Harmonize nbtree page split point code.

An nbtree split point can be thought of as a point between two adjoining
tuples from an imaginary version of the page being split that includes
the incoming/new item (in addition to the items that really are on the
page).  These adjoining tuples are called the lastleft and firstright
tuples.

The variables that represent split points contained a field called
firstright, which is an offset number of the first data item from the
original page that goes on the new right page.  The corresponding tuple
from origpage was usually the same thing as the actual firstright tuple,
but not always: the firstright tuple is sometimes the new/incoming item
instead.  This situation seems unnecessarily confusing.

Make things clearer by renaming the origpage offset returned by
_bt_findsplitloc() to "firstrightoff".  We now have a firstright tuple
and a firstrightoff offset number which are comparable to the
newitem/lastleft tuples and the newitemoff/lastleftoff offset numbers
respectively.  Also make sure that we are consistent about how we
describe nbtree page split point state.

Push the responsibility for dealing with pg_upgrade'd !heapkeyspace
indexes down to lower level code, relieving _bt_split() from dealing
with it directly.  This means that we always have a palloc'd left page
high key on the leaf level, no matter what.  This enables simplifying
some of the code (and code comments) within _bt_split().

Finally, restructure the page split code to make it clearer why suffix
truncation (which only takes place during leaf page splits) is
completely different to the first data item truncation that takes place
during internal page splits.  Tuples are marked as having fewer
attributes stored in both cases, and the firstright tuple is truncated
in both cases, so it's easy to imagine somebody missing the distinction.

contrib/amcheck/verify_nbtree.c

@@ -1121,7 +1121,7 @@ bt_target_page_check(BtreeCheckState *state)
 		 * designated purpose.  Enforce the lower limit for pivot tuples when
 		 * an explicit heap TID isn't actually present. (In all other cases
 		 * suffix truncation is guaranteed to generate a pivot tuple that's no
-		 * larger than the first right tuple provided to it by its caller.)
+		 * larger than the firstright tuple provided to it by its caller.)
 		 */
 		lowersizelimit = skey->heapkeyspace &&
 			(P_ISLEAF(topaque) || BTreeTupleGetHeapTID(itup) == NULL);

src/backend/access/nbtree/nbtsort.c

@@ -269,7 +269,8 @@ static Page _bt_blnewpage(uint32 level);
 static BTPageState *_bt_pagestate(BTWriteState *wstate, uint32 level);
 static void _bt_slideleft(Page page);
 static void _bt_sortaddtup(Page page, Size itemsize,
-						   IndexTuple itup, OffsetNumber itup_off);
+						   IndexTuple itup, OffsetNumber itup_off,
+						   bool newfirstdataitem);
 static void _bt_buildadd(BTWriteState *wstate, BTPageState *state,
 						 IndexTuple itup, Size truncextra);
 static void _bt_sort_dedup_finish_pending(BTWriteState *wstate,
@@ -750,26 +751,24 @@ _bt_slideleft(Page page)
 /*
  * Add an item to a page being built.
  *
- * The main difference between this routine and a bare PageAddItem call
- * is that this code knows that the leftmost data item on a non-leaf btree
- * page has a key that must be treated as minus infinity.  Therefore, it
- * truncates away all attributes.
+ * This is very similar to nbtinsert.c's _bt_pgaddtup(), but this variant
+ * raises an error directly.
  *
- * This is almost like nbtinsert.c's _bt_pgaddtup(), but we can't use
- * that because it assumes that P_RIGHTMOST() will return the correct
- * answer for the page.  Here, we don't know yet if the page will be
- * rightmost.  Offset P_FIRSTKEY is always the first data key.
+ * Note that our nbtsort.c caller does not know yet if the page will be
+ * rightmost.  Offset P_FIRSTKEY is always assumed to be the first data key by
+ * caller.  Page that turns out to be the rightmost on its level is fixed by
+ * calling _bt_slideleft().
  */
 static void
 _bt_sortaddtup(Page page,
 			   Size itemsize,
 			   IndexTuple itup,
-			   OffsetNumber itup_off)
+			   OffsetNumber itup_off,
+			   bool newfirstdataitem)
 {
-	BTPageOpaque opaque = (BTPageOpaque) PageGetSpecialPointer(page);
 	IndexTupleData trunctuple;
 
-	if (!P_ISLEAF(opaque) && itup_off == P_FIRSTKEY)
+	if (newfirstdataitem)
 	{
 		trunctuple = *itup;
 		trunctuple.t_info = sizeof(IndexTupleData);
@@ -867,12 +866,13 @@ _bt_buildadd(BTWriteState *wstate, BTPageState *state, IndexTuple itup,
 	 * Every newly built index will treat heap TID as part of the keyspace,
 	 * which imposes the requirement that new high keys must occasionally have
 	 * a heap TID appended within _bt_truncate().  That may leave a new pivot
-	 * tuple one or two MAXALIGN() quantums larger than the original first
-	 * right tuple it's derived from.  v4 deals with the problem by decreasing
-	 * the limit on the size of tuples inserted on the leaf level by the same
-	 * small amount.  Enforce the new v4+ limit on the leaf level, and the old
-	 * limit on internal levels, since pivot tuples may need to make use of
-	 * the reserved space.  This should never fail on internal pages.
+	 * tuple one or two MAXALIGN() quantums larger than the original
+	 * firstright tuple it's derived from.  v4 deals with the problem by
+	 * decreasing the limit on the size of tuples inserted on the leaf level
+	 * by the same small amount.  Enforce the new v4+ limit on the leaf level,
+	 * and the old limit on internal levels, since pivot tuples may need to
+	 * make use of the reserved space.  This should never fail on internal
+	 * pages.
 	 */
 	if (unlikely(itupsz > BTMaxItemSize(npage)))
 		_bt_check_third_page(wstate->index, wstate->heap, isleaf, npage,
@@ -925,7 +925,8 @@ _bt_buildadd(BTWriteState *wstate, BTPageState *state, IndexTuple itup,
 		Assert(last_off > P_FIRSTKEY);
 		ii = PageGetItemId(opage, last_off);
 		oitup = (IndexTuple) PageGetItem(opage, ii);
-		_bt_sortaddtup(npage, ItemIdGetLength(ii), oitup, P_FIRSTKEY);
+		_bt_sortaddtup(npage, ItemIdGetLength(ii), oitup, P_FIRSTKEY,
+					   !isleaf);
 
 		/*
 		 * Move 'last' into the high key position on opage.  _bt_blnewpage()
@@ -1054,7 +1055,8 @@ _bt_buildadd(BTWriteState *wstate, BTPageState *state, IndexTuple itup,
 	 * Add the new item into the current page.
 	 */
 	last_off = OffsetNumberNext(last_off);
-	_bt_sortaddtup(npage, itupsz, itup, last_off);
+	_bt_sortaddtup(npage, itupsz, itup, last_off,
+				   !isleaf && last_off == P_FIRSTKEY);
 
 	state->btps_page = npage;
 	state->btps_blkno = nblkno;

src/backend/access/nbtree/nbtutils.c

@@ -2346,17 +2346,12 @@ _bt_keep_natts(Relation rel, IndexTuple lastleft, IndexTuple firstright,
 	ScanKey		scankey;
 
 	/*
-	 * Be consistent about the representation of BTREE_VERSION 2/3 tuples
-	 * across Postgres versions; don't allow new pivot tuples to have
-	 * truncated key attributes there.  _bt_compare() treats truncated key
-	 * attributes as having the value minus infinity, which would break
-	 * searches within !heapkeyspace indexes.
+	 * _bt_compare() treats truncated key attributes as having the value minus
+	 * infinity, which would break searches within !heapkeyspace indexes.  We
+	 * must still truncate away non-key attribute values, though.
 	 */
 	if (!itup_key->heapkeyspace)
-	{
-		Assert(nkeyatts != IndexRelationGetNumberOfAttributes(rel));
 		return nkeyatts;
-	}
 
 	scankey = itup_key->scankeys;
 	keepnatts = 1;

src/backend/access/nbtree/nbtxlog.c

@@ -251,7 +251,7 @@ btree_xlog_insert(bool isleaf, bool ismeta, bool posting,
 }
 
 static void
-btree_xlog_split(bool onleft, XLogReaderState *record)
+btree_xlog_split(bool newitemonleft, XLogReaderState *record)
 {
 	XLogRecPtr	lsn = record->EndRecPtr;
 	xl_btree_split *xlrec = (xl_btree_split *) XLogRecGetData(record);
@@ -323,7 +323,7 @@ btree_xlog_split(bool onleft, XLogReaderState *record)
 
 		datapos = XLogRecGetBlockData(record, 0, &datalen);
 
-		if (onleft || xlrec->postingoff != 0)
+		if (newitemonleft || xlrec->postingoff != 0)
 		{
 			newitem = (IndexTuple) datapos;
 			newitemsz = MAXALIGN(IndexTupleSize(newitem));
@@ -368,7 +368,7 @@ btree_xlog_split(bool onleft, XLogReaderState *record)
 			elog(PANIC, "failed to add high key to left page after split");
 		leftoff = OffsetNumberNext(leftoff);
 
-		for (off = P_FIRSTDATAKEY(lopaque); off < xlrec->firstright; off++)
+		for (off = P_FIRSTDATAKEY(lopaque); off < xlrec->firstrightoff; off++)
 		{
 			ItemId		itemid;
 			Size		itemsz;
@@ -377,7 +377,8 @@ btree_xlog_split(bool onleft, XLogReaderState *record)
 			/* Add replacement posting list when required */
 			if (off == replacepostingoff)
 			{
-				Assert(onleft || xlrec->firstright == xlrec->newitemoff);
+				Assert(newitemonleft ||
+					   xlrec->firstrightoff == xlrec->newitemoff);
 				if (PageAddItem(newlpage, (Item) nposting,
 								MAXALIGN(IndexTupleSize(nposting)), leftoff,
 								false, false) == InvalidOffsetNumber)
@@ -387,7 +388,7 @@ btree_xlog_split(bool onleft, XLogReaderState *record)
 			}
 
 			/* add the new item if it was inserted on left page */
-			else if (onleft && off == xlrec->newitemoff)
+			else if (newitemonleft && off == xlrec->newitemoff)
 			{
 				if (PageAddItem(newlpage, (Item) newitem, newitemsz, leftoff,
 								false, false) == InvalidOffsetNumber)
@@ -405,7 +406,7 @@ btree_xlog_split(bool onleft, XLogReaderState *record)
 		}
 
 		/* cope with possibility that newitem goes at the end */
-		if (onleft && off == xlrec->newitemoff)
+		if (newitemonleft && off == xlrec->newitemoff)
 		{
 			if (PageAddItem(newlpage, (Item) newitem, newitemsz, leftoff,
 							false, false) == InvalidOffsetNumber)

src/backend/access/rmgrdesc/nbtdesc.c

@@ -39,8 +39,8 @@ btree_desc(StringInfo buf, XLogReaderState *record)
 			{
 				xl_btree_split *xlrec = (xl_btree_split *) rec;
 
-				appendStringInfo(buf, "level %u, firstright %d, newitemoff %d, postingoff %d",
-								 xlrec->level, xlrec->firstright,
+				appendStringInfo(buf, "level %u, firstrightoff %d, newitemoff %d, postingoff %d",
+								 xlrec->level, xlrec->firstrightoff,
 								 xlrec->newitemoff, xlrec->postingoff);
 				break;
 			}

src/include/access/nbtxlog.h

@@ -99,9 +99,9 @@ typedef struct xl_btree_insert
  * left or right split page (and thus, whether the new item is stored or not).
  * We always log the left page high key because suffix truncation can generate
  * a new leaf high key using user-defined code.  This is also necessary on
- * internal pages, since the first right item that the left page's high key
- * was based on will have been truncated to zero attributes in the right page
- * (the original is unavailable from the right page).
+ * internal pages, since the firstright item that the left page's high key was
+ * based on will have been truncated to zero attributes in the right page (the
+ * separator key is unavailable from the right page).
  *
  * Backup Blk 0: original page / new left page
  *
@@ -153,7 +153,7 @@ typedef struct xl_btree_insert
 typedef struct xl_btree_split
 {
 	uint32		level;			/* tree level of page being split */
-	OffsetNumber firstright;	/* first item moved to right page */
+	OffsetNumber firstrightoff; /* first origpage item on rightpage */
 	OffsetNumber newitemoff;	/* new item's offset */
 	uint16		postingoff;		/* offset inside orig posting tuple */
 } xl_btree_split;