Added query-aware dynamic pruning [skip ci]

README.md

@@ -312,6 +312,10 @@ Two things you can try are:
 1. use dimensionality reduction
 2. compile Postgres with a larger block size (`./configure --with-blocksize=32`) and edit the limit in `src/ivfflat.h`
 
+#### Why am I seeing less results after adding an index?
+
+The index was likely created with too little data for the number of lists. Drop the index until the table has more data.
+
 ## Reference
 
 ### Vector Type

src/ivfflat.h

@@ -187,14 +187,6 @@ typedef struct IvfflatScanList
 	double		distance;
 }			IvfflatScanList;
 
-typedef struct IvfflatScanItem
-{
-	pairingheap_node ph_node;
-	BlockNumber searchPage;
-	double		distance;
-	ItemPointerData tid;
-}			IvfflatScanItem;
-
 typedef struct IvfflatScanOpaqueData
 {
 	int			probes;
@@ -212,15 +204,9 @@ typedef struct IvfflatScanOpaqueData
 	FmgrInfo   *normprocinfo;
 	Oid			collation;
 
-	/* Items */
-	int			maxItems;
-	int			itemCount;
-	pairingheap *itemQueue;
-	IvfflatScanItem *items;
-	IvfflatScanItem **sortedItems;
-
 	/* Lists */
 	pairingheap *listQueue;
+	double		minDistance;
 	IvfflatScanList lists[FLEXIBLE_ARRAY_MEMBER];	/* must come last */
 }			IvfflatScanOpaqueData;
 

src/ivfscan.c

@@ -26,21 +26,6 @@ CompareLists(const pairingheap_node *a, const pairingheap_node *b, void *arg)
 	return 0;
 }
 
-/*
- * Compare item distances
- */
-static int
-CompareItems(const pairingheap_node *a, const pairingheap_node *b, void *arg)
-{
-	if (((const IvfflatScanItem *) a)->distance > ((const IvfflatScanItem *) b)->distance)
-		return 1;
-
-	if (((const IvfflatScanItem *) a)->distance < ((const IvfflatScanItem *) b)->distance)
-		return -1;
-
-	return 0;
-}
-
 /*
  * Get lists and sort by distance
  */
@@ -75,6 +60,9 @@ GetScanLists(IndexScanDesc scan, Datum value)
 			/* Use procinfo from the index instead of scan key for performance */
 			distance = DatumGetFloat8(FunctionCall2Coll(so->procinfo, so->collation, PointerGetDatum(&list->center), value));
 
+			if (distance < so->minDistance)
+				so->minDistance = distance;
+
 			if (listCount < so->probes)
 			{
 				scanlist = &so->lists[listCount];
@@ -126,10 +114,13 @@ GetScanItems(IndexScanDesc scan, Datum value)
 	Datum		datum;
 	bool		isnull;
 	TupleDesc	tupdesc = RelationGetDescr(scan->indexRelation);
-	int			i;
+	double		tuples = 0;
-	double		distance;
+
-	IvfflatScanItem *scanitem;
+#if PG_VERSION_NUM >= 120000
-	double		maxDistance = DBL_MAX;
+	TupleTableSlot *slot = MakeSingleTupleTableSlot(so->tupdesc, &TTSOpsVirtual);
+#else
+	TupleTableSlot *slot = MakeSingleTupleTableSlot(so->tupdesc);
+#endif
 
 	/*
 	 * Reuse same set of shared buffers for scan
@@ -141,7 +132,13 @@ GetScanItems(IndexScanDesc scan, Datum value)
 	/* Search closest probes lists */
 	while (!pairingheap_is_empty(so->listQueue))
 	{
-		searchPage = ((IvfflatScanList *) pairingheap_remove_first(so->listQueue))->startPage;
+		IvfflatScanList *scanlist = (IvfflatScanList *) pairingheap_remove_first(so->listQueue);
+
+		/* Query-aware dynamic pruning */
+		if (scanlist->distance > 2 * so->minDistance)
+			continue;
+
+		searchPage = scanlist->startPage;
 
 		/* Search all entry pages for list */
 		while (BlockNumberIsValid(searchPage))
@@ -155,40 +152,25 @@ GetScanItems(IndexScanDesc scan, Datum value)
 			{
 				itup = (IndexTuple) PageGetItem(page, PageGetItemId(page, offno));
 				datum = index_getattr(itup, 1, tupdesc, &isnull);
-				distance = DatumGetFloat8(FunctionCall2Coll(so->procinfo, so->collation, datum, value));
 
-				if (so->itemCount < so->maxItems)
+				/*
-				{
+				 * Add virtual tuple
-					scanitem = &so->items[so->itemCount];
+				 *
-					scanitem->searchPage = searchPage;
+				 * Use procinfo from the index instead of scan key for
-					scanitem->tid = itup->t_tid;
+				 * performance
-					scanitem->distance = distance;
+				 */
-					so->itemCount++;
+				ExecClearTuple(slot);
+				slot->tts_values[0] = FunctionCall2Coll(so->procinfo, so->collation, datum, value);
+				slot->tts_isnull[0] = false;
+				slot->tts_values[1] = PointerGetDatum(&itup->t_tid);
+				slot->tts_isnull[1] = false;
+				slot->tts_values[2] = Int32GetDatum((int) searchPage);
+				slot->tts_isnull[2] = false;
+				ExecStoreVirtualTuple(slot);
 
-					/* Add to heap */
+				tuplesort_puttupleslot(so->sortstate, slot);
-					pairingheap_add(so->itemQueue, &scanitem->ph_node);
 
-					/* Calculate max distance */
+				tuples++;
-					if (so->itemCount == so->maxItems)
-					{
-						maxDistance = ((IvfflatScanItem *) pairingheap_first(so->itemQueue))->distance;
-						scanitem = &so->items[so->itemCount];
-					}
-				}
-				else if (distance < maxDistance)
-				{
-					/* Reuse */
-					scanitem->searchPage = searchPage;
-					scanitem->tid = itup->t_tid;
-					scanitem->distance = distance;
-					pairingheap_add(so->itemQueue, &scanitem->ph_node);
-
-					/* Remove */
-					scanitem = (IvfflatScanItem *) pairingheap_remove_first(so->itemQueue);
-
-					/* Update max distance */
-					maxDistance = ((IvfflatScanItem *) pairingheap_first(so->itemQueue))->distance;
-				}
 			}
 
 			searchPage = IvfflatPageGetOpaque(page)->nextblkno;
@@ -197,10 +179,14 @@ GetScanItems(IndexScanDesc scan, Datum value)
 		}
 	}
 
-	for (i = 0; i < so->itemCount; i++)
+	/* TODO Scan more lists */
-		so->sortedItems[i] = (IvfflatScanItem *) pairingheap_remove_first(so->itemQueue);
+	if (tuples < 100)
+		ereport(DEBUG1,
+				(errmsg("index scan found few tuples"),
+				 errdetail("index may have been created without data or lists is too high"),
+				 errhint("recreate the index and possibly decrease lists")));
 
-	Assert(pairingheap_is_empty(so->itemQueue));
+	tuplesort_performsort(so->sortstate);
 }
 
 /*
@@ -212,6 +198,10 @@ ivfflatbeginscan(Relation index, int nkeys, int norderbys)
 	IndexScanDesc scan;
 	IvfflatScanOpaque so;
 	int			lists;
+	AttrNumber	attNums[] = {1};
+	Oid			sortOperators[] = {Float8LessOperator};
+	Oid			sortCollations[] = {InvalidOid};
+	bool		nullsFirstFlags[] = {false};
 	int			probes = ivfflat_probes;
 
 	scan = RelationGetIndexScan(index, nkeys, norderbys);
@@ -230,13 +220,26 @@ ivfflatbeginscan(Relation index, int nkeys, int norderbys)
 	so->normprocinfo = IvfflatOptionalProcInfo(index, IVFFLAT_NORM_PROC);
 	so->collation = index->rd_indcollation[0];
 
-	so->listQueue = pairingheap_allocate(CompareLists, scan);
+	/* Create tuple description for sorting */
+#if PG_VERSION_NUM >= 120000
+	so->tupdesc = CreateTemplateTupleDesc(3);
+#else
+	so->tupdesc = CreateTemplateTupleDesc(3, false);
+#endif
+	TupleDescInitEntry(so->tupdesc, (AttrNumber) 1, "distance", FLOAT8OID, -1, 0);
+	TupleDescInitEntry(so->tupdesc, (AttrNumber) 2, "tid", TIDOID, -1, 0);
+	TupleDescInitEntry(so->tupdesc, (AttrNumber) 3, "indexblkno", INT4OID, -1, 0);
 
-	so->maxItems = 10;
+	/* Prep sort */
-	so->itemCount = 0;
+	so->sortstate = tuplesort_begin_heap(so->tupdesc, 1, attNums, sortOperators, sortCollations, nullsFirstFlags, work_mem, NULL, false);
-	so->itemQueue = pairingheap_allocate(CompareItems, scan);
+
-	so->items = palloc(sizeof(IvfflatScanItem) * (so->maxItems + 1));
+#if PG_VERSION_NUM >= 120000
-	so->sortedItems = palloc(sizeof(IvfflatScanItem *) * so->maxItems);
+	so->slot = MakeSingleTupleTableSlot(so->tupdesc, &TTSOpsMinimalTuple);
+#else
+	so->slot = MakeSingleTupleTableSlot(so->tupdesc);
+#endif
+
+	so->listQueue = pairingheap_allocate(CompareLists, scan);
 
 	scan->opaque = so;
 
@@ -251,10 +254,14 @@ ivfflatrescan(IndexScanDesc scan, ScanKey keys, int nkeys, ScanKey orderbys, int
 {
 	IvfflatScanOpaque so = (IvfflatScanOpaque) scan->opaque;
 
+#if PG_VERSION_NUM >= 130000
+	if (!so->first)
+		tuplesort_reset(so->sortstate);
+#endif
+
 	so->first = true;
 	pairingheap_reset(so->listQueue);
-	pairingheap_reset(so->itemQueue);
+	so->minDistance = DBL_MAX;
-	so->itemCount = 0;
 
 	if (keys && scan->numberOfKeys > 0)
 		memmove(scan->keyData, keys, scan->numberOfKeys * sizeof(ScanKeyData));
@@ -314,18 +321,15 @@ ivfflatgettuple(IndexScanDesc scan, ScanDirection dir)
 			pfree(DatumGetPointer(value));
 	}
 
-	if (so->itemCount > 0)
+	if (tuplesort_gettupleslot(so->sortstate, true, false, so->slot, NULL))
 	{
-		IvfflatScanItem *scanitem;
+		ItemPointer tid = (ItemPointer) DatumGetPointer(slot_getattr(so->slot, 2, &so->isnull));
-
+		BlockNumber indexblkno = DatumGetInt32(slot_getattr(so->slot, 3, &so->isnull));
-		so->itemCount--;
-
-		scanitem = so->sortedItems[so->itemCount];
 
 #if PG_VERSION_NUM >= 120000
-		scan->xs_heaptid = scanitem->tid;
+		scan->xs_heaptid = *tid;
 #else
-		scan->xs_ctup.t_self = scanitem->tid;
+		scan->xs_ctup.t_self = *tid;
 #endif
 
 		if (BufferIsValid(so->buf))
@@ -337,7 +341,7 @@ ivfflatgettuple(IndexScanDesc scan, ScanDirection dir)
 		 *
 		 * https://www.postgresql.org/docs/current/index-locking.html
 		 */
-		so->buf = ReadBuffer(scan->indexRelation, scanitem->searchPage);
+		so->buf = ReadBuffer(scan->indexRelation, indexblkno);
 
 		scan->xs_recheckorderby = false;
 		return true;
@@ -359,10 +363,7 @@ ivfflatendscan(IndexScanDesc scan)
 		ReleaseBuffer(so->buf);
 
 	pairingheap_free(so->listQueue);
-
+	tuplesort_end(so->sortstate);
-	pairingheap_free(so->itemQueue);
-	pfree(so->items);
-	pfree(so->sortedItems);
 
 	pfree(so);
 	scan->opaque = NULL;