Replace ALTER TABLE ... SET STATISTICS DISTINCT with a more general mechanism.

Attributes can now have options, just as relations and tablespaces do, and
the reloptions code is used to parse, validate, and store them.  For
simplicity and because these options are not performance critical, we store
them in a separate cache rather than the main relcache.

Thanks to Alex Hunsaker for the review.

Author: robertmhaas

doc/src/sgml/catalogs.sgml

@@ -1,4 +1,4 @@
-<!-- $PostgreSQL: pgsql/doc/src/sgml/catalogs.sgml,v 2.218 2010/01/17 22:56:21 tgl Exp $ -->
+<!-- $PostgreSQL: pgsql/doc/src/sgml/catalogs.sgml,v 2.219 2010/01/22 16:40:18 rhaas Exp $ -->
 <!--
  Documentation of the system catalogs, directed toward PostgreSQL developers
  -->
@@ -901,19 +901,6 @@
       </entry>
      </row>
 
-     <row>
-      <entry><structfield>attdistinct</structfield></entry>
-      <entry><type>float4</type></entry>
-      <entry></entry>
-      <entry>
-       <structfield>attdistinct</structfield>, if nonzero, is a user-specified
-       number-of-distinct-values figure to be used instead of estimating the
-       number of distinct values during <command>ANALYZE</>.  Nonzero values
-       have the same meanings as for
-       <link linkend="catalog-pg-statistic"><structname>pg_statistic</></link>.<structfield>stadistinct</>
-      </entry>
-     </row>
-
      <row>
       <entry><structfield>attlen</structfield></entry>
       <entry><type>int2</type></entry>
@@ -1061,6 +1048,15 @@
       </entry>
      </row>
 
+     <row>
+      <entry><structfield>attoptions</structfield></entry>
+      <entry><type>text[]</type></entry>
+      <entry></entry>
+      <entry>
+       Attribute-level options, as <quote>keyword=value</> strings
+      </entry>
+     </row>
+
     </tbody>
    </tgroup>
   </table>

doc/src/sgml/ref/alter_table.sgml

@@ -1,5 +1,5 @@
 <!--
-$PostgreSQL: pgsql/doc/src/sgml/ref/alter_table.sgml,v 1.109 2009/09/18 05:00:41 petere Exp $
+$PostgreSQL: pgsql/doc/src/sgml/ref/alter_table.sgml,v 1.110 2010/01/22 16:40:18 rhaas Exp $
 PostgreSQL documentation
 -->
 
@@ -39,7 +39,8 @@ ALTER TABLE <replaceable class="PARAMETER">name</replaceable>
     ALTER [ COLUMN ] <replaceable class="PARAMETER">column</replaceable> DROP DEFAULT
     ALTER [ COLUMN ] <replaceable class="PARAMETER">column</replaceable> { SET | DROP } NOT NULL
     ALTER [ COLUMN ] <replaceable class="PARAMETER">column</replaceable> SET STATISTICS <replaceable class="PARAMETER">integer</replaceable>
-    ALTER [ COLUMN ] <replaceable class="PARAMETER">column</replaceable> SET STATISTICS DISTINCT <replaceable class="PARAMETER">number</replaceable>
+    ALTER [ COLUMN ] <replaceable class="PARAMETER">column</replaceable> SET ( <replaceable class="PARAMETER">attribute_option</replaceable> = <replaceable class="PARAMETER">value</replaceable> [, ... ] )
+    ALTER [ COLUMN ] <replaceable class="PARAMETER">column</replaceable> RESET ( <replaceable class="PARAMETER">attribute_option</replaceable> [, ... ] )
     ALTER [ COLUMN ] <replaceable class="PARAMETER">column</replaceable> SET STORAGE { PLAIN | EXTERNAL | EXTENDED | MAIN }
     ADD <replaceable class="PARAMETER">table_constraint</replaceable>
     DROP CONSTRAINT [ IF EXISTS ]  <replaceable class="PARAMETER">constraint_name</replaceable> [ RESTRICT | CASCADE ]
@@ -158,14 +159,21 @@ ALTER TABLE <replaceable class="PARAMETER">name</replaceable>
    </varlistentry>
 
    <varlistentry>
-    <term><literal>SET STATISTICS DISTINCT</literal></term>
+    <term><literal>SET ( <replaceable class="PARAMETER">attribute_option</replaceable> = <replaceable class="PARAMETER">value</replaceable> [, ... ] )</term></literal>
+    <term><literal>RESET ( <replaceable class="PARAMETER">attribute_option</replaceable> [, ... ] )</literal>
     <listitem>
      <para>
-      This form overrides the number-of-distinct-values estimate made by
-      subsequent <xref linkend="sql-analyze" endterm="sql-analyze-title">
-      operations.  When set to a positive value, <command>ANALYZE</> will
-      assume that the column contains exactly the specified number of distinct
-      nonnull values.  When set to a negative value, which must be greater
+      This form sets or resets attribute-level options.  Currently, the only
+      define attribute-level options are <literal>n_distinct</> and
+      <literal>n_distinct_inherited</>, which override the
+      number-of-distinct-values estimate made by subsequent
+      <xref linkend="sql-analyze" endterm="sql-analyze-title">
+      operations.  <literal>n_distinct</> affects the statistics for the table
+      itself, while <literal>n_distinct_inherited</> affects the statistics
+      gathered for the table and its inheritance children.  When set to a
+      positive value, <command>ANALYZE</> will assume that the column contains
+      exactly the specified number of distinct nonnull values.  When set to a
+      negative value, which must be greater
       than or equal to -1, <command>ANALYZE</> will assume that the number of
       distinct nonnull values in the column is linear in the size of the
       table; the exact count is to be computed by multiplying the estimated

doc/src/sgml/ref/analyze.sgml

@@ -1,5 +1,5 @@
 <!--
-$PostgreSQL: pgsql/doc/src/sgml/ref/analyze.sgml,v 1.27 2009/08/04 22:04:37 petere Exp $
+$PostgreSQL: pgsql/doc/src/sgml/ref/analyze.sgml,v 1.28 2010/01/22 16:40:18 rhaas Exp $
 PostgreSQL documentation
 -->
 
@@ -173,7 +173,7 @@ ANALYZE [ VERBOSE ] [ <replaceable class="PARAMETER">table</replaceable> [ ( <re
    with the largest possible statistics target.  If this inaccuracy leads to
    bad query plans, a more accurate value can be determined manually and then
    installed with
-   <command>ALTER TABLE ... ALTER COLUMN ... SET STATISTICS DISTINCT</>
+   <command>ALTER TABLE ... ALTER COLUMN ... SET (n_distinct = ...)</>
    (see <xref linkend="sql-altertable" endterm="sql-altertable-title">).
   </para>
  </refsect1>

src/backend/access/common/reloptions.c

@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/access/common/reloptions.c,v 1.31 2010/01/05 21:53:58 rhaas Exp $
+ *	  $PostgreSQL: pgsql/src/backend/access/common/reloptions.c,v 1.32 2010/01/22 16:40:18 rhaas Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -24,6 +24,7 @@
 #include "commands/tablespace.h"
 #include "nodes/makefuncs.h"
 #include "utils/array.h"
+#include "utils/attoptcache.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
 #include "utils/memutils.h"
@@ -196,6 +197,22 @@ static relopt_real realRelOpts[] =
 		},
 		-1, 0.0, DBL_MAX
 	},
+	{
+		{
+			"n_distinct",
+			"Sets the planner's estimate of the number of distinct values appearing in a column (excluding child relations).",
+			RELOPT_KIND_ATTRIBUTE
+		},
+		0, -1.0, DBL_MAX
+	},
+	{
+		{
+			"n_distinct_inherited",
+			"Sets the planner's estimate of the number of distinct values appearing in a column (including child relations).",
+			RELOPT_KIND_ATTRIBUTE
+		},
+		0, -1.0, DBL_MAX
+	},
 	/* list terminator */
 	{{NULL}}
 };
@@ -1186,6 +1203,37 @@ index_reloptions(RegProcedure amoptions, Datum reloptions, bool validate)
 	return DatumGetByteaP(result);
 }
 
+/*
+ * Option parser for attribute reloptions
+ */
+bytea *
+attribute_reloptions(Datum reloptions, bool validate)
+{
+	relopt_value *options;
+	AttributeOpts  *aopts;
+	int			numoptions;
+	static const relopt_parse_elt tab[] = {
+		{"n_distinct", RELOPT_TYPE_REAL, offsetof(AttributeOpts, n_distinct)},
+		{"n_distinct_inherited", RELOPT_TYPE_REAL, offsetof(AttributeOpts, n_distinct_inherited)}
+	};
+
+	options = parseRelOptions(reloptions, validate, RELOPT_KIND_ATTRIBUTE,
+							  &numoptions);
+
+	/* if none set, we're done */
+	if (numoptions == 0)
+		return NULL;
+
+	aopts = allocateReloptStruct(sizeof(AttributeOpts), options, numoptions);
+
+	fillRelOptions((void *) aopts, sizeof(AttributeOpts), options, numoptions,
+				   validate, tab, lengthof(tab));
+
+	pfree(options);
+
+	return (bytea *) aopts;
+}
+
 /*
  * Option parser for tablespace reloptions
  */

src/backend/access/common/tupdesc.c

@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/access/common/tupdesc.c,v 1.131 2010/01/02 16:57:33 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/backend/access/common/tupdesc.c,v 1.132 2010/01/22 16:40:18 rhaas Exp $
  *
  * NOTES
  *	  some of the executor utility code such as "ExecTypeFromTL" should be
@@ -338,8 +338,6 @@ equalTupleDescs(TupleDesc tupdesc1, TupleDesc tupdesc2)
 			return false;
 		if (attr1->attstattarget != attr2->attstattarget)
 			return false;
-		if (attr1->attdistinct != attr2->attdistinct)
-			return false;
 		if (attr1->attlen != attr2->attlen)
 			return false;
 		if (attr1->attndims != attr2->attndims)
@@ -362,7 +360,7 @@ equalTupleDescs(TupleDesc tupdesc1, TupleDesc tupdesc2)
 			return false;
 		if (attr1->attinhcount != attr2->attinhcount)
 			return false;
-		/* attacl is ignored, since it's not even present... */
+		/* attacl and attoptions are not even present... */
 	}
 
 	if (tupdesc1->constr != NULL)
@@ -467,7 +465,6 @@ TupleDescInitEntry(TupleDesc desc,
 		MemSet(NameStr(att->attname), 0, NAMEDATALEN);
 
 	att->attstattarget = -1;
-	att->attdistinct = 0;
 	att->attcacheoff = -1;
 	att->atttypmod = typmod;
 
@@ -479,7 +476,7 @@ TupleDescInitEntry(TupleDesc desc,
 	att->attisdropped = false;
 	att->attislocal = true;
 	att->attinhcount = 0;
-	/* attacl is not set because it's not present in tupledescs */
+	/* attacl and attoptions are not present in tupledescs */
 
 	tuple = SearchSysCache(TYPEOID,
 						   ObjectIdGetDatum(oidtypeid),

src/backend/bootstrap/bootstrap.c

@@ -8,7 +8,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/bootstrap/bootstrap.c,v 1.257 2010/01/20 09:16:23 heikki Exp $
+ *	  $PostgreSQL: pgsql/src/backend/bootstrap/bootstrap.c,v 1.258 2010/01/22 16:40:18 rhaas Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -737,7 +737,6 @@ DefineAttr(char *name, char *type, int attnum)
 	}
 
 	attrtypes[attnum]->attstattarget = -1;
-	attrtypes[attnum]->attdistinct = 0;
 	attrtypes[attnum]->attcacheoff = -1;
 	attrtypes[attnum]->atttypmod = -1;
 	attrtypes[attnum]->attislocal = true;

src/backend/catalog/genbki.pl

@@ -10,7 +10,7 @@
 # Portions Copyright (c) 1996-2010, PostgreSQL Global Development Group
 # Portions Copyright (c) 1994, Regents of the University of California
 #
-# $PostgreSQL: pgsql/src/backend/catalog/genbki.pl,v 1.6 2010/01/06 22:02:45 tgl Exp $
+# $PostgreSQL: pgsql/src/backend/catalog/genbki.pl,v 1.7 2010/01/22 16:40:18 rhaas Exp $
 #
 #----------------------------------------------------------------------
 
@@ -200,7 +200,8 @@
                 # Store schemapg entries for later.
                 $row = emit_schemapg_row($row, grep { $bki_attr{$_} eq 'bool' } @attnames);
                 push @{ $schemapg_entries{$table_name} },
-                  '{ ' . join(', ', map $row->{$_}, @attnames) . ' }';
+					'{ ' . join(', ', grep { defined $_ }
+					map $row->{$_}, @attnames) . ' }';
             }
 
             # Generate entries for system attributes.
@@ -351,14 +352,14 @@ sub emit_pgattr_row
 
     # Add in default values for pg_attribute
     my %PGATTR_DEFAULTS = (
-        attdistinct   => '0',
         attcacheoff   => '-1',
         atttypmod     => '-1',
         atthasdef     => 'f',
         attisdropped  => 'f',
         attislocal    => 't',
         attinhcount   => '0',
-        attacl        => '_null_'
+        attacl        => '_null_',
+        attoptions    => '_null_'
     );
     return {%PGATTR_DEFAULTS, %row};
 }
@@ -384,7 +385,11 @@ sub emit_schemapg_row
     $row->{attname}     = q|{"| . $row->{attname}    . q|"}|;
     $row->{attstorage}  = q|'|  . $row->{attstorage} . q|'|;
     $row->{attalign}    = q|'|  . $row->{attalign}   . q|'|;
-    $row->{attacl}      = q|{ 0 }|;
+
+    # We don't emit initializers for the variable length fields at all.
+    # Only the fixed-size portions of the descriptors are ever used.
+    delete $row->{attacl};
+    delete $row->{attoptions};
 
     # Expand booleans from 'f'/'t' to 'false'/'true'.
     # Some values might be other macros (eg FLOAT4PASSBYVAL), don't change.