Improved test for angular distance [skip ci]

CHANGELOG.md

@@ -1,7 +1,6 @@
 ## 0.5.1 (unreleased)
 
-- Improved performance of index scans for IVFFlat after updates and deletes
+- Added `angular_distance` function
-- Fixed locking for index scans for HNSW
 
 ## 0.5.0 (2023-08-28)
 

Makefile

@@ -8,7 +8,7 @@ HEADERS = src/vector.h
 
 TESTS = $(wildcard test/sql/*.sql)
 REGRESS = $(patsubst test/sql/%.sql,%,$(TESTS))
-REGRESS_OPTS = --inputdir=test --load-extension=$(EXTENSION)
+REGRESS_OPTS = --inputdir=test --load-extension=vector
 
 OPTFLAGS = -march=native
 

Makefile.win

@@ -5,7 +5,7 @@ OBJS = src\hnsw.obj src\hnswbuild.obj src\hnswinsert.obj src\hnswscan.obj src\hn
 HEADERS = src\vector.h
 
 REGRESS = btree cast copy functions input ivfflat_cosine ivfflat_ip ivfflat_l2 ivfflat_options ivfflat_unlogged
-REGRESS_OPTS = --inputdir=test --load-extension=$(EXTENSION)
+REGRESS_OPTS = --inputdir=test --load-extension=vector
 
 # For /arch flags
 # https://learn.microsoft.com/en-us/cpp/build/reference/arch-minimum-cpu-architecture

README.md

@@ -595,18 +595,12 @@ pgvector is available on [these providers](https://github.com/pgvector/pgvector/
 
 ## Upgrading
 
-Install the latest version. Then in each database you want to upgrade, run:
+Install the latest version and run:
 
 ```sql
 ALTER EXTENSION vector UPDATE;
 ```
 
-You can check the version in the current database with:
-
-```sql
-SELECT extversion FROM pg_extension WHERE extname = 'vector';
-```
-
 ## Upgrade Notes
 
 ### 0.4.0

sql/vector--0.5.0--0.5.1.sql

@@ -0,0 +1,5 @@
+-- complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "ALTER EXTENSION vector UPDATE TO '0.5.1'" to load this file. \quit
+
+CREATE FUNCTION angular_distance(vector, vector) RETURNS float8
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;

sql/vector.sql

@@ -87,6 +87,9 @@ CREATE FUNCTION vector_l2_squared_distance(vector, vector) RETURNS float8
 CREATE FUNCTION vector_negative_inner_product(vector, vector) RETURNS float8
 	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
 
+CREATE FUNCTION angular_distance(vector, vector) RETURNS float8
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
 CREATE FUNCTION vector_spherical_distance(vector, vector) RETURNS float8
 	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
 

src/hnsw.c

@@ -91,7 +91,7 @@ hnswcostestimate(PlannerInfo *root, IndexPath *path, double loop_count,
 	MemSet(&costs, 0, sizeof(costs));
 
 	index = index_open(path->indexinfo->indexoid, NoLock);
-	HnswGetMetaPageInfo(index, &m, NULL);
+	m = HnswGetM(index);
 	index_close(index, NoLock);
 
 	/* Approximate entry level */
@@ -196,7 +196,7 @@ hnswhandler(PG_FUNCTION_ARGS)
 	amroutine->aminsert = hnswinsert;
 	amroutine->ambulkdelete = hnswbulkdelete;
 	amroutine->amvacuumcleanup = hnswvacuumcleanup;
-	amroutine->amcanreturn = NULL;
+	amroutine->amcanreturn = NULL;	/* tuple not included in heapsort */
 	amroutine->amcostestimate = hnswcostestimate;
 	amroutine->amoptions = hnswoptions;
 	amroutine->amproperty = NULL;	/* TODO AMPROP_DISTANCE_ORDERABLE */

src/hnsw.h

@@ -218,6 +218,7 @@ typedef HnswNeighborTupleData * HnswNeighborTuple;
 typedef struct HnswScanOpaqueData
 {
 	bool		first;
+	Buffer		buf;
 	List	   *w;
 	MemoryContext tmpCtx;
 
@@ -265,9 +266,8 @@ Buffer		HnswNewBuffer(Relation index, ForkNumber forkNum);
 void		HnswInitPage(Buffer buf, Page page);
 void		HnswInitRegisterPage(Relation index, Buffer *buf, Page *page, GenericXLogState **state);
 void		HnswInit(void);
-List	   *HnswSearchLayer(Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool inserting, HnswElement skipElement);
+List	   *HnswSearchLayer(Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, bool inserting, HnswElement skipElement);
 HnswElement HnswGetEntryPoint(Relation index);
-void		HnswGetMetaPageInfo(Relation index, int *m, HnswElement * entryPoint);
 HnswElement HnswInitElement(ItemPointer tid, int m, double ml, int maxLevel);
 void		HnswFreeElement(HnswElement element);
 HnswElement HnswInitElementFromBlock(BlockNumber blkno, OffsetNumber offno);
@@ -284,7 +284,7 @@ void		HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool
 void		HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec);
 void		HnswSetElementTuple(HnswElementTuple etup, HnswElement element);
 void		HnswUpdateConnection(HnswElement element, HnswCandidate * hc, int m, int lc, int *updateIdx, Relation index, FmgrInfo *procinfo, Oid collation);
-void		HnswLoadNeighbors(HnswElement element, Relation index, int m);
+void		HnswLoadNeighbors(HnswElement element, Relation index);
 
 /* Index access methods */
 IndexBuildResult *hnswbuild(Relation heap, Relation index, IndexInfo *indexInfo);

src/hnswinsert.c

@@ -329,7 +329,7 @@ HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswE
 
 			/* Get latest neighbors since they may have changed */
 			/* Do not lock yet since selecting neighbors can take time */
-			HnswLoadNeighbors(hc->element, index, m);
+			HnswLoadNeighbors(hc->element, index);
 
 			/*
 			 * Could improve performance for vacuuming by checking neighbors
@@ -492,8 +492,9 @@ HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_ti
 	FmgrInfo   *normprocinfo;
 	HnswElement entryPoint;
 	HnswElement element;
-	int			m;
+	int			m = HnswGetM(index);
 	int			efConstruction = HnswGetEfConstruction(index);
+	double		ml = HnswGetMl(m);
 	FmgrInfo   *procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
 	Oid			collation = index->rd_indcollation[0];
 	HnswElement dup;
@@ -510,6 +511,10 @@ HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_ti
 			return false;
 	}
 
+	/* Create an element */
+	element = HnswInitElement(heap_tid, m, ml, HnswGetMaxLevel(m));
+	element->vec = DatumGetVector(value);
+
 	/*
 	 * Get a shared lock. This allows vacuum to ensure no in-flight inserts
 	 * before repairing graph. Use a page lock so it does not interfere with
@@ -517,12 +522,8 @@ HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_ti
 	 */
 	LockPage(index, HNSW_UPDATE_LOCK, lockmode);
 
-	/* Get m and entry point */
+	/* Get entry point */
-	HnswGetMetaPageInfo(index, &m, &entryPoint);
+	entryPoint = HnswGetEntryPoint(index);
-
-	/* Create an element */
-	element = HnswInitElement(heap_tid, m, HnswGetMl(m), HnswGetMaxLevel(m));
-	element->vec = DatumGetVector(value);
 
 	/* Prevent concurrent inserts when likely updating entry point */
 	if (entryPoint == NULL || element->level > entryPoint->level)

src/hnswscan.c

@@ -19,11 +19,7 @@ GetScanItems(IndexScanDesc scan, Datum q)
 	Oid			collation = so->collation;
 	List	   *ep;
 	List	   *w;
-	int			m;
+	HnswElement entryPoint = HnswGetEntryPoint(index);
-	HnswElement entryPoint;
-
-	/* Get m and entry point */
-	HnswGetMetaPageInfo(index, &m, &entryPoint);
 
 	if (entryPoint == NULL)
 		return NIL;
@@ -32,11 +28,11 @@ GetScanItems(IndexScanDesc scan, Datum q)
 
 	for (int lc = entryPoint->level; lc >= 1; lc--)
 	{
-		w = HnswSearchLayer(q, ep, 1, lc, index, procinfo, collation, m, false, NULL);
+		w = HnswSearchLayer(q, ep, 1, lc, index, procinfo, collation, false, NULL);
 		ep = w;
 	}
 
-	return HnswSearchLayer(q, ep, hnsw_ef_search, 0, index, procinfo, collation, m, false, NULL);
+	return HnswSearchLayer(q, ep, hnsw_ef_search, 0, index, procinfo, collation, false, NULL);
 }
 
 /*
@@ -62,33 +58,6 @@ GetDimensions(Relation index)
 	return dimensions;
 }
 
-/*
- * Get scan value
- */
-static Datum
-GetScanValue(IndexScanDesc scan)
-{
-	HnswScanOpaque so = (HnswScanOpaque) scan->opaque;
-	Datum		value;
-
-	if (scan->orderByData->sk_flags & SK_ISNULL)
-		value = PointerGetDatum(InitVector(GetDimensions(scan->indexRelation)));
-	else
-	{
-		value = scan->orderByData->sk_argument;
-
-		/* Value should not be compressed or toasted */
-		Assert(!VARATT_IS_COMPRESSED(DatumGetPointer(value)));
-		Assert(!VARATT_IS_EXTENDED(DatumGetPointer(value)));
-
-		/* Fine if normalization fails */
-		if (so->normprocinfo != NULL)
-			HnswNormValue(so->normprocinfo, so->collation, &value, NULL);
-	}
-
-	return value;
-}
-
 /*
  * Prepare for an index scan
  */
@@ -101,6 +70,7 @@ hnswbeginscan(Relation index, int nkeys, int norderbys)
 	scan = RelationGetIndexScan(index, nkeys, norderbys);
 
 	so = (HnswScanOpaque) palloc(sizeof(HnswScanOpaqueData));
+	so->buf = InvalidBuffer;
 	so->first = true;
 	so->tmpCtx = AllocSetContextCreate(CurrentMemoryContext,
 									   "Hnsw scan temporary context",
@@ -113,12 +83,6 @@ hnswbeginscan(Relation index, int nkeys, int norderbys)
 
 	scan->opaque = so;
 
-	/*
-	 * Get a shared lock. This allows vacuum to ensure no in-flight scans
-	 * before marking tuples as deleted.
-	 */
-	LockPage(scan->indexRelation, HNSW_SCAN_LOCK, ShareLock);
-
 	return scan;
 }
 
@@ -166,46 +130,72 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
 		if (scan->orderByData == NULL)
 			elog(ERROR, "cannot scan hnsw index without order");
 
-		/* Get scan value */
+		if (scan->orderByData->sk_flags & SK_ISNULL)
-		value = GetScanValue(scan);
+			value = PointerGetDatum(InitVector(GetDimensions(scan->indexRelation)));
+		else
+		{
+			value = scan->orderByData->sk_argument;
+
+			/* Value should not be compressed or toasted */
+			Assert(!VARATT_IS_COMPRESSED(DatumGetPointer(value)));
+			Assert(!VARATT_IS_EXTENDED(DatumGetPointer(value)));
+
+			/* Fine if normalization fails */
+			if (so->normprocinfo != NULL)
+				HnswNormValue(so->normprocinfo, so->collation, &value, NULL);
+		}
+
+		/*
+		 * Get a shared lock. This allows vacuum to ensure no in-flight scans
+		 * before marking tuples as deleted.
+		 */
+		LockPage(scan->indexRelation, HNSW_SCAN_LOCK, ShareLock);
 
 		so->w = GetScanItems(scan, value);
 
+		/* Release shared lock */
+		UnlockPage(scan->indexRelation, HNSW_SCAN_LOCK, ShareLock);
+
 		so->first = false;
 	}
 
 	while (list_length(so->w) > 0)
 	{
 		HnswCandidate *hc = llast(so->w);
-		ItemPointer heaptid;
+		ItemPointer tid;
+		BlockNumber indexblkno;
 
-		/* Move to next element if no valid heap TIDs */
+		/* Move to next element if no valid heap tids */
 		if (list_length(hc->element->heaptids) == 0)
 		{
 			so->w = list_delete_last(so->w);
 			continue;
 		}
 
-		heaptid = llast(hc->element->heaptids);
+		tid = llast(hc->element->heaptids);
+		indexblkno = hc->element->blkno;
 
 		hc->element->heaptids = list_delete_last(hc->element->heaptids);
 
 		MemoryContextSwitchTo(oldCtx);
 
 #if PG_VERSION_NUM >= 120000
-		scan->xs_heaptid = *heaptid;
+		scan->xs_heaptid = *tid;
 #else
-		scan->xs_ctup.t_self = *heaptid;
+		scan->xs_ctup.t_self = *tid;
 #endif
 
+		/* Unpin buffer */
+		if (BufferIsValid(so->buf))
+			ReleaseBuffer(so->buf);
+
 		/*
-		 * Typically, an index scan must maintain a pin on the index page
+		 * An index scan must maintain a pin on the index page holding the
-		 * holding the item last returned by amgettuple. However, this is not
+		 * item last returned by amgettuple
-		 * needed with the current vacuum strategy, which ensures scans do not
-		 * visit tuples in danger of being marked as deleted.
 		 *
 		 * https://www.postgresql.org/docs/current/index-locking.html
 		 */
+		so->buf = ReadBuffer(scan->indexRelation, indexblkno);
 
 		scan->xs_recheckorderby = false;
 		return true;
@@ -223,8 +213,9 @@ hnswendscan(IndexScanDesc scan)
 {
 	HnswScanOpaque so = (HnswScanOpaque) scan->opaque;
 
-	/* Release shared lock */
+	/* Release pin */
-	UnlockPage(scan->indexRelation, HNSW_SCAN_LOCK, ShareLock);
+	if (BufferIsValid(so->buf))
+		ReleaseBuffer(so->buf);
 
 	MemoryContextDelete(so->tmpCtx);
 

src/hnswutils.c

@@ -210,43 +210,25 @@ HnswInitElementFromBlock(BlockNumber blkno, OffsetNumber offno)
 }
 
 /*
- * Get the metapage info
+ * Get the entry point
  */
-void
+HnswElement
-HnswGetMetaPageInfo(Relation index, int *m, HnswElement * entryPoint)
+HnswGetEntryPoint(Relation index)
 {
 	Buffer		buf;
 	Page		page;
 	HnswMetaPage metap;
+	HnswElement entryPoint = NULL;
 
 	buf = ReadBuffer(index, HNSW_METAPAGE_BLKNO);
 	LockBuffer(buf, BUFFER_LOCK_SHARE);
 	page = BufferGetPage(buf);
 	metap = HnswPageGetMeta(page);
 
-	if (m != NULL)
+	if (BlockNumberIsValid(metap->entryBlkno))
-		*m = metap->m;
+		entryPoint = HnswInitElementFromBlock(metap->entryBlkno, metap->entryOffno);
-
-	if (entryPoint != NULL)
-	{
-		if (BlockNumberIsValid(metap->entryBlkno))
-			*entryPoint = HnswInitElementFromBlock(metap->entryBlkno, metap->entryOffno);
-		else
-			*entryPoint = NULL;
-	}
 
 	UnlockReleaseBuffer(buf);
-}
-
-/*
- * Get the entry point
- */
-HnswElement
-HnswGetEntryPoint(Relation index)
-{
-	HnswElement entryPoint;
-
-	HnswGetMetaPageInfo(index, NULL, &entryPoint);
 
 	return entryPoint;
 }
@@ -355,9 +337,10 @@ HnswSetNeighborTuple(HnswNeighborTuple ntup, HnswElement e, int m)
  * Load neighbors from page
  */
 static void
-LoadNeighborsFromPage(HnswElement element, Relation index, Page page, int m)
+LoadNeighborsFromPage(HnswElement element, Relation index, Page page)
 {
 	HnswNeighborTuple ntup = (HnswNeighborTuple) PageGetItem(page, PageGetItemId(page, element->neighborOffno));
+	int			m = HnswGetM(index);
 	int			neighborCount = (element->level + 2) * m;
 
 	Assert(HnswIsNeighborTuple(ntup));
@@ -398,7 +381,7 @@ LoadNeighborsFromPage(HnswElement element, Relation index, Page page, int m)
  * Load neighbors
  */
 void
-HnswLoadNeighbors(HnswElement element, Relation index, int m)
+HnswLoadNeighbors(HnswElement element, Relation index)
 {
 	Buffer		buf;
 	Page		page;
@@ -407,7 +390,7 @@ HnswLoadNeighbors(HnswElement element, Relation index, int m)
 	LockBuffer(buf, BUFFER_LOCK_SHARE);
 	page = BufferGetPage(buf);
 
-	LoadNeighborsFromPage(element, index, page, m);
+	LoadNeighborsFromPage(element, index, page);
 
 	UnlockReleaseBuffer(buf);
 }
@@ -560,7 +543,7 @@ AddToVisited(HTAB *v, HnswCandidate * hc, Relation index, bool *found)
  * Algorithm 2 from paper
  */
 List *
-HnswSearchLayer(Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool inserting, HnswElement skipElement)
+HnswSearchLayer(Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, bool inserting, HnswElement skipElement)
 {
 	ListCell   *lc2;
 
@@ -615,7 +598,7 @@ HnswSearchLayer(Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *pro
 			break;
 
 		if (c->element->neighbors == NULL)
-			HnswLoadNeighbors(c->element, index, m);
+			HnswLoadNeighbors(c->element, index);
 
 		/* Get the neighborhood at layer lc */
 		neighborhood = &c->element->neighbors[lc];
@@ -973,7 +956,7 @@ HnswInsertElement(HnswElement element, HnswElement entryPoint, Relation index, F
 	/* 1st phase: greedy search to insert level */
 	for (int lc = entryLevel; lc >= level + 1; lc--)
 	{
-		w = HnswSearchLayer(q, ep, 1, lc, index, procinfo, collation, m, true, skipElement);
+		w = HnswSearchLayer(q, ep, 1, lc, index, procinfo, collation, true, skipElement);
 		ep = w;
 	}
 
@@ -991,7 +974,7 @@ HnswInsertElement(HnswElement element, HnswElement entryPoint, Relation index, F
 		List	   *neighbors;
 		List	   *lw;
 
-		w = HnswSearchLayer(q, ep, efConstruction, lc, index, procinfo, collation, m, true, skipElement);
+		w = HnswSearchLayer(q, ep, efConstruction, lc, index, procinfo, collation, true, skipElement);
 
 		/* Elements being deleted or skipped can help with search */
 		/* but should be removed before selecting neighbors */

src/hnswvacuum.c

@@ -330,10 +330,7 @@ RepairGraph(HnswVacuumState * vacuumstate)
 	BufferAccessStrategy bas = vacuumstate->bas;
 	BlockNumber blkno = HNSW_HEAD_BLKNO;
 
-	/*
+	/* Wait for inserts to complete */
-	 * Wait for inserts to complete. Inserts before this point may have
-	 * neighbors about to be deleted. Inserts after this point will not.
-	 */
 	LockPage(index, HNSW_UPDATE_LOCK, ExclusiveLock);
 	UnlockPage(index, HNSW_UPDATE_LOCK, ExclusiveLock);
 
@@ -446,11 +443,7 @@ MarkDeleted(HnswVacuumState * vacuumstate)
 	Relation	index = vacuumstate->index;
 	BufferAccessStrategy bas = vacuumstate->bas;
 
-	/*
+	/* Wait for selects to complete */
-	 * Wait for index scans to complete. Scans before this point may contain
-	 * tuples about to be deleted. Scans after this point will not, since the
-	 * graph has been repaired.
-	 */
 	LockPage(index, HNSW_SCAN_LOCK, ExclusiveLock);
 	UnlockPage(index, HNSW_SCAN_LOCK, ExclusiveLock);
 
@@ -589,6 +582,7 @@ InitVacuumState(HnswVacuumState * vacuumstate, IndexVacuumInfo *info, IndexBulkD
 	vacuumstate->stats = stats;
 	vacuumstate->callback = callback;
 	vacuumstate->callback_state = callback_state;
+	vacuumstate->m = HnswGetM(index);
 	vacuumstate->efConstruction = HnswGetEfConstruction(index);
 	vacuumstate->bas = GetAccessStrategy(BAS_BULKREAD);
 	vacuumstate->procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
@@ -598,9 +592,6 @@ InitVacuumState(HnswVacuumState * vacuumstate, IndexVacuumInfo *info, IndexBulkD
 												"Hnsw vacuum temporary context",
 												ALLOCSET_DEFAULT_SIZES);
 
-	/* Get m from metapage */
-	HnswGetMetaPageInfo(index, &vacuumstate->m, NULL);
-
 	/* Create hash table */
 	hash_ctl.keysize = sizeof(ItemPointerData);
 	hash_ctl.entrysize = sizeof(ItemPointerData);

src/ivfflat.c

@@ -71,7 +71,7 @@ ivfflatcostestimate(PlannerInfo *root, IndexPath *path, double loop_count,
 	int			lists;
 	double		ratio;
 	double		spc_seq_page_cost;
-	Relation	index;
+	Relation	indexRel;
 #if PG_VERSION_NUM < 120000
 	List	   *qinfos;
 #endif
@@ -89,9 +89,9 @@ ivfflatcostestimate(PlannerInfo *root, IndexPath *path, double loop_count,
 
 	MemSet(&costs, 0, sizeof(costs));
 
-	index = index_open(path->indexinfo->indexoid, NoLock);
+	indexRel = index_open(path->indexinfo->indexoid, NoLock);
-	IvfflatGetMetaPageInfo(index, &lists, NULL);
+	lists = IvfflatGetLists(indexRel);
-	index_close(index, NoLock);
+	index_close(indexRel, NoLock);
 
 	/* Get the ratio of lists that we need to visit */
 	ratio = ((double) ivfflat_probes) / lists;

src/ivfflat.h

@@ -244,10 +244,8 @@ typedef struct IvfflatScanList
 typedef struct IvfflatScanOpaqueData
 {
 	int			probes;
-	int			dimensions;
 	bool		first;
 	Buffer		buf;
-	ItemPointerData heaptid;
 
 	/* Sorting */
 	Tuplesortstate *sortstate;
@@ -280,7 +278,6 @@ void		IvfflatKmeans(Relation index, VectorArray samples, VectorArray centers);
 FmgrInfo   *IvfflatOptionalProcInfo(Relation rel, uint16 procnum);
 bool		IvfflatNormValue(FmgrInfo *procinfo, Oid collation, Datum *value, Vector * result);
 int			IvfflatGetLists(Relation index);
-void		IvfflatGetMetaPageInfo(Relation index, int *lists, int *dimensions);
 void		IvfflatUpdateList(Relation index, ListInfo listInfo, BlockNumber insertPage, BlockNumber originalInsertPage, BlockNumber startPage, ForkNumber forkNum);
 void		IvfflatCommitBuffer(Buffer buf, GenericXLogState *state);
 void		IvfflatAppendPage(Relation index, Buffer *buf, Page *page, GenericXLogState **state, ForkNumber forkNum);

src/ivfscan.c

@@ -31,36 +31,36 @@ CompareLists(const pairingheap_node *a, const pairingheap_node *b, void *arg)
 static void
 GetScanLists(IndexScanDesc scan, Datum value)
 {
-	IvfflatScanOpaque so = (IvfflatScanOpaque) scan->opaque;
+	Buffer		cbuf;
+	Page		cpage;
+	IvfflatList list;
+	OffsetNumber offno;
+	OffsetNumber maxoffno;
 	BlockNumber nextblkno = IVFFLAT_HEAD_BLKNO;
 	int			listCount = 0;
+	IvfflatScanOpaque so = (IvfflatScanOpaque) scan->opaque;
+	double		distance;
+	IvfflatScanList *scanlist;
 	double		maxDistance = DBL_MAX;
 
 	/* Search all list pages */
 	while (BlockNumberIsValid(nextblkno))
 	{
-		Buffer		cbuf;
-		Page		cpage;
-		OffsetNumber maxoffno;
-
 		cbuf = ReadBuffer(scan->indexRelation, nextblkno);
 		LockBuffer(cbuf, BUFFER_LOCK_SHARE);
 		cpage = BufferGetPage(cbuf);
 
 		maxoffno = PageGetMaxOffsetNumber(cpage);
 
-		for (OffsetNumber offno = FirstOffsetNumber; offno <= maxoffno; offno = OffsetNumberNext(offno))
+		for (offno = FirstOffsetNumber; offno <= maxoffno; offno = OffsetNumberNext(offno))
 		{
-			IvfflatList list = (IvfflatList) PageGetItem(cpage, PageGetItemId(cpage, offno));
+			list = (IvfflatList) PageGetItem(cpage, PageGetItemId(cpage, offno));
-			double		distance;
 
 			/* Use procinfo from the index instead of scan key for performance */
 			distance = DatumGetFloat8(FunctionCall2Coll(so->procinfo, so->collation, PointerGetDatum(&list->center), value));
 
 			if (listCount < so->probes)
 			{
-				IvfflatScanList *scanlist;
-
 				scanlist = &so->lists[listCount];
 				scanlist->startPage = list->startPage;
 				scanlist->distance = distance;
@@ -75,8 +75,6 @@ GetScanLists(IndexScanDesc scan, Datum value)
 			}
 			else if (distance < maxDistance)
 			{
-				IvfflatScanList *scanlist;
-
 				/* Remove */
 				scanlist = (IvfflatScanList *) pairingheap_remove_first(so->listQueue);
 
@@ -103,6 +101,14 @@ static void
 GetScanItems(IndexScanDesc scan, Datum value)
 {
 	IvfflatScanOpaque so = (IvfflatScanOpaque) scan->opaque;
+	Buffer		buf;
+	Page		page;
+	IndexTuple	itup;
+	BlockNumber searchPage;
+	OffsetNumber offno;
+	OffsetNumber maxoffno;
+	Datum		datum;
+	bool		isnull;
 	TupleDesc	tupdesc = RelationGetDescr(scan->indexRelation);
 	double		tuples = 0;
 
@@ -122,32 +128,19 @@ GetScanItems(IndexScanDesc scan, Datum value)
 	/* Search closest probes lists */
 	while (!pairingheap_is_empty(so->listQueue))
 	{
-		BlockNumber searchPage = ((IvfflatScanList *) pairingheap_remove_first(so->listQueue))->startPage;
+		searchPage = ((IvfflatScanList *) pairingheap_remove_first(so->listQueue))->startPage;
 
 		/* Search all entry pages for list */
 		while (BlockNumberIsValid(searchPage))
 		{
-			Buffer		buf;
-			Page		page;
-			OffsetNumber maxoffno;
-
 			buf = ReadBufferExtended(scan->indexRelation, MAIN_FORKNUM, searchPage, RBM_NORMAL, bas);
 			LockBuffer(buf, BUFFER_LOCK_SHARE);
 			page = BufferGetPage(buf);
 			maxoffno = PageGetMaxOffsetNumber(page);
 
-			for (OffsetNumber offno = FirstOffsetNumber; offno <= maxoffno; offno = OffsetNumberNext(offno))
+			for (offno = FirstOffsetNumber; offno <= maxoffno; offno = OffsetNumberNext(offno))
 			{
-				IndexTuple	itup;
+				itup = (IndexTuple) PageGetItem(page, PageGetItemId(page, offno));
-				Datum		datum;
-				bool		isnull;
-				ItemId		itemid = PageGetItemId(page, offno);
-
-				/* Skip dead tuples */
-				if (scan->ignore_killed_tuples && ItemIdIsDead(itemid))
-					continue;
-
-				itup = (IndexTuple) PageGetItem(page, itemid);
 				datum = index_getattr(itup, 1, tupdesc, &isnull);
 
 				/*
@@ -188,52 +181,26 @@ GetScanItems(IndexScanDesc scan, Datum value)
 }
 
 /*
- * Mark prior tuple as dead
+ * Get dimensions from metapage
  */
-static void
+static int
-MarkPriorTupleDead(IndexScanDesc scan)
+GetDimensions(Relation index)
 {
-	IvfflatScanOpaque so = (IvfflatScanOpaque) scan->opaque;
+	Buffer		buf;
-	Buffer		buf = so->buf;
 	Page		page;
-	OffsetNumber maxoffno;
+	IvfflatMetaPage metap;
+	int			dimensions;
 
-	/* Safety check */
+	buf = ReadBuffer(index, IVFFLAT_METAPAGE_BLKNO);
-	if (!BufferIsValid(so->buf) || !ItemPointerIsValid(&so->heaptid))
-		return;
-
-	/* Only a shared locked is needed for ItemIdMarkDead */
 	LockBuffer(buf, BUFFER_LOCK_SHARE);
 	page = BufferGetPage(buf);
-	maxoffno = PageGetMaxOffsetNumber(page);
+	metap = IvfflatPageGetMeta(page);
 
-	for (OffsetNumber offno = FirstOffsetNumber; offno <= maxoffno; offno = OffsetNumberNext(offno))
+	dimensions = metap->dimensions;
-	{
-		ItemId		itemid = PageGetItemId(page, offno);
-		IndexTuple	itup = (IndexTuple) PageGetItem(page, itemid);
 
-		/*
+	UnlockReleaseBuffer(buf);
-		 * Find tuple. Since buffer has been pinned, tuple cannot have been
-		 * vacuumed (and heap TID reused).
-		 */
-		if (ItemPointerEquals(&itup->t_tid, &so->heaptid))
-		{
-			/*
-			 * Make sure tuple has not already been marked dead to avoid extra
-			 * WAL if wal_log_hints or data checksums enabled
-			 */
-			if (!ItemIdIsDead(itemid))
-			{
-				ItemIdMarkDead(itemid);
-				MarkBufferDirtyHint(buf, true);
-			}
 
-			break;
+	return dimensions;
-		}
-	}
-
-	/* Unlock buffer */
-	LockBuffer(buf, BUFFER_LOCK_UNLOCK);
 }
 
 /*
@@ -245,7 +212,6 @@ ivfflatbeginscan(Relation index, int nkeys, int norderbys)
 	IndexScanDesc scan;
 	IvfflatScanOpaque so;
 	int			lists;
-	int			dimensions;
 	AttrNumber	attNums[] = {1};
 	Oid			sortOperators[] = {Float8LessOperator};
 	Oid			sortCollations[] = {InvalidOid};
@@ -253,9 +219,7 @@ ivfflatbeginscan(Relation index, int nkeys, int norderbys)
 	int			probes = ivfflat_probes;
 
 	scan = RelationGetIndexScan(index, nkeys, norderbys);
-
+	lists = IvfflatGetLists(scan->indexRelation);
-	/* Get lists and dimensions from metapage */
-	IvfflatGetMetaPageInfo(index, &lists, &dimensions);
 
 	if (probes > lists)
 		probes = lists;
@@ -263,9 +227,7 @@ ivfflatbeginscan(Relation index, int nkeys, int norderbys)
 	so = (IvfflatScanOpaque) palloc(offsetof(IvfflatScanOpaqueData, lists) + probes * sizeof(IvfflatScanList));
 	so->buf = InvalidBuffer;
 	so->first = true;
-	ItemPointerSetInvalid(&so->heaptid);
 	so->probes = probes;
-	so->dimensions = dimensions;
 
 	/* Set support functions */
 	so->procinfo = index_getprocinfo(index, 1, IVFFLAT_DISTANCE_PROC);
@@ -279,7 +241,7 @@ ivfflatbeginscan(Relation index, int nkeys, int norderbys)
 	so->tupdesc = CreateTemplateTupleDesc(3, false);
 #endif
 	TupleDescInitEntry(so->tupdesc, (AttrNumber) 1, "distance", FLOAT8OID, -1, 0);
-	TupleDescInitEntry(so->tupdesc, (AttrNumber) 2, "heaptid", TIDOID, -1, 0);
+	TupleDescInitEntry(so->tupdesc, (AttrNumber) 2, "tid", TIDOID, -1, 0);
 	TupleDescInitEntry(so->tupdesc, (AttrNumber) 3, "indexblkno", INT4OID, -1, 0);
 
 	/* Prep sort */
@@ -312,7 +274,6 @@ ivfflatrescan(IndexScanDesc scan, ScanKey keys, int nkeys, ScanKey orderbys, int
 #endif
 
 	so->first = true;
-	ItemPointerSetInvalid(&so->heaptid);
 	pairingheap_reset(so->listQueue);
 
 	if (keys && scan->numberOfKeys > 0)
@@ -348,7 +309,7 @@ ivfflatgettuple(IndexScanDesc scan, ScanDirection dir)
 			elog(ERROR, "cannot scan ivfflat index without order");
 
 		if (scan->orderByData->sk_flags & SK_ISNULL)
-			value = PointerGetDatum(InitVector(so->dimensions));
+			value = PointerGetDatum(InitVector(GetDimensions(scan->indexRelation)));
 		else
 		{
 			value = scan->orderByData->sk_argument;
@@ -370,27 +331,18 @@ ivfflatgettuple(IndexScanDesc scan, ScanDirection dir)
 		if (value != scan->orderByData->sk_argument)
 			pfree(DatumGetPointer(value));
 	}
-	else
-	{
-		/* Mark prior tuple as dead */
-		if (scan->kill_prior_tuple)
-			MarkPriorTupleDead(scan);
-	}
 
 	if (tuplesort_gettupleslot(so->sortstate, true, false, so->slot, NULL))
 	{
-		ItemPointer heaptid = (ItemPointer) DatumGetPointer(slot_getattr(so->slot, 2, &so->isnull));
+		ItemPointer tid = (ItemPointer) DatumGetPointer(slot_getattr(so->slot, 2, &so->isnull));
 		BlockNumber indexblkno = DatumGetInt32(slot_getattr(so->slot, 3, &so->isnull));
 
 #if PG_VERSION_NUM >= 120000
-		scan->xs_heaptid = *heaptid;
+		scan->xs_heaptid = *tid;
 #else
-		scan->xs_ctup.t_self = *heaptid;
+		scan->xs_ctup.t_self = *tid;
 #endif
 
-		/* Keep track of info needed to mark tuple as dead */
-		so->heaptid = *heaptid;
-
 		/* Unpin buffer */
 		if (BufferIsValid(so->buf))
 			ReleaseBuffer(so->buf);

src/ivfutils.c

@@ -172,29 +172,6 @@ IvfflatAppendPage(Relation index, Buffer *buf, Page *page, GenericXLogState **st
 	*buf = newbuf;
 }
 
-/*
- * Get the metapage info
- */
-void
-IvfflatGetMetaPageInfo(Relation index, int *lists, int *dimensions)
-{
-	Buffer		buf;
-	Page		page;
-	IvfflatMetaPage metap;
-
-	buf = ReadBuffer(index, IVFFLAT_METAPAGE_BLKNO);
-	LockBuffer(buf, BUFFER_LOCK_SHARE);
-	page = BufferGetPage(buf);
-	metap = IvfflatPageGetMeta(page);
-
-	*lists = metap->lists;
-
-	if (dimensions != NULL)
-		*dimensions = metap->dimensions;
-
-	UnlockReleaseBuffer(buf);
-}
-
 /*
  * Update the start or insert page of a list
  */

src/vector.c

@@ -684,6 +684,49 @@ cosine_distance(PG_FUNCTION_ARGS)
 	PG_RETURN_FLOAT8(1.0 - similarity);
 }
 
+/*
+ * Get the angular distance between two vectors
+ */
+PGDLLEXPORT PG_FUNCTION_INFO_V1(angular_distance);
+Datum
+angular_distance(PG_FUNCTION_ARGS)
+{
+	Vector	   *a = PG_GETARG_VECTOR_P(0);
+	Vector	   *b = PG_GETARG_VECTOR_P(1);
+	float	   *ax = a->x;
+	float	   *bx = b->x;
+	float		distance = 0.0;
+	float		norma = 0.0;
+	float		normb = 0.0;
+	double		similarity;
+
+	CheckDims(a, b);
+
+	/* Auto-vectorized */
+	for (int i = 0; i < a->dim; i++)
+	{
+		distance += ax[i] * bx[i];
+		norma += ax[i] * ax[i];
+		normb += bx[i] * bx[i];
+	}
+
+	similarity = (double) distance / sqrt((double) norma * (double) normb);
+
+#ifdef _MSC_VER
+	/* /fp:fast may not propagate NaN */
+	if (isnan(similarity))
+		PG_RETURN_FLOAT8(NAN);
+#endif
+
+	/* Prevent NaN with acos with loss of precision */
+	if (similarity > 1)
+		similarity = 1;
+	else if (similarity < -1)
+		similarity = -1;
+
+	PG_RETURN_FLOAT8(acos(similarity) / M_PI);
+}
+
 /*
  * Get the distance for spherical k-means
  * Currently uses angular distance since needs to satisfy triangle inequality

test/expected/functions.out

@@ -106,12 +106,6 @@ SELECT cosine_distance('[1,1]', '[1,1]');
                0
 (1 row)
 
-SELECT cosine_distance('[1,0]', '[0,2]');
- cosine_distance 
------------------
-               1
-(1 row)
-
 SELECT cosine_distance('[1,1]', '[-1,-1]');
  cosine_distance 
 -----------------
@@ -158,6 +152,56 @@ SELECT l1_distance('[3e38]', '[-3e38]');
     Infinity
 (1 row)
 
+SELECT angular_distance('[1,2]', '[2,4]');
+ angular_distance 
+------------------
+                0
+(1 row)
+
+SELECT angular_distance('[1,2]', '[0,0]');
+ angular_distance 
+------------------
+              NaN
+(1 row)
+
+SELECT angular_distance('[1,1]', '[1,1]');
+ angular_distance 
+------------------
+                0
+(1 row)
+
+SELECT angular_distance('[1,0]', '[0,2]');
+ angular_distance 
+------------------
+              0.5
+(1 row)
+
+SELECT angular_distance('[1,1]', '[-1,-1]');
+ angular_distance 
+------------------
+                1
+(1 row)
+
+SELECT angular_distance('[1,2]', '[3]');
+ERROR:  different vector dimensions 2 and 1
+SELECT angular_distance('[1,1]', '[1.1,1.1]');
+ angular_distance 
+------------------
+                0
+(1 row)
+
+SELECT angular_distance('[1,1]', '[-1.1,-1.1]');
+ angular_distance 
+------------------
+                1
+(1 row)
+
+SELECT angular_distance('[3e38]', '[3e38]');
+ angular_distance 
+------------------
+              NaN
+(1 row)
+
 SELECT avg(v) FROM unnest(ARRAY['[1,2,3]'::vector, '[3,5,7]']) v;
     avg    
 -----------

test/sql/functions.sql

@@ -25,7 +25,6 @@ SELECT inner_product('[3e38]', '[3e38]');
 SELECT cosine_distance('[1,2]', '[2,4]');
 SELECT cosine_distance('[1,2]', '[0,0]');
 SELECT cosine_distance('[1,1]', '[1,1]');
-SELECT cosine_distance('[1,0]', '[0,2]');
 SELECT cosine_distance('[1,1]', '[-1,-1]');
 SELECT cosine_distance('[1,2]', '[3]');
 SELECT cosine_distance('[1,1]', '[1.1,1.1]');
@@ -37,6 +36,16 @@ SELECT l1_distance('[0,0]', '[0,1]');
 SELECT l1_distance('[1,2]', '[3]');
 SELECT l1_distance('[3e38]', '[-3e38]');
 
+SELECT angular_distance('[1,2]', '[2,4]');
+SELECT angular_distance('[1,2]', '[0,0]');
+SELECT angular_distance('[1,1]', '[1,1]');
+SELECT angular_distance('[1,0]', '[0,2]');
+SELECT angular_distance('[1,1]', '[-1,-1]');
+SELECT angular_distance('[1,2]', '[3]');
+SELECT angular_distance('[1,1]', '[1.1,1.1]');
+SELECT angular_distance('[1,1]', '[-1.1,-1.1]');
+SELECT angular_distance('[3e38]', '[3e38]');
+
 SELECT avg(v) FROM unnest(ARRAY['[1,2,3]'::vector, '[3,5,7]']) v;
 SELECT avg(v) FROM unnest(ARRAY['[1,2,3]'::vector, '[3,5,7]', NULL]) v;
 SELECT avg(v) FROM unnest(ARRAY[]::vector[]) v;

test/t/018_ivfflat_deletes.pl

@@ -1,43 +0,0 @@
-use strict;
-use warnings;
-use PostgresNode;
-use TestLib;
-use Test::More;
-
-my $dim = 3;
-
-my $array_sql = join(",", ('random()') x $dim);
-
-# Initialize node
-my $node = get_new_node('node');
-$node->init;
-$node->start;
-
-# Create table and index
-$node->safe_psql("postgres", "CREATE EXTENSION vector;");
-$node->safe_psql("postgres", "CREATE TABLE tst (i serial, v vector($dim));");
-$node->safe_psql("postgres",
-	"INSERT INTO tst (v) SELECT ARRAY[$array_sql] FROM generate_series(1, 10000) i;"
-);
-$node->safe_psql("postgres", "CREATE INDEX ON tst USING ivfflat (v vector_l2_ops);");
-
-# Delete data
-$node->safe_psql("postgres", "DELETE FROM tst WHERE i % 100 != 0;");
-
-my $exp = $node->safe_psql("postgres", qq(
-	SET enable_indexscan = off;
-	SELECT i FROM tst ORDER BY v <-> '[0,0,0]';
-));
-
-# Run twice to make sure correct tuples marked as dead
-for (1 .. 2)
-{
-	my $res = $node->safe_psql("postgres", qq(
-		SET enable_seqscan = off;
-		SET ivfflat.probes = 100;
-		SELECT i FROM tst ORDER BY v <-> '[0,0,0]';
-	));
-	is($res, $exp);
-}
-
-done_testing();

vector.control

@@ -1,4 +1,4 @@
-comment = 'vector data type and ivfflat and hnsw access methods'
+comment = 'vector data type and ivfflat access method'
 default_version = '0.5.0'
 module_pathname = '$libdir/vector'
 relocatable = true