Major overhaul of btree index code. Eliminate special BTP_CHAIN logic for

duplicate keys by letting search go to the left rather than right when an
equal key is seen at an upper tree level.  Fix poor choice of page split
point (leading to insertion failures) that was forced by chaining logic.
Don't store leftmost key in non-leaf pages, since it's not necessary.
Don't create root page until something is first stored in the index, so an
unused index is now 8K not 16K.  (Doesn't seem to be as easy to get rid of
the metadata page, unfortunately.)  Massive cleanup of unreadable code,
fix poor, obsolete, and just plain wrong documentation and comments.
See src/backend/access/nbtree/README for the gory details.

src/backend/access/nbtree/nbtree.c

@@ -12,7 +12,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * IDENTIFICATION
- *	  $Header: /cvsroot/pgsql/src/backend/access/nbtree/nbtree.c,v 1.61 2000/07/14 22:17:33 tgl Exp $
+ *	  $Header: /cvsroot/pgsql/src/backend/access/nbtree/nbtree.c,v 1.62 2000/07/21 06:42:32 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -26,6 +26,7 @@
 #include "executor/executor.h"
 #include "miscadmin.h"
 
+
 bool		BuildingBtree = false;		/* see comment in btbuild() */
 bool		FastBuild = true;	/* use sort/build instead of insertion
 								 * build */
@@ -206,8 +207,8 @@ btbuild(PG_FUNCTION_ARGS)
 		 * btree pages - NULLs greater NOT_NULLs and NULL = NULL is TRUE.
 		 * Sure, it's just rule for placing/finding items and no more -
 		 * keytest'll return FALSE for a = 5 for items having 'a' isNULL.
-		 * Look at _bt_skeycmp, _bt_compare and _bt_itemcmp for how it
-		 * works.				 - vadim 03/23/97
+		 * Look at _bt_compare for how it works.
+		 *				 - vadim 03/23/97
 		 *
 		 * if (itup->t_info & INDEX_NULL_MASK) { pfree(itup); continue; }
 		 */
@@ -321,14 +322,6 @@ btinsert(PG_FUNCTION_ARGS)
 	/* generate an index tuple */
 	itup = index_formtuple(RelationGetDescr(rel), datum, nulls);
 	itup->t_tid = *ht_ctid;
-
-	/*
-	 * See comments in btbuild.
-	 *
-	 * if (itup->t_info & INDEX_NULL_MASK)
-	 *		PG_RETURN_POINTER((InsertIndexResult) NULL);
-	 */
-
 	btitem = _bt_formitem(itup);
 
 	res = _bt_doinsert(rel, btitem, rel->rd_uniqueindex, heapRel);
@@ -357,10 +350,10 @@ btgettuple(PG_FUNCTION_ARGS)
 
 	if (ItemPointerIsValid(&(scan->currentItemData)))
 	{
-
 		/*
 		 * Restore scan position using heap TID returned by previous call
-		 * to btgettuple(). _bt_restscan() locks buffer.
+		 * to btgettuple(). _bt_restscan() re-grabs the read lock on
+		 * the buffer, too.
 		 */
 		_bt_restscan(scan);
 		res = _bt_next(scan, dir);
@@ -369,8 +362,9 @@ btgettuple(PG_FUNCTION_ARGS)
 		res = _bt_first(scan, dir);
 
 	/*
-	 * Save heap TID to use it in _bt_restscan. Unlock buffer before
-	 * leaving index !
+	 * Save heap TID to use it in _bt_restscan.  Then release the read
+	 * lock on the buffer so that we aren't blocking other backends.
+	 * NOTE: we do keep the pin on the buffer!
 	 */
 	if (res)
 	{
@@ -419,7 +413,18 @@ btrescan(PG_FUNCTION_ARGS)
 
 	so = (BTScanOpaque) scan->opaque;
 
-	/* we don't hold a read lock on the current page in the scan */
+	if (so == NULL)				/* if called from btbeginscan */
+	{
+		so = (BTScanOpaque) palloc(sizeof(BTScanOpaqueData));
+		so->btso_curbuf = so->btso_mrkbuf = InvalidBuffer;
+		so->keyData = (ScanKey) NULL;
+		if (scan->numberOfKeys > 0)
+			so->keyData = (ScanKey) palloc(scan->numberOfKeys * sizeof(ScanKeyData));
+		scan->opaque = so;
+		scan->flags = 0x0;
+	}
+
+	/* we aren't holding any read locks, but gotta drop the pins */
 	if (ItemPointerIsValid(iptr = &(scan->currentItemData)))
 	{
 		ReleaseBuffer(so->btso_curbuf);
@@ -427,7 +432,6 @@ btrescan(PG_FUNCTION_ARGS)
 		ItemPointerSetInvalid(iptr);
 	}
 
-	/* and we don't hold a read lock on the last marked item in the scan */
 	if (ItemPointerIsValid(iptr = &(scan->currentMarkData)))
 	{
 		ReleaseBuffer(so->btso_mrkbuf);
@@ -435,17 +439,6 @@ btrescan(PG_FUNCTION_ARGS)
 		ItemPointerSetInvalid(iptr);
 	}
 
-	if (so == NULL)				/* if called from btbeginscan */
-	{
-		so = (BTScanOpaque) palloc(sizeof(BTScanOpaqueData));
-		so->btso_curbuf = so->btso_mrkbuf = InvalidBuffer;
-		so->keyData = (ScanKey) NULL;
-		if (scan->numberOfKeys > 0)
-			so->keyData = (ScanKey) palloc(scan->numberOfKeys * sizeof(ScanKeyData));
-		scan->opaque = so;
-		scan->flags = 0x0;
-	}
-
 	/*
 	 * Reset the scan keys. Note that keys ordering stuff moved to
 	 * _bt_first.	   - vadim 05/05/97
@@ -472,7 +465,7 @@ btmovescan(IndexScanDesc scan, Datum v)
 
 	so = (BTScanOpaque) scan->opaque;
 
-	/* we don't hold a read lock on the current page in the scan */
+	/* we aren't holding any read locks, but gotta drop the pin */
 	if (ItemPointerIsValid(iptr = &(scan->currentItemData)))
 	{
 		ReleaseBuffer(so->btso_curbuf);
@@ -480,7 +473,6 @@ btmovescan(IndexScanDesc scan, Datum v)
 		ItemPointerSetInvalid(iptr);
 	}
 
-/*	  scan->keyData[0].sk_argument = v; */
 	so->keyData[0].sk_argument = v;
 }
 
@@ -496,7 +488,7 @@ btendscan(PG_FUNCTION_ARGS)
 
 	so = (BTScanOpaque) scan->opaque;
 
-	/* we don't hold any read locks */
+	/* we aren't holding any read locks, but gotta drop the pins */
 	if (ItemPointerIsValid(iptr = &(scan->currentItemData)))
 	{
 		if (BufferIsValid(so->btso_curbuf))
@@ -534,7 +526,7 @@ btmarkpos(PG_FUNCTION_ARGS)
 
 	so = (BTScanOpaque) scan->opaque;
 
-	/* we don't hold any read locks */
+	/* we aren't holding any read locks, but gotta drop the pin */
 	if (ItemPointerIsValid(iptr = &(scan->currentMarkData)))
 	{
 		ReleaseBuffer(so->btso_mrkbuf);
@@ -542,7 +534,7 @@ btmarkpos(PG_FUNCTION_ARGS)
 		ItemPointerSetInvalid(iptr);
 	}
 
-	/* bump pin on current buffer */
+	/* bump pin on current buffer for assignment to mark buffer */
 	if (ItemPointerIsValid(&(scan->currentItemData)))
 	{
 		so->btso_mrkbuf = ReadBuffer(scan->relation,
@@ -566,7 +558,7 @@ btrestrpos(PG_FUNCTION_ARGS)
 
 	so = (BTScanOpaque) scan->opaque;
 
-	/* we don't hold any read locks */
+	/* we aren't holding any read locks, but gotta drop the pin */
 	if (ItemPointerIsValid(iptr = &(scan->currentItemData)))
 	{
 		ReleaseBuffer(so->btso_curbuf);
@@ -579,7 +571,6 @@ btrestrpos(PG_FUNCTION_ARGS)
 	{
 		so->btso_curbuf = ReadBuffer(scan->relation,
 								  BufferGetBlockNumber(so->btso_mrkbuf));
-
 		scan->currentItemData = scan->currentMarkData;
 		so->curHeapIptr = so->mrkHeapIptr;
 	}
@@ -603,6 +594,9 @@ btdelete(PG_FUNCTION_ARGS)
 	PG_RETURN_VOID();
 }
 
+/*
+ * Restore scan position when btgettuple is called to continue a scan.
+ */
 static void
 _bt_restscan(IndexScanDesc scan)
 {
@@ -618,7 +612,12 @@ _bt_restscan(IndexScanDesc scan)
 	BTItem		item;
 	BlockNumber blkno;
 
-	LockBuffer(buf, BT_READ);	/* lock buffer first! */
+	/*
+	 * Get back the read lock we were holding on the buffer.
+	 * (We still have a reference-count pin on it, though.)
+	 */
+	LockBuffer(buf, BT_READ);
+
 	page = BufferGetPage(buf);
 	maxoff = PageGetMaxOffsetNumber(page);
 	opaque = (BTPageOpaque) PageGetSpecialPointer(page);
@@ -631,43 +630,40 @@ _bt_restscan(IndexScanDesc scan)
 	 */
 	if (!ItemPointerIsValid(&target))
 	{
-		ItemPointerSetOffsetNumber(&(scan->currentItemData),
-		   OffsetNumberPrev(P_RIGHTMOST(opaque) ? P_HIKEY : P_FIRSTKEY));
+		ItemPointerSetOffsetNumber(current,
+								   OffsetNumberPrev(P_FIRSTDATAKEY(opaque)));
 		return;
 	}
 
-	if (maxoff >= offnum)
+	/*
+	 * The item we were on may have moved right due to insertions.
+	 * Find it again.
+	 */
+	for (;;)
 	{
-
-		/*
-		 * if the item is where we left it or has just moved right on this
-		 * page, we're done
-		 */
+		/* Check for item on this page */
 		for (;
 			 offnum <= maxoff;
 			 offnum = OffsetNumberNext(offnum))
 		{
 			item = (BTItem) PageGetItem(page, PageGetItemId(page, offnum));
-			if (item->bti_itup.t_tid.ip_blkid.bi_hi == \
-				target.ip_blkid.bi_hi && \
-				item->bti_itup.t_tid.ip_blkid.bi_lo == \
-				target.ip_blkid.bi_lo && \
+			if (item->bti_itup.t_tid.ip_blkid.bi_hi ==
+				target.ip_blkid.bi_hi &&
+				item->bti_itup.t_tid.ip_blkid.bi_lo ==
+				target.ip_blkid.bi_lo &&
 				item->bti_itup.t_tid.ip_posid == target.ip_posid)
 			{
 				current->ip_posid = offnum;
 				return;
 			}
 		}
-	}
 
-	/*
-	 * By here, the item we're looking for moved right at least one page
-	 */
-	for (;;)
-	{
+		/*
+		 * By here, the item we're looking for moved right at least one page
+		 */
 		if (P_RIGHTMOST(opaque))
-			elog(FATAL, "_bt_restscan: my bits moved right off the end of the world!\
-\n\tRecreate index %s.", RelationGetRelationName(rel));
+			elog(FATAL, "_bt_restscan: my bits moved right off the end of the world!"
+				 "\n\tRecreate index %s.", RelationGetRelationName(rel));
 
 		blkno = opaque->btpo_next;
 		_bt_relbuf(rel, buf, BT_READ);
@@ -675,23 +671,8 @@ _bt_restscan(IndexScanDesc scan)
 		page = BufferGetPage(buf);
 		maxoff = PageGetMaxOffsetNumber(page);
 		opaque = (BTPageOpaque) PageGetSpecialPointer(page);
-
-		/* see if it's on this page */
-		for (offnum = P_RIGHTMOST(opaque) ? P_HIKEY : P_FIRSTKEY;
-			 offnum <= maxoff;
-			 offnum = OffsetNumberNext(offnum))
-		{
-			item = (BTItem) PageGetItem(page, PageGetItemId(page, offnum));
-			if (item->bti_itup.t_tid.ip_blkid.bi_hi == \
-				target.ip_blkid.bi_hi && \
-				item->bti_itup.t_tid.ip_blkid.bi_lo == \
-				target.ip_blkid.bi_lo && \
-				item->bti_itup.t_tid.ip_posid == target.ip_posid)
-			{
-				ItemPointerSet(current, blkno, offnum);
-				so->btso_curbuf = buf;
-				return;
-			}
-		}
+		offnum = P_FIRSTDATAKEY(opaque);
+		ItemPointerSet(current, blkno, offnum);
+		so->btso_curbuf = buf;
 	}
 }

src/backend/access/nbtree/nbtscan.c

@@ -8,22 +8,25 @@
  *
  *
  * IDENTIFICATION
- *	  $Header: /cvsroot/pgsql/src/backend/access/nbtree/Attic/nbtscan.c,v 1.31 2000/04/12 17:14:49 momjian Exp $
+ *	  $Header: /cvsroot/pgsql/src/backend/access/nbtree/Attic/nbtscan.c,v 1.32 2000/07/21 06:42:32 tgl Exp $
  *
  *
  * NOTES
  *	 Because we can be doing an index scan on a relation while we update
  *	 it, we need to avoid missing data that moves around in the index.
- *	 The routines and global variables in this file guarantee that all
- *	 scans in the local address space stay correctly positioned.  This
- *	 is all we need to worry about, since write locking guarantees that
- *	 no one else will be on the same page at the same time as we are.
+ *	 Insertions and page splits are no problem because _bt_restscan()
+ *	 can figure out where the current item moved to, but if a deletion
+ *	 happens at or before the current scan position, we'd better do
+ *	 something to stay in sync.
+ *
+ *	 The routines in this file handle the problem for deletions issued
+ *	 by the current backend.  Currently, that's all we need, since
+ *	 deletions are only done by VACUUM and it gets an exclusive lock.
  *
  *	 The scheme is to manage a list of active scans in the current backend.
- *	 Whenever we add or remove records from an index, or whenever we
- *	 split a leaf page, we check the list of active scans to see if any
- *	 has been affected.  A scan is affected only if it is on the same
- *	 relation, and the same page, as the update.
+ *	 Whenever we remove a record from an index, we check the list of active
+ *	 scans to see if any has been affected.  A scan is affected only if it
+ *	 is on the same relation, and the same page, as the update.
  *
  *-------------------------------------------------------------------------
  */
@@ -111,7 +114,7 @@ _bt_dropscan(IndexScanDesc scan)
 
 /*
  *	_bt_adjscans() -- adjust all scans in the scan list to compensate
- *					  for a given deletion or insertion
+ *					  for a given deletion
  */
 void
 _bt_adjscans(Relation rel, ItemPointer tid)
@@ -153,7 +156,7 @@ _bt_scandel(IndexScanDesc scan, BlockNumber blkno, OffsetNumber offno)
 	{
 		page = BufferGetPage(buf);
 		opaque = (BTPageOpaque) PageGetSpecialPointer(page);
-		start = P_RIGHTMOST(opaque) ? P_HIKEY : P_FIRSTKEY;
+		start = P_FIRSTDATAKEY(opaque);
 		if (ItemPointerGetOffsetNumber(current) == start)
 			ItemPointerSetInvalid(&(so->curHeapIptr));
 		else
@@ -165,7 +168,6 @@ _bt_scandel(IndexScanDesc scan, BlockNumber blkno, OffsetNumber offno)
 			 */
 			LockBuffer(buf, BT_READ);
 			_bt_step(scan, &buf, BackwardScanDirection);
-			so->btso_curbuf = buf;
 			if (ItemPointerIsValid(current))
 			{
 				Page		pg = BufferGetPage(buf);
@@ -183,10 +185,9 @@ _bt_scandel(IndexScanDesc scan, BlockNumber blkno, OffsetNumber offno)
 		&& ItemPointerGetBlockNumber(current) == blkno
 		&& ItemPointerGetOffsetNumber(current) >= offno)
 	{
-
 		page = BufferGetPage(so->btso_mrkbuf);
 		opaque = (BTPageOpaque) PageGetSpecialPointer(page);
-		start = P_RIGHTMOST(opaque) ? P_HIKEY : P_FIRSTKEY;
+		start = P_FIRSTDATAKEY(opaque);
 
 		if (ItemPointerGetOffsetNumber(current) == start)
 			ItemPointerSetInvalid(&(so->mrkHeapIptr));

src/backend/access/nbtree/nbtutils.c

@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $Header: /cvsroot/pgsql/src/backend/access/nbtree/nbtutils.c,v 1.37 2000/05/30 04:24:33 tgl Exp $
+ *	  $Header: /cvsroot/pgsql/src/backend/access/nbtree/nbtutils.c,v 1.38 2000/07/21 06:42:33 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -20,16 +20,13 @@
 #include "access/nbtree.h"
 #include "executor/execdebug.h"
 
-extern int	NIndexTupleProcessed;
-
 
 /*
  * _bt_mkscankey
  *		Build a scan key that contains comparison data from itup
  *		as well as comparator routines appropriate to the key datatypes.
  *
- *		The result is intended for use with _bt_skeycmp() or _bt_compare(),
- *		although it could be used with _bt_itemcmp() or _bt_tuplecompare().
+ *		The result is intended for use with _bt_compare().
  */
 ScanKey
 _bt_mkscankey(Relation rel, IndexTuple itup)
@@ -68,8 +65,9 @@ _bt_mkscankey(Relation rel, IndexTuple itup)
  *		Build a scan key that contains comparator routines appropriate to
  *		the key datatypes, but no comparison data.
  *
- *		The result can be used with _bt_itemcmp() or _bt_tuplecompare(),
- *		but not with _bt_skeycmp() or _bt_compare().
+ *		The result cannot be used with _bt_compare().  Currently this
+ *		routine is only called by utils/sort/tuplesort.c, which has its
+ *		own comparison routine.
  */
 ScanKey
 _bt_mkscankey_nodata(Relation rel)
@@ -114,7 +112,6 @@ _bt_freestack(BTStack stack)
 	{
 		ostack = stack;
 		stack = stack->bts_parent;
-		pfree(ostack->bts_btitem);
 		pfree(ostack);
 	}
 }
@@ -331,55 +328,16 @@ _bt_formitem(IndexTuple itup)
 	Size		tuplen;
 	extern Oid	newoid();
 
-	/*
-	 * see comments in btbuild
-	 *
-	 * if (itup->t_info & INDEX_NULL_MASK) elog(ERROR, "btree indices cannot
-	 * include null keys");
-	 */
-
 	/* make a copy of the index tuple with room for the sequence number */
 	tuplen = IndexTupleSize(itup);
 	nbytes_btitem = tuplen + (sizeof(BTItemData) - sizeof(IndexTupleData));
 
 	btitem = (BTItem) palloc(nbytes_btitem);
-	memmove((char *) &(btitem->bti_itup), (char *) itup, tuplen);
+	memcpy((char *) &(btitem->bti_itup), (char *) itup, tuplen);
 
 	return btitem;
 }
 
-#ifdef NOT_USED
-bool
-_bt_checkqual(IndexScanDesc scan, IndexTuple itup)
-{
-	BTScanOpaque so;
-
-	so = (BTScanOpaque) scan->opaque;
-	if (so->numberOfKeys > 0)
-		return (index_keytest(itup, RelationGetDescr(scan->relation),
-							  so->numberOfKeys, so->keyData));
-	else
-		return true;
-}
-
-#endif
-
-#ifdef NOT_USED
-bool
-_bt_checkforkeys(IndexScanDesc scan, IndexTuple itup, Size keysz)
-{
-	BTScanOpaque so;
-
-	so = (BTScanOpaque) scan->opaque;
-	if (keysz > 0 && so->numberOfKeys >= keysz)
-		return (index_keytest(itup, RelationGetDescr(scan->relation),
-							  keysz, so->keyData));
-	else
-		return true;
-}
-
-#endif
-
 bool
 _bt_checkkeys(IndexScanDesc scan, IndexTuple tuple, Size *keysok)
 {

src/backend/storage/page/bufpage.c

@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $Header: /cvsroot/pgsql/src/backend/storage/page/bufpage.c,v 1.30 2000/07/03 02:54:16 vadim Exp $
+ *	  $Header: /cvsroot/pgsql/src/backend/storage/page/bufpage.c,v 1.31 2000/07/21 06:42:33 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -19,10 +19,10 @@
 
 #include "storage/bufpage.h"
 
+
 static void PageIndexTupleDeleteAdjustLinePointers(PageHeader phdr,
 									   char *location, Size size);
 
-static bool PageManagerShuffle = true;	/* default is shuffle mode */
 
 /* ----------------------------------------------------------------
  *						Page support functions
@@ -53,21 +53,17 @@ PageInit(Page page, Size pageSize, Size specialSize)
 /* ----------------
  *		PageAddItem
  *
- *		add an item to a page.
- *
- *   !!! ELOG(ERROR) IS DISALLOWED HERE !!!
+ *		Add an item to a page.  Return value is offset at which it was
+ *		inserted, or InvalidOffsetNumber if there's not room to insert.
  *
- *	 Notes on interface:
- *		If offsetNumber is valid, shuffle ItemId's down to make room
- *		to use it, if PageManagerShuffle is true.  If PageManagerShuffle is
- *		false, then overwrite the specified ItemId.  (PageManagerShuffle is
- *		true by default, and is modified by calling PageManagerModeSet.)
+ *		If offsetNumber is valid and <= current max offset in the page,
+ *		insert item into the array at that position by shuffling ItemId's
+ *		down to make room.
  *		If offsetNumber is not valid, then assign one by finding the first
  *		one that is both unused and deallocated.
  *
- *	 NOTE: If offsetNumber is valid, and PageManagerShuffle is true, it
- *		is assumed that there is room on the page to shuffle the ItemId's
- *		down by one.
+ *   !!! ELOG(ERROR) IS DISALLOWED HERE !!!
+ *
  * ----------------
  */
 OffsetNumber
@@ -82,11 +78,8 @@ PageAddItem(Page page,
 	Offset		lower;
 	Offset		upper;
 	ItemId		itemId;
-	ItemId		fromitemId,
-				toitemId;
 	OffsetNumber limit;
-
-	bool		shuffled = false;
+	bool		needshuffle = false;
 
 	/*
 	 * Find first unallocated offsetNumber
@@ -96,31 +89,12 @@ PageAddItem(Page page,
 	/* was offsetNumber passed in? */
 	if (OffsetNumberIsValid(offsetNumber))
 	{
-		if (PageManagerShuffle == true)
-		{
-			/* shuffle ItemId's (Do the PageManager Shuffle...) */
-			for (i = (limit - 1); i >= offsetNumber; i--)
-			{
-				fromitemId = &((PageHeader) page)->pd_linp[i - 1];
-				toitemId = &((PageHeader) page)->pd_linp[i];
-				*toitemId = *fromitemId;
-			}
-			shuffled = true;	/* need to increase "lower" */
-		}
-		else
-		{						/* overwrite mode */
-			itemId = &((PageHeader) page)->pd_linp[offsetNumber - 1];
-			if (((*itemId).lp_flags & LP_USED) ||
-				((*itemId).lp_len != 0))
-			{
-				elog(NOTICE, "PageAddItem: tried overwrite of used ItemId");
-				return InvalidOffsetNumber;
-			}
-		}
+		needshuffle = true;		/* need to increase "lower" */
+		/* don't actually do the shuffle till we've checked free space! */
 	}
 	else
-	{							/* offsetNumber was not passed in, so find
-								 * one */
+	{
+		/* offsetNumber was not passed in, so find one */
 		/* look for "recyclable" (unused & deallocated) ItemId */
 		for (offsetNumber = 1; offsetNumber < limit; offsetNumber++)
 		{
@@ -130,9 +104,13 @@ PageAddItem(Page page,
 				break;
 		}
 	}
+
+	/*
+	 * Compute new lower and upper pointers for page, see if it'll fit
+	 */
 	if (offsetNumber > limit)
 		lower = (Offset) (((char *) (&((PageHeader) page)->pd_linp[offsetNumber])) - ((char *) page));
-	else if (offsetNumber == limit || shuffled == true)
+	else if (offsetNumber == limit || needshuffle)
 		lower = ((PageHeader) page)->pd_lower + sizeof(ItemIdData);
 	else
 		lower = ((PageHeader) page)->pd_lower;
@@ -144,6 +122,23 @@ PageAddItem(Page page,
 	if (lower > upper)
 		return InvalidOffsetNumber;
 
+	/*
+	 * OK to insert the item.  First, shuffle the existing pointers if needed.
+	 */
+	if (needshuffle)
+	{
+		/* shuffle ItemId's (Do the PageManager Shuffle...) */
+		for (i = (limit - 1); i >= offsetNumber; i--)
+		{
+			ItemId		fromitemId,
+						toitemId;
+
+			fromitemId = &((PageHeader) page)->pd_linp[i - 1];
+			toitemId = &((PageHeader) page)->pd_linp[i];
+			*toitemId = *fromitemId;
+		}
+	}
+
 	itemId = &((PageHeader) page)->pd_linp[offsetNumber - 1];
 	(*itemId).lp_off = upper;
 	(*itemId).lp_len = size;
@@ -168,9 +163,7 @@ PageGetTempPage(Page page, Size specialSize)
 	PageHeader	thdr;
 
 	pageSize = PageGetPageSize(page);
-
-	if ((temp = (Page) palloc(pageSize)) == (Page) NULL)
-		elog(FATAL, "Cannot allocate %d bytes for temp page.", pageSize);
+	temp = (Page) palloc(pageSize);
 	thdr = (PageHeader) temp;
 
 	/* copy old page in */
@@ -327,23 +320,6 @@ PageGetFreeSpace(Page page)
 	return space;
 }
 
-/*
- * PageManagerModeSet
- *
- *	 Sets mode to either: ShufflePageManagerMode (the default) or
- *	 OverwritePageManagerMode.	For use by access methods code
- *	 for determining semantics of PageAddItem when the offsetNumber
- *	 argument is passed in.
- */
-void
-PageManagerModeSet(PageManagerMode mode)
-{
-	if (mode == ShufflePageManagerMode)
-		PageManagerShuffle = true;
-	else if (mode == OverwritePageManagerMode)
-		PageManagerShuffle = false;
-}
-
 /*
  *----------------------------------------------------------------
  * PageIndexTupleDelete

src/include/access/nbtree.h

@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2000, PostgreSQL, Inc
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $Id: nbtree.h,v 1.38 2000/06/15 03:32:31 momjian Exp $
+ * $Id: nbtree.h,v 1.39 2000/07/21 06:42:35 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -24,14 +24,9 @@
  *	info.  In addition, we need to know what sort of page this is
  *	(leaf or internal), and whether the page is available for reuse.
  *
- *	Lehman and Yao's algorithm requires a ``high key'' on every page.
- *	The high key on a page is guaranteed to be greater than or equal
- *	to any key that appears on this page.  Our insertion algorithm
- *	guarantees that we can use the initial least key on our right
- *	sibling as the high key.  We allocate space for the line pointer
- *	to the high key in the opaque data at the end of the page.
- *
- *	Rightmost pages in the tree have no high key.
+ *	We also store a back-link to the parent page, but this cannot be trusted
+ *	very far since it does not get updated when the parent is split.
+ *	See backend/access/nbtree/README for details.
  */
 
 typedef struct BTPageOpaqueData
@@ -41,11 +36,11 @@ typedef struct BTPageOpaqueData
 	BlockNumber btpo_parent;
 	uint16		btpo_flags;
 
-#define BTP_LEAF		(1 << 0)
-#define BTP_ROOT		(1 << 1)
-#define BTP_FREE		(1 << 2)
-#define BTP_META		(1 << 3)
-#define BTP_CHAIN		(1 << 4)
+/* Bits defined in btpo_flags */
+#define BTP_LEAF		(1 << 0)	/* It's a leaf page */
+#define BTP_ROOT		(1 << 1)	/* It's the root page (has no parent) */
+#define BTP_FREE		(1 << 2)	/* not currently used... */
+#define BTP_META		(1 << 3)	/* Set in the meta-page only */
 
 } BTPageOpaqueData;
 
@@ -84,21 +79,24 @@ typedef struct BTScanOpaqueData
 typedef BTScanOpaqueData *BTScanOpaque;
 
 /*
- *	BTItems are what we store in the btree.  Each item has an index
- *	tuple, including key and pointer values.  In addition, we must
- *	guarantee that all tuples in the index are unique, in order to
- *	satisfy some assumptions in Lehman and Yao.  The way that we do
- *	this is by generating a new OID for every insertion that we do in
- *	the tree.  This adds eight bytes to the size of btree index
- *	tuples.  Note that we do not use the OID as part of a composite
- *	key; the OID only serves as a unique identifier for a given index
- *	tuple (logical position within a page).
+ *	BTItems are what we store in the btree.  Each item is an index tuple,
+ *	including key and pointer values.  (In some cases either the key or the
+ *	pointer may go unused, see backend/access/nbtree/README for details.)
+ *
+ *	Old comments:
+ *	In addition, we must guarantee that all tuples in the index are unique,
+ *	in order to satisfy some assumptions in Lehman and Yao.  The way that we
+ *	do this is by generating a new OID for every insertion that we do in the
+ *	tree.  This adds eight bytes to the size of btree index tuples.  Note
+ *	that we do not use the OID as part of a composite key; the OID only
+ *	serves as a unique identifier for a given index tuple (logical position
+ *	within a page).
  *
  *	New comments:
  *	actually, we must guarantee that all tuples in A LEVEL
  *	are unique, not in ALL INDEX. So, we can use bti_itup->t_tid
  *	as unique identifier for a given index tuple (logical position
- *	within a level).	- vadim 04/09/97
+ *	within a level). - vadim 04/09/97
  */
 
 typedef struct BTItemData
@@ -108,12 +106,13 @@ typedef struct BTItemData
 
 typedef BTItemData *BTItem;
 
-#define BTItemSame(i1, i2)	  ( i1->bti_itup.t_tid.ip_blkid.bi_hi == \
-								i2->bti_itup.t_tid.ip_blkid.bi_hi && \
-								i1->bti_itup.t_tid.ip_blkid.bi_lo == \
-								i2->bti_itup.t_tid.ip_blkid.bi_lo && \
-								i1->bti_itup.t_tid.ip_posid == \
-								i2->bti_itup.t_tid.ip_posid )
+/* Test whether items are the "same" per the above notes */
+#define BTItemSame(i1, i2)	  ( (i1)->bti_itup.t_tid.ip_blkid.bi_hi == \
+								(i2)->bti_itup.t_tid.ip_blkid.bi_hi && \
+								(i1)->bti_itup.t_tid.ip_blkid.bi_lo == \
+								(i2)->bti_itup.t_tid.ip_blkid.bi_lo && \
+								(i1)->bti_itup.t_tid.ip_posid == \
+								(i2)->bti_itup.t_tid.ip_posid )
 
 /*
  *	BTStackData -- As we descend a tree, we push the (key, pointer)
@@ -129,24 +128,12 @@ typedef struct BTStackData
 {
 	BlockNumber bts_blkno;
 	OffsetNumber bts_offset;
-	BTItem		bts_btitem;
+	BTItemData	bts_btitem;
 	struct BTStackData *bts_parent;
 } BTStackData;
 
 typedef BTStackData *BTStack;
 
-typedef struct BTPageState
-{
-	Buffer		btps_buf;
-	Page		btps_page;
-	BTItem		btps_lastbti;
-	OffsetNumber btps_lastoff;
-	OffsetNumber btps_firstoff;
-	int			btps_level;
-	bool		btps_doupper;
-	struct BTPageState *btps_next;
-} BTPageState;
-
 /*
  *	We need to be able to tell the difference between read and write
  *	requests for pages, in order to do locking correctly.
@@ -155,31 +142,49 @@ typedef struct BTPageState
 #define BT_READ			BUFFER_LOCK_SHARE
 #define BT_WRITE		BUFFER_LOCK_EXCLUSIVE
 
-/*
- *	Similarly, the difference between insertion and non-insertion binary
- *	searches on a given page makes a difference when we're descending the
- *	tree.
- */
-
-#define BT_INSERTION	0
-#define BT_DESCENT		1
-
 /*
  *	In general, the btree code tries to localize its knowledge about
  *	page layout to a couple of routines.  However, we need a special
  *	value to indicate "no page number" in those places where we expect
- *	page numbers.
+ *	page numbers.  We can use zero for this because we never need to
+ *	make a pointer to the metadata page.
  */
 
 #define P_NONE			0
+
+/*
+ * Macros to test whether a page is leftmost or rightmost on its tree level,
+ * as well as other state info kept in the opaque data.
+ */
 #define P_LEFTMOST(opaque)		((opaque)->btpo_prev == P_NONE)
 #define P_RIGHTMOST(opaque)		((opaque)->btpo_next == P_NONE)
+#define P_ISLEAF(opaque)		((opaque)->btpo_flags & BTP_LEAF)
+#define P_ISROOT(opaque)		((opaque)->btpo_flags & BTP_ROOT)
+
+/*
+ *	Lehman and Yao's algorithm requires a ``high key'' on every non-rightmost
+ *	page.  The high key is not a data key, but gives info about what range of
+ *	keys is supposed to be on this page.  The high key on a page is required
+ *	to be greater than or equal to any data key that appears on the page.
+ *	If we find ourselves trying to insert a key > high key, we know we need
+ *	to move right (this should only happen if the page was split since we
+ *	examined the parent page).
+ *
+ *	Our insertion algorithm guarantees that we can use the initial least key
+ *	on our right sibling as the high key.  Once a page is created, its high
+ *	key changes only if the page is split.
+ *
+ *	On a non-rightmost page, the high key lives in item 1 and data items
+ *	start in item 2.  Rightmost pages have no high key, so we store data
+ *	items beginning in item 1.
+ */
 
 #define P_HIKEY			((OffsetNumber) 1)
 #define P_FIRSTKEY		((OffsetNumber) 2)
+#define P_FIRSTDATAKEY(opaque)  (P_RIGHTMOST(opaque) ? P_HIKEY : P_FIRSTKEY)
 
 /*
- *	Strategy numbers -- ordering of these is <, <=, =, >=, >
+ *	Operator strategy numbers -- ordering of these is <, <=, =, >=, >
  */
 
 #define BTLessStrategyNumber			1
@@ -199,13 +204,27 @@ typedef struct BTPageState
 
 #define BTORDER_PROC	1
 
+/*
+ * prototypes for functions in nbtree.c (external entry points for btree)
+ */
+extern bool BuildingBtree;		/* in nbtree.c */
+
+extern Datum btbuild(PG_FUNCTION_ARGS);
+extern Datum btinsert(PG_FUNCTION_ARGS);
+extern Datum btgettuple(PG_FUNCTION_ARGS);
+extern Datum btbeginscan(PG_FUNCTION_ARGS);
+extern Datum btrescan(PG_FUNCTION_ARGS);
+extern void btmovescan(IndexScanDesc scan, Datum v);
+extern Datum btendscan(PG_FUNCTION_ARGS);
+extern Datum btmarkpos(PG_FUNCTION_ARGS);
+extern Datum btrestrpos(PG_FUNCTION_ARGS);
+extern Datum btdelete(PG_FUNCTION_ARGS);
+
 /*
  * prototypes for functions in nbtinsert.c
  */
 extern InsertIndexResult _bt_doinsert(Relation rel, BTItem btitem,
 			 bool index_is_unique, Relation heapRel);
-extern bool _bt_itemcmp(Relation rel, Size keysz, ScanKey scankey,
-			BTItem item1, BTItem item2, StrategyNumber strat);
 
 /*
  * prototypes for functions in nbtpage.c
@@ -218,25 +237,8 @@ extern void _bt_wrtbuf(Relation rel, Buffer buf);
 extern void _bt_wrtnorelbuf(Relation rel, Buffer buf);
 extern void _bt_pageinit(Page page, Size size);
 extern void _bt_metaproot(Relation rel, BlockNumber rootbknum, int level);
-extern Buffer _bt_getstackbuf(Relation rel, BTStack stack, int access);
 extern void _bt_pagedel(Relation rel, ItemPointer tid);
 
-/*
- * prototypes for functions in nbtree.c
- */
-extern bool BuildingBtree;		/* in nbtree.c */
-
-extern Datum btbuild(PG_FUNCTION_ARGS);
-extern Datum btinsert(PG_FUNCTION_ARGS);
-extern Datum btgettuple(PG_FUNCTION_ARGS);
-extern Datum btbeginscan(PG_FUNCTION_ARGS);
-extern Datum btrescan(PG_FUNCTION_ARGS);
-extern void btmovescan(IndexScanDesc scan, Datum v);
-extern Datum btendscan(PG_FUNCTION_ARGS);
-extern Datum btmarkpos(PG_FUNCTION_ARGS);
-extern Datum btrestrpos(PG_FUNCTION_ARGS);
-extern Datum btdelete(PG_FUNCTION_ARGS);
-
 /*
  * prototypes for functions in nbtscan.c
  */
@@ -249,13 +251,13 @@ extern void AtEOXact_nbtree(void);
  * prototypes for functions in nbtsearch.c
  */
 extern BTStack _bt_search(Relation rel, int keysz, ScanKey scankey,
-		   Buffer *bufP);
+						  Buffer *bufP, int access);
 extern Buffer _bt_moveright(Relation rel, Buffer buf, int keysz,
 			  ScanKey scankey, int access);
-extern bool _bt_skeycmp(Relation rel, Size keysz, ScanKey scankey,
-			Page page, ItemId itemid, StrategyNumber strat);
 extern OffsetNumber _bt_binsrch(Relation rel, Buffer buf, int keysz,
-			ScanKey scankey, int srchtype);
+								ScanKey scankey);
+extern int32 _bt_compare(Relation rel, int keysz, ScanKey scankey,
+						 Page page, OffsetNumber offnum);
 extern RetrieveIndexResult _bt_next(IndexScanDesc scan, ScanDirection dir);
 extern RetrieveIndexResult _bt_first(IndexScanDesc scan, ScanDirection dir);
 extern bool _bt_step(IndexScanDesc scan, Buffer *bufP, ScanDirection dir);

src/include/storage/bufpage.h

@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2000, PostgreSQL, Inc
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $Id: bufpage.h,v 1.30 2000/07/03 02:54:21 vadim Exp $
+ * $Id: bufpage.h,v 1.31 2000/07/21 06:42:39 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -309,7 +309,6 @@ extern Page PageGetTempPage(Page page, Size specialSize);
 extern void PageRestoreTempPage(Page tempPage, Page oldPage);
 extern void PageRepairFragmentation(Page page);
 extern Size PageGetFreeSpace(Page page);
-extern void PageManagerModeSet(PageManagerMode mode);
 extern void PageIndexTupleDelete(Page page, OffsetNumber offset);