Move the tuple freezing point in CLUSTER to a point further back in the past,

to avoid losing useful Xid information in not-so-old tuples.  This makes
CLUSTER behave the same as VACUUM as far a tuple-freezing behavior goes
(though CLUSTER does not yet advance the table's relfrozenxid).

While at it, move the actual freezing operation in rewriteheap.c to a more
appropriate place, and document it thoroughly.  This part of the patch from
Tom Lane.

src/backend/access/heap/rewriteheap.c

@@ -96,7 +96,7 @@
  * Portions Copyright (c) 1994-5, Regents of the University of California
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/access/heap/rewriteheap.c,v 1.4 2007/05/16 16:36:56 alvherre Exp $
+ *	  $PostgreSQL: pgsql/src/backend/access/heap/rewriteheap.c,v 1.5 2007/05/17 15:28:29 alvherre Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -123,6 +123,8 @@ typedef struct RewriteStateData
 	bool			rs_use_wal;			/* must we WAL-log inserts? */
 	TransactionId	rs_oldest_xmin;		/* oldest xmin used by caller to
 										 * determine tuple visibility */
+	TransactionId	rs_freeze_xid;		/* Xid that will be used as freeze
+										 * cutoff point */
 	MemoryContext	rs_cxt;				/* for hash tables and entries and
 										 * tuples in them */
 	HTAB		   *rs_unresolved_tups;	/* unmatched A tuples */
@@ -171,6 +173,7 @@ static void raw_heap_insert(RewriteState state, HeapTuple tup);
  *
  * new_heap		new, locked heap relation to insert tuples to
  * oldest_xmin	xid used by the caller to determine which tuples are dead
+ * freeze_xid	xid before which tuples will be frozen
  * use_wal		should the inserts to the new heap be WAL-logged?
  *
  * Returns an opaque RewriteState, allocated in current memory context,
@@ -178,7 +181,7 @@ static void raw_heap_insert(RewriteState state, HeapTuple tup);
  */
 RewriteState
 begin_heap_rewrite(Relation new_heap, TransactionId oldest_xmin,
-				   bool use_wal)
+				   TransactionId freeze_xid, bool use_wal)
 {
 	RewriteState state;
 	MemoryContext rw_cxt;
@@ -206,6 +209,7 @@ begin_heap_rewrite(Relation new_heap, TransactionId oldest_xmin,
 	state->rs_buffer_valid = false;
 	state->rs_use_wal = use_wal;
 	state->rs_oldest_xmin = oldest_xmin;
+	state->rs_freeze_xid = freeze_xid;
 	state->rs_cxt = rw_cxt;
 
 	/* Initialize hash tables used to track update chains */
@@ -292,7 +296,9 @@ end_heap_rewrite(RewriteState state)
 /*
  * Add a tuple to the new heap.
  *
- * Visibility information is copied from the original tuple.
+ * Visibility information is copied from the original tuple, except that
+ * we "freeze" very-old tuples.  Note that since we scribble on new_tuple,
+ * it had better be temp storage not a pointer to the original tuple.
  *
  * state		opaque state as returned by begin_heap_rewrite
  * old_tuple	original tuple in the old heap
@@ -323,6 +329,17 @@ rewrite_heap_tuple(RewriteState state,
 	new_tuple->t_data->t_infomask |=
 		old_tuple->t_data->t_infomask & HEAP_XACT_MASK;
 
+	/*
+	 * While we have our hands on the tuple, we may as well freeze any
+	 * very-old xmin or xmax, so that future VACUUM effort can be saved.
+	 *
+	 * Note we abuse heap_freeze_tuple() a bit here, since it's expecting
+	 * to be given a pointer to a tuple in a disk buffer.  It happens
+	 * though that we can get the right things to happen by passing
+	 * InvalidBuffer for the buffer.
+	 */
+	heap_freeze_tuple(new_tuple->t_data, state->rs_freeze_xid, InvalidBuffer);
+
 	/*
 	 * Invalid ctid means that ctid should point to the tuple itself.
 	 * We'll override it later if the tuple is part of an update chain.
@@ -538,8 +555,6 @@ raw_heap_insert(RewriteState state, HeapTuple tup)
 	OffsetNumber	newoff;
 	HeapTuple		heaptup;
 
-	heap_freeze_tuple(tup->t_data, state->rs_oldest_xmin, InvalidBuffer);
-
 	/*
 	 * If the new tuple is too big for storage or contains already toasted
 	 * out-of-line attributes from some other relation, invoke the toaster.

src/backend/commands/cluster.c

@@ -11,7 +11,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/commands/cluster.c,v 1.159 2007/04/08 01:26:28 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/commands/cluster.c,v 1.160 2007/05/17 15:28:29 alvherre Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -29,6 +29,7 @@
 #include "catalog/namespace.h"
 #include "catalog/toasting.h"
 #include "commands/cluster.h"
+#include "commands/vacuum.h"
 #include "miscadmin.h"
 #include "storage/procarray.h"
 #include "utils/acl.h"
@@ -657,6 +658,7 @@ copy_heap_data(Oid OIDNewHeap, Oid OIDOldHeap, Oid OIDOldIndex)
 	HeapTuple	tuple;
 	bool		use_wal;
 	TransactionId OldestXmin;
+	TransactionId FreezeXid;
 	RewriteState rwstate;
 
 	/*
@@ -688,11 +690,16 @@ copy_heap_data(Oid OIDNewHeap, Oid OIDOldHeap, Oid OIDOldIndex)
 	/* use_wal off requires rd_targblock be initially invalid */
 	Assert(NewHeap->rd_targblock == InvalidBlockNumber);
 
-	/* Get the cutoff xmin we'll use to weed out dead tuples */
-	OldestXmin = GetOldestXmin(OldHeap->rd_rel->relisshared, true);
+	/*
+	 * compute xids used to freeze and weed out dead tuples.  We use -1
+	 * freeze_min_age to avoid having CLUSTER freeze tuples earlier than
+	 * a plain VACUUM would.
+	 */
+	vacuum_set_xid_limits(-1, OldHeap->rd_rel->relisshared,
+						  &OldestXmin, &FreezeXid);
 
 	/* Initialize the rewrite operation */
-	rwstate = begin_heap_rewrite(NewHeap, OldestXmin, use_wal);
+	rwstate = begin_heap_rewrite(NewHeap, OldestXmin, FreezeXid, use_wal);
 
 	/*
 	 * Scan through the OldHeap in OldIndex order and copy each tuple into the

src/backend/commands/vacuum.c

@@ -13,7 +13,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/commands/vacuum.c,v 1.350 2007/04/16 18:29:50 alvherre Exp $
+ *	  $PostgreSQL: pgsql/src/backend/commands/vacuum.c,v 1.351 2007/05/17 15:28:29 alvherre Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -566,7 +566,7 @@ get_rel_oids(List *relids, const RangeVar *vacrel, const char *stmttype)
  * vacuum_set_xid_limits() -- compute oldest-Xmin and freeze cutoff points
  */
 void
-vacuum_set_xid_limits(VacuumStmt *vacstmt, bool sharedRel,
+vacuum_set_xid_limits(int freeze_min_age, bool sharedRel,
 					  TransactionId *oldestXmin,
 					  TransactionId *freezeLimit)
 {
@@ -588,12 +588,12 @@ vacuum_set_xid_limits(VacuumStmt *vacstmt, bool sharedRel,
 	Assert(TransactionIdIsNormal(*oldestXmin));
 
 	/*
-	 * Determine the minimum freeze age to use: as specified in the vacstmt,
+	 * Determine the minimum freeze age to use: as specified by the caller,
 	 * or vacuum_freeze_min_age, but in any case not more than half
 	 * autovacuum_freeze_max_age, so that autovacuums to prevent XID
 	 * wraparound won't occur too frequently.
 	 */
-	freezemin = vacstmt->freeze_min_age;
+	freezemin = freeze_min_age;
 	if (freezemin < 0)
 		freezemin = vacuum_freeze_min_age;
 	freezemin = Min(freezemin, autovacuum_freeze_max_age / 2);
@@ -1154,7 +1154,7 @@ full_vacuum_rel(Relation onerel, VacuumStmt *vacstmt)
 				i;
 	VRelStats  *vacrelstats;
 
-	vacuum_set_xid_limits(vacstmt, onerel->rd_rel->relisshared,
+	vacuum_set_xid_limits(vacstmt->freeze_min_age, onerel->rd_rel->relisshared,
 						  &OldestXmin, &FreezeLimit);
 
 	/*

src/backend/commands/vacuumlazy.c

@@ -36,7 +36,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/commands/vacuumlazy.c,v 1.88 2007/04/30 03:23:48 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/commands/vacuumlazy.c,v 1.89 2007/05/17 15:28:29 alvherre Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -158,7 +158,7 @@ lazy_vacuum_rel(Relation onerel, VacuumStmt *vacstmt)
 	else
 		elevel = DEBUG2;
 
-	vacuum_set_xid_limits(vacstmt, onerel->rd_rel->relisshared,
+	vacuum_set_xid_limits(vacstmt->freeze_min_age, onerel->rd_rel->relisshared,
 						  &OldestXmin, &FreezeLimit);
 
 	vacrelstats = (LVRelStats *) palloc0(sizeof(LVRelStats));

src/include/access/rewriteheap.h

@@ -6,7 +6,7 @@
  * Portions Copyright (c) 1996-2007, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994-5, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/access/rewriteheap.h,v 1.1 2007/04/08 01:26:33 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/access/rewriteheap.h,v 1.2 2007/05/17 15:28:29 alvherre Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -20,10 +20,11 @@
 typedef struct RewriteStateData *RewriteState;
 
 extern RewriteState begin_heap_rewrite(Relation NewHeap,
-									   TransactionId OldestXmin, bool use_wal);
+				   TransactionId OldestXmin, TransactionId FreezeXid,
+				   bool use_wal);
 extern void end_heap_rewrite(RewriteState state);
 extern void rewrite_heap_tuple(RewriteState state, HeapTuple oldTuple,
-							   HeapTuple newTuple);
+				   HeapTuple newTuple);
 extern void rewrite_heap_dead_tuple(RewriteState state, HeapTuple oldTuple);
 
 #endif /* REWRITE_HEAP_H */

src/include/commands/vacuum.h

@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2007, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/commands/vacuum.h,v 1.70 2007/03/13 00:33:43 tgl Exp $
+ * $PostgreSQL: pgsql/src/include/commands/vacuum.h,v 1.71 2007/05/17 15:28:29 alvherre Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -119,7 +119,7 @@ extern void vac_update_relstats(Oid relid,
 					double num_tuples,
 					bool hasindex,
 					TransactionId frozenxid);
-extern void vacuum_set_xid_limits(VacuumStmt *vacstmt, bool sharedRel,
+extern void vacuum_set_xid_limits(int freeze_min_age, bool sharedRel,
 					  TransactionId *oldestXmin,
 					  TransactionId *freezeLimit);
 extern void vac_update_datfrozenxid(void);