Increase the default value of default_statistics_target from 10 to 100,

and its maximum value from 1000 to 10000.  ALTER TABLE SET STATISTICS
similarly now allows a value up to 10000.  Per discussion.

5 files changed, 15 insertions, 15 deletions

diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c
index 6b95075be1f..2b3af54ff05 100644
--- a/src/backend/commands/analyze.c
+++ b/src/backend/commands/analyze.c
@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/commands/analyze.c,v 1.128 2008/11/10 00:49:37 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/commands/analyze.c,v 1.129 2008/12/13 19:13:44 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -67,7 +67,7 @@ typedef struct AnlIndexData
 
 
 /* Default statistics target (GUC parameter) */
-int			default_statistics_target = 10;
+int			default_statistics_target = 100;
 
 /* A few variables that don't seem worth passing around as parameters */
 static int	elevel = -1;
@@ -1531,10 +1531,10 @@ std_typanalyze(VacAttrStats *stats)
 		 * error in bin size f, and error probability gamma, the minimum
 		 * random sample size is
 		 *		r = 4 * k * ln(2*n/gamma) / f^2
-		 * Taking f = 0.5, gamma = 0.01, n = 1 million rows, we obtain
+		 * Taking f = 0.5, gamma = 0.01, n = 10^6 rows, we obtain
 		 *		r = 305.82 * k
 		 * Note that because of the log function, the dependence on n is
-		 * quite weak; even at n = 1 billion, a 300*k sample gives <= 0.59
+		 * quite weak; even at n = 10^12, a 300*k sample gives <= 0.66
 		 * bin size error with probability 0.99.  So there's no real need to
 		 * scale for n, which is a good thing because we don't necessarily
 		 * know it at this point.
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index 8e12a77d11c..6c60ddd5c10 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/commands/tablecmds.c,v 1.272 2008/12/06 23:22:46 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/backend/commands/tablecmds.c,v 1.273 2008/12/13 19:13:44 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -3942,9 +3942,9 @@ ATExecSetStatistics(Relation rel, const char *colName, Node *newValue)
 				 errmsg("statistics target %d is too low",
 						newtarget)));
 	}
-	else if (newtarget > 1000)
+	else if (newtarget > 10000)
 	{
-		newtarget = 1000;
+		newtarget = 10000;
 		ereport(WARNING,
 				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
 				 errmsg("lowering statistics target to %d",
diff --git a/src/backend/tsearch/ts_typanalyze.c b/src/backend/tsearch/ts_typanalyze.c
index 199432097bc..d30afe352c5 100644
--- a/src/backend/tsearch/ts_typanalyze.c
+++ b/src/backend/tsearch/ts_typanalyze.c
@@ -7,7 +7,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/tsearch/ts_typanalyze.c,v 1.3 2008/11/27 21:17:39 heikki Exp $
+ *	  $PostgreSQL: pgsql/src/backend/tsearch/ts_typanalyze.c,v 1.4 2008/12/13 19:13:44 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -63,7 +63,7 @@ ts_typanalyze(PG_FUNCTION_ARGS)
 		attr->attstattarget = default_statistics_target;
 
 	stats->compute_stats = compute_tsvector_stats;
-	/* see comment about the choice of minrows from analyze.c */
+	/* see comment about the choice of minrows in commands/analyze.c */
 	stats->minrows = 300 * attr->attstattarget;
 
 	PG_RETURN_BOOL(true);
@@ -105,8 +105,8 @@ ts_typanalyze(PG_FUNCTION_ARGS)
  *	is no more than a few times w.
  *
  *	We use a hashtable for the D structure and a bucket width of
- *	statistic_target * 100, where 100 is an arbitrarily chosen constant, meant
- *	to approximate the number of lexemes in a single tsvector.
+ *	statistics_target * 100, where 100 is an arbitrarily chosen constant,
+ *	meant to approximate the number of lexemes in a single tsvector.
  */
 static void
 compute_tsvector_stats(VacAttrStats *stats,
@@ -130,7 +130,7 @@ compute_tsvector_stats(VacAttrStats *stats,
 	LexemeHashKey 	hash_key;
 	TrackItem		*item;
 
-	/* We want statistic_target * 100 lexemes in the MCELEM array */
+	/* We want statistics_target * 100 lexemes in the MCELEM array */
 	num_mcelem = stats->attr->attstattarget * 100;
 
 	/*
diff --git a/src/backend/utils/misc/guc.c b/src/backend/utils/misc/guc.c
index 00dac28c27e..8e3be6fe371 100644
--- a/src/backend/utils/misc/guc.c
+++ b/src/backend/utils/misc/guc.c
@@ -10,7 +10,7 @@
  * Written by Peter Eisentraut <peter_e@gmx.net>.
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/utils/misc/guc.c,v 1.482 2008/12/02 02:00:32 alvherre Exp $
+ *	  $PostgreSQL: pgsql/src/backend/utils/misc/guc.c,v 1.483 2008/12/13 19:13:44 tgl Exp $
  *
  *--------------------------------------------------------------------
  */
@@ -1245,7 +1245,7 @@ static struct config_int ConfigureNamesInt[] =
 				"column-specific target set via ALTER TABLE SET STATISTICS.")
 		},
 		&default_statistics_target,
-		10, 1, 1000, NULL, NULL
+		100, 1, 10000, NULL, NULL
 	},
 	{
 		{"from_collapse_limit", PGC_USERSET, QUERY_TUNING_OTHER,
diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample
index f886ef74b21..bf85ae083c6 100644
--- a/src/backend/utils/misc/postgresql.conf.sample
+++ b/src/backend/utils/misc/postgresql.conf.sample
@@ -210,7 +210,7 @@
 
 # - Other Planner Options -
 
-#default_statistics_target = 10		# range 1-1000
+#default_statistics_target = 100	# range 1-10000
 #constraint_exclusion = off
 #cursor_tuple_fraction = 0.1		# range 0.0-1.0
 #from_collapse_limit = 8