HOT updates. When we update a tuple without changing any of its indexed

columns, and the new version can be stored on the same heap page, we no longer
generate extra index entries for the new version.  Instead, index searches
follow the HOT-chain links to ensure they find the correct tuple version.

In addition, this patch introduces the ability to "prune" dead tuples on a
per-page basis, without having to do a complete VACUUM pass to recover space.
VACUUM is still needed to clean up dead index entries, however.

Pavan Deolasee, with help from a bunch of other people.

2 files changed, 60 insertions, 2 deletions

diff --git a/src/backend/optimizer/util/plancat.c b/src/backend/optimizer/util/plancat.c
index 70b3d7d43f5..21dd342593a 100644
--- a/src/backend/optimizer/util/plancat.c
+++ b/src/backend/optimizer/util/plancat.c
@@ -9,7 +9,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/optimizer/util/plancat.c,v 1.136 2007/05/31 16:57:34 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/optimizer/util/plancat.c,v 1.137 2007/09/20 17:56:31 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -19,6 +19,7 @@
 
 #include "access/genam.h"
 #include "access/heapam.h"
+#include "access/transam.h"
 #include "catalog/pg_inherits.h"
 #include "nodes/makefuncs.h"
 #include "optimizer/clauses.h"
@@ -164,6 +165,20 @@ get_relation_info(PlannerInfo *root, Oid relationObjectId, bool inhparent,
 				continue;
 			}
 
+			/*
+			 * If the index is valid, but cannot yet be used, ignore it;
+			 * but mark the plan we are generating as transient.
+			 * See src/backend/access/heap/README.HOT for discussion.
+			 */
+			if (index->indcheckxmin &&
+				!TransactionIdPrecedes(HeapTupleHeaderGetXmin(indexRelation->rd_indextuple->t_data),
+									   TransactionXmin))
+			{
+				root->glob->transientPlan = true;
+				index_close(indexRelation, NoLock);
+				continue;
+			}
+
 			info = makeNode(IndexOptInfo);
 
 			info->indexoid = index->indexrelid;
diff --git a/src/backend/optimizer/util/var.c b/src/backend/optimizer/util/var.c
index c501c827922..efb1ad9343d 100644
--- a/src/backend/optimizer/util/var.c
+++ b/src/backend/optimizer/util/var.c
@@ -8,12 +8,13 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/optimizer/util/var.c,v 1.70 2007/06/11 01:16:23 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/optimizer/util/var.c,v 1.71 2007/09/20 17:56:31 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
 #include "postgres.h"
 
+#include "access/htup.h"
 #include "optimizer/clauses.h"
 #include "optimizer/prep.h"
 #include "optimizer/var.h"
@@ -54,6 +55,7 @@ typedef struct
 
 static bool pull_varnos_walker(Node *node,
 				   pull_varnos_context *context);
+static bool pull_varattnos_walker(Node *node, Bitmapset **varattnos);
 static bool contain_var_reference_walker(Node *node,
 							 contain_var_reference_context *context);
 static bool contain_var_clause_walker(Node *node, void *context);
@@ -134,6 +136,47 @@ pull_varnos_walker(Node *node, pull_varnos_context *context)
 								  (void *) context);
 }
 
+/*
+ * pull_varattnos
+ *		Find all the distinct attribute numbers present in an expression tree,
+ *		and add them to the initial contents of *varattnos.
+ *		Only Vars that reference RTE 1 of rtable level zero are considered.
+ *
+ * Attribute numbers are offset by FirstLowInvalidHeapAttributeNumber so that
+ * we can include system attributes (e.g., OID) in the bitmap representation.
+ *
+ * Currently, this does not support subqueries nor expressions containing
+ * references to multiple tables; not needed since it's only applied to
+ * index expressions and predicates.
+ */
+void
+pull_varattnos(Node *node, Bitmapset **varattnos)
+{
+	(void) pull_varattnos_walker(node, varattnos);
+}
+
+static bool
+pull_varattnos_walker(Node *node, Bitmapset **varattnos)
+{
+	if (node == NULL)
+		return false;
+	if (IsA(node, Var))
+	{
+		Var		   *var = (Var *) node;
+
+		Assert(var->varno == 1);
+		*varattnos = bms_add_member(*varattnos,
+						var->varattno - FirstLowInvalidHeapAttributeNumber);
+		return false;
+	}
+	/* Should not find a subquery or subplan */
+	Assert(!IsA(node, Query));
+	Assert(!is_subplan(node));
+
+	return expression_tree_walker(node, pull_varattnos_walker,
+								  (void *) varattnos);
+}
+
 
 /*
  *		contain_var_reference