Create new routines systable_beginscan_ordered, systable_getnext_ordered,

systable_endscan_ordered that have API similar to systable_beginscan etc
(in particular, the passed-in scankeys have heap not index attnums),
but guarantee ordered output, unlike the existing functions.  For the moment
these are just very thin wrappers around index_beginscan/index_getnext/etc.
Someday they might need to get smarter; but for now this is just a code
refactoring exercise to reduce the number of direct callers of index_getnext,
in preparation for changing that function's API.

In passing, remove index_getnext_indexitem, which has been dead code for
quite some time, and will have even less use than that in the presence
of run-time-lossy indexes.

3 files changed, 110 insertions, 67 deletions

diff --git a/src/backend/access/heap/tuptoaster.c b/src/backend/access/heap/tuptoaster.c
index bd92b9adfb..cf2edbf31e 100644
--- a/src/backend/access/heap/tuptoaster.c
+++ b/src/backend/access/heap/tuptoaster.c
@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/access/heap/tuptoaster.c,v 1.85 2008/03/26 21:10:37 alvherre Exp $
+ *	  $PostgreSQL: pgsql/src/backend/access/heap/tuptoaster.c,v 1.86 2008/04/12 23:14:21 tgl Exp $
  *
  *
  * INTERFACE ROUTINES
@@ -1184,7 +1184,9 @@ toast_save_datum(Relation rel, Datum value,
 		toast_pointer.va_extsize = data_todo;
 	}
 
-	toast_pointer.va_valueid = GetNewOidWithIndex(toastrel, toastidx);
+	toast_pointer.va_valueid = GetNewOidWithIndex(toastrel,
+												  RelationGetRelid(toastidx),
+												  (AttrNumber) 1);
 	toast_pointer.va_toastrelid = rel->rd_rel->reltoastrelid;
 
 	/*
@@ -1273,7 +1275,7 @@ toast_delete_datum(Relation rel, Datum value)
 	Relation	toastrel;
 	Relation	toastidx;
 	ScanKeyData toastkey;
-	IndexScanDesc toastscan;
+	SysScanDesc toastscan;
 	HeapTuple	toasttup;
 
 	if (!VARATT_IS_EXTERNAL(attr))
@@ -1289,8 +1291,7 @@ toast_delete_datum(Relation rel, Datum value)
 	toastidx = index_open(toastrel->rd_rel->reltoastidxid, RowExclusiveLock);
 
 	/*
-	 * Setup a scan key to fetch from the index by va_valueid (we don't
-	 * particularly care whether we see them in sequence or not)
+	 * Setup a scan key to find chunks with matching va_valueid
 	 */
 	ScanKeyInit(&toastkey,
 				(AttrNumber) 1,
@@ -1298,11 +1299,13 @@ toast_delete_datum(Relation rel, Datum value)
 				ObjectIdGetDatum(toast_pointer.va_valueid));
 
 	/*
-	 * Find the chunks by index
+	 * Find all the chunks.  (We don't actually care whether we see them in
+	 * sequence or not, but since we've already locked the index we might
+	 * as well use systable_beginscan_ordered.)
 	 */
-	toastscan = index_beginscan(toastrel, toastidx,
-								SnapshotToast, 1, &toastkey);
-	while ((toasttup = index_getnext(toastscan, ForwardScanDirection)) != NULL)
+	toastscan = systable_beginscan_ordered(toastrel, toastidx,
+										   SnapshotToast, 1, &toastkey);
+	while ((toasttup = systable_getnext_ordered(toastscan, ForwardScanDirection)) != NULL)
 	{
 		/*
 		 * Have a chunk, delete it
@@ -1313,7 +1316,7 @@ toast_delete_datum(Relation rel, Datum value)
 	/*
 	 * End scan and close relations
 	 */
-	index_endscan(toastscan);
+	systable_endscan_ordered(toastscan);
 	index_close(toastidx, RowExclusiveLock);
 	heap_close(toastrel, RowExclusiveLock);
 }
@@ -1332,7 +1335,7 @@ toast_fetch_datum(struct varlena * attr)
 	Relation	toastrel;
 	Relation	toastidx;
 	ScanKeyData toastkey;
-	IndexScanDesc toastscan;
+	SysScanDesc toastscan;
 	HeapTuple	ttup;
 	TupleDesc	toasttupDesc;
 	struct varlena *result;
@@ -1383,9 +1386,9 @@ toast_fetch_datum(struct varlena * attr)
 	 */
 	nextidx = 0;
 
-	toastscan = index_beginscan(toastrel, toastidx,
-								SnapshotToast, 1, &toastkey);
-	while ((ttup = index_getnext(toastscan, ForwardScanDirection)) != NULL)
+	toastscan = systable_beginscan_ordered(toastrel, toastidx,
+										   SnapshotToast, 1, &toastkey);
+	while ((ttup = systable_getnext_ordered(toastscan, ForwardScanDirection)) != NULL)
 	{
 		/*
 		 * Have a chunk, extract the sequence number and the data
@@ -1464,7 +1467,7 @@ toast_fetch_datum(struct varlena * attr)
 	/*
 	 * End scan and close relations
 	 */
-	index_endscan(toastscan);
+	systable_endscan_ordered(toastscan);
 	index_close(toastidx, AccessShareLock);
 	heap_close(toastrel, AccessShareLock);
 
@@ -1485,7 +1488,7 @@ toast_fetch_datum_slice(struct varlena * attr, int32 sliceoffset, int32 length)
 	Relation	toastidx;
 	ScanKeyData toastkey[3];
 	int			nscankeys;
-	IndexScanDesc toastscan;
+	SysScanDesc toastscan;
 	HeapTuple	ttup;
 	TupleDesc	toasttupDesc;
 	struct varlena *result;
@@ -1592,9 +1595,9 @@ toast_fetch_datum_slice(struct varlena * attr, int32 sliceoffset, int32 length)
 	 * The index is on (valueid, chunkidx) so they will come in order
 	 */
 	nextidx = startchunk;
-	toastscan = index_beginscan(toastrel, toastidx,
-								SnapshotToast, nscankeys, toastkey);
-	while ((ttup = index_getnext(toastscan, ForwardScanDirection)) != NULL)
+	toastscan = systable_beginscan_ordered(toastrel, toastidx,
+										   SnapshotToast, nscankeys, toastkey);
+	while ((ttup = systable_getnext_ordered(toastscan, ForwardScanDirection)) != NULL)
 	{
 		/*
 		 * Have a chunk, extract the sequence number and the data
@@ -1681,7 +1684,7 @@ toast_fetch_datum_slice(struct varlena * attr, int32 sliceoffset, int32 length)
 	/*
 	 * End scan and close relations
 	 */
-	index_endscan(toastscan);
+	systable_endscan_ordered(toastscan);
 	index_close(toastidx, AccessShareLock);
 	heap_close(toastrel, AccessShareLock);
 
diff --git a/src/backend/access/index/genam.c b/src/backend/access/index/genam.c
index 8877938322..cafb1e6867 100644
--- a/src/backend/access/index/genam.c
+++ b/src/backend/access/index/genam.c
@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/access/index/genam.c,v 1.66 2008/04/10 22:25:25 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/access/index/genam.c,v 1.67 2008/04/12 23:14:21 tgl Exp $
  *
  * NOTES
  *	  many of the old access method routines have been turned into
@@ -258,3 +258,87 @@ systable_endscan(SysScanDesc sysscan)
 
 	pfree(sysscan);
 }
+
+
+/*
+ * systable_beginscan_ordered --- set up for ordered catalog scan
+ *
+ * These routines have essentially the same API as systable_beginscan etc,
+ * except that they guarantee to return multiple matching tuples in
+ * index order.  Also, for largely historical reasons, the index to use
+ * is opened and locked by the caller, not here.
+ *
+ * Currently we do not support non-index-based scans here.  (In principle
+ * we could do a heapscan and sort, but the uses are in places that
+ * probably don't need to still work with corrupted catalog indexes.)
+ * For the moment, therefore, these functions are merely the thinnest of
+ * wrappers around index_beginscan/index_getnext.  The main reason for their
+ * existence is to centralize possible future support of lossy operators
+ * in catalog scans.
+ */
+SysScanDesc
+systable_beginscan_ordered(Relation heapRelation,
+						   Relation indexRelation,
+						   Snapshot snapshot,
+						   int nkeys, ScanKey key)
+{
+	SysScanDesc sysscan;
+	int			i;
+
+	/* REINDEX can probably be a hard error here ... */
+	if (ReindexIsProcessingIndex(RelationGetRelid(indexRelation)))
+		elog(ERROR, "cannot do ordered scan on index \"%s\", because it is the current REINDEX target",
+			 RelationGetRelationName(indexRelation));
+	/* ... but we only throw a warning about violating IgnoreSystemIndexes */
+	if (IgnoreSystemIndexes)
+		elog(WARNING, "using index \"%s\" despite IgnoreSystemIndexes",
+			 RelationGetRelationName(indexRelation));
+
+	sysscan = (SysScanDesc) palloc(sizeof(SysScanDescData));
+
+	sysscan->heap_rel = heapRelation;
+	sysscan->irel = indexRelation;
+
+	/*
+	 * Change attribute numbers to be index column numbers.
+	 *
+	 * This code could be generalized to search for the index key numbers
+	 * to substitute, but for now there's no need.
+	 */
+	for (i = 0; i < nkeys; i++)
+	{
+		Assert(key[i].sk_attno == indexRelation->rd_index->indkey.values[i]);
+		key[i].sk_attno = i + 1;
+	}
+
+	sysscan->iscan = index_beginscan(heapRelation, indexRelation,
+									 snapshot, nkeys, key);
+	sysscan->scan = NULL;
+
+	return sysscan;
+}
+
+/*
+ * systable_getnext_ordered --- get next tuple in an ordered catalog scan
+ */
+HeapTuple
+systable_getnext_ordered(SysScanDesc sysscan, ScanDirection direction)
+{
+	HeapTuple	htup;
+
+	Assert(sysscan->irel);
+	htup = index_getnext(sysscan->iscan, direction);
+
+	return htup;
+}
+
+/*
+ * systable_endscan_ordered --- close scan, release resources
+ */
+void
+systable_endscan_ordered(SysScanDesc sysscan)
+{
+	Assert(sysscan->irel);
+	index_endscan(sysscan->iscan);
+	pfree(sysscan);
+}
diff --git a/src/backend/access/index/indexam.c b/src/backend/access/index/indexam.c
index d59f1529db..7a06d0074e 100644
--- a/src/backend/access/index/indexam.c
+++ b/src/backend/access/index/indexam.c
@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/access/index/indexam.c,v 1.105 2008/04/10 22:25:25 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/access/index/indexam.c,v 1.106 2008/04/12 23:14:21 tgl Exp $
  *
  * INTERFACE ROUTINES
  *		index_open		- open an index relation by relation OID
@@ -206,12 +206,7 @@ index_insert(Relation indexRelation,
 /*
  * index_beginscan - start a scan of an index with amgettuple
  *
- * Note: heapRelation may be NULL if there is no intention of calling
- * index_getnext on this scan; index_getnext_indexitem will not use the
- * heapRelation link (nor the snapshot).  However, the caller had better
- * be holding some kind of lock on the heap relation in any case, to ensure
- * no one deletes it (or the index) out from under us.	Caller must also
- * be holding a lock on the index.
+ * Caller must be holding suitable locks on the heap and the index.
  */
 IndexScanDesc
 index_beginscan(Relation heapRelation,
@@ -635,45 +630,6 @@ index_getnext(IndexScanDesc scan, ScanDirection direction)
 }
 
 /* ----------------
- *		index_getnext_indexitem - get the next index tuple from a scan
- *
- * Finds the next index tuple satisfying the scan keys.  Note that the
- * corresponding heap tuple is not accessed, and thus no time qual (snapshot)
- * check is done, other than the index AM's internal check for killed tuples
- * (which most callers of this routine will probably want to suppress by
- * setting scan->ignore_killed_tuples = false).
- *
- * On success (TRUE return), the heap TID of the found index entry is in
- * scan->xs_ctup.t_self.  scan->xs_cbuf is untouched.
- * ----------------
- */
-bool
-index_getnext_indexitem(IndexScanDesc scan,
-						ScanDirection direction)
-{
-	FmgrInfo   *procedure;
-	bool		found;
-
-	SCAN_CHECKS;
-	GET_SCAN_PROCEDURE(amgettuple);
-
-	/* just make sure this is false... */
-	scan->kill_prior_tuple = false;
-
-	/*
-	 * have the am's gettuple proc do all the work.
-	 */
-	found = DatumGetBool(FunctionCall2(procedure,
-									   PointerGetDatum(scan),
-									   Int32GetDatum(direction)));
-
-	if (found)
-		pgstat_count_index_tuples(scan->indexRelation, 1);
-
-	return found;
-}
-
-/* ----------------
  *		index_getbitmap - get all tuples at once from an index scan
  *
  * Adds the TIDs of all heap tuples satisfying the scan keys to a bitmap.