make a two-element set, then sweep through the existing
+ * equijoin sets looking for matches to item1 or item2. When we find one,
+ * we remove that set from equi_key_list and union it into our new set.
+ * When done, we add the new set to the front of equi_key_list.
+ *
+ * This is a standard UNION-FIND problem, for which there exist better
+ * data structures than simple lists. If this code ever proves to be
+ * a bottleneck then it could be sped up --- but for now, simple is
+ * beautiful.
+ */
+ newset = lcons(item1, lcons(item2, NIL));
+
+ foreach(cursetlink, root->equi_key_list)
+ {
+ List *curset = lfirst(cursetlink);
+
+ if (member(item1, curset) || member(item2, curset))
+ {
+ /* Found a set to merge into our new set */
+ newset = LispUnion(newset, curset);
+ /* Remove old set from equi_key_list. NOTE this does not change
+ * lnext(cursetlink), so the outer foreach doesn't break.
+ */
+ root->equi_key_list = lremove(curset, root->equi_key_list);
+ freeList(curset); /* might as well recycle old cons cells */
+ }
+ }
+
+ root->equi_key_list = lcons(newset, root->equi_key_list);
+}
+
+/*
+ * make_canonical_pathkey
+ * Given a PathKeyItem, find the equi_key_list subset it is a member of,
+ * if any. If so, return a pointer to that sublist, which is the
+ * canonical representation (for this query) of that PathKeyItem's
+ * equivalence set. If it is not found, return a single-element list
+ * containing the PathKeyItem (when the item has no equivalence peers,
+ * we just allow it to be a standalone list).
+ *
+ * Note that this function must not be used until after we have completed
+ * scanning the WHERE clause for equijoin operators.
+ */
+static List *
+make_canonical_pathkey(Query *root, PathKeyItem *item)
+{
+ List *cursetlink;
+
+ foreach(cursetlink, root->equi_key_list)
+ {
+ List *curset = lfirst(cursetlink);
+
+ if (member(item, curset))
+ return curset;
+ }
+ return lcons(item, NIL);
+}
+
+/*
+ * canonicalize_pathkeys
+ * Convert a not-necessarily-canonical pathkeys list to canonical form.
+ *
+ * Note that this function must not be used until after we have completed
+ * scanning the WHERE clause for equijoin operators.
+ */
+List *
+canonicalize_pathkeys(Query *root, List *pathkeys)
+{
+ List *new_pathkeys = NIL;
+ List *i;
+
+ foreach(i, pathkeys)
+ {
+ List *pathkey = (List *) lfirst(i);
+ PathKeyItem *item;
+
+ /*
+ * It's sufficient to look at the first entry in the sublist;
+ * if there are more entries, they're already part of an
+ * equivalence set by definition.
+ */
+ Assert(pathkey != NIL);
+ item = (PathKeyItem *) lfirst(pathkey);
+ new_pathkeys = lappend(new_pathkeys,
+ make_canonical_pathkey(root, item));
+ }
+ return new_pathkeys;
+}
+
/****************************************************************************
* PATHKEY COMPARISONS
****************************************************************************/
@@ -126,15 +322,21 @@ makePathKeyItem(Node *key, Oid sortop)
* it contains all the keys of the other plus more. For example, either
* ((A) (B)) or ((A B)) is better than ((A)).
*
- * This gets called a lot, so it is optimized.
+ * Because we actually only expect to see canonicalized pathkey sublists,
+ * we don't have to do the full two-way-subset-inclusion test on each
+ * pair of sublists that is implied by the above statement. Instead we
+ * just do an equal(). In the normal case where multi-element sublists
+ * are pointers into the root's equi_key_list, equal() will be very fast:
+ * it will recognize pointer equality when the sublists are the same,
+ * and will fail at the first sublist element when they are not.
+ *
+ * Yes, this gets called enough to be worth coding it this tensely.
*/
PathKeysComparison
compare_pathkeys(List *keys1, List *keys2)
{
List *key1,
*key2;
- bool key1_subsetof_key2 = true,
- key2_subsetof_key1 = true;
for (key1 = keys1, key2 = keys2;
key1 != NIL && key2 != NIL;
@@ -142,36 +344,12 @@ compare_pathkeys(List *keys1, List *keys2)
{
List *subkey1 = lfirst(key1);
List *subkey2 = lfirst(key2);
- List *i;
- /* We have to do this the hard way since the ordering of the subkey
- * lists is arbitrary.
+ /* We will never have two subkeys where one is a subset of the other,
+ * because of the canonicalization explained above. Either they are
+ * equal or they ain't.
*/
- if (key1_subsetof_key2)
- {
- foreach(i, subkey1)
- {
- if (! member(lfirst(i), subkey2))
- {
- key1_subsetof_key2 = false;
- break;
- }
- }
- }
-
- if (key2_subsetof_key1)
- {
- foreach(i, subkey2)
- {
- if (! member(lfirst(i), subkey1))
- {
- key2_subsetof_key1 = false;
- break;
- }
- }
- }
-
- if (!key1_subsetof_key2 && !key2_subsetof_key1)
+ if (! equal(subkey1, subkey2))
return PATHKEYS_DIFFERENT; /* no need to keep looking */
}
@@ -180,18 +358,11 @@ compare_pathkeys(List *keys1, List *keys2)
* of the other list are not NIL --- no pathkey list should ever have
* a NIL sublist.)
*/
- if (key1 != NIL)
- key1_subsetof_key2 = false;
- if (key2 != NIL)
- key2_subsetof_key1 = false;
-
- if (key1_subsetof_key2 && key2_subsetof_key1)
+ if (key1 == NIL && key2 == NIL)
return PATHKEYS_EQUAL;
- if (key1_subsetof_key2)
- return PATHKEYS_BETTER2;
- if (key2_subsetof_key1)
- return PATHKEYS_BETTER1;
- return PATHKEYS_DIFFERENT;
+ if (key1 != NIL)
+ return PATHKEYS_BETTER1; /* key1 is longer */
+ return PATHKEYS_BETTER2; /* key2 is longer */
}
/*
@@ -215,16 +386,16 @@ pathkeys_contained_in(List *keys1, List *keys2)
/*
* get_cheapest_path_for_pathkeys
- * Find the cheapest path in 'paths' that satisfies the given pathkeys.
- * Return NULL if no such path.
+ * Find the cheapest path (according to the specified criterion) that
+ * satisfies the given pathkeys. Return NULL if no such path.
*
- * 'paths' is a list of possible paths (either inner or outer)
- * 'pathkeys' represents a required ordering
- * if 'indexpaths_only' is true, only IndexPaths will be considered.
+ * 'paths' is a list of possible paths that all generate the same relation
+ * 'pathkeys' represents a required ordering (already canonicalized!)
+ * 'cost_criterion' is STARTUP_COST or TOTAL_COST
*/
Path *
get_cheapest_path_for_pathkeys(List *paths, List *pathkeys,
- bool indexpaths_only)
+ CostSelector cost_criterion)
{
Path *matched_path = NULL;
List *i;
@@ -233,15 +404,55 @@ get_cheapest_path_for_pathkeys(List *paths, List *pathkeys,
{
Path *path = (Path *) lfirst(i);
- if (indexpaths_only && ! IsA(path, IndexPath))
+ /*
+ * Since cost comparison is a lot cheaper than pathkey comparison,
+ * do that first. (XXX is that still true?)
+ */
+ if (matched_path != NULL &&
+ compare_path_costs(matched_path, path, cost_criterion) <= 0)
continue;
if (pathkeys_contained_in(pathkeys, path->pathkeys))
- {
- if (matched_path == NULL ||
- path->path_cost < matched_path->path_cost)
- matched_path = path;
- }
+ matched_path = path;
+ }
+ return matched_path;
+}
+
+/*
+ * get_cheapest_fractional_path_for_pathkeys
+ * Find the cheapest path (for retrieving a specified fraction of all
+ * the tuples) that satisfies the given pathkeys.
+ * Return NULL if no such path.
+ *
+ * See compare_fractional_path_costs() for the interpretation of the fraction
+ * parameter.
+ *
+ * 'paths' is a list of possible paths that all generate the same relation
+ * 'pathkeys' represents a required ordering (already canonicalized!)
+ * 'fraction' is the fraction of the total tuples expected to be retrieved
+ */
+Path *
+get_cheapest_fractional_path_for_pathkeys(List *paths,
+ List *pathkeys,
+ double fraction)
+{
+ Path *matched_path = NULL;
+ List *i;
+
+ foreach(i, paths)
+ {
+ Path *path = (Path *) lfirst(i);
+
+ /*
+ * Since cost comparison is a lot cheaper than pathkey comparison,
+ * do that first.
+ */
+ if (matched_path != NULL &&
+ compare_fractional_path_costs(matched_path, path, fraction) <= 0)
+ continue;
+
+ if (pathkeys_contained_in(pathkeys, path->pathkeys))
+ matched_path = path;
}
return matched_path;
}
@@ -255,18 +466,22 @@ get_cheapest_path_for_pathkeys(List *paths, List *pathkeys,
* Build a pathkeys list that describes the ordering induced by an index
* scan using the given index. (Note that an unordered index doesn't
* induce any ordering; such an index will have no sortop OIDS in
- * its "ordering" field.)
+ * its "ordering" field, and we will return NIL.)
*
- * Vars in the resulting pathkeys list are taken from the rel's targetlist.
- * If we can't find the indexkey in the targetlist, we assume that the
- * ordering of that key is not interesting.
+ * If 'scandir' is BackwardScanDirection, attempt to build pathkeys
+ * representing a backwards scan of the index. Return NIL if can't do it.
*/
List *
-build_index_pathkeys(Query *root, RelOptInfo *rel, IndexOptInfo *index)
+build_index_pathkeys(Query *root,
+ RelOptInfo *rel,
+ IndexOptInfo *index,
+ ScanDirection scandir)
{
List *retval = NIL;
int *indexkeys = index->indexkeys;
Oid *ordering = index->ordering;
+ PathKeyItem *item;
+ Oid sortop;
if (!indexkeys || indexkeys[0] == 0 ||
!ordering || ordering[0] == InvalidOid)
@@ -275,8 +490,6 @@ build_index_pathkeys(Query *root, RelOptInfo *rel, IndexOptInfo *index)
if (index->indproc)
{
/* Functional index: build a representation of the function call */
- int relid = lfirsti(rel->relids);
- Oid reloid = getrelid(relid, root->rtable);
Func *funcnode = makeNode(Func);
List *funcargs = NIL;
@@ -291,43 +504,42 @@ build_index_pathkeys(Query *root, RelOptInfo *rel, IndexOptInfo *index)
while (*indexkeys != 0)
{
- int varattno = *indexkeys;
- Oid vartypeid = get_atttype(reloid, varattno);
- int32 type_mod = get_atttypmod(reloid, varattno);
-
funcargs = lappend(funcargs,
- makeVar(relid, varattno, vartypeid,
- type_mod, 0));
+ find_indexkey_var(root, rel, *indexkeys));
indexkeys++;
}
+ sortop = *ordering;
+ if (ScanDirectionIsBackward(scandir))
+ {
+ sortop = get_commutator(sortop);
+ if (sortop == InvalidOid)
+ return NIL; /* oops, no reverse sort operator? */
+ }
+
/* Make a one-sublist pathkeys list for the function expression */
- retval = lcons(lcons(
- makePathKeyItem((Node *) make_funcclause(funcnode, funcargs),
- *ordering),
- NIL), NIL);
+ item = makePathKeyItem((Node *) make_funcclause(funcnode, funcargs),
+ sortop);
+ retval = lcons(make_canonical_pathkey(root, item), NIL);
}
else
{
/* Normal non-functional index */
- List *rel_tlist = rel->targetlist;
-
while (*indexkeys != 0 && *ordering != InvalidOid)
{
- Var *relvar = find_indexkey_var(*indexkeys, rel_tlist);
+ Var *relvar = find_indexkey_var(root, rel, *indexkeys);
- /* If we can find no tlist entry for the n'th sort key,
- * then we're done generating pathkeys; any subsequent sort keys
- * no longer apply, since we can't represent the ordering properly
- * even if there are tlist entries for them.
- */
- if (!relvar)
- break;
- /* OK, make a one-element sublist for this sort key */
- retval = lappend(retval,
- lcons(makePathKeyItem((Node *) relvar,
- *ordering),
- NIL));
+ sortop = *ordering;
+ if (ScanDirectionIsBackward(scandir))
+ {
+ sortop = get_commutator(sortop);
+ if (sortop == InvalidOid)
+ break; /* oops, no reverse sort operator? */
+ }
+
+ /* OK, make a sublist for this sort key */
+ item = makePathKeyItem((Node *) relvar, sortop);
+ retval = lappend(retval, make_canonical_pathkey(root, item));
indexkeys++;
ordering++;
@@ -338,21 +550,37 @@ build_index_pathkeys(Query *root, RelOptInfo *rel, IndexOptInfo *index)
}
/*
- * Find a var in a relation's targetlist that matches an indexkey attrnum.
+ * Find or make a Var node for the specified attribute of the rel.
+ *
+ * We first look for the var in the rel's target list, because that's
+ * easy and fast. But the var might not be there (this should normally
+ * only happen for vars that are used in WHERE restriction clauses,
+ * but not in join clauses or in the SELECT target list). In that case,
+ * gin up a Var node the hard way.
*/
static Var *
-find_indexkey_var(int indexkey, List *tlist)
+find_indexkey_var(Query *root, RelOptInfo *rel, AttrNumber varattno)
{
List *temp;
+ int relid;
+ Oid reloid,
+ vartypeid;
+ int32 type_mod;
- foreach(temp, tlist)
+ foreach(temp, rel->targetlist)
{
Var *tle_var = get_expr(lfirst(temp));
- if (IsA(tle_var, Var) && tle_var->varattno == indexkey)
+ if (IsA(tle_var, Var) && tle_var->varattno == varattno)
return tle_var;
}
- return NULL;
+
+ relid = lfirsti(rel->relids);
+ reloid = getrelid(relid, root->rtable);
+ vartypeid = get_atttype(reloid, varattno);
+ type_mod = get_atttypmod(reloid, varattno);
+
+ return makeVar(relid, varattno, vartypeid, type_mod, 0);
}
/*
@@ -360,164 +588,33 @@ find_indexkey_var(int indexkey, List *tlist)
* Build the path keys for a join relation constructed by mergejoin or
* nestloop join. These keys should include all the path key vars of the
* outer path (since the join will retain the ordering of the outer path)
- * plus any vars of the inner path that are mergejoined to the outer vars.
+ * plus any vars of the inner path that are equijoined to the outer vars.
*
- * Per the discussion at the top of this file, mergejoined inner vars
+ * Per the discussion at the top of this file, equijoined inner vars
* can be considered path keys of the result, just the same as the outer
- * vars they were joined with.
- *
- * We can also use inner path vars as pathkeys of a nestloop join, but we
- * must be careful that we only consider equijoin clauses and not general
- * join clauses. For example, "t1.a < t2.b" might be a join clause of a
- * nestloop, but it doesn't result in b acquiring the ordering of a!
- * joinpath.c handles that problem by only passing this routine clauses
- * that are marked mergejoinable, even if a nestloop join is being built.
- * Therefore we only have 't1.a = t2.b' style clauses, and can expect that
- * the inner var will acquire the outer's ordering no matter which join
- * method is actually used.
- *
- * We drop pathkeys that are not vars of the join relation's tlist,
- * on the assumption that they are not interesting to higher levels.
- * (Is this correct?? To support expression pathkeys we might want to
- * check that all vars mentioned in the key are in the tlist, instead.)
- *
- * All vars in the result are taken from the join relation's tlist,
- * not from the given pathkeys or joinclauses.
+ * vars they were joined with; furthermore, it doesn't matter what kind
+ * of join algorithm is actually used.
*
* 'outer_pathkeys' is the list of the outer path's path keys
* 'join_rel_tlist' is the target list of the join relation
- * 'joinclauses' is the list of mergejoinable clauses to consider (note this
- * is a list of RestrictInfos, not just bare qual clauses); can be NIL
+ * 'equi_key_list' is the query's list of pathkeyitem equivalence sets
*
* Returns the list of new path keys.
- *
*/
List *
build_join_pathkeys(List *outer_pathkeys,
List *join_rel_tlist,
- List *joinclauses)
+ List *equi_key_list)
{
- List *final_pathkeys = NIL;
- List *i;
-
- foreach(i, outer_pathkeys)
- {
- List *outer_pathkey = lfirst(i);
- List *new_pathkey;
-
- new_pathkey = build_join_pathkey(outer_pathkey, join_rel_tlist,
- joinclauses);
- /* if we can find no sortable vars for the n'th sort key,
- * then we're done generating pathkeys; any subsequent sort keys
- * no longer apply, since we can't represent the ordering properly.
- */
- if (new_pathkey == NIL)
- break;
- final_pathkeys = lappend(final_pathkeys, new_pathkey);
- }
- return final_pathkeys;
-}
-
-/*
- * build_join_pathkey
- * Generate an individual pathkey sublist, consisting of the outer vars
- * already mentioned in 'pathkey' plus any inner vars that are joined to
- * them (and thus can now also be considered path keys, per discussion
- * at the top of this file).
- *
- * Note that each returned pathkey uses the var node found in
- * 'join_rel_tlist' rather than the input pathkey or joinclause var node.
- * (Is this important?)
- *
- * Returns a new pathkey (list of PathKeyItems).
- */
-static List *
-build_join_pathkey(List *pathkey,
- List *join_rel_tlist,
- List *joinclauses)
-{
- List *new_pathkey = NIL;
- List *i,
- *j;
-
- foreach(i, pathkey)
- {
- PathKeyItem *key = (PathKeyItem *) lfirst(i);
- Node *tlist_key;
-
- Assert(key && IsA(key, PathKeyItem));
-
- tlist_key = matching_tlist_expr(key->key, join_rel_tlist);
- if (tlist_key)
- new_pathkey = lcons(makePathKeyItem(tlist_key,
- key->sortop),
- new_pathkey);
-
- foreach(j, joinclauses)
- {
- RestrictInfo *restrictinfo = (RestrictInfo *) lfirst(j);
- Expr *joinclause = restrictinfo->clause;
- /* We assume the clause is a binary opclause... */
- Node *l = (Node *) get_leftop(joinclause);
- Node *r = (Node *) get_rightop(joinclause);
- Node *other_var = NULL;
- Oid other_sortop = InvalidOid;
-
- if (equal(key->key, l))
- {
- other_var = r;
- other_sortop = restrictinfo->right_sortop;
- }
- else if (equal(key->key, r))
- {
- other_var = l;
- other_sortop = restrictinfo->left_sortop;
- }
-
- if (other_var && other_sortop)
- {
- tlist_key = matching_tlist_expr(other_var, join_rel_tlist);
- if (tlist_key)
- new_pathkey = lcons(makePathKeyItem(tlist_key,
- other_sortop),
- new_pathkey);
- }
- }
- }
-
- return new_pathkey;
-}
-
-/*
- * commute_pathkeys
- * Attempt to commute the operators in a set of pathkeys, producing
- * pathkeys that describe the reverse sort order (DESC instead of ASC).
- * Returns TRUE if successful (all the operators have commutators).
- *
- * CAUTION: given pathkeys are modified in place, even if not successful!!
- * Usually, caller should have just built or copied the pathkeys list to
- * ensure there are no unwanted side-effects.
- */
-bool
-commute_pathkeys(List *pathkeys)
-{
- List *i;
-
- foreach(i, pathkeys)
- {
- List *pathkey = lfirst(i);
- List *j;
-
- foreach(j, pathkey)
- {
- PathKeyItem *key = lfirst(j);
-
- key->sortop = get_commutator(key->sortop);
- if (key->sortop == InvalidOid)
- return false;
- }
- }
- return true; /* successful */
+ /*
+ * This used to be quite a complex bit of code, but now that all
+ * pathkey sublists start out life canonicalized, we don't have to
+ * do a darn thing here! The inner-rel vars we used to need to add
+ * are *already* part of the outer pathkey!
+ *
+ * I'd remove the routine entirely, but maybe someday we'll need it...
+ */
+ return outer_pathkeys;
}
/****************************************************************************
@@ -529,11 +626,18 @@ commute_pathkeys(List *pathkeys)
* Generate a pathkeys list that represents the sort order specified
* by a list of SortClauses (GroupClauses will work too!)
*
+ * NB: the result is NOT in canonical form, but must be passed through
+ * canonicalize_pathkeys() before it can be used for comparisons or
+ * labeling relation sort orders. (We do things this way because
+ * union_planner needs to be able to construct requested pathkeys before
+ * the pathkey equivalence sets have been created for the query.)
+ *
* 'sortclauses' is a list of SortClause or GroupClause nodes
* 'tlist' is the targetlist to find the referenced tlist entries in
*/
List *
-make_pathkeys_for_sortclauses(List *sortclauses, List *tlist)
+make_pathkeys_for_sortclauses(List *sortclauses,
+ List *tlist)
{
List *pathkeys = NIL;
List *i;
@@ -546,7 +650,11 @@ make_pathkeys_for_sortclauses(List *sortclauses, List *tlist)
sortkey = get_sortgroupclause_expr(sortcl, tlist);
pathkey = makePathKeyItem(sortkey, sortcl->sortop);
- /* pathkey becomes a one-element sublist */
+ /*
+ * The pathkey becomes a one-element sublist, for now;
+ * canonicalize_pathkeys() might replace it with a longer
+ * sublist later.
+ */
pathkeys = lappend(pathkeys, lcons(pathkey, NIL));
}
return pathkeys;
@@ -599,6 +707,7 @@ find_mergeclauses_for_pathkeys(List *pathkeys, List *restrictinfos)
{
PathKeyItem *keyitem = lfirst(j);
Node *key = keyitem->key;
+ Oid keyop = keyitem->sortop;
List *k;
foreach(k, restrictinfos)
@@ -607,8 +716,10 @@ find_mergeclauses_for_pathkeys(List *pathkeys, List *restrictinfos)
Assert(restrictinfo->mergejoinoperator != InvalidOid);
- if ((equal(key, get_leftop(restrictinfo->clause)) ||
- equal(key, get_rightop(restrictinfo->clause))) &&
+ if (((keyop == restrictinfo->left_sortop &&
+ equal(key, get_leftop(restrictinfo->clause))) ||
+ (keyop == restrictinfo->right_sortop &&
+ equal(key, get_rightop(restrictinfo->clause)))) &&
! member(restrictinfo, mergeclauses))
{
matched_restrictinfo = restrictinfo;
@@ -645,7 +756,7 @@ find_mergeclauses_for_pathkeys(List *pathkeys, List *restrictinfos)
* 'mergeclauses' is a list of RestrictInfos for mergejoin clauses
* that will be used in a merge join.
* 'tlist' is a relation target list for either the inner or outer
- * side of the proposed join rel.
+ * side of the proposed join rel. (Not actually needed anymore)
*
* Returns a pathkeys list that can be applied to the indicated relation.
*
@@ -654,7 +765,9 @@ find_mergeclauses_for_pathkeys(List *pathkeys, List *restrictinfos)
* just make the keys, eh?
*/
List *
-make_pathkeys_for_mergeclauses(List *mergeclauses, List *tlist)
+make_pathkeys_for_mergeclauses(Query *root,
+ List *mergeclauses,
+ List *tlist)
{
List *pathkeys = NIL;
List *i;
@@ -664,32 +777,24 @@ make_pathkeys_for_mergeclauses(List *mergeclauses, List *tlist)
RestrictInfo *restrictinfo = (RestrictInfo *) lfirst(i);
Node *key;
Oid sortop;
+ PathKeyItem *item;
Assert(restrictinfo->mergejoinoperator != InvalidOid);
/*
* Find the key and sortop needed for this mergeclause.
*
- * We can use either side of the mergeclause, since we haven't yet
- * committed to which side will be inner.
+ * Both sides of the mergeclause should appear in one of the
+ * query's pathkey equivalence classes, so it doesn't matter
+ * which one we use here.
*/
- key = matching_tlist_expr((Node *) get_leftop(restrictinfo->clause),
- tlist);
+ key = (Node *) get_leftop(restrictinfo->clause);
sortop = restrictinfo->left_sortop;
- if (! key)
- {
- key = matching_tlist_expr((Node *) get_rightop(restrictinfo->clause),
- tlist);
- sortop = restrictinfo->right_sortop;
- }
- if (! key)
- elog(ERROR, "make_pathkeys_for_mergeclauses: can't find key");
/*
* Add a pathkey sublist for this sort item
*/
- pathkeys = lappend(pathkeys,
- lcons(makePathKeyItem(key, sortop),
- NIL));
+ item = makePathKeyItem(key, sortop);
+ pathkeys = lappend(pathkeys, make_canonical_pathkey(root, item));
}
return pathkeys;
diff --git a/src/backend/optimizer/path/tidpath.c b/src/backend/optimizer/path/tidpath.c
index ab0427ef32263d36eb468dc75af4f2dbf9dc6562..1e7dc43473b24f638a02263ae750c575ffb144b8 100644
--- a/src/backend/optimizer/path/tidpath.c
+++ b/src/backend/optimizer/path/tidpath.c
@@ -9,7 +9,7 @@
*
*
* IDENTIFICATION
- * $Header: /cvsroot/pgsql/src/backend/optimizer/path/tidpath.c,v 1.4 2000/02/07 04:40:59 tgl Exp $
+ * $Header: /cvsroot/pgsql/src/backend/optimizer/path/tidpath.c,v 1.5 2000/02/15 20:49:17 tgl Exp $
*
*-------------------------------------------------------------------------
*/
@@ -36,7 +36,7 @@
#include "parser/parsetree.h"
#include "utils/lsyscache.h"
-static List *create_tidscan_joinpaths(RelOptInfo *);
+static void create_tidscan_joinpaths(RelOptInfo *rel);
static List *TidqualFromRestrictinfo(List *relids, List *restrictinfo);
static bool isEvaluable(int varno, Node *node);
static Node *TidequalClause(int varno, Expr *node);
@@ -234,61 +234,54 @@ TidqualFromRestrictinfo(List *relids, List *restrictinfo)
/*
* create_tidscan_joinpaths
- * Creates a path corresponding to a tid_direct scan, returning the
- * pathnode.
+ * Create innerjoin paths if there are suitable joinclauses.
*
+ * XXX does this actually work?
*/
-List *
+static void
create_tidscan_joinpaths(RelOptInfo *rel)
{
List *rlst = NIL,
*lst;
- TidPath *pathnode = (TidPath *) NULL;
- List *restinfo,
- *tideval;
foreach (lst, rel->joininfo)
{
- JoinInfo *joininfo = (JoinInfo *)lfirst(lst);
+ JoinInfo *joininfo = (JoinInfo *) lfirst(lst);
+ List *restinfo,
+ *tideval;
restinfo = joininfo->jinfo_restrictinfo;
tideval = TidqualFromRestrictinfo(rel->relids, restinfo);
if (length(tideval) == 1)
{
- pathnode = makeNode(TidPath);
+ TidPath *pathnode = makeNode(TidPath);
pathnode->path.pathtype = T_TidScan;
pathnode->path.parent = rel;
pathnode->path.pathkeys = NIL;
- pathnode->path.path_cost = cost_tidscan(rel, tideval);
pathnode->tideval = tideval;
pathnode->unjoined_relids = joininfo->unjoined_relids;
+
+ cost_tidscan(&pathnode->path, rel, tideval);
+
rlst = lappend(rlst, pathnode);
}
}
rel->innerjoin = nconc(rel->innerjoin, rlst);
- return rlst;
}
/*
* create_tidscan_paths
- * Creates a path corresponding to a tid direct scan, returning the
- * pathnode List.
- *
+ * Creates paths corresponding to tid direct scans of the given rel.
+ * Candidate paths are added to the rel's pathlist (using add_path).
*/
-List *
+void
create_tidscan_paths(Query *root, RelOptInfo *rel)
{
- List *rlst = NIL;
- TidPath *pathnode = (TidPath *) NULL;
List *tideval = TidqualFromRestrictinfo(rel->relids,
rel->baserestrictinfo);
if (tideval)
- pathnode = create_tidscan_path(rel, tideval);
- if (pathnode)
- rlst = lcons(pathnode, rlst);
+ add_path(rel, (Path *) create_tidscan_path(rel, tideval));
create_tidscan_joinpaths(rel);
-
- return rlst;
}
diff --git a/src/backend/optimizer/plan/createplan.c b/src/backend/optimizer/plan/createplan.c
index 97a021a2dd221fbf9deeaacc765099108dc077a9..55af1426fdca3e75bb7ec953da212a2eb31a65da 100644
--- a/src/backend/optimizer/plan/createplan.c
+++ b/src/backend/optimizer/plan/createplan.c
@@ -10,7 +10,7 @@
*
*
* IDENTIFICATION
- * $Header: /cvsroot/pgsql/src/backend/optimizer/plan/createplan.c,v 1.84 2000/02/07 04:41:00 tgl Exp $
+ * $Header: /cvsroot/pgsql/src/backend/optimizer/plan/createplan.c,v 1.85 2000/02/15 20:49:18 tgl Exp $
*
*-------------------------------------------------------------------------
*/
@@ -57,7 +57,9 @@ static Node *fix_indxqual_operand(Node *node, int baserelid,
Form_pg_index index,
Oid *opclass);
static IndexScan *make_indexscan(List *qptlist, List *qpqual, Index scanrelid,
- List *indxid, List *indxqual, List *indxqualorig);
+ List *indxid, List *indxqual,
+ List *indxqualorig,
+ ScanDirection indexscandir);
static TidScan *make_tidscan(List *qptlist, List *qpqual, Index scanrelid,
List *tideval);
static NestLoop *make_nestloop(List *qptlist, List *qpqual, Plan *lefttree,
@@ -427,9 +429,13 @@ create_indexscan_node(Query *root,
baserelid,
best_path->indexid,
fixed_indxqual,
- indxqual);
+ indxqual,
+ best_path->indexscandir);
copy_path_costsize(&scan_node->scan.plan, &best_path->path);
+ /* set up rows estimate (just to make EXPLAIN output reasonable) */
+ if (plan_rows < 1.0)
+ plan_rows = 1.0;
scan_node->scan.plan.plan_rows = plan_rows;
return scan_node;
@@ -437,16 +443,14 @@ create_indexscan_node(Query *root,
static TidScan *
make_tidscan(List *qptlist,
- List *qpqual,
- Index scanrelid,
- List *tideval)
+ List *qpqual,
+ Index scanrelid,
+ List *tideval)
{
TidScan *node = makeNode(TidScan);
Plan *plan = &node->scan.plan;
- plan->cost = 0;
- plan->plan_rows = 0;
- plan->plan_width = 0;
+ /* cost should be inserted by caller */
plan->state = (EState *) NULL;
plan->targetlist = qptlist;
plan->qual = qpqual;
@@ -1038,13 +1042,15 @@ copy_path_costsize(Plan *dest, Path *src)
{
if (src)
{
- dest->cost = src->path_cost;
+ dest->startup_cost = src->startup_cost;
+ dest->total_cost = src->total_cost;
dest->plan_rows = src->parent->rows;
dest->plan_width = src->parent->width;
}
else
{
- dest->cost = 0;
+ dest->startup_cost = 0;
+ dest->total_cost = 0;
dest->plan_rows = 0;
dest->plan_width = 0;
}
@@ -1061,13 +1067,15 @@ copy_plan_costsize(Plan *dest, Plan *src)
{
if (src)
{
- dest->cost = src->cost;
+ dest->startup_cost = src->startup_cost;
+ dest->total_cost = src->total_cost;
dest->plan_rows = src->plan_rows;
dest->plan_width = src->plan_width;
}
else
{
- dest->cost = 0;
+ dest->startup_cost = 0;
+ dest->total_cost = 0;
dest->plan_rows = 0;
dest->plan_width = 0;
}
@@ -1130,7 +1138,7 @@ make_seqscan(List *qptlist,
SeqScan *node = makeNode(SeqScan);
Plan *plan = &node->plan;
- copy_plan_costsize(plan, NULL);
+ /* cost should be inserted by caller */
plan->state = (EState *) NULL;
plan->targetlist = qptlist;
plan->qual = qpqual;
@@ -1148,12 +1156,13 @@ make_indexscan(List *qptlist,
Index scanrelid,
List *indxid,
List *indxqual,
- List *indxqualorig)
+ List *indxqualorig,
+ ScanDirection indexscandir)
{
IndexScan *node = makeNode(IndexScan);
Plan *plan = &node->scan.plan;
- copy_plan_costsize(plan, NULL);
+ /* cost should be inserted by caller */
plan->state = (EState *) NULL;
plan->targetlist = qptlist;
plan->qual = qpqual;
@@ -1163,7 +1172,7 @@ make_indexscan(List *qptlist,
node->indxid = indxid;
node->indxqual = indxqual;
node->indxqualorig = indxqualorig;
- node->indxorderdir = NoMovementScanDirection;
+ node->indxorderdir = indexscandir;
node->scan.scanstate = (CommonScanState *) NULL;
return node;
@@ -1219,6 +1228,10 @@ make_hash(List *tlist, Var *hashkey, Plan *lefttree)
Plan *plan = &node->plan;
copy_plan_costsize(plan, lefttree);
+ /* For plausibility, make startup & total costs equal total cost of
+ * input plan; this only affects EXPLAIN display not decisions.
+ */
+ plan->startup_cost = plan->total_cost;
plan->state = (EState *) NULL;
plan->targetlist = tlist;
plan->qual = NULL;
@@ -1255,9 +1268,12 @@ make_sort(List *tlist, Oid nonameid, Plan *lefttree, int keycount)
{
Sort *node = makeNode(Sort);
Plan *plan = &node->plan;
+ Path sort_path; /* dummy for result of cost_sort */
- copy_plan_costsize(plan, lefttree);
- plan->cost += cost_sort(NIL, plan->plan_rows, plan->plan_width);
+ copy_plan_costsize(plan, lefttree); /* only care about copying size */
+ cost_sort(&sort_path, NIL, lefttree->plan_rows, lefttree->plan_width);
+ plan->startup_cost = sort_path.startup_cost + lefttree->total_cost;
+ plan->total_cost = sort_path.total_cost + lefttree->total_cost;
plan->state = (EState *) NULL;
plan->targetlist = tlist;
plan->qual = NIL;
@@ -1279,7 +1295,11 @@ make_material(List *tlist,
Plan *plan = &node->plan;
copy_plan_costsize(plan, lefttree);
- /* XXX shouldn't we charge some additional cost for materialization? */
+ /* For plausibility, make startup & total costs equal total cost of
+ * input plan; this only affects EXPLAIN display not decisions.
+ * XXX shouldn't we charge some additional cost for materialization?
+ */
+ plan->startup_cost = plan->total_cost;
plan->state = (EState *) NULL;
plan->targetlist = tlist;
plan->qual = NIL;
@@ -1292,30 +1312,38 @@ make_material(List *tlist,
}
Agg *
-make_agg(List *tlist, Plan *lefttree)
+make_agg(List *tlist, List *qual, Plan *lefttree)
{
Agg *node = makeNode(Agg);
+ Plan *plan = &node->plan;
- copy_plan_costsize(&node->plan, lefttree);
+ copy_plan_costsize(plan, lefttree);
+ /*
+ * Charge one cpu_operator_cost per aggregate function per input tuple.
+ */
+ plan->total_cost += cpu_operator_cost * plan->plan_rows *
+ (length(pull_agg_clause((Node *) tlist)) +
+ length(pull_agg_clause((Node *) qual)));
/*
- * The tuple width from the input node is OK, as is the cost (we are
- * ignoring the cost of computing the aggregate; is there any value
- * in accounting for it?). But the tuple count is bogus. We will
- * produce a single tuple if the input is not a Group, and a tuple
- * per group otherwise. For now, estimate the number of groups as
- * 10% of the number of tuples --- bogus, but how to do better?
+ * We will produce a single output tuple if the input is not a Group,
+ * and a tuple per group otherwise. For now, estimate the number of
+ * groups as 10% of the number of tuples --- bogus, but how to do better?
* (Note we assume the input Group node is in "tuplePerGroup" mode,
* so it didn't reduce its row count already.)
*/
if (IsA(lefttree, Group))
- node->plan.plan_rows *= 0.1;
+ plan->plan_rows *= 0.1;
else
- node->plan.plan_rows = 1;
- node->plan.state = (EState *) NULL;
- node->plan.qual = NULL;
- node->plan.targetlist = tlist;
- node->plan.lefttree = lefttree;
- node->plan.righttree = (Plan *) NULL;
+ {
+ plan->plan_rows = 1;
+ plan->startup_cost = plan->total_cost;
+ }
+
+ plan->state = (EState *) NULL;
+ plan->qual = qual;
+ plan->targetlist = tlist;
+ plan->lefttree = lefttree;
+ plan->righttree = (Plan *) NULL;
return node;
}
@@ -1328,8 +1356,14 @@ make_group(List *tlist,
Plan *lefttree)
{
Group *node = makeNode(Group);
+ Plan *plan = &node->plan;
- copy_plan_costsize(&node->plan, lefttree);
+ copy_plan_costsize(plan, lefttree);
+ /*
+ * Charge one cpu_operator_cost per comparison per input tuple.
+ * We assume all columns get compared at most of the tuples.
+ */
+ plan->total_cost += cpu_operator_cost * plan->plan_rows * ngrp;
/*
* If tuplePerGroup (which is named exactly backwards) is true,
* we will return all the input tuples, so the input node's row count
@@ -1338,12 +1372,13 @@ make_group(List *tlist,
* tuples --- bogus, but how to do better?
*/
if (! tuplePerGroup)
- node->plan.plan_rows *= 0.1;
- node->plan.state = (EState *) NULL;
- node->plan.qual = NULL;
- node->plan.targetlist = tlist;
- node->plan.lefttree = lefttree;
- node->plan.righttree = (Plan *) NULL;
+ plan->plan_rows *= 0.1;
+
+ plan->state = (EState *) NULL;
+ plan->qual = NULL;
+ plan->targetlist = tlist;
+ plan->lefttree = lefttree;
+ plan->righttree = (Plan *) NULL;
node->tuplePerGroup = tuplePerGroup;
node->numCols = ngrp;
node->grpColIdx = grpColIdx;
@@ -1367,11 +1402,17 @@ make_unique(List *tlist, Plan *lefttree, List *distinctList)
List *slitem;
copy_plan_costsize(plan, lefttree);
+ /*
+ * Charge one cpu_operator_cost per comparison per input tuple.
+ * We assume all columns get compared at most of the tuples.
+ */
+ plan->total_cost += cpu_operator_cost * plan->plan_rows * numCols;
/*
* As for Group, we make the unsupported assumption that there will be
* 10% as many tuples out as in.
*/
plan->plan_rows *= 0.1;
+
plan->state = (EState *) NULL;
plan->targetlist = tlist;
plan->qual = NIL;
diff --git a/src/backend/optimizer/plan/initsplan.c b/src/backend/optimizer/plan/initsplan.c
index b94cc3e4b425e532d1f8683c62df909143fdbaa8..6b6f3971719d05b0eefec89cb022a6daa29c7998 100644
--- a/src/backend/optimizer/plan/initsplan.c
+++ b/src/backend/optimizer/plan/initsplan.c
@@ -8,7 +8,7 @@
*
*
* IDENTIFICATION
- * $Header: /cvsroot/pgsql/src/backend/optimizer/plan/initsplan.c,v 1.44 2000/02/07 04:41:00 tgl Exp $
+ * $Header: /cvsroot/pgsql/src/backend/optimizer/plan/initsplan.c,v 1.45 2000/02/15 20:49:18 tgl Exp $
*
*-------------------------------------------------------------------------
*/
@@ -21,6 +21,7 @@
#include "optimizer/cost.h"
#include "optimizer/joininfo.h"
#include "optimizer/pathnode.h"
+#include "optimizer/paths.h"
#include "optimizer/planmain.h"
#include "optimizer/tlist.h"
#include "optimizer/var.h"
@@ -31,7 +32,6 @@ static void add_restrict_and_join_to_rel(Query *root, Node *clause);
static void add_join_info_to_rels(Query *root, RestrictInfo *restrictinfo,
Relids join_relids);
static void add_vars_to_targetlist(Query *root, List *vars);
-static void set_restrictinfo_joininfo(RestrictInfo *restrictinfo);
static void check_mergejoinable(RestrictInfo *restrictinfo);
static void check_hashjoinable(RestrictInfo *restrictinfo);
@@ -150,7 +150,9 @@ add_restrict_and_join_to_rels(Query *root, List *clauses)
* Add clause information to either the 'RestrictInfo' or 'JoinInfo' field
* (depending on whether the clause is a join) of each base relation
* mentioned in the clause. A RestrictInfo node is created and added to
- * the appropriate list for each rel.
+ * the appropriate list for each rel. Also, if the clause uses a
+ * mergejoinable operator, enter the left- and right-side expressions
+ * into the query's lists of equijoined vars.
*/
static void
add_restrict_and_join_to_rel(Query *root, Node *clause)
@@ -181,14 +183,29 @@ add_restrict_and_join_to_rel(Query *root, Node *clause)
rel->baserestrictinfo = lcons(restrictinfo,
rel->baserestrictinfo);
+ /*
+ * Check for a "mergejoinable" clause even though it's not a join
+ * clause. This is so that we can recognize that "a.x = a.y" makes
+ * x and y eligible to be considered equal, even when they belong
+ * to the same rel. Without this, we would not recognize that
+ * "a.x = a.y AND a.x = b.z AND a.y = c.q" allows us to consider
+ * z and q equal after their rels are joined.
+ */
+ check_mergejoinable(restrictinfo);
}
else
{
/*
* 'clause' is a join clause, since there is more than one atom in
* the relid list. Set additional RestrictInfo fields for joining.
+ *
+ * We need the merge info whether or not mergejoin is enabled (for
+ * constructing equijoined-var lists), but we don't bother setting
+ * hash info if hashjoin is disabled.
*/
- set_restrictinfo_joininfo(restrictinfo);
+ check_mergejoinable(restrictinfo);
+ if (enable_hashjoin)
+ check_hashjoinable(restrictinfo);
/*
* Add clause to the join lists of all the relevant
* relations. (If, perchance, 'clause' contains NO vars, then
@@ -202,6 +219,15 @@ add_restrict_and_join_to_rel(Query *root, Node *clause)
*/
add_vars_to_targetlist(root, vars);
}
+
+ /*
+ * If the clause has a mergejoinable operator, then the two sides
+ * represent equivalent PathKeyItems for path keys: any path that is
+ * sorted by one side will also be sorted by the other (after joining,
+ * that is). Record the key equivalence for future use.
+ */
+ if (restrictinfo->mergejoinoperator != InvalidOid)
+ add_equijoined_keys(root, restrictinfo);
}
/*
@@ -247,24 +273,10 @@ add_join_info_to_rels(Query *root, RestrictInfo *restrictinfo,
/*****************************************************************************
*
- * JOININFO
+ * CHECKS FOR MERGEJOINABLE AND HASHJOINABLE CLAUSES
*
*****************************************************************************/
-/*
- * set_restrictinfo_joininfo
- * Examine a RestrictInfo that has been determined to be a join clause,
- * and set the merge and hash info fields if it can be merge/hash joined.
- */
-static void
-set_restrictinfo_joininfo(RestrictInfo *restrictinfo)
-{
- if (enable_mergejoin)
- check_mergejoinable(restrictinfo);
- if (enable_hashjoin)
- check_hashjoinable(restrictinfo);
-}
-
/*
* check_mergejoinable
* If the restrictinfo's clause is mergejoinable, set the mergejoin
@@ -272,10 +284,7 @@ set_restrictinfo_joininfo(RestrictInfo *restrictinfo)
*
* Currently, we support mergejoin for binary opclauses where
* both operands are simple Vars and the operator is a mergejoinable
- * operator. (Note: since we are only examining clauses that were
- * classified as joins, it is certain that the two Vars belong to
- * different relations... if we accepted more general clause structures
- * we might need to check that the two sides refer to different rels...)
+ * operator.
*/
static void
check_mergejoinable(RestrictInfo *restrictinfo)
@@ -320,10 +329,7 @@ check_mergejoinable(RestrictInfo *restrictinfo)
*
* Currently, we support hashjoin for binary opclauses where
* both operands are simple Vars and the operator is a hashjoinable
- * operator. (Note: since we are only examining clauses that were
- * classified as joins, it is certain that the two Vars belong to
- * different relations... if we accepted more general clause structures
- * we might need to check that the two sides refer to different rels...)
+ * operator.
*/
static void
check_hashjoinable(RestrictInfo *restrictinfo)
diff --git a/src/backend/optimizer/plan/planmain.c b/src/backend/optimizer/plan/planmain.c
index a414a910fefe8e55fe5f3bee9e4cd5424f367307..cfa134a3889fea78419bfa7c0eab2baaee99ba48 100644
--- a/src/backend/optimizer/plan/planmain.c
+++ b/src/backend/optimizer/plan/planmain.c
@@ -8,7 +8,7 @@
*
*
* IDENTIFICATION
- * $Header: /cvsroot/pgsql/src/backend/optimizer/plan/planmain.c,v 1.51 2000/02/07 04:41:00 tgl Exp $
+ * $Header: /cvsroot/pgsql/src/backend/optimizer/plan/planmain.c,v 1.52 2000/02/15 20:49:18 tgl Exp $
*
*-------------------------------------------------------------------------
*/
@@ -19,6 +19,7 @@
#include "optimizer/clauses.h"
#include "optimizer/cost.h"
+#include "optimizer/pathnode.h"
#include "optimizer/paths.h"
#include "optimizer/planmain.h"
#include "optimizer/prep.h"
@@ -27,10 +28,11 @@
#include "utils/lsyscache.h"
-static Plan *subplanner(Query *root, List *flat_tlist, List *qual);
+static Plan *subplanner(Query *root, List *flat_tlist, List *qual,
+ double tuple_fraction);
-/*
+/*--------------------
* query_planner
* Routine to create a query plan. It does so by first creating a
* subplan for the topmost level of attributes in the query. Then,
@@ -41,25 +43,41 @@ static Plan *subplanner(Query *root, List *flat_tlist, List *qual);
* be placed where and any relation level qualifications to be
* satisfied.
*
- * tlist is the target list of the query (do NOT use root->targetList!)
- * qual is the qualification of the query (likewise!)
+ * tlist is the target list of the query (do NOT use root->targetList!)
+ * qual is the qualification of the query (likewise!)
+ * tuple_fraction is the fraction of tuples we expect will be retrieved
+ *
+ * Note: the Query node now also includes a query_pathkeys field, which
+ * is both an input and an output of query_planner(). The input value
+ * signals query_planner that the indicated sort order is wanted in the
+ * final output plan. The output value is the actual pathkeys of the
+ * selected path. This might not be the same as what the caller requested;
+ * the caller must do pathkeys_contained_in() to decide whether an
+ * explicit sort is still needed. (The main reason query_pathkeys is a
+ * Query field and not a passed parameter is that the low-level routines
+ * in indxpath.c need to see it.) The pathkeys value passed to query_planner
+ * has not yet been "canonicalized", since the necessary info does not get
+ * computed until subplanner() scans the qual clauses. We canonicalize it
+ * inside subplanner() as soon as that task is done. The output value
+ * will be in canonical form as well.
*
- * Note: the Query node now also includes a query_pathkeys field, which
- * is both an input and an output of query_planner(). The input value
- * signals query_planner that the indicated sort order is wanted in the
- * final output plan. The output value is the actual pathkeys of the
- * selected path. This might not be the same as what the caller requested;
- * the caller must do pathkeys_contained_in() to decide whether an
- * explicit sort is still needed. (The main reason query_pathkeys is a
- * Query field and not a passed parameter is that the low-level routines
- * in indxpath.c need to see it.)
+ * tuple_fraction is interpreted as follows:
+ * 0 (or less): expect all tuples to be retrieved (normal case)
+ * 0 < tuple_fraction < 1: expect the given fraction of tuples available
+ * from the plan to be retrieved
+ * tuple_fraction >= 1: tuple_fraction is the absolute number of tuples
+ * expected to be retrieved (ie, a LIMIT specification)
+ * Note that while this routine and its subroutines treat a negative
+ * tuple_fraction the same as 0, union_planner has a different interpretation.
*
- * Returns a query plan.
+ * Returns a query plan.
+ *--------------------
*/
Plan *
query_planner(Query *root,
List *tlist,
- List *qual)
+ List *qual,
+ double tuple_fraction)
{
List *constant_qual = NIL;
List *var_only_tlist;
@@ -149,7 +167,7 @@ query_planner(Query *root,
/*
* Choose the best access path and build a plan for it.
*/
- subplan = subplanner(root, var_only_tlist, qual);
+ subplan = subplanner(root, var_only_tlist, qual, tuple_fraction);
/*
* Build a result node to control the plan if we have constant quals.
@@ -192,33 +210,50 @@ query_planner(Query *root,
* Subplanner creates an entire plan consisting of joins and scans
* for processing a single level of attributes.
*
- * flat_tlist is the flattened target list
- * qual is the qualification to be satisfied
+ * flat_tlist is the flattened target list
+ * qual is the qualification to be satisfied
+ * tuple_fraction is the fraction of tuples we expect will be retrieved
*
- * Returns a subplan.
+ * See query_planner() comments about the interpretation of tuple_fraction.
*
+ * Returns a subplan.
*/
static Plan *
subplanner(Query *root,
List *flat_tlist,
- List *qual)
+ List *qual,
+ double tuple_fraction)
{
RelOptInfo *final_rel;
- Cost cheapest_cost;
- Path *sortedpath;
+ Path *cheapestpath;
+ Path sort_path; /* dummy for result of cost_sort */
+ Path *presortedpath;
/*
* Initialize the targetlist and qualification, adding entries to
* base_rel_list as relation references are found (e.g., in the
- * qualification, the targetlist, etc.)
+ * qualification, the targetlist, etc.). Restrict and join clauses
+ * are added to appropriate lists belonging to the mentioned relations,
+ * and we also build lists of equijoined keys for pathkey construction.
*/
root->base_rel_list = NIL;
root->join_rel_list = NIL;
+ root->equi_key_list = NIL;
make_var_only_tlist(root, flat_tlist);
add_restrict_and_join_to_rels(root, qual);
add_missing_rels_to_query(root);
+ /*
+ * We should now have all the pathkey equivalence sets built,
+ * so it's now possible to convert the requested query_pathkeys
+ * to canonical form.
+ */
+ root->query_pathkeys = canonicalize_pathkeys(root, root->query_pathkeys);
+
+ /*
+ * Ready to do the primary planning.
+ */
final_rel = make_one_rel(root);
if (! final_rel)
@@ -258,96 +293,81 @@ subplanner(Query *root,
foreach(pathnode, final_rel->pathlist)
{
if (xfunc_do_predmig((Path *) lfirst(pathnode)))
- set_cheapest(final_rel, final_rel->pathlist);
+ set_cheapest(final_rel);
}
}
#endif
/*
- * Determine the cheapest path and create a subplan to execute it.
+ * Now that we have an estimate of the final rel's size, we can convert
+ * a tuple_fraction specified as an absolute count (ie, a LIMIT option)
+ * into a fraction of the total tuples.
+ */
+ if (tuple_fraction >= 1.0)
+ tuple_fraction /= final_rel->rows;
+
+ /*
+ * Determine the cheapest path, independently of any ordering
+ * considerations. We do, however, take into account whether the
+ * whole plan is expected to be evaluated or not.
+ */
+ if (tuple_fraction <= 0.0 || tuple_fraction >= 1.0)
+ cheapestpath = final_rel->cheapest_total_path;
+ else
+ cheapestpath =
+ get_cheapest_fractional_path_for_pathkeys(final_rel->pathlist,
+ NIL,
+ tuple_fraction);
+
+ Assert(cheapestpath != NULL);
+
+ /*
+ * Select the best path and create a subplan to execute it.
*
* If no special sort order is wanted, or if the cheapest path is
- * already appropriately ordered, just use the cheapest path.
+ * already appropriately ordered, we use the cheapest path found above.
*/
if (root->query_pathkeys == NIL ||
pathkeys_contained_in(root->query_pathkeys,
- final_rel->cheapestpath->pathkeys))
+ cheapestpath->pathkeys))
{
- root->query_pathkeys = final_rel->cheapestpath->pathkeys;
- return create_plan(root, final_rel->cheapestpath);
+ root->query_pathkeys = cheapestpath->pathkeys;
+ return create_plan(root, cheapestpath);
}
/*
* Otherwise, look to see if we have an already-ordered path that is
- * cheaper than doing an explicit sort on cheapestpath.
+ * cheaper than doing an explicit sort on the cheapest-total-cost path.
*/
- cheapest_cost = final_rel->cheapestpath->path_cost +
- cost_sort(root->query_pathkeys, final_rel->rows, final_rel->width);
-
- sortedpath = get_cheapest_path_for_pathkeys(final_rel->pathlist,
- root->query_pathkeys,
- false);
- if (sortedpath)
+ cheapestpath = final_rel->cheapest_total_path;
+ cost_sort(&sort_path, root->query_pathkeys,
+ final_rel->rows, final_rel->width);
+ sort_path.startup_cost += cheapestpath->total_cost;
+ sort_path.total_cost += cheapestpath->total_cost;
+
+ presortedpath =
+ get_cheapest_fractional_path_for_pathkeys(final_rel->pathlist,
+ root->query_pathkeys,
+ tuple_fraction);
+ if (presortedpath)
{
- if (sortedpath->path_cost <= cheapest_cost)
+ if (compare_fractional_path_costs(presortedpath, &sort_path,
+ tuple_fraction) <= 0)
{
/* Found a better presorted path, use it */
- root->query_pathkeys = sortedpath->pathkeys;
- return create_plan(root, sortedpath);
+ root->query_pathkeys = presortedpath->pathkeys;
+ return create_plan(root, presortedpath);
}
/* otherwise, doing it the hard way is still cheaper */
}
- else
- {
- /*
- * If we found no usable presorted path at all, it is possible
- * that the user asked for descending sort order. Check to see
- * if we can satisfy the pathkeys by using a backwards indexscan.
- * To do this, we commute all the operators in the pathkeys and
- * then look for a matching path that is an IndexPath.
- */
- List *commuted_pathkeys = copyObject(root->query_pathkeys);
-
- if (commute_pathkeys(commuted_pathkeys))
- {
- /* pass 'true' to force only IndexPaths to be considered */
- sortedpath = get_cheapest_path_for_pathkeys(final_rel->pathlist,
- commuted_pathkeys,
- true);
- if (sortedpath && sortedpath->path_cost <= cheapest_cost)
- {
- /*
- * Kluge here: since IndexPath has no representation for
- * backwards scan, we have to convert to Plan format and
- * then poke the result.
- */
- Plan *sortedplan = create_plan(root, sortedpath);
- List *sortedpathkeys;
-
- Assert(IsA(sortedplan, IndexScan));
- ((IndexScan *) sortedplan)->indxorderdir = BackwardScanDirection;
- /*
- * Need to generate commuted keys representing the actual
- * sort order. This should succeed, probably, but just in
- * case it does not, use the original root->query_pathkeys
- * as a conservative approximation.
- */
- sortedpathkeys = copyObject(sortedpath->pathkeys);
- if (commute_pathkeys(sortedpathkeys))
- root->query_pathkeys = sortedpathkeys;
-
- return sortedplan;
- }
- }
- }
/*
- * Nothing for it but to sort the cheapestpath --- but we let the
- * caller do that. union_planner has to be able to add a sort node
+ * Nothing for it but to sort the cheapest-total-cost path --- but we let
+ * the caller do that. union_planner has to be able to add a sort node
* anyway, so no need for extra code here. (Furthermore, the given
- * pathkeys might involve something we can't compute here, such as
- * an aggregate function...)
+ * pathkeys might involve something we can't compute here, such as an
+ * aggregate function...)
*/
- root->query_pathkeys = final_rel->cheapestpath->pathkeys;
- return create_plan(root, final_rel->cheapestpath);
+ root->query_pathkeys = cheapestpath->pathkeys;
+ return create_plan(root, cheapestpath);
}
diff --git a/src/backend/optimizer/plan/planner.c b/src/backend/optimizer/plan/planner.c
index 28483fd4734966caab4ec8ee3bbeadbe6a6d099c..cf400f8df1bb84b77bc176657f3c86f96e96f005 100644
--- a/src/backend/optimizer/plan/planner.c
+++ b/src/backend/optimizer/plan/planner.c
@@ -8,7 +8,7 @@
*
*
* IDENTIFICATION
- * $Header: /cvsroot/pgsql/src/backend/optimizer/plan/planner.c,v 1.74 2000/01/27 18:11:31 tgl Exp $
+ * $Header: /cvsroot/pgsql/src/backend/optimizer/plan/planner.c,v 1.75 2000/02/15 20:49:18 tgl Exp $
*
*-------------------------------------------------------------------------
*/
@@ -61,7 +61,7 @@ planner(Query *parse)
transformKeySetQuery(parse);
- result_plan = union_planner(parse);
+ result_plan = union_planner(parse, -1.0 /* default case */);
Assert(PlannerQueryLevel == 1);
if (PlannerPlanId > 0)
@@ -76,23 +76,39 @@ planner(Query *parse)
return result_plan;
}
-/*
+/*--------------------
* union_planner
+ * Invokes the planner on union-type queries (both regular UNIONs and
+ * appends produced by inheritance), recursing if necessary to get them
+ * all, then processes normal plans.
*
- * Invokes the planner on union queries if there are any left,
- * recursing if necessary to get them all, then processes normal plans.
+ * parse is the querytree produced by the parser & rewriter.
+ * tuple_fraction is the fraction of tuples we expect will be retrieved
*
- * Returns a query plan.
+ * tuple_fraction is interpreted as follows:
+ * < 0: determine fraction by inspection of query (normal case)
+ * 0: expect all tuples to be retrieved
+ * 0 < tuple_fraction < 1: expect the given fraction of tuples available
+ * from the plan to be retrieved
+ * tuple_fraction >= 1: tuple_fraction is the absolute number of tuples
+ * expected to be retrieved (ie, a LIMIT specification)
+ * The normal case is to pass -1, but some callers pass values >= 0 to
+ * override this routine's determination of the appropriate fraction.
*
+ * Returns a query plan.
+ *--------------------
*/
Plan *
-union_planner(Query *parse)
+union_planner(Query *parse,
+ double tuple_fraction)
{
List *tlist = parse->targetList;
List *rangetable = parse->rtable;
Plan *result_plan = (Plan *) NULL;
AttrNumber *groupColIdx = NULL;
List *current_pathkeys = NIL;
+ List *group_pathkeys;
+ List *sort_pathkeys;
Index rt_index;
/*
@@ -139,6 +155,12 @@ union_planner(Query *parse)
* Actually, for a normal UNION we have done an explicit sort; ought
* to change interface to plan_union_queries to pass that info back!
*/
+
+ /* Calculate pathkeys that represent grouping/ordering requirements */
+ group_pathkeys = make_pathkeys_for_sortclauses(parse->groupClause,
+ tlist);
+ sort_pathkeys = make_pathkeys_for_sortclauses(parse->sortClause,
+ tlist);
}
else if ((rt_index = first_inherit_rt_entry(rangetable)) != -1)
{
@@ -176,6 +198,12 @@ union_planner(Query *parse)
* We leave current_pathkeys NIL indicating we do not know sort order
* of the Append-ed results.
*/
+
+ /* Calculate pathkeys that represent grouping/ordering requirements */
+ group_pathkeys = make_pathkeys_for_sortclauses(parse->groupClause,
+ tlist);
+ sort_pathkeys = make_pathkeys_for_sortclauses(parse->sortClause,
+ tlist);
}
else
{
@@ -229,32 +257,131 @@ union_planner(Query *parse)
*/
sub_tlist = make_subplanTargetList(parse, tlist, &groupColIdx);
+ /* Calculate pathkeys that represent grouping/ordering requirements */
+ group_pathkeys = make_pathkeys_for_sortclauses(parse->groupClause,
+ tlist);
+ sort_pathkeys = make_pathkeys_for_sortclauses(parse->sortClause,
+ tlist);
+
/*
* Figure out whether we need a sorted result from query_planner.
*
* If we have a GROUP BY clause, then we want a result sorted
* properly for grouping. Otherwise, if there is an ORDER BY clause,
- * we want to sort by the ORDER BY clause.
+ * we want to sort by the ORDER BY clause. (Note: if we have both,
+ * and ORDER BY is a superset of GROUP BY, it would be tempting to
+ * request sort by ORDER BY --- but that might just leave us failing
+ * to exploit an available sort order at all. Needs more thought...)
*/
if (parse->groupClause)
+ parse->query_pathkeys = group_pathkeys;
+ else if (parse->sortClause)
+ parse->query_pathkeys = sort_pathkeys;
+ else
+ parse->query_pathkeys = NIL;
+
+ /*
+ * Figure out whether we expect to retrieve all the tuples that the
+ * plan can generate, or to stop early due to a LIMIT or other
+ * factors. If the caller passed a value >= 0, believe that value,
+ * else do our own examination of the query context.
+ */
+ if (tuple_fraction < 0.0)
{
- parse->query_pathkeys =
- make_pathkeys_for_sortclauses(parse->groupClause, tlist);
+ /* Initial assumption is we need all the tuples */
+ tuple_fraction = 0.0;
+ /*
+ * Check for a LIMIT.
+ *
+ * For now, we deliberately ignore the OFFSET clause, so that
+ * queries with the same LIMIT and different OFFSETs will get
+ * the same queryplan and therefore generate consistent results
+ * (to the extent the planner can guarantee that, anyway).
+ * XXX Perhaps it would be better to use the OFFSET too, and tell
+ * users to specify ORDER BY if they want consistent results
+ * across different LIMIT queries.
+ */
+ if (parse->limitCount != NULL)
+ {
+ if (IsA(parse->limitCount, Const))
+ {
+ Const *ccount = (Const *) parse->limitCount;
+ tuple_fraction = (double) ((int) (ccount->constvalue));
+ /* the constant can legally be either 0 ("ALL") or a
+ * positive integer; either is consistent with our
+ * conventions for tuple_fraction.
+ */
+ }
+ else
+ {
+ /* It's a PARAM ... don't know exactly what the limit
+ * will be, but for lack of a better idea assume 10%
+ * of the plan's result is wanted.
+ */
+ tuple_fraction = 0.10;
+ }
+ }
+ /*
+ * Check for a retrieve-into-portal, ie DECLARE CURSOR.
+ *
+ * We have no real idea how many tuples the user will ultimately
+ * FETCH from a cursor, but it seems a good bet that he doesn't
+ * want 'em all. Optimize for 10% retrieval (you gotta better
+ * number?)
+ */
+ if (parse->isPortal)
+ tuple_fraction = 0.10;
}
- else if (parse->sortClause)
+ /*
+ * Adjust tuple_fraction if we see that we are going to apply
+ * grouping/aggregation/etc. This is not overridable by the
+ * caller, since it reflects plan actions that this routine
+ * will certainly take, not assumptions about context.
+ */
+ if (parse->groupClause)
{
- parse->query_pathkeys =
- make_pathkeys_for_sortclauses(parse->sortClause, tlist);
+ /*
+ * In GROUP BY mode, we have the little problem that we don't
+ * really know how many input tuples will be needed to make a
+ * group, so we can't translate an output LIMIT count into an
+ * input count. For lack of a better idea, assume 10% of the
+ * input data will be processed if there is any output limit.
+ */
+ if (tuple_fraction > 0.0)
+ tuple_fraction = 0.10;
+ /*
+ * If both GROUP BY and ORDER BY are specified, we will need
+ * two levels of sort --- and, therefore, certainly need to
+ * read all the input tuples --- unless ORDER BY is a subset
+ * of GROUP BY. (Although we are comparing non-canonicalized
+ * pathkeys here, it should be OK since they will both contain
+ * only single-element sublists at this point. See pathkeys.c.)
+ */
+ if (parse->groupClause && parse->sortClause &&
+ ! pathkeys_contained_in(sort_pathkeys, group_pathkeys))
+ tuple_fraction = 0.0;
}
- else
+ else if (parse->hasAggs)
{
- parse->query_pathkeys = NIL;
+ /* Ungrouped aggregate will certainly want all the input tuples. */
+ tuple_fraction = 0.0;
+ }
+ else if (parse->distinctClause)
+ {
+ /*
+ * SELECT DISTINCT, like GROUP, will absorb an unpredictable
+ * number of input tuples per output tuple. So, fall back to
+ * our same old 10% default...
+ */
+ if (tuple_fraction > 0.0)
+ tuple_fraction = 0.10;
}
/* Generate the (sub) plan */
result_plan = query_planner(parse,
sub_tlist,
- (List *) parse->qual);
+ (List *) parse->qual,
+ tuple_fraction);
/* query_planner returns actual sort order (which is not
* necessarily what we requested) in query_pathkeys.
@@ -266,6 +393,13 @@ union_planner(Query *parse)
if (! result_plan)
elog(ERROR, "union_planner: failed to create plan");
+ /*
+ * We couldn't canonicalize group_pathkeys and sort_pathkeys before
+ * running query_planner(), so do it now.
+ */
+ group_pathkeys = canonicalize_pathkeys(parse, group_pathkeys);
+ sort_pathkeys = canonicalize_pathkeys(parse, sort_pathkeys);
+
/*
* If we have a GROUP BY clause, insert a group node (plus the
* appropriate sort node, if necessary).
@@ -274,7 +408,6 @@ union_planner(Query *parse)
{
bool tuplePerGroup;
List *group_tlist;
- List *group_pathkeys;
bool is_sorted;
/*
@@ -300,8 +433,6 @@ union_planner(Query *parse)
* Figure out whether the path result is already ordered the way we
* need it --- if so, no need for an explicit sort step.
*/
- group_pathkeys = make_pathkeys_for_sortclauses(parse->groupClause,
- tlist);
if (pathkeys_contained_in(group_pathkeys, current_pathkeys))
{
is_sorted = true; /* no sort needed now */
@@ -352,15 +483,15 @@ union_planner(Query *parse)
}
/*
- * If aggregate is present, insert the agg node
+ * If aggregate is present, insert the Agg node
+ *
+ * HAVING clause, if any, becomes qual of the Agg node
*/
if (parse->hasAggs)
{
- result_plan = (Plan *) make_agg(tlist, result_plan);
-
- /* HAVING clause, if any, becomes qual of the Agg node */
- result_plan->qual = (List *) parse->havingQual;
-
+ result_plan = (Plan *) make_agg(tlist,
+ (List *) parse->havingQual,
+ result_plan);
/* Note: Agg does not affect any existing sort order of the tuples */
}
@@ -370,10 +501,6 @@ union_planner(Query *parse)
*/
if (parse->sortClause)
{
- List *sort_pathkeys;
-
- sort_pathkeys = make_pathkeys_for_sortclauses(parse->sortClause,
- tlist);
if (! pathkeys_contained_in(sort_pathkeys, current_pathkeys))
{
result_plan = make_sortplan(tlist, parse->sortClause, result_plan);
diff --git a/src/backend/optimizer/plan/subselect.c b/src/backend/optimizer/plan/subselect.c
index da95a2df41f6796f739848cbccf60a5e858b3d05..2790b2740b69ba1f5e0280cba6e4bb375f25db61 100644
--- a/src/backend/optimizer/plan/subselect.c
+++ b/src/backend/optimizer/plan/subselect.c
@@ -7,7 +7,7 @@
* Portions Copyright (c) 1994, Regents of the University of California
*
* IDENTIFICATION
- * $Header: /cvsroot/pgsql/src/backend/optimizer/plan/subselect.c,v 1.27 2000/01/26 05:56:38 momjian Exp $
+ * $Header: /cvsroot/pgsql/src/backend/optimizer/plan/subselect.c,v 1.28 2000/02/15 20:49:18 tgl Exp $
*
*-------------------------------------------------------------------------
*/
@@ -123,6 +123,7 @@ static Node *
make_subplan(SubLink *slink)
{
SubPlan *node = makeNode(SubPlan);
+ double tuple_fraction;
Plan *plan;
List *lst;
Node *result;
@@ -132,7 +133,26 @@ make_subplan(SubLink *slink)
PlannerQueryLevel++; /* we becomes child */
- node->plan = plan = union_planner((Query *) slink->subselect);
+ /*
+ * For an EXISTS subplan, tell lower-level planner to expect that
+ * only the first tuple will be retrieved. For ALL, ANY, and MULTIEXPR
+ * subplans, we will be able to stop evaluating if the test condition
+ * fails, so very often not all the tuples will be retrieved; for lack
+ * of a better idea, specify 50% retrieval. For EXPR_SUBLINK use default
+ * behavior.
+ *
+ * NOTE: if you change these numbers, also change cost_qual_eval_walker
+ * in costsize.c.
+ */
+ if (slink->subLinkType == EXISTS_SUBLINK)
+ tuple_fraction = 1.0; /* just like a LIMIT 1 */
+ else if (slink->subLinkType == EXPR_SUBLINK)
+ tuple_fraction = -1.0; /* default behavior */
+ else
+ tuple_fraction = 0.5; /* 50% */
+
+ node->plan = plan = union_planner((Query *) slink->subselect,
+ tuple_fraction);
/*
* Assign subPlan, extParam and locParam to plan nodes. At the moment,
diff --git a/src/backend/optimizer/prep/prepunion.c b/src/backend/optimizer/prep/prepunion.c
index 9a86cb23488dd051012213c8e522bdee6a70324b..10a48c666e66ca7645bab4e5404237901dacec59 100644
--- a/src/backend/optimizer/prep/prepunion.c
+++ b/src/backend/optimizer/prep/prepunion.c
@@ -8,7 +8,7 @@
*
*
* IDENTIFICATION
- * $Header: /cvsroot/pgsql/src/backend/optimizer/prep/prepunion.c,v 1.44 2000/02/15 03:37:26 thomas Exp $
+ * $Header: /cvsroot/pgsql/src/backend/optimizer/prep/prepunion.c,v 1.45 2000/02/15 20:49:19 tgl Exp $
*
*-------------------------------------------------------------------------
*/
@@ -122,28 +122,35 @@ plan_union_queries(Query *parse)
/* Is this a simple one */
if (!union_all_found ||
!union_found ||
- /* A trailing UNION negates the affect of earlier UNION ALLs */
+ /* A trailing UNION negates the effect of earlier UNION ALLs */
!last_union_all_flag)
{
List *hold_unionClause = parse->unionClause;
+ double tuple_fraction = -1.0; /* default processing */
- /* we will do this later, so don't do it now */
+ /* we will do sorting later, so don't do it now */
if (!union_all_found ||
!last_union_all_flag)
{
parse->sortClause = NIL;
parse->distinctClause = NIL;
+ /*
+ * force lower-level planning to assume that all tuples will
+ * be retrieved, even if it sees a LIMIT in the query node.
+ */
+ tuple_fraction = 0.0;
}
parse->unionClause = NIL; /* prevent recursion */
- union_plans = lcons(union_planner(parse), NIL);
+ union_plans = lcons(union_planner(parse, tuple_fraction), NIL);
union_rts = lcons(parse->rtable, NIL);
foreach(ulist, hold_unionClause)
{
Query *union_query = lfirst(ulist);
- union_plans = lappend(union_plans, union_planner(union_query));
+ union_plans = lappend(union_plans,
+ union_planner(union_query, tuple_fraction));
union_rts = lappend(union_rts, union_query->rtable);
}
}
@@ -165,9 +172,12 @@ plan_union_queries(Query *parse)
/*
* Recursion, but UNION only. The last one is a UNION, so it will
- * not come here in recursion,
+ * not come here in recursion.
+ *
+ * XXX is it OK to pass default -1 to union_planner in this path,
+ * or should we force a tuple_fraction value?
*/
- union_plans = lcons(union_planner(parse), NIL);
+ union_plans = lcons(union_planner(parse, -1.0), NIL);
union_rts = lcons(parse->rtable, NIL);
/* Append the remaining UNION ALLs */
@@ -175,7 +185,8 @@ plan_union_queries(Query *parse)
{
Query *union_all_query = lfirst(ulist);
- union_plans = lappend(union_plans, union_planner(union_all_query));
+ union_plans = lappend(union_plans,
+ union_planner(union_all_query, -1.0));
union_rts = lappend(union_rts, union_all_query->rtable);
}
}
@@ -295,6 +306,7 @@ plan_inherit_query(Relids relids,
List *union_plans = NIL;
List *union_rtentries = NIL;
List *save_tlist = root->targetList;
+ double tuple_fraction;
List *i;
/*
@@ -303,6 +315,17 @@ plan_inherit_query(Relids relids,
*/
root->targetList = NIL;
+ /*
+ * If we are going to need sorting or grouping at the top level,
+ * force lower-level planners to assume that all tuples will be
+ * retrieved.
+ */
+ if (root->distinctClause || root->sortClause ||
+ root->groupClause || root->hasAggs)
+ tuple_fraction = 0.0; /* will need all tuples from each subplan */
+ else
+ tuple_fraction = -1.0; /* default behavior is OK (I think) */
+
foreach(i, relids)
{
int relid = lfirsti(i);
@@ -344,7 +367,8 @@ plan_inherit_query(Relids relids,
relid,
new_root);
- union_plans = lappend(union_plans, union_planner(new_root));
+ union_plans = lappend(union_plans,
+ union_planner(new_root, tuple_fraction));
union_rtentries = lappend(union_rtentries, new_rt_entry);
}
@@ -551,14 +575,17 @@ make_append(List *appendplans,
node->unionrtables = unionrtables;
node->inheritrelid = rt_index;
node->inheritrtable = inheritrtable;
- node->plan.cost = 0;
+ node->plan.startup_cost = 0;
+ node->plan.total_cost = 0;
node->plan.plan_rows = 0;
node->plan.plan_width = 0;
foreach(subnode, appendplans)
{
Plan *subplan = (Plan *) lfirst(subnode);
- node->plan.cost += subplan->cost;
+ if (subnode == appendplans) /* first node? */
+ node->plan.startup_cost = subplan->startup_cost;
+ node->plan.total_cost += subplan->total_cost;
node->plan.plan_rows += subplan->plan_rows;
if (node->plan.plan_width < subplan->plan_width)
node->plan.plan_width = subplan->plan_width;
diff --git a/src/backend/optimizer/util/pathnode.c b/src/backend/optimizer/util/pathnode.c
index 7c3c20b855f0327ae097eedb25f878f64bd0d72a..ba991388de0962d7a234c2d3876e90fde93a6e62 100644
--- a/src/backend/optimizer/util/pathnode.c
+++ b/src/backend/optimizer/util/pathnode.c
@@ -8,7 +8,7 @@
*
*
* IDENTIFICATION
- * $Header: /cvsroot/pgsql/src/backend/optimizer/util/pathnode.c,v 1.59 2000/02/07 04:41:01 tgl Exp $
+ * $Header: /cvsroot/pgsql/src/backend/optimizer/util/pathnode.c,v 1.60 2000/02/15 20:49:20 tgl Exp $
*
*-------------------------------------------------------------------------
*/
@@ -29,67 +29,122 @@
*****************************************************************************/
/*
- * path_is_cheaper
- * Returns t iff 'path1' is cheaper than 'path2'.
+ * compare_path_costs
+ * Return -1, 0, or +1 according as path1 is cheaper, the same cost,
+ * or more expensive than path2 for the specified criterion.
+ */
+int
+compare_path_costs(Path *path1, Path *path2, CostSelector criterion)
+{
+ if (criterion == STARTUP_COST)
+ {
+ if (path1->startup_cost < path2->startup_cost)
+ return -1;
+ if (path1->startup_cost > path2->startup_cost)
+ return +1;
+ /*
+ * If paths have the same startup cost (not at all unlikely),
+ * order them by total cost.
+ */
+ if (path1->total_cost < path2->total_cost)
+ return -1;
+ if (path1->total_cost > path2->total_cost)
+ return +1;
+ }
+ else
+ {
+ if (path1->total_cost < path2->total_cost)
+ return -1;
+ if (path1->total_cost > path2->total_cost)
+ return +1;
+ /*
+ * If paths have the same total cost, order them by startup cost.
+ */
+ if (path1->startup_cost < path2->startup_cost)
+ return -1;
+ if (path1->startup_cost > path2->startup_cost)
+ return +1;
+ }
+ return 0;
+}
+
+/*
+ * compare_path_fractional_costs
+ * Return -1, 0, or +1 according as path1 is cheaper, the same cost,
+ * or more expensive than path2 for fetching the specified fraction
+ * of the total tuples.
*
+ * If fraction is <= 0 or > 1, we interpret it as 1, ie, we select the
+ * path with the cheaper total_cost.
*/
-bool
-path_is_cheaper(Path *path1, Path *path2)
+int
+compare_fractional_path_costs(Path *path1, Path *path2,
+ double fraction)
{
- return (bool) (path1->path_cost < path2->path_cost);
+ Cost cost1,
+ cost2;
+
+ if (fraction <= 0.0 || fraction >= 1.0)
+ return compare_path_costs(path1, path2, TOTAL_COST);
+ cost1 = path1->startup_cost +
+ fraction * (path1->total_cost - path1->startup_cost);
+ cost2 = path2->startup_cost +
+ fraction * (path2->total_cost - path2->startup_cost);
+ if (cost1 < cost2)
+ return -1;
+ if (cost1 > cost2)
+ return +1;
+ return 0;
}
/*
* set_cheapest
- * Finds the minimum cost path from among a relation's paths.
+ * Find the minimum-cost paths from among a relation's paths,
+ * and save them in the rel's cheapest-path fields.
*
- * 'parent_rel' is the parent relation
- * 'pathlist' is a list of path nodes corresponding to 'parent_rel'
- *
- * Returns and sets the relation entry field with the pathnode that
- * is minimum.
+ * This is normally called only after we've finished constructing the path
+ * list for the rel node.
*
+ * If we find two paths of identical costs, try to keep the better-sorted one.
+ * The paths might have unrelated sort orderings, in which case we can only
+ * guess which might be better to keep, but if one is superior then we
+ * definitely should keep it.
*/
-Path *
-set_cheapest(RelOptInfo *parent_rel, List *pathlist)
+void
+set_cheapest(RelOptInfo *parent_rel)
{
+ List *pathlist = parent_rel->pathlist;
List *p;
- Path *cheapest_so_far;
+ Path *cheapest_startup_path;
+ Path *cheapest_total_path;
Assert(IsA(parent_rel, RelOptInfo));
Assert(pathlist != NIL);
- cheapest_so_far = (Path *) lfirst(pathlist);
+ cheapest_startup_path = cheapest_total_path = (Path *) lfirst(pathlist);
foreach(p, lnext(pathlist))
{
Path *path = (Path *) lfirst(p);
-
- if (path_is_cheaper(path, cheapest_so_far))
- cheapest_so_far = path;
+ int cmp;
+
+ cmp = compare_path_costs(cheapest_startup_path, path, STARTUP_COST);
+ if (cmp > 0 ||
+ (cmp == 0 &&
+ compare_pathkeys(cheapest_startup_path->pathkeys,
+ path->pathkeys) == PATHKEYS_BETTER2))
+ cheapest_startup_path = path;
+
+ cmp = compare_path_costs(cheapest_total_path, path, TOTAL_COST);
+ if (cmp > 0 ||
+ (cmp == 0 &&
+ compare_pathkeys(cheapest_total_path->pathkeys,
+ path->pathkeys) == PATHKEYS_BETTER2))
+ cheapest_total_path = path;
}
- parent_rel->cheapestpath = cheapest_so_far;
-
- return cheapest_so_far;
-}
-
-/*
- * add_pathlist
- * Consider each path given in new_paths, and add it to the parent rel's
- * pathlist if it seems worthy.
- */
-void
-add_pathlist(RelOptInfo *parent_rel, List *new_paths)
-{
- List *p1;
-
- foreach(p1, new_paths)
- {
- Path *new_path = (Path *) lfirst(p1);
-
- add_path(parent_rel, new_path);
- }
+ parent_rel->cheapest_startup_path = cheapest_startup_path;
+ parent_rel->cheapest_total_path = cheapest_total_path;
}
/*
@@ -97,12 +152,18 @@ add_pathlist(RelOptInfo *parent_rel, List *new_paths)
* Consider a potential implementation path for the specified parent rel,
* and add it to the rel's pathlist if it is worthy of consideration.
* A path is worthy if it has either a better sort order (better pathkeys)
- * or cheaper cost than any of the existing old paths.
+ * or cheaper cost (on either dimension) than any of the existing old paths.
*
* Unless parent_rel->pruneable is false, we also remove from the rel's
* pathlist any old paths that are dominated by new_path --- that is,
* new_path is both cheaper and at least as well ordered.
*
+ * NOTE: discarded Path objects are immediately pfree'd to reduce planner
+ * memory consumption. We dare not try to free the substructure of a Path,
+ * since much of it may be shared with other Paths or the query tree itself;
+ * but just recycling discarded Path nodes is a very useful savings in
+ * a large join tree.
+ *
* 'parent_rel' is the relation entry to which the path corresponds.
* 'new_path' is a potential path for parent_rel.
*
@@ -124,26 +185,40 @@ add_path(RelOptInfo *parent_rel, Path *new_path)
{
Path *old_path = (Path *) lfirst(p1);
bool remove_old = false; /* unless new proves superior */
+ int costcmp;
- switch (compare_pathkeys(new_path->pathkeys, old_path->pathkeys))
+ costcmp = compare_path_costs(new_path, old_path, TOTAL_COST);
+ /*
+ * If the two paths compare differently for startup and total cost,
+ * then we want to keep both, and we can skip the (much slower)
+ * comparison of pathkeys. If they compare the same, proceed with
+ * the pathkeys comparison. Note this test relies on the fact that
+ * compare_path_costs will only return 0 if both costs are equal
+ * (and, therefore, there's no need to call it twice in that case).
+ */
+ if (costcmp == 0 ||
+ costcmp == compare_path_costs(new_path, old_path, STARTUP_COST))
{
- case PATHKEYS_EQUAL:
- if (new_path->path_cost < old_path->path_cost)
- remove_old = true; /* new dominates old */
- else
- accept_new = false; /* old equals or dominates new */
- break;
- case PATHKEYS_BETTER1:
- if (new_path->path_cost <= old_path->path_cost)
- remove_old = true; /* new dominates old */
- break;
- case PATHKEYS_BETTER2:
- if (new_path->path_cost >= old_path->path_cost)
- accept_new = false; /* old dominates new */
- break;
- case PATHKEYS_DIFFERENT:
- /* keep both paths, since they have different ordering */
- break;
+ switch (compare_pathkeys(new_path->pathkeys, old_path->pathkeys))
+ {
+ case PATHKEYS_EQUAL:
+ if (costcmp < 0)
+ remove_old = true; /* new dominates old */
+ else
+ accept_new = false; /* old equals or dominates new */
+ break;
+ case PATHKEYS_BETTER1:
+ if (costcmp <= 0)
+ remove_old = true; /* new dominates old */
+ break;
+ case PATHKEYS_BETTER2:
+ if (costcmp >= 0)
+ accept_new = false; /* old dominates new */
+ break;
+ case PATHKEYS_DIFFERENT:
+ /* keep both paths, since they have different ordering */
+ break;
+ }
}
/*
@@ -156,6 +231,7 @@ add_path(RelOptInfo *parent_rel, Path *new_path)
lnext(p1_prev) = lnext(p1);
else
parent_rel->pathlist = lnext(p1);
+ pfree(old_path);
}
else
p1_prev = p1;
@@ -174,6 +250,11 @@ add_path(RelOptInfo *parent_rel, Path *new_path)
/* Accept the path */
parent_rel->pathlist = lcons(new_path, parent_rel->pathlist);
}
+ else
+ {
+ /* Reject and recycle the path */
+ pfree(new_path);
+ }
}
@@ -195,7 +276,8 @@ create_seqscan_path(RelOptInfo *rel)
pathnode->pathtype = T_SeqScan;
pathnode->parent = rel;
pathnode->pathkeys = NIL; /* seqscan has unordered result */
- pathnode->path_cost = cost_seqscan(rel);
+
+ cost_seqscan(pathnode, rel);
return pathnode;
}
@@ -208,6 +290,10 @@ create_seqscan_path(RelOptInfo *rel)
* 'index' is an index on 'rel'
* 'restriction_clauses' is a list of RestrictInfo nodes
* to be used as index qual conditions in the scan.
+ * 'indexscandir' is ForwardScanDirection or BackwardScanDirection
+ * if the caller expects a specific scan direction,
+ * or NoMovementScanDirection if the caller is willing to accept
+ * an unordered index.
*
* Returns the new path node.
*/
@@ -215,14 +301,31 @@ IndexPath *
create_index_path(Query *root,
RelOptInfo *rel,
IndexOptInfo *index,
- List *restriction_clauses)
+ List *restriction_clauses,
+ ScanDirection indexscandir)
{
IndexPath *pathnode = makeNode(IndexPath);
List *indexquals;
pathnode->path.pathtype = T_IndexScan;
pathnode->path.parent = rel;
- pathnode->path.pathkeys = build_index_pathkeys(root, rel, index);
+
+ pathnode->path.pathkeys = build_index_pathkeys(root, rel, index,
+ indexscandir);
+ if (pathnode->path.pathkeys == NIL)
+ {
+ /* No ordering available from index, is that OK? */
+ if (! ScanDirectionIsNoMovement(indexscandir))
+ elog(ERROR, "create_index_path: failed to create ordered index scan");
+ }
+ else
+ {
+ /* The index is ordered, and build_index_pathkeys defaulted to
+ * forward scan, so make sure we mark the pathnode properly.
+ */
+ if (ScanDirectionIsNoMovement(indexscandir))
+ indexscandir = ForwardScanDirection;
+ }
indexquals = get_actual_clauses(restriction_clauses);
/* expand special operators to indexquals the executor can handle */
@@ -234,10 +337,10 @@ create_index_path(Query *root,
*/
pathnode->indexid = lconsi(index->indexoid, NIL);
pathnode->indexqual = lcons(indexquals, NIL);
+ pathnode->indexscandir = indexscandir;
pathnode->joinrelids = NIL; /* no join clauses here */
- pathnode->path.path_cost = cost_index(root, rel, index, indexquals,
- false);
+ cost_index(&pathnode->path, root, rel, index, indexquals, false);
return pathnode;
}
@@ -256,13 +359,14 @@ create_tidscan_path(RelOptInfo *rel, List *tideval)
pathnode->path.pathtype = T_TidScan;
pathnode->path.parent = rel;
pathnode->path.pathkeys = NIL;
- pathnode->path.path_cost = cost_tidscan(rel, tideval);
- /* divide selectivity for each clause to get an equal selectivity
- * as IndexScan does OK ?
- */
pathnode->tideval = copyObject(tideval); /* is copy really necessary? */
pathnode->unjoined_relids = NIL;
+ cost_tidscan(&pathnode->path, rel, tideval);
+ /* divide selectivity for each clause to get an equal selectivity
+ * as IndexScan does OK ?
+ */
+
return pathnode;
}
@@ -296,9 +400,8 @@ create_nestloop_path(RelOptInfo *joinrel,
pathnode->joinrestrictinfo = restrict_clauses;
pathnode->path.pathkeys = pathkeys;
- pathnode->path.path_cost = cost_nestloop(outer_path,
- inner_path,
- IsA(inner_path, IndexPath));
+ cost_nestloop(&pathnode->path, outer_path, inner_path,
+ restrict_clauses, IsA(inner_path, IndexPath));
return pathnode;
}
@@ -350,10 +453,13 @@ create_mergejoin_path(RelOptInfo *joinrel,
pathnode->path_mergeclauses = mergeclauses;
pathnode->outersortkeys = outersortkeys;
pathnode->innersortkeys = innersortkeys;
- pathnode->jpath.path.path_cost = cost_mergejoin(outer_path,
- inner_path,
- outersortkeys,
- innersortkeys);
+
+ cost_mergejoin(&pathnode->jpath.path,
+ outer_path,
+ inner_path,
+ restrict_clauses,
+ outersortkeys,
+ innersortkeys);
return pathnode;
}
@@ -388,9 +494,12 @@ create_hashjoin_path(RelOptInfo *joinrel,
/* A hashjoin never has pathkeys, since its ordering is unpredictable */
pathnode->jpath.path.pathkeys = NIL;
pathnode->path_hashclauses = hashclauses;
- pathnode->jpath.path.path_cost = cost_hashjoin(outer_path,
- inner_path,
- innerdisbursion);
+
+ cost_hashjoin(&pathnode->jpath.path,
+ outer_path,
+ inner_path,
+ restrict_clauses,
+ innerdisbursion);
return pathnode;
}
diff --git a/src/backend/optimizer/util/plancat.c b/src/backend/optimizer/util/plancat.c
index d81eebfbb1317113fd58dc293302a47e4ae4be76..8663cdb0241de0d4aaa475cbfca59a20b9514ee1 100644
--- a/src/backend/optimizer/util/plancat.c
+++ b/src/backend/optimizer/util/plancat.c
@@ -9,7 +9,7 @@
*
*
* IDENTIFICATION
- * $Header: /cvsroot/pgsql/src/backend/optimizer/util/plancat.c,v 1.46 2000/01/26 05:56:40 momjian Exp $
+ * $Header: /cvsroot/pgsql/src/backend/optimizer/util/plancat.c,v 1.47 2000/02/15 20:49:20 tgl Exp $
*
*-------------------------------------------------------------------------
*/
@@ -118,6 +118,7 @@ find_secondary_indexes(Query *root, Index relid)
}
else
info->indpred = NIL;
+ info->lossy = index->indislossy;
for (i = 0; i < INDEX_MAX_KEYS; i++)
info->indexkeys[i] = index->indkey[i];
diff --git a/src/backend/optimizer/util/relnode.c b/src/backend/optimizer/util/relnode.c
index d22daa0f638c7677abe51fa0ffebd12c69c5fe4a..f11dd60d243f3fe7f1a10a78eac2b4156a9bf7bc 100644
--- a/src/backend/optimizer/util/relnode.c
+++ b/src/backend/optimizer/util/relnode.c
@@ -8,7 +8,7 @@
*
*
* IDENTIFICATION
- * $Header: /cvsroot/pgsql/src/backend/optimizer/util/relnode.c,v 1.23 2000/02/07 04:41:02 tgl Exp $
+ * $Header: /cvsroot/pgsql/src/backend/optimizer/util/relnode.c,v 1.24 2000/02/15 20:49:21 tgl Exp $
*
*-------------------------------------------------------------------------
*/
@@ -62,12 +62,14 @@ get_base_rel(Query *root, int relid)
rel->width = 0;
rel->targetlist = NIL;
rel->pathlist = NIL;
- rel->cheapestpath = (Path *) NULL;
+ rel->cheapest_startup_path = NULL;
+ rel->cheapest_total_path = NULL;
rel->pruneable = true;
rel->indexed = false;
rel->pages = 0;
rel->tuples = 0;
rel->baserestrictinfo = NIL;
+ rel->baserestrictcost = 0;
rel->joininfo = NIL;
rel->innerjoin = NIL;
@@ -180,12 +182,14 @@ get_join_rel(Query *root,
joinrel->width = 0;
joinrel->targetlist = NIL;
joinrel->pathlist = NIL;
- joinrel->cheapestpath = (Path *) NULL;
+ joinrel->cheapest_startup_path = NULL;
+ joinrel->cheapest_total_path = NULL;
joinrel->pruneable = true;
joinrel->indexed = false;
joinrel->pages = 0;
joinrel->tuples = 0;
joinrel->baserestrictinfo = NIL;
+ joinrel->baserestrictcost = 0;
joinrel->joininfo = NIL;
joinrel->innerjoin = NIL;
diff --git a/src/backend/utils/adt/selfuncs.c b/src/backend/utils/adt/selfuncs.c
index ab41413432c5d6d5481cf0799ee60fc0ccc3d7fa..30106744ded9f3e091e5dbbb5260eb3b62f69d3a 100644
--- a/src/backend/utils/adt/selfuncs.c
+++ b/src/backend/utils/adt/selfuncs.c
@@ -15,7 +15,7 @@
*
*
* IDENTIFICATION
- * $Header: /cvsroot/pgsql/src/backend/utils/adt/selfuncs.c,v 1.54 2000/01/26 05:57:14 momjian Exp $
+ * $Header: /cvsroot/pgsql/src/backend/utils/adt/selfuncs.c,v 1.55 2000/02/15 20:49:21 tgl Exp $
*
*-------------------------------------------------------------------------
*/
@@ -756,7 +756,9 @@ getattstatistics(Oid relid,
static void
genericcostestimate(Query *root, RelOptInfo *rel,
IndexOptInfo *index, List *indexQuals,
- Cost *indexAccessCost, Selectivity *indexSelectivity)
+ Cost *indexStartupCost,
+ Cost *indexTotalCost,
+ Selectivity *indexSelectivity)
{
double numIndexTuples;
double numIndexPages;
@@ -771,8 +773,17 @@ genericcostestimate(Query *root, RelOptInfo *rel,
/* Estimate the number of index pages that will be retrieved */
numIndexPages = *indexSelectivity * index->pages;
- /* Compute the index access cost */
- *indexAccessCost = numIndexPages + cpu_index_page_weight * numIndexTuples;
+ /*
+ * Compute the index access cost.
+ *
+ * Our generic assumption is that the index pages will be read
+ * sequentially, so they have cost 1.0 each, not random_page_cost.
+ * Also, we charge for evaluation of the indexquals at each index tuple.
+ * All the costs are assumed to be paid incrementally during the scan.
+ */
+ *indexStartupCost = 0;
+ *indexTotalCost = numIndexPages +
+ (cpu_index_tuple_cost + cost_qual_eval(indexQuals)) * numIndexTuples;
}
/*
@@ -782,35 +793,43 @@ genericcostestimate(Query *root, RelOptInfo *rel,
void
btcostestimate(Query *root, RelOptInfo *rel,
IndexOptInfo *index, List *indexQuals,
- Cost *indexAccessCost, Selectivity *indexSelectivity)
+ Cost *indexStartupCost,
+ Cost *indexTotalCost,
+ Selectivity *indexSelectivity)
{
genericcostestimate(root, rel, index, indexQuals,
- indexAccessCost, indexSelectivity);
+ indexStartupCost, indexTotalCost, indexSelectivity);
}
void
rtcostestimate(Query *root, RelOptInfo *rel,
IndexOptInfo *index, List *indexQuals,
- Cost *indexAccessCost, Selectivity *indexSelectivity)
+ Cost *indexStartupCost,
+ Cost *indexTotalCost,
+ Selectivity *indexSelectivity)
{
genericcostestimate(root, rel, index, indexQuals,
- indexAccessCost, indexSelectivity);
+ indexStartupCost, indexTotalCost, indexSelectivity);
}
void
hashcostestimate(Query *root, RelOptInfo *rel,
IndexOptInfo *index, List *indexQuals,
- Cost *indexAccessCost, Selectivity *indexSelectivity)
+ Cost *indexStartupCost,
+ Cost *indexTotalCost,
+ Selectivity *indexSelectivity)
{
genericcostestimate(root, rel, index, indexQuals,
- indexAccessCost, indexSelectivity);
+ indexStartupCost, indexTotalCost, indexSelectivity);
}
void
gistcostestimate(Query *root, RelOptInfo *rel,
IndexOptInfo *index, List *indexQuals,
- Cost *indexAccessCost, Selectivity *indexSelectivity)
+ Cost *indexStartupCost,
+ Cost *indexTotalCost,
+ Selectivity *indexSelectivity)
{
genericcostestimate(root, rel, index, indexQuals,
- indexAccessCost, indexSelectivity);
+ indexStartupCost, indexTotalCost, indexSelectivity);
}
diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index 50a15fc7d0b721ad17d92505b5b3482a2fdce90a..8f8c2fad8c7dd0c94a1cb85e02c3ce529727d9f3 100644
--- a/src/bin/psql/tab-complete.c
+++ b/src/bin/psql/tab-complete.c
@@ -3,7 +3,7 @@
*
* Copyright 2000 by PostgreSQL Global Development Group
*
- * $Header: /cvsroot/pgsql/src/bin/psql/tab-complete.c,v 1.10 2000/02/07 23:10:07 petere Exp $
+ * $Header: /cvsroot/pgsql/src/bin/psql/tab-complete.c,v 1.11 2000/02/15 20:49:22 tgl Exp $
*/
/*-----------
@@ -172,8 +172,30 @@ char ** psql_completion(char *text, int start, int end)
};
static char * pgsql_variables[] = {
- "Client_Encoding", "Names", "DateStyle", "Server_Encoding", "TimeZone",
- "TRANSACTION", "Cost_Heap", "Cost_Index", "GEQO", "KSQO", "Query_Limit",
+ /* these SET arguments are known in gram.y */
+ "TRANSACTION ISOLATION LEVEL",
+ "NAMES",
+ /* rest should match table in src/backend/commands/variable.c */
+ "DateStyle",
+ "TimeZone",
+ "effective_cache_size",
+ "random_page_cost",
+ "cpu_tuple_cost",
+ "cpu_index_tuple_cost",
+ "cpu_operator_cost",
+ "enable_seqscan",
+ "enable_indexscan",
+ "enable_tidscan",
+ "enable_sort",
+ "enable_nestloop",
+ "enable_mergejoin",
+ "enable_hashjoin",
+ "GEQO",
+ "client_encoding",
+ "server_encoding",
+ "KSQO",
+ "XactIsoLevel",
+ "PG_Options",
NULL
};
diff --git a/src/include/catalog/catversion.h b/src/include/catalog/catversion.h
index d6d8ff6ffba407164c55fa4f40c4ec0e8dcedd39..bf93830ca21ccd3ca45352e8815fa2f7fd7a2640 100644
--- a/src/include/catalog/catversion.h
+++ b/src/include/catalog/catversion.h
@@ -37,7 +37,7 @@
* Portions Copyright (c) 1996-2000, PostgreSQL, Inc
* Portions Copyright (c) 1994, Regents of the University of California
*
- * $Id: catversion.h,v 1.13 2000/01/27 18:11:40 tgl Exp $
+ * $Id: catversion.h,v 1.14 2000/02/15 20:49:23 tgl Exp $
*
*-------------------------------------------------------------------------
*/
@@ -53,6 +53,6 @@
*/
/* yyyymmddN */
-#define CATALOG_VERSION_NO 200001271
+#define CATALOG_VERSION_NO 200002151
#endif
diff --git a/src/include/catalog/pg_proc.h b/src/include/catalog/pg_proc.h
index 064232d62ccaaae15666415d52ab2bc1b10ac1bc..87107b1df367553325787ed1c12876d32a2f74ae 100644
--- a/src/include/catalog/pg_proc.h
+++ b/src/include/catalog/pg_proc.h
@@ -7,7 +7,7 @@
* Portions Copyright (c) 1996-2000, PostgreSQL, Inc
* Portions Copyright (c) 1994, Regents of the University of California
*
- * $Id: pg_proc.h,v 1.120 2000/02/10 19:51:46 momjian Exp $
+ * $Id: pg_proc.h,v 1.121 2000/02/15 20:49:23 tgl Exp $
*
* NOTES
* The script catalog/genbki.sh reads this file and generates .bki
@@ -212,9 +212,9 @@ DESCR("not equal");
DATA(insert OID = 89 ( version PGUID 11 f t f 0 f 25 "" 100 0 0 100 version - ));
DESCR("PostgreSQL version string");
-DATA(insert OID = 1265 ( rtcostestimate PGUID 11 f t f 6 f 0 "0 0 0 0 0 0" 100 0 0 100 rtcostestimate - ));
+DATA(insert OID = 1265 ( rtcostestimate PGUID 11 f t f 7 f 0 "0 0 0 0 0 0 0" 100 0 0 100 rtcostestimate - ));
DESCR("r-tree cost estimator");
-DATA(insert OID = 1268 ( btcostestimate PGUID 11 f t f 6 f 0 "0 0 0 0 0 0" 100 0 0 100 btcostestimate - ));
+DATA(insert OID = 1268 ( btcostestimate PGUID 11 f t f 7 f 0 "0 0 0 0 0 0 0" 100 0 0 100 btcostestimate - ));
DESCR("btree cost estimator");
/* OIDS 100 - 199 */
@@ -796,7 +796,7 @@ DESCR("convert name to char()");
DATA(insert OID = 409 ( bpchar_name PGUID 11 f t t 1 f 19 "1042" 100 0 0 100 bpchar_name - ));
DESCR("convert char() to name");
-DATA(insert OID = 438 ( hashcostestimate PGUID 11 f t f 6 f 0 "0 0 0 0 0 0" 100 0 0 100 hashcostestimate - ));
+DATA(insert OID = 438 ( hashcostestimate PGUID 11 f t f 7 f 0 "0 0 0 0 0 0 0" 100 0 0 100 hashcostestimate - ));
DESCR("hash index cost estimator");
DATA(insert OID = 440 ( hashgettuple PGUID 11 f t f 2 f 23 "0" 100 0 0 100 hashgettuple - ));
@@ -1031,7 +1031,7 @@ DESCR("larger of two");
DATA(insert OID = 771 ( int2smaller PGUID 11 f t t 2 f 21 "21 21" 100 0 0 100 int2smaller - ));
DESCR("smaller of two");
-DATA(insert OID = 772 ( gistcostestimate PGUID 11 f t f 6 f 0 "0 0 0 0 0 0" 100 0 0 100 gistcostestimate - ));
+DATA(insert OID = 772 ( gistcostestimate PGUID 11 f t f 7 f 0 "0 0 0 0 0 0 0" 100 0 0 100 gistcostestimate - ));
DESCR("gist cost estimator");
DATA(insert OID = 774 ( gistgettuple PGUID 11 f t f 2 f 23 "0" 100 0 0 100 gistgettuple - ));
DESCR("gist(internal)");
diff --git a/src/include/nodes/nodes.h b/src/include/nodes/nodes.h
index c1d6c4c1ca5f427f803564de7fd2927f48bcfe5d..161b53c25af97db7ad2d96d18aaccde3f7c75f94 100644
--- a/src/include/nodes/nodes.h
+++ b/src/include/nodes/nodes.h
@@ -7,7 +7,7 @@
* Portions Copyright (c) 1996-2000, PostgreSQL, Inc
* Portions Copyright (c) 1994, Regents of the University of California
*
- * $Id: nodes.h,v 1.63 2000/01/26 05:58:16 momjian Exp $
+ * $Id: nodes.h,v 1.64 2000/02/15 20:49:24 tgl Exp $
*
*-------------------------------------------------------------------------
*/
@@ -257,6 +257,9 @@ typedef struct Node
(IsA(t, Noname) || IsA(t, Material) || IsA(t, Sort) || \
IsA(t, Unique))
+#define IsA_Value(t) \
+ (IsA(t, Integer) || IsA(t, Float) || IsA(t, String))
+
/* ----------------------------------------------------------------
* extern declarations follow
* ----------------------------------------------------------------
diff --git a/src/include/nodes/parsenodes.h b/src/include/nodes/parsenodes.h
index 6eb47618c5e02ee14961e94ea4722291851ed187..df7bec10f0008912ca33a9ec008fbd73a4d4cf1e 100644
--- a/src/include/nodes/parsenodes.h
+++ b/src/include/nodes/parsenodes.h
@@ -7,7 +7,7 @@
* Portions Copyright (c) 1996-2000, PostgreSQL, Inc
* Portions Copyright (c) 1994, Regents of the University of California
*
- * $Id: parsenodes.h,v 1.98 2000/02/15 03:38:14 thomas Exp $
+ * $Id: parsenodes.h,v 1.99 2000/02/15 20:49:24 tgl Exp $
*
*-------------------------------------------------------------------------
*/
@@ -72,6 +72,7 @@ typedef struct Query
/* internal to planner */
List *base_rel_list; /* list of base-relation RelOptInfos */
List *join_rel_list; /* list of join-relation RelOptInfos */
+ List *equi_key_list; /* list of lists of equijoined PathKeyItems */
List *query_pathkeys; /* pathkeys for query_planner()'s result */
} Query;
@@ -1124,7 +1125,6 @@ typedef struct RangeTblEntry
{
NodeTag type;
char *relname; /* real name of the relation */
-// char *refname; /* reference name (given in FROM clause) */
#ifndef DISABLE_JOIN_SYNTAX
Attr *ref; /* reference names (given in FROM clause) */
#endif
diff --git a/src/include/nodes/plannodes.h b/src/include/nodes/plannodes.h
index ff83431e580841812a81e70e7013392822d0776a..2731c57948cc13db433cd55f81a9b417ffc7cba2 100644
--- a/src/include/nodes/plannodes.h
+++ b/src/include/nodes/plannodes.h
@@ -7,7 +7,7 @@
* Portions Copyright (c) 1996-2000, PostgreSQL, Inc
* Portions Copyright (c) 1994, Regents of the University of California
*
- * $Id: plannodes.h,v 1.37 2000/01/27 18:11:44 tgl Exp $
+ * $Id: plannodes.h,v 1.38 2000/02/15 20:49:25 tgl Exp $
*
*-------------------------------------------------------------------------
*/
@@ -65,10 +65,15 @@ typedef struct Plan
{
NodeTag type;
- /* planner's estimates of cost and result size */
- Cost cost;
- double plan_rows;
- int plan_width;
+ /* estimated execution costs for plan (see costsize.c for more info) */
+ Cost startup_cost; /* cost expended before fetching any tuples */
+ Cost total_cost; /* total cost (assuming all tuples fetched) */
+
+ /* planner's estimate of result size (note: LIMIT, if any, is not
+ * considered in setting plan_rows)
+ */
+ double plan_rows; /* number of rows plan is expected to emit */
+ int plan_width; /* average row width in bytes */
EState *state; /* at execution time, state's of
* individual nodes point to one EState
diff --git a/src/include/nodes/relation.h b/src/include/nodes/relation.h
index 529aa5cea7a8c88d0e64c102739cc48d8946ca82..3efdaa5b32562da5c1689dcd02e3d35e541f602a 100644
--- a/src/include/nodes/relation.h
+++ b/src/include/nodes/relation.h
@@ -7,13 +7,14 @@
* Portions Copyright (c) 1996-2000, PostgreSQL, Inc
* Portions Copyright (c) 1994, Regents of the University of California
*
- * $Id: relation.h,v 1.43 2000/02/07 04:41:02 tgl Exp $
+ * $Id: relation.h,v 1.44 2000/02/15 20:49:25 tgl Exp $
*
*-------------------------------------------------------------------------
*/
#ifndef RELATION_H
#define RELATION_H
+#include "access/sdir.h"
#include "nodes/parsenodes.h"
/*
@@ -25,6 +26,12 @@
typedef List *Relids;
+/*
+ * When looking for a "cheapest path", this enum specifies whether we want
+ * cheapest startup cost or cheapest total cost.
+ */
+typedef enum CostSelector { STARTUP_COST, TOTAL_COST } CostSelector;
+
/*
* RelOptInfo
* Per-relation information for planning/optimization
@@ -38,10 +45,14 @@ typedef List *Relids;
* clauses have been applied (ie, output rows of a plan for it)
* width - avg. number of bytes per tuple in the relation after the
* appropriate projections have been done (ie, output width)
- * targetlist - List of TargetList nodes
+ * targetlist - List of TargetEntry nodes for the attributes we need
+ * to output from this relation
* pathlist - List of Path nodes, one for each potentially useful
* method of generating the relation
- * cheapestpath - least expensive Path (regardless of ordering)
+ * cheapest_startup_path - the pathlist member with lowest startup cost
+ * (regardless of its ordering)
+ * cheapest_total_path - the pathlist member with lowest total cost
+ * (regardless of its ordering)
* pruneable - flag to let the planner know whether it can prune the
* pathlist of this RelOptInfo or not.
*
@@ -57,6 +68,8 @@ typedef List *Relids;
* baserestrictinfo - List of RestrictInfo nodes, containing info about
* each qualification clause in which this relation
* participates (only used for base rels)
+ * baserestrictcost - Estimated cost of evaluating the baserestrictinfo
+ * clauses at a single tuple (only used for base rels)
* joininfo - List of JoinInfo nodes, containing info about each join
* clause in which this relation participates
* innerjoin - List of Path nodes that represent indices that may be used
@@ -74,6 +87,10 @@ typedef List *Relids;
* (field joinrestrictinfo), not in the parent relation. But it's OK for
* the RelOptInfo to store the joininfo lists, because those are the same
* for a given rel no matter how we form it.
+ *
+ * We store baserestrictcost in the RelOptInfo (for base relations) because
+ * we know we will need it at least once (to price the sequential scan)
+ * and may need it multiple times to price index scans.
*/
typedef struct RelOptInfo
@@ -90,7 +107,8 @@ typedef struct RelOptInfo
/* materialization information */
List *targetlist;
List *pathlist; /* Path structures */
- struct Path *cheapestpath;
+ struct Path *cheapest_startup_path;
+ struct Path *cheapest_total_path;
bool pruneable;
/* statistics from pg_class (only valid if it's a base rel!) */
@@ -100,6 +118,7 @@ typedef struct RelOptInfo
/* used by various scans and joins: */
List *baserestrictinfo; /* RestrictInfo structures (if base rel) */
+ Cost baserestrictcost; /* cost of evaluating the above */
List *joininfo; /* JoinInfo structures */
List *innerjoin; /* potential indexscans for nestloop joins */
/* innerjoin indexscans are not in the main pathlist because they are
@@ -126,6 +145,7 @@ typedef struct RelOptInfo
* amcostestimate - OID of the relam's cost estimator
* indproc - OID of the function if a functional index, else 0
* indpred - index predicate if a partial index, else NULL
+ * lossy - true if index is lossy (may return non-matching tuples)
*
* NB. the last element of the arrays classlist, indexkeys and ordering
* is always 0.
@@ -151,6 +171,7 @@ typedef struct IndexOptInfo
Oid indproc; /* if a functional index */
List *indpred; /* if a partial index */
+ bool lossy; /* if a lossy index */
} IndexOptInfo;
/*
@@ -190,7 +211,9 @@ typedef struct Path
RelOptInfo *parent; /* the relation this path can build */
- Cost path_cost; /* estimated execution cost of path */
+ /* estimated execution costs for path (see costsize.c for more info) */
+ Cost startup_cost; /* cost expended before fetching any tuples */
+ Cost total_cost; /* total cost (assuming all tuples fetched) */
NodeTag pathtype; /* tag identifying scan/join method */
/* XXX why is pathtype separate from the NodeTag? */
@@ -207,27 +230,34 @@ typedef struct Path
* the same tuple more than once, even if it is matched in multiple scans.)
*
* 'indexid' is a list of index relation OIDs, one per scan to be performed.
+ *
* 'indexqual' is a list of index qualifications, also one per scan.
* Each entry in 'indexqual' is a sublist of qualification expressions with
* implicit AND semantics across the sublist items. Only expressions that
* are usable as indexquals (as determined by indxpath.c) may appear here.
- *
* NOTE that the semantics of the top-level list in 'indexqual' is OR
* combination, while the sublists are implicitly AND combinations!
+ *
+ * 'indexscandir' is one of:
+ * ForwardScanDirection: forward scan of an ordered index
+ * BackwardScanDirection: backward scan of an ordered index
+ * NoMovementScanDirection: scan of an unordered index, or don't care
+ * (The executor doesn't care whether it gets ForwardScanDirection or
+ * NoMovementScanDirection for an indexscan, but the planner wants to
+ * distinguish ordered from unordered indexes for building pathkeys.)
+ *
+ * 'joinrelids' is only used in IndexPaths that are constructed for use
+ * as the inner path of a nestloop join. These paths have indexquals
+ * that refer to values of other rels, so those other rels must be
+ * included in the outer joinrel in order to make a usable join.
*----------
*/
-
typedef struct IndexPath
{
Path path;
List *indexid;
List *indexqual;
- /*
- * joinrelids is only used in IndexPaths that are constructed for use
- * as the inner path of a nestloop join. These paths have indexquals
- * that refer to values of other rels, so those other rels must be
- * included in the outer joinrel in order to make a usable join.
- */
+ ScanDirection indexscandir;
Relids joinrelids; /* other rels mentioned in indexqual */
} IndexPath;
diff --git a/src/include/optimizer/cost.h b/src/include/optimizer/cost.h
index 79153c01d83e421466cf4b4487e1e6d392861b03..960a2ea9e9aafd72d9a79689ff6581cf0e6c276b 100644
--- a/src/include/optimizer/cost.h
+++ b/src/include/optimizer/cost.h
@@ -7,7 +7,7 @@
* Portions Copyright (c) 1996-2000, PostgreSQL, Inc
* Portions Copyright (c) 1994, Regents of the University of California
*
- * $Id: cost.h,v 1.29 2000/02/07 04:41:04 tgl Exp $
+ * $Id: cost.h,v 1.30 2000/02/15 20:49:25 tgl Exp $
*
*-------------------------------------------------------------------------
*/
@@ -17,9 +17,12 @@
#include "nodes/relation.h"
/* defaults for costsize.c's Cost parameters */
-/* NB: cost-estimation code should use the variables, not the constants! */
-#define CPU_PAGE_WEIGHT 0.033
-#define CPU_INDEX_PAGE_WEIGHT 0.017
+/* NB: cost-estimation code should use the variables, not these constants! */
+#define DEFAULT_EFFECTIVE_CACHE_SIZE 1000.0 /* measured in pages */
+#define DEFAULT_RANDOM_PAGE_COST 4.0
+#define DEFAULT_CPU_TUPLE_COST 0.01
+#define DEFAULT_CPU_INDEX_TUPLE_COST 0.001
+#define DEFAULT_CPU_OPERATOR_COST 0.0025
/* defaults for function attributes used for expensive function calculations */
#define BYTE_PCT 100
@@ -33,8 +36,12 @@
* routines to compute costs and sizes
*/
-extern Cost cpu_page_weight;
-extern Cost cpu_index_page_weight;
+/* parameter variables and flags */
+extern double effective_cache_size;
+extern Cost random_page_cost;
+extern Cost cpu_tuple_cost;
+extern Cost cpu_index_tuple_cost;
+extern Cost cpu_operator_cost;
extern Cost disable_cost;
extern bool enable_seqscan;
extern bool enable_indexscan;
@@ -44,17 +51,20 @@ extern bool enable_nestloop;
extern bool enable_mergejoin;
extern bool enable_hashjoin;
-extern Cost cost_seqscan(RelOptInfo *baserel);
-extern Cost cost_index(Query *root, RelOptInfo *baserel, IndexOptInfo *index,
+extern void cost_seqscan(Path *path, RelOptInfo *baserel);
+extern void cost_index(Path *path, Query *root,
+ RelOptInfo *baserel, IndexOptInfo *index,
List *indexQuals, bool is_injoin);
-extern Cost cost_tidscan(RelOptInfo *baserel, List *tideval);
-extern Cost cost_sort(List *pathkeys, double tuples, int width);
-extern Cost cost_nestloop(Path *outer_path, Path *inner_path,
- bool is_indexjoin);
-extern Cost cost_mergejoin(Path *outer_path, Path *inner_path,
+extern void cost_tidscan(Path *path, RelOptInfo *baserel, List *tideval);
+extern void cost_sort(Path *path, List *pathkeys, double tuples, int width);
+extern void cost_nestloop(Path *path, Path *outer_path, Path *inner_path,
+ List *restrictlist, bool is_indexjoin);
+extern void cost_mergejoin(Path *path, Path *outer_path, Path *inner_path,
+ List *restrictlist,
List *outersortkeys, List *innersortkeys);
-extern Cost cost_hashjoin(Path *outer_path, Path *inner_path,
- Selectivity innerdisbursion);
+extern void cost_hashjoin(Path *path, Path *outer_path, Path *inner_path,
+ List *restrictlist, Selectivity innerdisbursion);
+extern Cost cost_qual_eval(List *quals);
extern void set_baserel_size_estimates(Query *root, RelOptInfo *rel);
extern void set_joinrel_size_estimates(Query *root, RelOptInfo *rel,
RelOptInfo *outer_rel,
diff --git a/src/include/optimizer/pathnode.h b/src/include/optimizer/pathnode.h
index eefb2553b3d6649aefad807b2404693189980f89..e59848278f4f626c011a0277e984e8451c6bb5b0 100644
--- a/src/include/optimizer/pathnode.h
+++ b/src/include/optimizer/pathnode.h
@@ -7,7 +7,7 @@
* Portions Copyright (c) 1996-2000, PostgreSQL, Inc
* Portions Copyright (c) 1994, Regents of the University of California
*
- * $Id: pathnode.h,v 1.25 2000/02/07 04:41:04 tgl Exp $
+ * $Id: pathnode.h,v 1.26 2000/02/15 20:49:26 tgl Exp $
*
*-------------------------------------------------------------------------
*/
@@ -19,15 +19,18 @@
/*
* prototypes for pathnode.c
*/
-extern bool path_is_cheaper(Path *path1, Path *path2);
-extern Path *set_cheapest(RelOptInfo *parent_rel, List *pathlist);
+extern int compare_path_costs(Path *path1, Path *path2,
+ CostSelector criterion);
+extern int compare_fractional_path_costs(Path *path1, Path *path2,
+ double fraction);
+extern void set_cheapest(RelOptInfo *parent_rel);
extern void add_path(RelOptInfo *parent_rel, Path *new_path);
-extern void add_pathlist(RelOptInfo *parent_rel, List *new_paths);
extern Path *create_seqscan_path(RelOptInfo *rel);
extern IndexPath *create_index_path(Query *root, RelOptInfo *rel,
IndexOptInfo *index,
- List *restriction_clauses);
+ List *restriction_clauses,
+ ScanDirection indexscandir);
extern TidPath *create_tidscan_path(RelOptInfo *rel, List *tideval);
extern NestPath *create_nestloop_path(RelOptInfo *joinrel,
diff --git a/src/include/optimizer/paths.h b/src/include/optimizer/paths.h
index 256aac90d754c2dd6db3ac1784f3788bd9b787dd..d7a0cc2d54602f4c6b21977d2adb13f2314cc3fc 100644
--- a/src/include/optimizer/paths.h
+++ b/src/include/optimizer/paths.h
@@ -8,7 +8,7 @@
* Portions Copyright (c) 1996-2000, PostgreSQL, Inc
* Portions Copyright (c) 1994, Regents of the University of California
*
- * $Id: paths.h,v 1.42 2000/02/07 04:41:04 tgl Exp $
+ * $Id: paths.h,v 1.43 2000/02/15 20:49:26 tgl Exp $
*
*-------------------------------------------------------------------------
*/
@@ -33,9 +33,9 @@ extern RelOptInfo *make_one_rel(Query *root);
* indxpath.c
* routines to generate index paths
*/
-extern List *create_index_paths(Query *root, RelOptInfo *rel, List *indices,
- List *restrictinfo_list,
- List *joininfo_list);
+extern void create_index_paths(Query *root, RelOptInfo *rel, List *indices,
+ List *restrictinfo_list,
+ List *joininfo_list);
extern Oid indexable_operator(Expr *clause, Oid opclass, Oid relam,
bool indexkey_on_left);
extern List *extract_or_indexqual_conditions(RelOptInfo *rel,
@@ -47,14 +47,14 @@ extern List *expand_indexqual_conditions(List *indexquals);
* orindxpath.c
* additional routines for indexable OR clauses
*/
-extern List *create_or_index_paths(Query *root, RelOptInfo *rel,
- List *clauses);
+extern void create_or_index_paths(Query *root, RelOptInfo *rel,
+ List *clauses);
/*
* tidpath.h
* routines to generate tid paths
*/
-extern List *create_tidscan_paths(Query *root, RelOptInfo *rel);
+extern void create_tidscan_paths(Query *root, RelOptInfo *rel);
/*
* joinpath.c
@@ -89,20 +89,27 @@ typedef enum
PATHKEYS_DIFFERENT /* neither pathkey includes the other */
} PathKeysComparison;
+extern void add_equijoined_keys(Query *root, RestrictInfo *restrictinfo);
+extern List *canonicalize_pathkeys(Query *root, List *pathkeys);
extern PathKeysComparison compare_pathkeys(List *keys1, List *keys2);
extern bool pathkeys_contained_in(List *keys1, List *keys2);
extern Path *get_cheapest_path_for_pathkeys(List *paths, List *pathkeys,
- bool indexpaths_only);
+ CostSelector cost_criterion);
+extern Path *get_cheapest_fractional_path_for_pathkeys(List *paths,
+ List *pathkeys,
+ double fraction);
extern List *build_index_pathkeys(Query *root, RelOptInfo *rel,
- IndexOptInfo *index);
+ IndexOptInfo *index,
+ ScanDirection scandir);
extern List *build_join_pathkeys(List *outer_pathkeys,
- List *join_rel_tlist, List *joinclauses);
-extern bool commute_pathkeys(List *pathkeys);
+ List *join_rel_tlist,
+ List *equi_key_list);
extern List *make_pathkeys_for_sortclauses(List *sortclauses,
List *tlist);
extern List *find_mergeclauses_for_pathkeys(List *pathkeys,
List *restrictinfos);
-extern List *make_pathkeys_for_mergeclauses(List *mergeclauses,
+extern List *make_pathkeys_for_mergeclauses(Query *root,
+ List *mergeclauses,
List *tlist);
#endif /* PATHS_H */
diff --git a/src/include/optimizer/planmain.h b/src/include/optimizer/planmain.h
index 340f54485cb7c0470cd24d2328d5d90a4530104b..2d61a035bf86ea72d77a42f5a17aa6873938dc46 100644
--- a/src/include/optimizer/planmain.h
+++ b/src/include/optimizer/planmain.h
@@ -7,7 +7,7 @@
* Portions Copyright (c) 1996-2000, PostgreSQL, Inc
* Portions Copyright (c) 1994, Regents of the University of California
*
- * $Id: planmain.h,v 1.37 2000/01/27 18:11:45 tgl Exp $
+ * $Id: planmain.h,v 1.38 2000/02/15 20:49:26 tgl Exp $
*
*-------------------------------------------------------------------------
*/
@@ -20,7 +20,8 @@
/*
* prototypes for plan/planmain.c
*/
-extern Plan *query_planner(Query *root, List *tlist, List *qual);
+extern Plan *query_planner(Query *root, List *tlist, List *qual,
+ double tuple_fraction);
/*
* prototypes for plan/createplan.c
@@ -29,7 +30,7 @@ extern Plan *create_plan(Query *root, Path *best_path);
extern SeqScan *make_seqscan(List *qptlist, List *qpqual, Index scanrelid);
extern Sort *make_sort(List *tlist, Oid nonameid, Plan *lefttree,
int keycount);
-extern Agg *make_agg(List *tlist, Plan *lefttree);
+extern Agg *make_agg(List *tlist, List *qual, Plan *lefttree);
extern Group *make_group(List *tlist, bool tuplePerGroup, int ngrp,
AttrNumber *grpColIdx, Plan *lefttree);
extern Noname *make_noname(List *tlist, List *pathkeys, Plan *subplan);
diff --git a/src/include/optimizer/planner.h b/src/include/optimizer/planner.h
index 00a6e55dfd0affdb4ed3891a9601bf0a1a14776b..c06f41b852ebd022ceec1bf135559783d7b767b1 100644
--- a/src/include/optimizer/planner.h
+++ b/src/include/optimizer/planner.h
@@ -7,7 +7,7 @@
* Portions Copyright (c) 1996-2000, PostgreSQL, Inc
* Portions Copyright (c) 1994, Regents of the University of California
*
- * $Id: planner.h,v 1.13 2000/01/26 05:58:21 momjian Exp $
+ * $Id: planner.h,v 1.14 2000/02/15 20:49:26 tgl Exp $
*
*-------------------------------------------------------------------------
*/
@@ -21,7 +21,7 @@
#include "nodes/plannodes.h"
extern Plan *planner(Query *parse);
-extern Plan *union_planner(Query *parse);
+extern Plan *union_planner(Query *parse, double tuple_fraction);
extern void pg_checkretval(Oid rettype, List *querytree_list);
#endif /* PLANNER_H */
diff --git a/src/include/utils/builtins.h b/src/include/utils/builtins.h
index cb7ab0e802736f18a0e0f968da9c920510af9c58..7f9dcc6c4696757a93532358dadb7c947f717a95 100644
--- a/src/include/utils/builtins.h
+++ b/src/include/utils/builtins.h
@@ -7,7 +7,7 @@
* Portions Copyright (c) 1996-2000, PostgreSQL, Inc
* Portions Copyright (c) 1994, Regents of the University of California
*
- * $Id: builtins.h,v 1.100 2000/02/10 19:51:52 momjian Exp $
+ * $Id: builtins.h,v 1.101 2000/02/15 20:49:27 tgl Exp $
*
* NOTES
* This should normally only be included by fmgr.h.
@@ -403,19 +403,23 @@ extern bool convert_to_scalar(Datum value, Oid typid, double *scaleval);
extern void btcostestimate(Query *root, RelOptInfo *rel,
IndexOptInfo *index, List *indexQuals,
- Cost *indexAccessCost,
+ Cost *indexStartupCost,
+ Cost *indexTotalCost,
Selectivity *indexSelectivity);
extern void rtcostestimate(Query *root, RelOptInfo *rel,
IndexOptInfo *index, List *indexQuals,
- Cost *indexAccessCost,
+ Cost *indexStartupCost,
+ Cost *indexTotalCost,
Selectivity *indexSelectivity);
extern void hashcostestimate(Query *root, RelOptInfo *rel,
IndexOptInfo *index, List *indexQuals,
- Cost *indexAccessCost,
+ Cost *indexStartupCost,
+ Cost *indexTotalCost,
Selectivity *indexSelectivity);
extern void gistcostestimate(Query *root, RelOptInfo *rel,
IndexOptInfo *index, List *indexQuals,
- Cost *indexAccessCost,
+ Cost *indexStartupCost,
+ Cost *indexTotalCost,
Selectivity *indexSelectivity);
/* tid.c */
diff --git a/src/interfaces/libpq/fe-connect.c b/src/interfaces/libpq/fe-connect.c
index 94bf6bf0b866fdfbb437c81bb9d3bdf063e2bf89..9202cb23c965431b284de3b0026b55a519a186ac 100644
--- a/src/interfaces/libpq/fe-connect.c
+++ b/src/interfaces/libpq/fe-connect.c
@@ -8,7 +8,7 @@
*
*
* IDENTIFICATION
- * $Header: /cvsroot/pgsql/src/interfaces/libpq/fe-connect.c,v 1.118 2000/02/07 23:10:09 petere Exp $
+ * $Header: /cvsroot/pgsql/src/interfaces/libpq/fe-connect.c,v 1.119 2000/02/15 20:49:28 tgl Exp $
*
*-------------------------------------------------------------------------
*/
@@ -172,12 +172,6 @@ static struct EnvironmentOptions
},
#endif
/* internal performance-related settings */
- {
- "PGCOSTHEAP", "cost_heap"
- },
- {
- "PGCOSTINDEX", "cost_index"
- },
{
"PGGEQO", "geqo"
},
diff --git a/src/test/regress/expected/alter_table.out b/src/test/regress/expected/alter_table.out
index 53561ab33c8d94903750c89d0354ae6781da8859..174925df849c77702856a39183d120f827ce1cf5 100644
--- a/src/test/regress/expected/alter_table.out
+++ b/src/test/regress/expected/alter_table.out
@@ -93,8 +93,11 @@ SELECT * FROM tmp;
DROP TABLE tmp;
--
-- rename -
--- should preserve indices
+-- should preserve indices, which we can check by seeing if a SELECT
+-- chooses an indexscan; however, in the absence of vacuum statistics
+-- it might not. Therefore, vacuum first.
--
+VACUUM ANALYZE tenk1;
ALTER TABLE tenk1 RENAME TO ten_k;
-- 20 values, sorted
SELECT unique1 FROM ten_k WHERE unique1 < 20;
diff --git a/src/test/regress/expected/select.out b/src/test/regress/expected/select.out
index d6953ab5a571b6a54a16bee590e8182a299292ec..ed6cbac1df06d61e884e60393f32683154d17373 100644
--- a/src/test/regress/expected/select.out
+++ b/src/test/regress/expected/select.out
@@ -4,7 +4,8 @@
-- btree index
-- awk '{if($1<10){print;}else{next;}}' onek.data | sort +0n -1
--
-SELECT onek.* WHERE onek.unique1 < 10;
+SELECT onek.* WHERE onek.unique1 < 10
+ ORDER BY onek.unique1;
unique1 | unique2 | two | four | ten | twenty | hundred | thousand | twothousand | fivethous | tenthous | odd | even | stringu1 | stringu2 | string4
---------+---------+-----+------+-----+--------+---------+----------+-------------+-----------+----------+-----+------+----------+----------+---------
0 | 998 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | AAAAAA | KMBAAA | OOOOxx
diff --git a/src/test/regress/sql/alter_table.sql b/src/test/regress/sql/alter_table.sql
index bef443b9302553e9017a37a2acfdd92e30bc6d17..5ba66c46e8f62d3d4cd3acdfe6b5e2eb6b8cf1f9 100644
--- a/src/test/regress/sql/alter_table.sql
+++ b/src/test/regress/sql/alter_table.sql
@@ -141,8 +141,12 @@ DROP TABLE tmp;
--
-- rename -
--- should preserve indices
+-- should preserve indices, which we can check by seeing if a SELECT
+-- chooses an indexscan; however, in the absence of vacuum statistics
+-- it might not. Therefore, vacuum first.
--
+VACUUM ANALYZE tenk1;
+
ALTER TABLE tenk1 RENAME TO ten_k;
-- 20 values, sorted
diff --git a/src/test/regress/sql/select.sql b/src/test/regress/sql/select.sql
index 3d5e66c98cd3d6709069a4e31aa0667506313960..42b664eaaee200cc465d70a32817a359474564cd 100644
--- a/src/test/regress/sql/select.sql
+++ b/src/test/regress/sql/select.sql
@@ -5,7 +5,8 @@
-- btree index
-- awk '{if($1<10){print;}else{next;}}' onek.data | sort +0n -1
--
-SELECT onek.* WHERE onek.unique1 < 10;
+SELECT onek.* WHERE onek.unique1 < 10
+ ORDER BY onek.unique1;
--
-- awk '{if($1<20){print $1,$14;}else{next;}}' onek.data | sort +0nr -1