Generic implementation of red-black binary tree. It's planned to use in

several places, but for now only GIN uses it during index creation.
Using self-balanced tree greatly speeds up index creation in corner cases
with preordered data.

src/backend/access/gin/ginfast.c

@@ -11,7 +11,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * IDENTIFICATION
- *			$PostgreSQL: pgsql/src/backend/access/gin/ginfast.c,v 1.6 2010/01/02 16:57:33 momjian Exp $
+ *			$PostgreSQL: pgsql/src/backend/access/gin/ginfast.c,v 1.7 2010/02/11 14:29:50 teodor Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -765,8 +765,7 @@ ginInsertCleanup(Relation index, GinState *ginstate,
 		 */
 		if (GinPageGetOpaque(page)->rightlink == InvalidBlockNumber ||
 			(GinPageHasFullRow(page) &&
-			 (accum.allocatedMemory >= maintenance_work_mem * 1024L ||
-			  accum.maxdepth > GIN_MAX_TREE_DEPTH)))
+			 (accum.allocatedMemory >= maintenance_work_mem * 1024L)))
 		{
 			ItemPointerData *list;
 			uint32		nlist;

src/backend/access/gin/gininsert.c

@@ -8,7 +8,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * IDENTIFICATION
- *			$PostgreSQL: pgsql/src/backend/access/gin/gininsert.c,v 1.25 2010/01/02 16:57:33 momjian Exp $
+ *			$PostgreSQL: pgsql/src/backend/access/gin/gininsert.c,v 1.26 2010/02/11 14:29:50 teodor Exp $
  *-------------------------------------------------------------------------
  */
 
@@ -247,9 +247,7 @@ ginBuildCallback(Relation index, HeapTuple htup, Datum *values,
 															&htup->t_self);
 
 	/* If we've maxed out our available memory, dump everything to the index */
-	/* Also dump if the tree seems to be getting too unbalanced */
-	if (buildstate->accum.allocatedMemory >= maintenance_work_mem * 1024L ||
-		buildstate->accum.maxdepth > GIN_MAX_TREE_DEPTH)
+	if (buildstate->accum.allocatedMemory >= maintenance_work_mem * 1024L)
 	{
 		ItemPointerData *list;
 		Datum		entry;

src/backend/utils/misc/Makefile

@@ -4,7 +4,7 @@
 #    Makefile for utils/misc
 #
 # IDENTIFICATION
-#    $PostgreSQL: pgsql/src/backend/utils/misc/Makefile,v 1.29 2009/08/28 20:26:19 petere Exp $
+#    $PostgreSQL: pgsql/src/backend/utils/misc/Makefile,v 1.30 2010/02/11 14:29:50 teodor Exp $
 #
 #-------------------------------------------------------------------------
 
@@ -14,7 +14,8 @@ include $(top_builddir)/src/Makefile.global
 
 override CPPFLAGS := -I. -I$(srcdir) $(CPPFLAGS)
 
-OBJS = guc.o help_config.o pg_rusage.o ps_status.o superuser.o tzparser.o
+OBJS = guc.o help_config.o pg_rusage.o ps_status.o superuser.o tzparser.o \
+       rbtree.o
 
 # This location might depend on the installation directories. Therefore
 # we can't subsitute it into pg_config.h.

src/include/access/gin.h

@@ -4,7 +4,7 @@
  *
  *	Copyright (c) 2006-2010, PostgreSQL Global Development Group
  *
- *	$PostgreSQL: pgsql/src/include/access/gin.h,v 1.36 2010/01/02 16:58:00 momjian Exp $
+ *	$PostgreSQL: pgsql/src/include/access/gin.h,v 1.37 2010/02/11 14:29:50 teodor Exp $
  *--------------------------------------------------------------------------
  */
 #ifndef GIN_H
@@ -13,6 +13,7 @@
 #include "access/genam.h"
 #include "access/itup.h"
 #include "access/xlog.h"
+#include "utils/rbtree.h"
 #include "fmgr.h"
 
 
@@ -26,14 +27,6 @@
 #define GIN_COMPARE_PARTIAL_PROC	   5
 #define GINNProcs					   5
 
-/*
- * Max depth allowed in search tree during bulk inserts.  This is to keep from
- * degenerating to O(N^2) behavior when the tree is unbalanced due to sorted
- * or nearly-sorted input.	(Perhaps it would be better to use a balanced-tree
- * algorithm, but in common cases that would only add useless overhead.)
- */
-#define GIN_MAX_TREE_DEPTH 100
-
 /*
  * Page opaque data in a inverted index page.
  *
@@ -570,27 +563,23 @@ extern Datum ginarrayconsistent(PG_FUNCTION_ARGS);
 /* ginbulk.c */
 typedef struct EntryAccumulator
 {
-	OffsetNumber attnum;
 	Datum		value;
 	uint32		length;
 	uint32		number;
-	ItemPointerData *list;
+	OffsetNumber attnum;
 	bool		shouldSort;
-	struct EntryAccumulator *left;
-	struct EntryAccumulator *right;
+	ItemPointerData *list;
 } EntryAccumulator;
 
 typedef struct
 {
 	GinState   *ginstate;
-	EntryAccumulator *entries;
-	uint32		maxdepth;
-	EntryAccumulator **stack;
-	uint32		stackpos;
 	long		allocatedMemory;
-
 	uint32		length;
 	EntryAccumulator   *entryallocator;
+	ItemPointerData	   *tmpList;
+	RBTree	   *tree;
+	RBTreeIterator *iterator;
 } BuildAccumulator;
 
 extern void ginInitBA(BuildAccumulator *accum);

src/include/utils/rbtree.h

+/*-------------------------------------------------------------------------
+ *
+ * rbtree.h
+ *    interface for PostgreSQL generic Red-Black binary tree package
+ *
+ * Copyright (c) 1996-2009, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ * 		$PostgreSQL: pgsql/src/include/utils/rbtree.h,v 1.1 2010/02/11 14:29:50 teodor Exp $
+ *
+ *-------------------------------------------------------------------------
+ */
+
+#ifndef RBTREE_H
+#define RBTREE_H
+
+typedef struct RBTree RBTree;
+typedef struct RBTreeIterator RBTreeIterator;
+
+typedef int (*rb_comparator) (const void *a, const void *b, void *arg);
+typedef void* (*rb_appendator) (void *current, void *new, void *arg);
+typedef void (*rb_freefunc) (void *a);
+
+extern RBTree *rb_create(rb_comparator comparator,
+							rb_appendator appendator,
+							rb_freefunc freefunc,
+							void *arg);
+
+extern void *rb_find(RBTree *rb, void *data);
+extern void *rb_insert(RBTree *rb, void *data);
+extern void rb_delete(RBTree *rb, void *data);
+extern void *rb_leftmost(RBTree *rb);
+
+typedef enum RBOrderControl
+{
+	LeftRightWalk,
+	RightLeftWalk,
+	DirectWalk,
+	InvertedWalk
+} RBOrderControl;
+
+extern RBTreeIterator* rb_begin_iterate(RBTree *rb, RBOrderControl ctrl);
+extern void *rb_iterate(RBTreeIterator *iterator);
+extern void rb_free_iterator(RBTreeIterator *iterator);
+
+#endif