Clarify a confusing comment about MCVs vs histogram entries.

tglsfdc · tglsfdc · commit 82c9662378e7 · 2009-01-06T23:46:06.000Z
Per Nathan Boley.
diff --git 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 1.131 2009/01/01 17:23:37 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/backend/commands/analyze.c,v 1.132 2009/01/06 23:46:06 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -2149,7 +2149,9 @@ compute_scalar_stats(VacAttrStatsP stats,
 		 * least 2 instances in the sample.  Also, we won't suppress values
 		 * that have a frequency of at least 1/K where K is the intended
 		 * number of histogram bins; such values might otherwise cause us to
-		 * emit duplicate histogram bin boundaries.
+		 * emit duplicate histogram bin boundaries.  (We might end up with
+		 * duplicate histogram entries anyway, if the distribution is skewed;
+		 * but we prefer to treat such values as MCVs if at all possible.)
 		 */
 		if (track_cnt == ndistinct && toowide_cnt == 0 &&
 			stats->stadistinct > 0 &&

Original file line number	Diff line number	Diff line change
`@@ -8,7 +8,7 @@`
`8`	`8`	`*`
`9`	`9`	`*`
`10`	`10`	`* IDENTIFICATION`
`11`		`- * $PostgreSQL: pgsql/src/backend/commands/analyze.c,v 1.131 2009/01/01 17:23:37 momjian Exp $`
	`11`	`+ * $PostgreSQL: pgsql/src/backend/commands/analyze.c,v 1.132 2009/01/06 23:46:06 tgl Exp $`
`12`	`12`	`*`
`13`	`13`	`*-------------------------------------------------------------------------`
`14`	`14`	`*/`
`@@ -2149,7 +2149,9 @@ compute_scalar_stats(VacAttrStatsP stats,`
`2149`	`2149`	`* least 2 instances in the sample. Also, we won't suppress values`
`2150`	`2150`	`* that have a frequency of at least 1/K where K is the intended`
`2151`	`2151`	`* number of histogram bins; such values might otherwise cause us to`
`2152`		`- * emit duplicate histogram bin boundaries.`
	`2152`	`+ * emit duplicate histogram bin boundaries. (We might end up with`
	`2153`	`+ * duplicate histogram entries anyway, if the distribution is skewed;`
	`2154`	`+ * but we prefer to treat such values as MCVs if at all possible.)`
`2153`	`2155`	`*/`
`2154`	`2156`	`if (track_cnt == ndistinct && toowide_cnt == 0 &&`
`2155`	`2157`	`stats->stadistinct > 0 &&`