Make btree index structure adjustments and WAL logging changes needed to

support btree compaction, as per proposal of a few days ago.  btree index
pages no longer store parent links, instead they have a level indicator
(counting up from zero for leaf pages).  The FixBTree recovery logic is
removed, and replaced by code that detects missing parent-level insertions
during WAL replay.  Also, generate appropriate WAL entries when updating
btree metapage and when building a btree index from scratch.  I believe
btree indexes are now completely WAL-legal for the first time.
initdb forced due to index and WAL changes.

src/backend/access/nbtree/Makefile

@@ -4,7 +4,7 @@
 #    Makefile for access/nbtree
 #
 # IDENTIFICATION
-#    $Header: /cvsroot/pgsql/src/backend/access/nbtree/Makefile,v 1.11 2001/07/15 22:48:16 tgl Exp $
+#    $Header: /cvsroot/pgsql/src/backend/access/nbtree/Makefile,v 1.12 2003/02/21 00:06:21 tgl Exp $
 #
 #-------------------------------------------------------------------------
 
@@ -13,7 +13,7 @@ top_builddir = ../../../..
 include $(top_builddir)/src/Makefile.global
 
 OBJS = nbtcompare.o nbtinsert.o nbtpage.o nbtree.o nbtsearch.o \
-       nbtstrat.o nbtutils.o nbtsort.o
+       nbtstrat.o nbtutils.o nbtsort.o nbtxlog.o
 
 all: SUBSYS.o
 

src/backend/access/nbtree/nbtsearch.c

@@ -8,7 +8,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * IDENTIFICATION
- *	  $Header: /cvsroot/pgsql/src/backend/access/nbtree/nbtsearch.c,v 1.72 2002/06/20 20:29:25 momjian Exp $
+ *	  $Header: /cvsroot/pgsql/src/backend/access/nbtree/nbtsearch.c,v 1.73 2003/02/21 00:06:21 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -895,6 +895,89 @@ _bt_step(IndexScanDesc scan, Buffer *bufP, ScanDirection dir)
 	return true;
 }
 
+/*
+ * _bt_get_endpoint() -- Find the first or last page on a given tree level
+ *
+ * If the index is empty, we will return InvalidBuffer; any other failure
+ * condition causes elog().
+ *
+ * The returned buffer is pinned and read-locked.
+ */
+Buffer
+_bt_get_endpoint(Relation rel, uint32 level, bool rightmost)
+{
+	Buffer		buf;
+	Page		page;
+	BTPageOpaque opaque;
+	OffsetNumber offnum;
+	BlockNumber blkno;
+	BTItem		btitem;
+	IndexTuple	itup;
+
+	/*
+	 * If we are looking for a leaf page, okay to descend from fast root;
+	 * otherwise better descend from true root.  (There is no point in being
+	 * smarter about intermediate levels.)
+	 */
+	if (level == 0)
+		buf = _bt_getroot(rel, BT_READ);
+	else
+		buf = _bt_gettrueroot(rel);
+
+	if (!BufferIsValid(buf))
+	{
+		/* empty index... */
+		return InvalidBuffer;
+	}
+
+	page = BufferGetPage(buf);
+	opaque = (BTPageOpaque) PageGetSpecialPointer(page);
+
+	for (;;)
+	{
+		/*
+		 * If we landed on a deleted page, step right to find a live page
+		 * (there must be one).  Also, if we want the rightmost page,
+		 * step right if needed to get to it (this could happen if the
+		 * page split since we obtained a pointer to it).
+		 */
+		while (P_ISDELETED(opaque) ||
+			   (rightmost && !P_RIGHTMOST(opaque)))
+		{
+			blkno = opaque->btpo_next;
+			if (blkno == P_NONE)
+				elog(ERROR, "_bt_get_endpoint: ran off end of btree");
+			_bt_relbuf(rel, buf);
+			buf = _bt_getbuf(rel, blkno, BT_READ);
+			page = BufferGetPage(buf);
+			opaque = (BTPageOpaque) PageGetSpecialPointer(page);
+		}
+
+		/* Done? */
+		if (opaque->btpo.level == level)
+			break;
+		if (opaque->btpo.level < level)
+			elog(ERROR, "_bt_get_endpoint: btree level %u not found", level);
+
+		/* Step to leftmost or rightmost child page */
+		if (rightmost)
+			offnum = PageGetMaxOffsetNumber(page);
+		else
+			offnum = P_FIRSTDATAKEY(opaque);
+
+		btitem = (BTItem) PageGetItem(page, PageGetItemId(page, offnum));
+		itup = &(btitem->bti_itup);
+		blkno = ItemPointerGetBlockNumber(&(itup->t_tid));
+
+		_bt_relbuf(rel, buf);
+		buf = _bt_getbuf(rel, blkno, BT_READ);
+		page = BufferGetPage(buf);
+		opaque = (BTPageOpaque) PageGetSpecialPointer(page);
+	}
+
+	return buf;
+}
+
 /*
  *	_bt_endpoint() -- Find the first or last key in the index.
  *
@@ -910,8 +993,7 @@ _bt_endpoint(IndexScanDesc scan, ScanDirection dir)
 	Page		page;
 	BTPageOpaque opaque;
 	ItemPointer current;
-	OffsetNumber offnum,
-				maxoff;
+	OffsetNumber maxoff;
 	OffsetNumber start;
 	BlockNumber blkno;
 	BTItem		btitem;
@@ -929,7 +1011,7 @@ _bt_endpoint(IndexScanDesc scan, ScanDirection dir)
 	 * simplified version of _bt_search().	We don't maintain a stack
 	 * since we know we won't need it.
 	 */
-	buf = _bt_getroot(rel, BT_READ);
+	buf = _bt_get_endpoint(rel, 0, ScanDirectionIsBackward(dir));
 
 	if (!BufferIsValid(buf))
 	{
@@ -942,51 +1024,14 @@ _bt_endpoint(IndexScanDesc scan, ScanDirection dir)
 	blkno = BufferGetBlockNumber(buf);
 	page = BufferGetPage(buf);
 	opaque = (BTPageOpaque) PageGetSpecialPointer(page);
+	Assert(P_ISLEAF(opaque));
 
-	for (;;)
-	{
-		if (P_ISLEAF(opaque))
-			break;
-
-		if (ScanDirectionIsForward(dir))
-			offnum = P_FIRSTDATAKEY(opaque);
-		else
-			offnum = PageGetMaxOffsetNumber(page);
-
-		btitem = (BTItem) PageGetItem(page, PageGetItemId(page, offnum));
-		itup = &(btitem->bti_itup);
-		blkno = ItemPointerGetBlockNumber(&(itup->t_tid));
-
-		_bt_relbuf(rel, buf);
-		buf = _bt_getbuf(rel, blkno, BT_READ);
-
-		page = BufferGetPage(buf);
-		opaque = (BTPageOpaque) PageGetSpecialPointer(page);
-
-		/*
-		 * Race condition: If the child page we just stepped onto was just
-		 * split, we need to make sure we're all the way at the right edge
-		 * of the tree.  See the paper by Lehman and Yao.
-		 */
-		if (ScanDirectionIsBackward(dir) && !P_RIGHTMOST(opaque))
-		{
-			do
-			{
-				blkno = opaque->btpo_next;
-				_bt_relbuf(rel, buf);
-				buf = _bt_getbuf(rel, blkno, BT_READ);
-				page = BufferGetPage(buf);
-				opaque = (BTPageOpaque) PageGetSpecialPointer(page);
-			} while (!P_RIGHTMOST(opaque));
-		}
-	}
-
-	/* okay, we've got the {left,right}-most page in the tree */
 	maxoff = PageGetMaxOffsetNumber(page);
 
 	if (ScanDirectionIsForward(dir))
 	{
-		Assert(P_LEFTMOST(opaque));
+		/* There could be dead pages to the left, so not this: */
+		/* Assert(P_LEFTMOST(opaque)); */
 
 		start = P_FIRSTDATAKEY(opaque);
 	}

src/backend/access/nbtree/nbtsort.c

@@ -35,7 +35,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * IDENTIFICATION
- *	  $Header: /cvsroot/pgsql/src/backend/access/nbtree/nbtsort.c,v 1.70 2002/11/15 01:26:08 momjian Exp $
+ *	  $Header: /cvsroot/pgsql/src/backend/access/nbtree/nbtsort.c,v 1.71 2003/02/21 00:06:21 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -43,6 +43,7 @@
 #include "postgres.h"
 
 #include "access/nbtree.h"
+#include "miscadmin.h"
 #include "utils/tuplesort.h"
 
 
@@ -76,7 +77,7 @@ typedef struct BTPageState
 	BTItem		btps_minkey;	/* copy of minimum key (first item) on
 								 * page */
 	OffsetNumber btps_lastoff;	/* last item offset loaded */
-	int			btps_level;		/* tree level (0 = leaf) */
+	uint32		btps_level;		/* tree level (0 = leaf) */
 	Size		btps_full;		/* "full" if less than this much free
 								 * space */
 	struct BTPageState *btps_next;		/* link to parent level, if any */
@@ -90,8 +91,9 @@ typedef struct BTPageState
 	 0)
 
 
-static void _bt_blnewpage(Relation index, Buffer *buf, Page *page, int flags);
-static BTPageState *_bt_pagestate(Relation index, int flags, int level);
+static void _bt_blnewpage(Relation index, Buffer *buf, Page *page,
+						  uint32 level);
+static BTPageState *_bt_pagestate(Relation index, uint32 level);
 static void _bt_slideleft(Relation index, Buffer buf, Page page);
 static void _bt_sortaddtup(Page page, Size itemsize,
 			   BTItem btitem, OffsetNumber itup_off);
@@ -179,7 +181,7 @@ _bt_leafbuild(BTSpool *btspool, BTSpool *btspool2)
  * allocate a new, clean btree page, not linked to any siblings.
  */
 static void
-_bt_blnewpage(Relation index, Buffer *buf, Page *page, int flags)
+_bt_blnewpage(Relation index, Buffer *buf, Page *page, uint32 level)
 {
 	BTPageOpaque opaque;
 
@@ -192,23 +194,67 @@ _bt_blnewpage(Relation index, Buffer *buf, Page *page, int flags)
 	/* Initialize BT opaque state */
 	opaque = (BTPageOpaque) PageGetSpecialPointer(*page);
 	opaque->btpo_prev = opaque->btpo_next = P_NONE;
-	opaque->btpo_flags = flags;
+	opaque->btpo.level = level;
+	opaque->btpo_flags = (level > 0) ? 0 : BTP_LEAF;
 
 	/* Make the P_HIKEY line pointer appear allocated */
 	((PageHeader) *page)->pd_lower += sizeof(ItemIdData);
 }
 
+/*
+ * emit a completed btree page, and release the lock and pin on it.
+ * This is essentially _bt_wrtbuf except we also emit a WAL record.
+ */
+static void
+_bt_blwritepage(Relation index, Buffer buf)
+{
+	Page		pg = BufferGetPage(buf);
+
+	/* NO ELOG(ERROR) from here till newpage op is logged */
+	START_CRIT_SECTION();
+
+	/* XLOG stuff */
+	if (!index->rd_istemp)
+	{
+		xl_btree_newpage xlrec;
+		XLogRecPtr	recptr;
+		XLogRecData rdata[2];
+
+		xlrec.node = index->rd_node;
+		xlrec.blkno = BufferGetBlockNumber(buf);
+
+		rdata[0].buffer = InvalidBuffer;
+		rdata[0].data = (char *) &xlrec;
+		rdata[0].len = SizeOfBtreeNewpage;
+		rdata[0].next = &(rdata[1]);
+
+		rdata[1].buffer = buf;
+		rdata[1].data = (char *) pg;
+		rdata[1].len = BLCKSZ;
+		rdata[1].next = NULL;
+
+		recptr = XLogInsert(RM_BTREE_ID, XLOG_BTREE_NEWPAGE, rdata);
+
+		PageSetLSN(pg, recptr);
+		PageSetSUI(pg, ThisStartUpID);
+	}
+
+	END_CRIT_SECTION();
+
+	_bt_wrtbuf(index, buf);
+}
+
 /*
  * allocate and initialize a new BTPageState.  the returned structure
  * is suitable for immediate use by _bt_buildadd.
  */
 static BTPageState *
-_bt_pagestate(Relation index, int flags, int level)
+_bt_pagestate(Relation index, uint32 level)
 {
 	BTPageState *state = (BTPageState *) palloc0(sizeof(BTPageState));
 
 	/* create initial page */
-	_bt_blnewpage(index, &(state->btps_buf), &(state->btps_page), flags);
+	_bt_blnewpage(index, &(state->btps_buf), &(state->btps_page), level);
 
 	state->btps_minkey = (BTItem) NULL;
 	/* initialize lastoff so first item goes into P_FIRSTKEY */
@@ -365,9 +411,8 @@ _bt_buildadd(Relation index, BTPageState *state, BTItem bti)
 		ItemId		hii;
 		BTItem		obti;
 
-		/* Create new page */
-		_bt_blnewpage(index, &nbuf, &npage,
-					  (state->btps_level > 0) ? 0 : BTP_LEAF);
+		/* Create new page on same level */
+		_bt_blnewpage(index, &nbuf, &npage, state->btps_level);
 
 		/*
 		 * We copy the last item on the page into the new page, and then
@@ -396,10 +441,8 @@ _bt_buildadd(Relation index, BTPageState *state, BTItem bti)
 		 * btree level.
 		 */
 		if (state->btps_next == (BTPageState *) NULL)
-		{
-			state->btps_next =
-				_bt_pagestate(index, 0, state->btps_level + 1);
-		}
+			state->btps_next = _bt_pagestate(index, state->btps_level + 1);
+
 		Assert(state->btps_minkey != NULL);
 		ItemPointerSet(&(state->btps_minkey->bti_itup.t_tid),
 					   BufferGetBlockNumber(obuf), P_HIKEY);
@@ -414,16 +457,7 @@ _bt_buildadd(Relation index, BTPageState *state, BTItem bti)
 		state->btps_minkey = _bt_formitem(&(obti->bti_itup));
 
 		/*
-		 * Set the sibling links for both pages, and parent links too.
-		 *
-		 * It's not necessary to set the parent link at all, because it's
-		 * only used for handling concurrent root splits, but we may as
-		 * well do it as a debugging aid.  Note we set new page's link as
-		 * well as old's, because if the new page turns out to be the last
-		 * of the level, _bt_uppershutdown won't change it.  The links may
-		 * be out of date by the time the build finishes, but that's OK;
-		 * they need only point to a left-sibling of the true parent.  See
-		 * the README file for more info.
+		 * Set the sibling links for both pages.
 		 */
 		{
 			BTPageOpaque oopaque = (BTPageOpaque) PageGetSpecialPointer(opage);
@@ -431,9 +465,7 @@ _bt_buildadd(Relation index, BTPageState *state, BTItem bti)
 
 			oopaque->btpo_next = BufferGetBlockNumber(nbuf);
 			nopaque->btpo_prev = BufferGetBlockNumber(obuf);
-			nopaque->btpo_next = P_NONE;
-			oopaque->btpo_parent = nopaque->btpo_parent =
-				BufferGetBlockNumber(state->btps_next->btps_buf);
+			nopaque->btpo_next = P_NONE; /* redundant */
 		}
 
 		/*
@@ -441,7 +473,7 @@ _bt_buildadd(Relation index, BTPageState *state, BTItem bti)
 		 * can give up our lock (if we had one; most likely BuildingBtree
 		 * is set, so we aren't locking).
 		 */
-		_bt_wrtbuf(index, obuf);
+		_bt_blwritepage(index, obuf);
 
 		/*
 		 * Reset last_off to point to new page
@@ -519,7 +551,7 @@ _bt_uppershutdown(Relation index, BTPageState *state)
 		 * slid back one slot.	Then we can dump out the page.
 		 */
 		_bt_slideleft(index, s->btps_buf, s->btps_page);
-		_bt_wrtbuf(index, s->btps_buf);
+		_bt_blwritepage(index, s->btps_buf);
 	}
 }
 
@@ -603,7 +635,7 @@ _bt_load(Relation index, BTSpool *btspool, BTSpool *btspool2)
 
 			/* When we see first tuple, create first index page */
 			if (state == NULL)
-				state = _bt_pagestate(index, BTP_LEAF, 0);
+				state = _bt_pagestate(index, 0);
 
 			if (load1)
 			{
@@ -623,13 +655,13 @@ _bt_load(Relation index, BTSpool *btspool, BTSpool *btspool2)
 		_bt_freeskey(indexScanKey);
 	}
 	else
-/* merge is unnecessary */
 	{
+		/* merge is unnecessary */
 		while (bti = (BTItem) tuplesort_getindextuple(btspool->sortstate, true, &should_free), bti != (BTItem) NULL)
 		{
 			/* When we see first tuple, create first index page */
 			if (state == NULL)
-				state = _bt_pagestate(index, BTP_LEAF, 0);
+				state = _bt_pagestate(index, 0);
 
 			_bt_buildadd(index, state, bti);
 			if (should_free)

src/backend/access/transam/rmgr.c

@@ -3,7 +3,7 @@
  *
  * Resource managers definition
  *
- * $Header: /cvsroot/pgsql/src/backend/access/transam/rmgr.c,v 1.9 2001/08/25 18:52:41 tgl Exp $
+ * $Header: /cvsroot/pgsql/src/backend/access/transam/rmgr.c,v 1.10 2003/02/21 00:06:22 tgl Exp $
  */
 #include "postgres.h"
 
@@ -19,21 +19,22 @@
 #include "commands/sequence.h"
 
 
-RmgrData	RmgrTable[] = {
-	{"XLOG", xlog_redo, xlog_undo, xlog_desc},
-	{"Transaction", xact_redo, xact_undo, xact_desc},
-	{"Storage", smgr_redo, smgr_undo, smgr_desc},
-	{"CLOG", clog_redo, clog_undo, clog_desc},
-	{"Reserved 4", NULL, NULL, NULL},
-	{"Reserved 5", NULL, NULL, NULL},
-	{"Reserved 6", NULL, NULL, NULL},
-	{"Reserved 7", NULL, NULL, NULL},
-	{"Reserved 8", NULL, NULL, NULL},
-	{"Reserved 9", NULL, NULL, NULL},
-	{"Heap", heap_redo, heap_undo, heap_desc},
-	{"Btree", btree_redo, btree_undo, btree_desc},
-	{"Hash", hash_redo, hash_undo, hash_desc},
-	{"Rtree", rtree_redo, rtree_undo, rtree_desc},
-	{"Gist", gist_redo, gist_undo, gist_desc},
-	{"Sequence", seq_redo, seq_undo, seq_desc}
+RmgrData	RmgrTable[RM_MAX_ID+1] = {
+	{"XLOG", xlog_redo, xlog_undo, xlog_desc, NULL, NULL},
+	{"Transaction", xact_redo, xact_undo, xact_desc, NULL, NULL},
+	{"Storage", smgr_redo, smgr_undo, smgr_desc, NULL, NULL},
+	{"CLOG", clog_redo, clog_undo, clog_desc, NULL, NULL},
+	{"Reserved 4", NULL, NULL, NULL, NULL, NULL},
+	{"Reserved 5", NULL, NULL, NULL, NULL, NULL},
+	{"Reserved 6", NULL, NULL, NULL, NULL, NULL},
+	{"Reserved 7", NULL, NULL, NULL, NULL, NULL},
+	{"Reserved 8", NULL, NULL, NULL, NULL, NULL},
+	{"Reserved 9", NULL, NULL, NULL, NULL, NULL},
+	{"Heap", heap_redo, heap_undo, heap_desc, NULL, NULL},
+	{"Btree", btree_redo, btree_undo, btree_desc,
+	 btree_xlog_startup, btree_xlog_cleanup},
+	{"Hash", hash_redo, hash_undo, hash_desc, NULL, NULL},
+	{"Rtree", rtree_redo, rtree_undo, rtree_desc, NULL, NULL},
+	{"Gist", gist_redo, gist_undo, gist_desc, NULL, NULL},
+	{"Sequence", seq_redo, seq_undo, seq_desc, NULL, NULL}
 };

src/backend/access/transam/xlog.c

@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2002, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $Header: /cvsroot/pgsql/src/backend/access/transam/xlog.c,v 1.111 2003/01/25 03:06:04 tgl Exp $
+ * $Header: /cvsroot/pgsql/src/backend/access/transam/xlog.c,v 1.112 2003/02/21 00:06:22 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -1203,16 +1203,6 @@ XLogFlush(XLogRecPtr record)
 	XLogRecPtr	WriteRqstPtr;
 	XLogwrtRqst WriteRqst;
 
-	if (XLOG_DEBUG)
-	{
-		elog(LOG, "XLogFlush%s%s: request %X/%X; write %X/%X; flush %X/%X",
-			 (IsBootstrapProcessingMode()) ? "(bootstrap)" : "",
-			 (InRedo) ? "(redo)" : "",
-			 record.xlogid, record.xrecoff,
-			 LogwrtResult.Write.xlogid, LogwrtResult.Write.xrecoff,
-			 LogwrtResult.Flush.xlogid, LogwrtResult.Flush.xrecoff);
-	}
-
 	/* Disabled during REDO */
 	if (InRedo)
 		return;
@@ -1221,6 +1211,15 @@ XLogFlush(XLogRecPtr record)
 	if (XLByteLE(record, LogwrtResult.Flush))
 		return;
 
+	if (XLOG_DEBUG)
+	{
+		elog(LOG, "XLogFlush%s: request %X/%X; write %X/%X; flush %X/%X",
+			 (IsBootstrapProcessingMode()) ? "(bootstrap)" : "",
+			 record.xlogid, record.xrecoff,
+			 LogwrtResult.Write.xlogid, LogwrtResult.Write.xrecoff,
+			 LogwrtResult.Flush.xlogid, LogwrtResult.Flush.xrecoff);
+	}
+
 	START_CRIT_SECTION();
 
 	/*
@@ -2515,6 +2514,12 @@ StartupXLOG(void)
 		elog(LOG, "database system was interrupted at %s",
 			 str_time(ControlFile->time));
 
+	/* This is just to allow attaching to startup process with a debugger */
+#ifdef XLOG_REPLAY_DELAY
+	if (XLOG_DEBUG && ControlFile->state != DB_SHUTDOWNED)
+		sleep(60);
+#endif
+
 	/*
 	 * Get the last valid checkpoint record.  If the latest one according
 	 * to pg_control is broken, try the next-to-last one.
@@ -2578,14 +2583,23 @@ StartupXLOG(void)
 	/* REDO */
 	if (InRecovery)
 	{
+		int		rmid;
+
 		elog(LOG, "database system was not properly shut down; "
 			 "automatic recovery in progress");
 		ControlFile->state = DB_IN_RECOVERY;
 		ControlFile->time = time(NULL);
 		UpdateControlFile();
 
+		/* Start up the recovery environment */
 		XLogInitRelationCache();
 
+		for (rmid = 0; rmid <= RM_MAX_ID; rmid++)
+		{
+			if (RmgrTable[rmid].rm_startup != NULL)
+				RmgrTable[rmid].rm_startup();
+		}
+
 		/* Is REDO required ? */
 		if (XLByteLT(checkPoint.redo, RecPtr))
 			record = ReadRecord(&(checkPoint.redo), PANIC, buffer);
@@ -2737,7 +2751,25 @@ StartupXLOG(void)
 
 	if (InRecovery)
 	{
+		int		rmid;
+
+		/*
+		 * Allow resource managers to do any required cleanup.
+		 */
+		for (rmid = 0; rmid <= RM_MAX_ID; rmid++)
+		{
+			if (RmgrTable[rmid].rm_cleanup != NULL)
+				RmgrTable[rmid].rm_cleanup();
+		}
+
+		/* suppress in-transaction check in CreateCheckPoint */
+		MyLastRecPtr.xrecoff = 0;
+		MyXactMadeXLogEntry = false;
+		MyXactMadeTempRelUpdate = false;
+
 		/*
+		 * Perform a new checkpoint to update our recovery activity to disk.
+		 *
 		 * In case we had to use the secondary checkpoint, make sure that
 		 * it will still be shown as the secondary checkpoint after this
 		 * CreateCheckPoint operation; we don't want the broken primary
@@ -2745,6 +2777,10 @@ StartupXLOG(void)
 		 */
 		ControlFile->checkPoint = checkPointLoc;
 		CreateCheckPoint(true, true);
+
+		/*
+		 * Close down recovery environment
+		 */
 		XLogCloseRelationCache();
 	}
 

src/include/access/xlog.h

@@ -6,7 +6,7 @@
  * Portions Copyright (c) 1996-2002, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $Id: xlog.h,v 1.40 2002/11/15 02:44:57 momjian Exp $
+ * $Id: xlog.h,v 1.41 2003/02/21 00:06:22 tgl Exp $
  */
 #ifndef XLOG_H
 #define XLOG_H
@@ -145,10 +145,12 @@ typedef XLogPageHeaderData *XLogPageHeader;
  */
 typedef struct RmgrData
 {
-	char	   *rm_name;
+	const char *rm_name;
 	void		(*rm_redo) (XLogRecPtr lsn, XLogRecord *rptr);
 	void		(*rm_undo) (XLogRecPtr lsn, XLogRecord *rptr);
 	void		(*rm_desc) (char *buf, uint8 xl_info, char *rec);
+	void		(*rm_startup) (void);
+	void		(*rm_cleanup) (void);
 } RmgrData;
 
 extern RmgrData RmgrTable[];

src/include/catalog/catversion.h

@@ -37,7 +37,7 @@
  * Portions Copyright (c) 1996-2002, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $Id: catversion.h,v 1.177 2003/02/16 02:30:39 tgl Exp $
+ * $Id: catversion.h,v 1.178 2003/02/21 00:06:22 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -53,6 +53,6 @@
  */
 
 /*							yyyymmddN */
-#define CATALOG_VERSION_NO	200302151
+#define CATALOG_VERSION_NO	200302171
 
 #endif