Improve UniquePath logic to detect the case where the input is already

known unique (eg, it is a SELECT DISTINCT ... subquery), and not do a
redundant unique-ification step.

2 files changed, 18 insertions, 6 deletions

diff --git a/src/include/nodes/relation.h b/src/include/nodes/relation.h
index 14486591da9..166f1242b0e 100644
--- a/src/include/nodes/relation.h
+++ b/src/include/nodes/relation.h
@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2003, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/nodes/relation.h,v 1.91 2004/01/05 05:07:36 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/nodes/relation.h,v 1.92 2004/01/05 18:04:39 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -442,15 +442,26 @@ typedef struct MaterialPath
  * its subpath.
  *
  * This is unlike the other Path nodes in that it can actually generate
- * two different plans: either hash-based or sort-based implementation.
- * The decision is sufficiently localized that it's not worth having two
- * separate Path node types.
+ * different plans: either hash-based or sort-based implementation, or a
+ * no-op if the input path can be proven distinct already.  The decision
+ * is sufficiently localized that it's not worth having separate Path node
+ * types.  (Note: in the no-op case, we could eliminate the UniquePath node
+ * entirely and just return the subpath; but it's convenient to have a
+ * UniquePath in the path tree to signal upper-level routines that the input
+ * is known distinct.)
  */
+typedef enum
+{
+	UNIQUE_PATH_NOOP,			/* input is known unique already */
+	UNIQUE_PATH_HASH,			/* use hashing */
+	UNIQUE_PATH_SORT			/* use sorting */
+} UniquePathMethod;
+
 typedef struct UniquePath
 {
 	Path		path;
 	Path	   *subpath;
-	bool		use_hash;
+	UniquePathMethod umethod;
 	double		rows;			/* estimated number of result tuples */
 } UniquePath;
 
diff --git a/src/include/optimizer/clauses.h b/src/include/optimizer/clauses.h
index c948a9039fb..947c4467e7b 100644
--- a/src/include/optimizer/clauses.h
+++ b/src/include/optimizer/clauses.h
@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2003, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/optimizer/clauses.h,v 1.71 2004/01/04 03:51:52 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/optimizer/clauses.h,v 1.72 2004/01/05 18:04:39 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -57,6 +57,7 @@ extern bool is_pseudo_constant_clause(Node *clause);
 extern bool is_pseudo_constant_clause_relids(Node *clause, Relids relids);
 extern List *pull_constant_clauses(List *quals, List **constantQual);
 
+extern bool has_distinct_clause(Query *query);
 extern bool has_distinct_on_clause(Query *query);
 
 extern int	NumRelids(Node *clause);