Add ALTER TABLE ... ALTER COLUMN ... SET STATISTICS DISTINCT

Robert Haas

doc/src/sgml/catalogs.sgml

-<!-- $PostgreSQL: pgsql/doc/src/sgml/catalogs.sgml,v 2.203 2009/07/29 20:56:17 tgl Exp $ -->
+<!-- $PostgreSQL: pgsql/doc/src/sgml/catalogs.sgml,v 2.204 2009/08/02 22:14:51 tgl Exp $ -->
 <!--
  Documentation of the system catalogs, directed toward PostgreSQL developers
  -->
@@ -886,6 +886,19 @@
       </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>
@@ -4303,9 +4316,10 @@
       <entry></entry>
       <entry>The number of distinct nonnull data values in the column.
       A value greater than zero is the actual number of distinct values.
-      A value less than zero is the negative of a fraction of the number
-      of rows in the table (for example, a column in which values appear about
-      twice on the average could be represented by <structfield>stadistinct</> = -0.5).
+      A value less than zero is the negative of a multiplier for the number
+      of rows in the table; for example, a column in which values appear about
+      twice on the average could be represented by
+      <structfield>stadistinct</> = -0.5.
       A zero value means the number of distinct values is unknown
       </entry>
      </row>

doc/src/sgml/ref/alter_table.sgml

 <!--
-$PostgreSQL: pgsql/doc/src/sgml/ref/alter_table.sgml,v 1.107 2009/07/20 02:42:27 adunstan Exp $
+$PostgreSQL: pgsql/doc/src/sgml/ref/alter_table.sgml,v 1.108 2009/08/02 22:14:51 tgl Exp $
 PostgreSQL documentation
 -->
 
@@ -39,6 +39,7 @@ where <replaceable class="PARAMETER">action</replaceable> is one of:
     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 STORAGE { PLAIN | EXTERNAL | EXTENDED | MAIN }
     ADD <replaceable class="PARAMETER">table_constraint</replaceable>
     DROP CONSTRAINT [ IF EXISTS ]  <replaceable class="PARAMETER">constraint_name</replaceable> [ RESTRICT | CASCADE ]
@@ -90,8 +91,8 @@ where <replaceable class="PARAMETER">action</replaceable> is one of:
       dropped as well.  You will need to say <literal>CASCADE</> if
       anything outside the table depends on the column, for example,
       foreign key references or views.
-      If <literal>IF EXISTS</literal> is specified and the column 
-      does not exist, no error is thrown. In this case a notice 
+      If <literal>IF EXISTS</literal> is specified and the column
+      does not exist, no error is thrown. In this case a notice
       is issued instead.
      </para>
     </listitem>
@@ -156,6 +157,31 @@ where <replaceable class="PARAMETER">action</replaceable> is one of:
     </listitem>
    </varlistentry>
 
+   <varlistentry>
+    <term><literal>SET STATISTICS DISTINCT</literal></term>
+    <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
+      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
+      table size by the absolute value of the given number.  For example,
+      a value of -1 implies that all values in the column are distinct, while
+      a value of -0.5 implies that each value appears twice on the average.
+      This can be useful when the size of the table changes over time, since
+      the multiplication by the number of rows in the table is not performed
+      until query planning time.  Specify a value of 0 to revert to estimating
+      the number of distinct values normally.  For more information on the use
+      of statistics by the <productname>PostgreSQL</productname> query
+      planner, refer to <xref linkend="planner-stats">.
+     </para>
+    </listitem>
+   </varlistentry>
+
    <varlistentry>
     <indexterm>
      <primary>TOAST</primary>

doc/src/sgml/ref/analyze.sgml

 <!--
-$PostgreSQL: pgsql/doc/src/sgml/ref/analyze.sgml,v 1.25 2008/12/13 19:13:44 tgl Exp $
+$PostgreSQL: pgsql/doc/src/sgml/ref/analyze.sgml,v 1.26 2009/08/02 22:14:51 tgl Exp $
 PostgreSQL documentation
 -->
 
@@ -165,6 +165,17 @@ ANALYZE [ VERBOSE ] [ <replaceable class="PARAMETER">table</replaceable> [ ( <re
    the target causes a proportional increase in the time and space needed
    to do <command>ANALYZE</command>.
   </para>
+
+  <para>
+   One of the values estimated by <command>ANALYZE</command> is the number of
+   distinct values that appear in each column.  Because only a subset of the
+   rows are examined, this estimate can sometimes be quite inaccurate, even
+   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</>
+   (see <xref linkend="sql-altertable" endterm="sql-altertable-title">).
+  </para>
  </refsect1>
 
  <refsect1>

src/backend/access/common/tupdesc.c

@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/access/common/tupdesc.c,v 1.127 2009/07/16 06:33:42 petere Exp $
+ *	  $PostgreSQL: pgsql/src/backend/access/common/tupdesc.c,v 1.128 2009/08/02 22:14:51 tgl Exp $
  *
  * NOTES
  *	  some of the executor utility code such as "ExecTypeFromTL" should be
@@ -338,6 +338,8 @@ 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)
@@ -465,6 +467,7 @@ TupleDescInitEntry(TupleDesc desc,
 		MemSet(NameStr(att->attname), 0, NAMEDATALEN);
 
 	att->attstattarget = -1;
+	att->attdistinct = 0;
 	att->attcacheoff = -1;
 	att->atttypmod = typmod;
 

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 1.251 2009/07/31 20:26:22 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/bootstrap/bootstrap.c,v 1.252 2009/08/02 22:14:51 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -757,6 +757,7 @@ 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/heap.c

@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/catalog/heap.c,v 1.356 2009/07/30 02:45:36 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/catalog/heap.c,v 1.357 2009/08/02 22:14:52 tgl Exp $
  *
  *
  * INTERFACE ROUTINES
@@ -111,37 +111,37 @@ static List *insert_ordered_unique_oid(List *list, Oid datum);
  */
 
 static FormData_pg_attribute a1 = {
-	0, {"ctid"}, TIDOID, 0, sizeof(ItemPointerData),
+	0, {"ctid"}, TIDOID, 0, 0, sizeof(ItemPointerData),
 	SelfItemPointerAttributeNumber, 0, -1, -1,
 	false, 'p', 's', true, false, false, true, 0, {0}
 };
 
 static FormData_pg_attribute a2 = {
-	0, {"oid"}, OIDOID, 0, sizeof(Oid),
+	0, {"oid"}, OIDOID, 0, 0, sizeof(Oid),
 	ObjectIdAttributeNumber, 0, -1, -1,
 	true, 'p', 'i', true, false, false, true, 0, {0}
 };
 
 static FormData_pg_attribute a3 = {
-	0, {"xmin"}, XIDOID, 0, sizeof(TransactionId),
+	0, {"xmin"}, XIDOID, 0, 0, sizeof(TransactionId),
 	MinTransactionIdAttributeNumber, 0, -1, -1,
 	true, 'p', 'i', true, false, false, true, 0, {0}
 };
 
 static FormData_pg_attribute a4 = {
-	0, {"cmin"}, CIDOID, 0, sizeof(CommandId),
+	0, {"cmin"}, CIDOID, 0, 0, sizeof(CommandId),
 	MinCommandIdAttributeNumber, 0, -1, -1,
 	true, 'p', 'i', true, false, false, true, 0, {0}
 };
 
 static FormData_pg_attribute a5 = {
-	0, {"xmax"}, XIDOID, 0, sizeof(TransactionId),
+	0, {"xmax"}, XIDOID, 0, 0, sizeof(TransactionId),
 	MaxTransactionIdAttributeNumber, 0, -1, -1,
 	true, 'p', 'i', true, false, false, true, 0, {0}
 };
 
 static FormData_pg_attribute a6 = {
-	0, {"cmax"}, CIDOID, 0, sizeof(CommandId),
+	0, {"cmax"}, CIDOID, 0, 0, sizeof(CommandId),
 	MaxCommandIdAttributeNumber, 0, -1, -1,
 	true, 'p', 'i', true, false, false, true, 0, {0}
 };
@@ -153,7 +153,7 @@ static FormData_pg_attribute a6 = {
  * used in SQL.
  */
 static FormData_pg_attribute a7 = {
-	0, {"tableoid"}, OIDOID, 0, sizeof(Oid),
+	0, {"tableoid"}, OIDOID, 0, 0, sizeof(Oid),
 	TableOidAttributeNumber, 0, -1, -1,
 	true, 'p', 'i', true, false, false, true, 0, {0}
 };
@@ -501,6 +501,7 @@ InsertPgAttributeTuple(Relation pg_attribute_rel,
 	values[Anum_pg_attribute_attname - 1] = NameGetDatum(&new_attribute->attname);
 	values[Anum_pg_attribute_atttypid - 1] = ObjectIdGetDatum(new_attribute->atttypid);
 	values[Anum_pg_attribute_attstattarget - 1] = Int32GetDatum(new_attribute->attstattarget);
+	values[Anum_pg_attribute_attdistinct - 1] = Float4GetDatum(new_attribute->attdistinct);
 	values[Anum_pg_attribute_attlen - 1] = Int16GetDatum(new_attribute->attlen);
 	values[Anum_pg_attribute_attnum - 1] = Int16GetDatum(new_attribute->attnum);
 	values[Anum_pg_attribute_attndims - 1] = Int32GetDatum(new_attribute->attndims);
@@ -571,6 +572,7 @@ AddNewAttributeTuples(Oid new_rel_oid,
 		attr->attrelid = new_rel_oid;
 		/* Make sure these are OK, too */
 		attr->attstattarget = -1;
+		attr->attdistinct = 0;
 		attr->attcacheoff = -1;
 
 		InsertPgAttributeTuple(rel, attr, indstate);

src/backend/catalog/index.c

@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/catalog/index.c,v 1.320 2009/07/29 20:56:18 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/catalog/index.c,v 1.321 2009/08/02 22:14:52 tgl Exp $
  *
  *
  * INTERFACE ROUTINES
@@ -192,6 +192,7 @@ ConstructTupleDescriptor(Relation heapRelation,
 			to->attnum = i + 1;
 
 			to->attstattarget = -1;
+			to->attdistinct = 0;
 			to->attcacheoff = -1;
 			to->attnotnull = false;
 			to->atthasdef = false;

src/backend/commands/analyze.c

@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/commands/analyze.c,v 1.139 2009/06/11 14:48:55 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/backend/commands/analyze.c,v 1.140 2009/08/02 22:14:52 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -425,6 +425,11 @@ analyze_rel(Oid relid, VacuumStmt *vacstmt,
 									 std_fetch_func,
 									 numrows,
 									 totalrows);
+
+			/* If attdistinct is set, override with that value */
+			if (stats->attr->attdistinct != 0)
+				stats->stadistinct = stats->attr->attdistinct;
+
 			MemoryContextResetAndDeleteChildren(col_context);
 		}
 
@@ -679,6 +684,9 @@ compute_index_stats(Relation onerel, double totalrows,
 										 ind_fetch_func,
 										 numindexrows,
 										 totalindexrows);
+				/* If attdistinct is set, override with that value */
+				if (stats->attr->attdistinct != 0)
+					stats->stadistinct = stats->attr->attdistinct;
 				MemoryContextResetAndDeleteChildren(col_context);
 			}
 		}

src/backend/commands/tablecmds.c

@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/commands/tablecmds.c,v 1.294 2009/07/30 02:45:36 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/commands/tablecmds.c,v 1.295 2009/08/02 22:14:52 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -280,9 +280,13 @@ static void ATExecSetNotNull(AlteredTableInfo *tab, Relation rel,
 static void ATExecColumnDefault(Relation rel, const char *colName,
 					Node *newDefault);
 static void ATPrepSetStatistics(Relation rel, const char *colName,
-					Node *flagValue);
+					Node *newValue);
 static void ATExecSetStatistics(Relation rel, const char *colName,
 					Node *newValue);
+static void ATPrepSetDistinct(Relation rel, const char *colName,
+					Node *newValue);
+static void ATExecSetDistinct(Relation rel, const char *colName,
+				 Node *newValue);
 static void ATExecSetStorage(Relation rel, const char *colName,
 				 Node *newValue);
 static void ATExecDropColumn(List **wqueue, Relation rel, const char *colName,
@@ -2399,13 +2403,19 @@ ATPrepCmd(List **wqueue, Relation rel, AlterTableCmd *cmd,
 			/* No command-specific prep needed */
 			pass = AT_PASS_ADD_CONSTR;
 			break;
-		case AT_SetStatistics:	/* ALTER COLUMN STATISTICS */
+		case AT_SetStatistics:	/* ALTER COLUMN SET STATISTICS */
 			ATSimpleRecursion(wqueue, rel, cmd, recurse);
 			/* Performs own permission checks */
 			ATPrepSetStatistics(rel, cmd->name, cmd->def);
 			pass = AT_PASS_COL_ATTRS;
 			break;
-		case AT_SetStorage:		/* ALTER COLUMN STORAGE */
+		case AT_SetDistinct:	/* ALTER COLUMN SET STATISTICS DISTINCT */
+			ATSimpleRecursion(wqueue, rel, cmd, recurse);
+			/* Performs own permission checks */
+			ATPrepSetDistinct(rel, cmd->name, cmd->def);
+			pass = AT_PASS_COL_ATTRS;
+			break;
+		case AT_SetStorage:		/* ALTER COLUMN SET STORAGE */
 			ATSimplePermissions(rel, false);
 			ATSimpleRecursion(wqueue, rel, cmd, recurse);
 			/* No command-specific prep needed */
@@ -2616,10 +2626,13 @@ ATExecCmd(List **wqueue, AlteredTableInfo *tab, Relation rel,
 		case AT_SetNotNull:		/* ALTER COLUMN SET NOT NULL */
 			ATExecSetNotNull(tab, rel, cmd->name);
 			break;
-		case AT_SetStatistics:	/* ALTER COLUMN STATISTICS */
+		case AT_SetStatistics:	/* ALTER COLUMN SET STATISTICS */
 			ATExecSetStatistics(rel, cmd->name, cmd->def);
 			break;
-		case AT_SetStorage:		/* ALTER COLUMN STORAGE */
+		case AT_SetDistinct:	/* ALTER COLUMN SET STATISTICS DISTINCT */
+			ATExecSetDistinct(rel, cmd->name, cmd->def);
+			break;
+		case AT_SetStorage:		/* ALTER COLUMN SET STORAGE */
 			ATExecSetStorage(rel, cmd->name, cmd->def);
 			break;
 		case AT_DropColumn:		/* DROP COLUMN */
@@ -3620,6 +3633,7 @@ ATExecAddColumn(AlteredTableInfo *tab, Relation rel,
 	namestrcpy(&(attribute.attname), colDef->colname);
 	attribute.atttypid = typeOid;
 	attribute.attstattarget = (newattnum > 0) ? -1 : 0;
+	attribute.attdistinct = 0;
 	attribute.attlen = tform->typlen;
 	attribute.attcacheoff = -1;
 	attribute.atttypmod = typmod;
@@ -4007,7 +4021,7 @@ ATExecColumnDefault(Relation rel, const char *colName,
  * ALTER TABLE ALTER COLUMN SET STATISTICS
  */
 static void
-ATPrepSetStatistics(Relation rel, const char *colName, Node *flagValue)
+ATPrepSetStatistics(Relation rel, const char *colName, Node *newValue)
 {
 	/*
 	 * We do our own permission checking because (a) we want to allow SET
@@ -4087,6 +4101,94 @@ ATExecSetStatistics(Relation rel, const char *colName, Node *newValue)
 	heap_close(attrelation, RowExclusiveLock);
 }
 
+/*
+ * ALTER TABLE ALTER COLUMN SET STATISTICS DISTINCT
+ */
+static void
+ATPrepSetDistinct(Relation rel, const char *colName, Node *newValue)
+{
+	/*
+	 * We do our own permission checking because (a) we want to allow SET
+	 * DISTINCT on indexes (for expressional index columns), and (b) we want
+	 * to allow SET DISTINCT on system catalogs without requiring
+	 * allowSystemTableMods to be turned on.
+	 */
+	if (rel->rd_rel->relkind != RELKIND_RELATION &&
+		rel->rd_rel->relkind != RELKIND_INDEX)
+		ereport(ERROR,
+				(errcode(ERRCODE_WRONG_OBJECT_TYPE),
+				 errmsg("\"%s\" is not a table or index",
+						RelationGetRelationName(rel))));
+
+	/* Permissions checks */
+	if (!pg_class_ownercheck(RelationGetRelid(rel), GetUserId()))
+		aclcheck_error(ACLCHECK_NOT_OWNER, ACL_KIND_CLASS,
+					   RelationGetRelationName(rel));
+}
+
+static void
+ATExecSetDistinct(Relation rel, const char *colName, Node *newValue)
+{
+	float4		newdistinct;
+	Relation	attrelation;
+	HeapTuple	tuple;
+	Form_pg_attribute attrtuple;
+
+	switch (nodeTag(newValue))
+	{
+		case T_Integer:
+			newdistinct = intVal(newValue);
+			break;
+		case T_Float:
+			newdistinct = floatVal(newValue);
+			break;
+		default:
+			elog(ERROR, "unrecognized node type: %d",
+				 (int) nodeTag(newValue));
+			newdistinct = 0;	/* keep compiler quiet */
+			break;
+	}
+
+	/*
+	 * Limit ndistinct to sane values
+	 */
+	if (newdistinct < -1.0)
+	{
+		ereport(ERROR,
+				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+				 errmsg("number of distinct values %g is too low",
+						newdistinct)));
+	}
+
+	attrelation = heap_open(AttributeRelationId, RowExclusiveLock);
+
+	tuple = SearchSysCacheCopyAttName(RelationGetRelid(rel), colName);
+
+	if (!HeapTupleIsValid(tuple))
+		ereport(ERROR,
+				(errcode(ERRCODE_UNDEFINED_COLUMN),
+				 errmsg("column \"%s\" of relation \"%s\" does not exist",
+						colName, RelationGetRelationName(rel))));
+	attrtuple = (Form_pg_attribute) GETSTRUCT(tuple);
+
+	if (attrtuple->attnum <= 0)
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("cannot alter system column \"%s\"",
+						colName)));
+
+	attrtuple->attdistinct = newdistinct;
+
+	simple_heap_update(attrelation, &tuple->t_self, tuple);
+
+	/* keep system catalog indexes current */
+	CatalogUpdateIndexes(attrelation, tuple);
+
+	heap_freetuple(tuple);
+
+	heap_close(attrelation, RowExclusiveLock);
+}
+
 /*
  * ALTER TABLE ALTER COLUMN SET STORAGE
  */

src/backend/parser/gram.y

@@ -11,7 +11,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/parser/gram.y,v 2.675 2009/07/30 02:45:37 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/parser/gram.y,v 2.676 2009/08/02 22:14:52 tgl Exp $
  *
  * HISTORY
  *	  AUTHOR			DATE			MAJOR EVENT
@@ -1605,6 +1605,15 @@ alter_table_cmd:
 					n->def = (Node *) makeInteger($6);
 					$$ = (Node *)n;
 				}
+			/* ALTER TABLE <name> ALTER [COLUMN] <colname> SET STATISTICS DISTINCT <NumericOnly> */
+			| ALTER opt_column ColId SET STATISTICS DISTINCT NumericOnly
+				{
+					AlterTableCmd *n = makeNode(AlterTableCmd);
+					n->subtype = AT_SetDistinct;
+					n->name = $3;
+					n->def = (Node *) $7;
+					$$ = (Node *)n;
+				}
 			/* ALTER TABLE <name> ALTER [COLUMN] <colname> SET STORAGE <storagemode> */
 			| ALTER opt_column ColId SET STORAGE ColId
 				{

src/bin/pg_dump/pg_dump.c

@@ -12,7 +12,7 @@
  *	by PostgreSQL
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/bin/pg_dump/pg_dump.c,v 1.543 2009/07/29 20:56:19 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/bin/pg_dump/pg_dump.c,v 1.544 2009/08/02 22:14:52 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -4707,6 +4707,7 @@ getTableAttrs(TableInfo *tblinfo, int numTables)
 	int			i_atttypname;
 	int			i_atttypmod;
 	int			i_attstattarget;
+	int			i_attdistinct;
 	int			i_attstorage;
 	int			i_typstorage;
 	int			i_attnotnull;
@@ -4752,11 +4753,28 @@ getTableAttrs(TableInfo *tblinfo, int numTables)
 
 		resetPQExpBuffer(q);
 
-		if (g_fout->remoteVersion >= 70300)
+		if (g_fout->remoteVersion >= 80500)
+		{
+			/* attdistinct is new in 8.5 */
+			appendPQExpBuffer(q, "SELECT a.attnum, a.attname, a.atttypmod, "
+							  "a.attstattarget, a.attdistinct, "
+							  "a.attstorage, t.typstorage, "
+							  "a.attnotnull, a.atthasdef, a.attisdropped, "
+							  "a.attlen, a.attalign, a.attislocal, "
+				   "pg_catalog.format_type(t.oid,a.atttypmod) AS atttypname "
+			 "FROM pg_catalog.pg_attribute a LEFT JOIN pg_catalog.pg_type t "
+							  "ON a.atttypid = t.oid "
+							  "WHERE a.attrelid = '%u'::pg_catalog.oid "
+							  "AND a.attnum > 0::pg_catalog.int2 "
+							  "ORDER BY a.attrelid, a.attnum",
+							  tbinfo->dobj.catId.oid);
+		}
+		else if (g_fout->remoteVersion >= 70300)
 		{
 			/* need left join here to not fail on dropped columns ... */
 			appendPQExpBuffer(q, "SELECT a.attnum, a.attname, a.atttypmod, "
-							  "a.attstattarget, a.attstorage, t.typstorage, "
+							  "a.attstattarget, 0 AS attdistinct, "
+							  "a.attstorage, t.typstorage, "
 							  "a.attnotnull, a.atthasdef, a.attisdropped, "
 							  "a.attlen, a.attalign, a.attislocal, "
 				   "pg_catalog.format_type(t.oid,a.atttypmod) AS atttypname "
@@ -4774,8 +4792,9 @@ getTableAttrs(TableInfo *tblinfo, int numTables)
 			 * we don't dump it because we can't tell whether it's been
 			 * explicitly set or was just a default.
 			 */
-			appendPQExpBuffer(q, "SELECT a.attnum, a.attname, "
-						   "a.atttypmod, -1 AS attstattarget, a.attstorage, "
+			appendPQExpBuffer(q, "SELECT a.attnum, a.attname, a.atttypmod, "
+							  "-1 AS attstattarget, 0 AS attdistinct, "
+							  "a.attstorage, "
 							  "t.typstorage, a.attnotnull, a.atthasdef, "
 							  "false AS attisdropped, a.attlen, "
 							  "a.attalign, false AS attislocal, "
@@ -4791,8 +4810,8 @@ getTableAttrs(TableInfo *tblinfo, int numTables)
 		{
 			/* format_type not available before 7.1 */
 			appendPQExpBuffer(q, "SELECT attnum, attname, atttypmod, "
-							  "-1 AS attstattarget, attstorage, "
-							  "attstorage AS typstorage, "
+							  "-1 AS attstattarget, 0 AS attdistinct, "
+							  "attstorage, attstorage AS typstorage, "
 							  "attnotnull, atthasdef, false AS attisdropped, "
 							  "attlen, attalign, "
 							  "false AS attislocal, "
@@ -4814,6 +4833,7 @@ getTableAttrs(TableInfo *tblinfo, int numTables)
 		i_atttypname = PQfnumber(res, "atttypname");
 		i_atttypmod = PQfnumber(res, "atttypmod");
 		i_attstattarget = PQfnumber(res, "attstattarget");
+		i_attdistinct = PQfnumber(res, "attdistinct");
 		i_attstorage = PQfnumber(res, "attstorage");
 		i_typstorage = PQfnumber(res, "typstorage");
 		i_attnotnull = PQfnumber(res, "attnotnull");
@@ -4828,6 +4848,7 @@ getTableAttrs(TableInfo *tblinfo, int numTables)
 		tbinfo->atttypnames = (char **) malloc(ntups * sizeof(char *));
 		tbinfo->atttypmod = (int *) malloc(ntups * sizeof(int));
 		tbinfo->attstattarget = (int *) malloc(ntups * sizeof(int));
+		tbinfo->attdistinct = (float4 *) malloc(ntups * sizeof(float4));
 		tbinfo->attstorage = (char *) malloc(ntups * sizeof(char));
 		tbinfo->typstorage = (char *) malloc(ntups * sizeof(char));
 		tbinfo->attisdropped = (bool *) malloc(ntups * sizeof(bool));
@@ -4853,6 +4874,8 @@ getTableAttrs(TableInfo *tblinfo, int numTables)
 			tbinfo->atttypnames[j] = strdup(PQgetvalue(res, j, i_atttypname));
 			tbinfo->atttypmod[j] = atoi(PQgetvalue(res, j, i_atttypmod));
 			tbinfo->attstattarget[j] = atoi(PQgetvalue(res, j, i_attstattarget));
+			tbinfo->attdistinct[j] = strtod(PQgetvalue(res, j, i_attdistinct),
+											(char **) NULL);
 			tbinfo->attstorage[j] = *(PQgetvalue(res, j, i_attstorage));
 			tbinfo->typstorage[j] = *(PQgetvalue(res, j, i_typstorage));
 			tbinfo->attisdropped[j] = (PQgetvalue(res, j, i_attisdropped)[0] == 't');
@@ -10189,6 +10212,22 @@ dumpTableSchema(Archive *fout, TableInfo *tbinfo)
 								  tbinfo->attstattarget[j]);
 			}
 
+			/*
+			 * Dump per-column ndistinct information. We only issue an ALTER
+			 * TABLE statement if the attdistinct entry for this column is
+			 * non-zero (i.e. it's not the default value)
+			 */
+			if (tbinfo->attdistinct[j] != 0 &&
+				!tbinfo->attisdropped[j])
+			{
+				appendPQExpBuffer(q, "ALTER TABLE ONLY %s ",
+								  fmtId(tbinfo->dobj.name));
+				appendPQExpBuffer(q, "ALTER COLUMN %s ",
+								  fmtId(tbinfo->attnames[j]));
+				appendPQExpBuffer(q, "SET STATISTICS DISTINCT %g;\n", 
+								  tbinfo->attdistinct[j]);
+			}
+
 			/*
 			 * Dump per-column storage information.  The statement is only
 			 * dumped if the storage has been changed from the type's default.

src/bin/pg_dump/pg_dump.h

@@ -6,7 +6,7 @@
  * Portions Copyright (c) 1996-2009, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/bin/pg_dump/pg_dump.h,v 1.155 2009/07/29 20:56:19 tgl Exp $
+ * $PostgreSQL: pgsql/src/bin/pg_dump/pg_dump.h,v 1.156 2009/08/02 22:14:52 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -243,6 +243,7 @@ typedef struct _tableInfo
 	char	  **atttypnames;	/* attribute type names */
 	int		   *atttypmod;		/* type-specific type modifiers */
 	int		   *attstattarget;	/* attribute statistics targets */
+	float4	   *attdistinct;	/* override ndistinct calculation */
 	char	   *attstorage;		/* attribute storage scheme */
 	char	   *typstorage;		/* type storage scheme */
 	bool	   *attisdropped;	/* true if attr is dropped; don't dump it */

src/bin/psql/tab-complete.c

@@ -3,7 +3,7 @@
  *
  * Copyright (c) 2000-2009, PostgreSQL Global Development Group
  *
- * $PostgreSQL: pgsql/src/bin/psql/tab-complete.c,v 1.184 2009/06/11 14:49:08 momjian Exp $
+ * $PostgreSQL: pgsql/src/bin/psql/tab-complete.c,v 1.185 2009/08/02 22:14:52 tgl Exp $
  */
 
 /*----------------------------------------------------------------------
@@ -674,12 +674,10 @@ psql_completion(char *text, int start, int end)
 	else if (pg_strcasecmp(prev_wd, "CREATE") == 0)
 		matches = completion_matches(text, create_command_generator);
 
-/* DROP, except ALTER (TABLE|DOMAIN|GROUP) sth DROP */
+/* DROP, but watch out for DROP embedded in other commands */
 	/* complete with something you can drop */
 	else if (pg_strcasecmp(prev_wd, "DROP") == 0 &&
-			 pg_strcasecmp(prev3_wd, "TABLE") != 0 &&
-			 pg_strcasecmp(prev3_wd, "DOMAIN") != 0 &&
-			 pg_strcasecmp(prev3_wd, "GROUP") != 0)
+			 pg_strcasecmp(prev2_wd, "DROP") == 0)
 		matches = completion_matches(text, drop_command_generator);
 
 /* ALTER */
@@ -967,13 +965,44 @@ psql_completion(char *text, int start, int end)
 			 (pg_strcasecmp(prev4_wd, "TABLE") == 0 &&
 			  pg_strcasecmp(prev2_wd, "ALTER") == 0))
 	{
-		/* DROP ... does not work well yet */
 		static const char *const list_COLUMNALTER[] =
-		{"TYPE", "SET DEFAULT", "DROP DEFAULT", "SET NOT NULL",
-		"DROP NOT NULL", "SET STATISTICS", "SET STORAGE", NULL};
+		{"TYPE", "SET", "DROP", NULL};
 
 		COMPLETE_WITH_LIST(list_COLUMNALTER);
 	}
+	else if (((pg_strcasecmp(prev4_wd, "ALTER") == 0 &&
+			   pg_strcasecmp(prev3_wd, "COLUMN") == 0) ||
+			  (pg_strcasecmp(prev5_wd, "TABLE") == 0 &&
+			   pg_strcasecmp(prev3_wd, "ALTER") == 0)) &&
+			 pg_strcasecmp(prev_wd, "SET") == 0)
+	{
+		static const char *const list_COLUMNSET[] =
+		{"DEFAULT", "NOT NULL", "STATISTICS", "STORAGE", NULL};
+
+		COMPLETE_WITH_LIST(list_COLUMNSET);
+	}
+	else if (((pg_strcasecmp(prev5_wd, "ALTER") == 0 &&
+			   pg_strcasecmp(prev4_wd, "COLUMN") == 0) ||
+			  pg_strcasecmp(prev4_wd, "ALTER") == 0) &&
+			 pg_strcasecmp(prev2_wd, "SET") == 0 &&
+			 pg_strcasecmp(prev_wd, "STATISTICS") == 0)
+	{
+		static const char *const list_COLUMNSETSTATS[] =
+		{"DISTINCT", NULL};
+
+		COMPLETE_WITH_LIST(list_COLUMNSETSTATS);
+	}
+	else if (((pg_strcasecmp(prev4_wd, "ALTER") == 0 &&
+			   pg_strcasecmp(prev3_wd, "COLUMN") == 0) ||
+			  (pg_strcasecmp(prev5_wd, "TABLE") == 0 &&
+			   pg_strcasecmp(prev3_wd, "ALTER") == 0)) &&
+			 pg_strcasecmp(prev_wd, "DROP") == 0)
+	{
+		static const char *const list_COLUMNDROP[] =
+		{"DEFAULT", "NOT NULL", NULL};
+
+		COMPLETE_WITH_LIST(list_COLUMNDROP);
+	}
 	else if (pg_strcasecmp(prev3_wd, "TABLE") == 0 &&
 			 pg_strcasecmp(prev_wd, "CLUSTER") == 0)
 		COMPLETE_WITH_CONST("ON");

src/include/catalog/catversion.h

@@ -37,7 +37,7 @@
  * Portions Copyright (c) 1996-2009, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/catalog/catversion.h,v 1.534 2009/07/29 20:56:19 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/catalog/catversion.h,v 1.535 2009/08/02 22:14:52 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -53,6 +53,6 @@
  */
 
 /*							yyyymmddN */
-#define CATALOG_VERSION_NO	200907291
+#define CATALOG_VERSION_NO	200908021
 
 #endif

src/include/catalog/pg_class.h

@@ -8,7 +8,7 @@
  * Portions Copyright (c) 1996-2009, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/catalog/pg_class.h,v 1.114 2009/06/11 14:49:09 momjian Exp $
+ * $PostgreSQL: pgsql/src/include/catalog/pg_class.h,v 1.115 2009/08/02 22:14:53 tgl Exp $
  *
  * NOTES
  *	  the genbki.sh script reads this file and generates .bki
@@ -125,7 +125,7 @@ typedef FormData_pg_class *Form_pg_class;
 /* Note: "3" in the relfrozenxid column stands for FirstNormalTransactionId */
 DATA(insert OID = 1247 (  pg_type		PGNSP 71 PGUID 0 1247 0 0 0 0 0 f f f r 28 0 t f f f f 3 _null_ _null_ ));
 DESCR("");
-DATA(insert OID = 1249 (  pg_attribute	PGNSP 75 PGUID 0 1249 0 0 0 0 0 f f f r 18 0 f f f f f 3 _null_ _null_ ));
+DATA(insert OID = 1249 (  pg_attribute	PGNSP 75 PGUID 0 1249 0 0 0 0 0 f f f r 19 0 f f f f f 3 _null_ _null_ ));
 DESCR("");
 DATA(insert OID = 1255 (  pg_proc		PGNSP 81 PGUID 0 1255 0 0 0 0 0 f f f r 25 0 t f f f f 3 _null_ _null_ ));
 DESCR("");

src/include/nodes/parsenodes.h

@@ -13,7 +13,7 @@
  * Portions Copyright (c) 1996-2009, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/nodes/parsenodes.h,v 1.400 2009/07/30 02:45:38 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/nodes/parsenodes.h,v 1.401 2009/08/02 22:14:53 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -1098,8 +1098,9 @@ typedef enum AlterTableType
 	AT_ColumnDefault,			/* alter column default */
 	AT_DropNotNull,				/* alter column drop not null */
 	AT_SetNotNull,				/* alter column set not null */
-	AT_SetStatistics,			/* alter column statistics */
-	AT_SetStorage,				/* alter column storage */
+	AT_SetStatistics,			/* alter column set statistics */
+	AT_SetDistinct,				/* alter column set statistics distinct */
+	AT_SetStorage,				/* alter column set storage */
 	AT_DropColumn,				/* drop column */
 	AT_DropColumnRecurse,		/* internal to commands/tablecmds.c */
 	AT_AddIndex,				/* add index */