Implement multivariate n-distinct coefficients

Add support for explicitly declared statistic objects (CREATE
STATISTICS), allowing collection of statistics on more complex
combinations that individual table columns.  Companion commands DROP
STATISTICS and ALTER STATISTICS ... OWNER TO / SET SCHEMA / RENAME are
added too.  All this DDL has been designed so that more statistic types
can be added later on, such as multivariate most-common-values and
multivariate histograms between columns of a single table, leaving room
for permitting columns on multiple tables, too, as well as expressions.

This commit only adds support for collection of n-distinct coefficient
on user-specified sets of columns in a single table.  This is useful to
estimate number of distinct groups in GROUP BY and DISTINCT clauses;
estimation errors there can cause over-allocation of memory in hashed
aggregates, for instance, so it's a worthwhile problem to solve.  A new
special pseudo-type pg_ndistinct is used.

(num-distinct estimation was deemed sufficiently useful by itself that
this is worthwhile even if no further statistic types are added
immediately; so much so that another version of essentially the same
functionality was submitted by Kyotaro Horiguchi:
https://postgr.es/m/20150828.173334.114731693.horiguchi.kyotaro@lab.ntt.co.jp
though this commit does not use that code.)

Author: Tomas Vondra.  Some code rework by Álvaro.
Reviewed-by: Dean Rasheed, David Rowley, Kyotaro Horiguchi, Jeff Janes,
    Ideriha Takeshi
Discussion: https://postgr.es/m/543AFA15.4080608@fuzzy.cz
    https://postgr.es/m/20170320190220.ixlaueanxegqd5gr@alvherre.pgsql

1 files changed, 31 insertions, 0 deletions

diff --git a/src/backend/nodes/outfuncs.c b/src/backend/nodes/outfuncs.c
index 1b9005fa537..541af029353 100644
--- a/src/backend/nodes/outfuncs.c
+++ b/src/backend/nodes/outfuncs.c
@@ -2202,6 +2202,7 @@ _outRelOptInfo(StringInfo str, const RelOptInfo *node)
 	WRITE_NODE_FIELD(lateral_vars);
 	WRITE_BITMAPSET_FIELD(lateral_referencers);
 	WRITE_NODE_FIELD(indexlist);
+	WRITE_NODE_FIELD(statlist);
 	WRITE_UINT_FIELD(pages);
 	WRITE_FLOAT_FIELD(tuples, "%.0f");
 	WRITE_FLOAT_FIELD(allvisfrac, "%.6f");
@@ -2275,6 +2276,18 @@ _outForeignKeyOptInfo(StringInfo str, const ForeignKeyOptInfo *node)
 }
 
 static void
+_outStatisticExtInfo(StringInfo str, const StatisticExtInfo *node)
+{
+	WRITE_NODE_TYPE("STATISTICEXTINFO");
+
+	/* NB: this isn't a complete set of fields */
+	WRITE_OID_FIELD(statOid);
+	/* don't write rel, leads to infinite recursion in plan tree dump */
+	WRITE_CHAR_FIELD(kind);
+	WRITE_BITMAPSET_FIELD(keys);
+}
+
+static void
 _outEquivalenceClass(StringInfo str, const EquivalenceClass *node)
 {
 	/*
@@ -2578,6 +2591,18 @@ _outIndexStmt(StringInfo str, const IndexStmt *node)
 }
 
 static void
+_outCreateStatsStmt(StringInfo str, const CreateStatsStmt *node)
+{
+	WRITE_NODE_TYPE("CREATESTATSSTMT");
+
+	WRITE_NODE_FIELD(defnames);
+	WRITE_NODE_FIELD(relation);
+	WRITE_NODE_FIELD(keys);
+	WRITE_NODE_FIELD(options);
+	WRITE_BOOL_FIELD(if_not_exists);
+}
+
+static void
 _outNotifyStmt(StringInfo str, const NotifyStmt *node)
 {
 	WRITE_NODE_TYPE("NOTIFY");
@@ -3936,6 +3961,9 @@ outNode(StringInfo str, const void *obj)
 			case T_PlannerParamItem:
 				_outPlannerParamItem(str, obj);
 				break;
+			case T_StatisticExtInfo:
+				_outStatisticExtInfo(str, obj);
+				break;
 
 			case T_ExtensibleNode:
 				_outExtensibleNode(str, obj);
@@ -3953,6 +3981,9 @@ outNode(StringInfo str, const void *obj)
 			case T_IndexStmt:
 				_outIndexStmt(str, obj);
 				break;
+			case T_CreateStatsStmt:
+				_outCreateStatsStmt(str, obj);
+				break;
 			case T_NotifyStmt:
 				_outNotifyStmt(str, obj);
 				break;