Improved test for angular distance [skip ci]

CHANGELOG.md

@@ -1,7 +1,6 @@
-## 0.5.1 (2023-10-10)
+## 0.5.1 (unreleased)
 
-- Improved performance of HNSW index builds
+- Added `angular_distance` function
-- Added check for MVCC-compliant snapshot for index scans
 
 ## 0.5.0 (2023-08-28)
 

META.json

@@ -2,7 +2,7 @@
 	"name": "vector",
 	"abstract": "Open-source vector similarity search for Postgres",
 	"description": "Supports L2 distance, inner product, and cosine distance",
-	"version": "0.5.1",
+	"version": "0.5.0",
 	"maintainer": [
 		"Andrew Kane <andrew@ankane.org>"
 	],
@@ -20,7 +20,7 @@
 		"vector": {
 			"file": "sql/vector.sql",
 			"docfile": "README.md",
-			"version": "0.5.1",
+			"version": "0.5.0",
 			"abstract": "Open-source vector similarity search for Postgres"
 		}
 	},

Makefile

@@ -1,5 +1,5 @@
 EXTENSION = vector
-EXTVERSION = 0.5.1
+EXTVERSION = 0.5.0
 
 MODULE_big = vector
 DATA = $(wildcard sql/*--*.sql)
@@ -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

@@ -1,11 +1,11 @@
 EXTENSION = vector
-EXTVERSION = 0.5.1
+EXTVERSION = 0.5.0
 
 OBJS = src\hnsw.obj src\hnswbuild.obj src\hnswinsert.obj src\hnswscan.obj src\hnswutils.obj src\hnswvacuum.obj src\ivfbuild.obj src\ivfflat.obj src\ivfinsert.obj src\ivfkmeans.obj src\ivfscan.obj src\ivfutils.obj src\ivfvacuum.obj src\vector.obj
 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

@@ -18,7 +18,7 @@ Compile and install the extension (supports Postgres 11+)
 
 ```sh
 cd /tmp
-git clone --branch v0.5.1 https://github.com/pgvector/pgvector.git
+git clone --branch v0.5.0 https://github.com/pgvector/pgvector.git
 cd pgvector
 make
 make install # may need sudo
@@ -509,7 +509,7 @@ Then use `nmake` to build:
 
 ```cmd
 set "PGROOT=C:\Program Files\PostgreSQL\15"
-git clone --branch v0.5.1 https://github.com/pgvector/pgvector.git
+git clone --branch v0.5.0 https://github.com/pgvector/pgvector.git
 cd pgvector
 nmake /F Makefile.win
 nmake /F Makefile.win install
@@ -530,7 +530,7 @@ This adds pgvector to the [Postgres image](https://hub.docker.com/_/postgres) (r
 You can also build the image manually:
 
 ```sh
-git clone --branch v0.5.1 https://github.com/pgvector/pgvector.git
+git clone --branch v0.5.0 https://github.com/pgvector/pgvector.git
 cd pgvector
 docker build --build-arg PG_MAJOR=15 -t myuser/pgvector .
 ```
@@ -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

@@ -1,2 +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

@@ -57,8 +57,6 @@
 /* PROGRESS_CREATEIDX_SUBPHASE_INITIALIZE is 1 */
 #define PROGRESS_HNSW_PHASE_LOAD		2
 
-#define HNSW_MAX_SIZE (BLCKSZ - MAXALIGN(SizeOfPageHeaderData) - MAXALIGN(sizeof(HnswPageOpaqueData)) - sizeof(ItemIdData))
-
 #define HNSW_ELEMENT_TUPLE_SIZE(_dim)	MAXALIGN(offsetof(HnswElementTupleData, vec) + VECTOR_SIZE(_dim))
 #define HNSW_NEIGHBOR_TUPLE_SIZE(level, m)	MAXALIGN(offsetof(HnswNeighborTupleData, indextids) + ((level) + 2) * (m) * sizeof(ItemPointerData))
 
@@ -112,13 +110,11 @@ typedef struct HnswCandidate
 {
 	HnswElement element;
 	float		distance;
-	bool		closer;
 }			HnswCandidate;
 
 typedef struct HnswNeighborArray
 {
 	int			length;
-	bool		closerSet;
 	HnswCandidate *items;
 }			HnswNeighborArray;
 
@@ -222,6 +218,7 @@ typedef HnswNeighborTupleData * HnswNeighborTuple;
 typedef struct HnswScanOpaqueData
 {
 	bool		first;
+	Buffer		buf;
 	List	   *w;
 	MemoryContext tmpCtx;
 
@@ -262,16 +259,15 @@ typedef struct HnswVacuumState
 /* Methods */
 int			HnswGetM(Relation index);
 int			HnswGetEfConstruction(Relation index);
-FmgrInfo   *HnswOptionalProcInfo(Relation index, uint16 procnum);
+FmgrInfo   *HnswOptionalProcInfo(Relation rel, uint16 procnum);
 bool		HnswNormValue(FmgrInfo *procinfo, Oid collation, Datum *value, Vector * result);
 void		HnswCommitBuffer(Buffer buf, GenericXLogState *state);
 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);
@@ -288,7 +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/hnswbuild.c

@@ -81,6 +81,7 @@ HnswBuildAppendPage(Relation index, Buffer *buf, Page *page, GenericXLogState **
 	HnswPageGetOpaque(*page)->nextblkno = BufferGetBlockNumber(newbuf);
 
 	/* Commit */
+	MarkBufferDirty(*buf);
 	GenericXLogFinish(*state);
 	UnlockReleaseBuffer(*buf);
 
@@ -117,12 +118,12 @@ CreateElementPages(HnswBuildState * buildstate)
 	ListCell   *lc;
 
 	/* Calculate sizes */
-	maxSize = HNSW_MAX_SIZE;
+	maxSize = BLCKSZ - MAXALIGN(SizeOfPageHeaderData) - MAXALIGN(sizeof(HnswPageOpaqueData));
 	etupSize = HNSW_ELEMENT_TUPLE_SIZE(dimensions);
 
 	/* Allocate once */
 	etup = palloc0(etupSize);
-	ntup = palloc0(BLCKSZ);
+	ntup = palloc0(maxSize);
 
 	/* Prepare first page */
 	buf = HnswNewBuffer(index, forkNum);
@@ -178,6 +179,7 @@ CreateElementPages(HnswBuildState * buildstate)
 	insertPage = BufferGetBlockNumber(buf);
 
 	/* Commit */
+	MarkBufferDirty(buf);
 	GenericXLogFinish(state);
 	UnlockReleaseBuffer(buf);
 
@@ -225,6 +227,7 @@ CreateNeighborPages(HnswBuildState * buildstate)
 			elog(ERROR, "failed to add index item to \"%s\"", RelationGetRelationName(index));
 
 		/* Commit */
+		MarkBufferDirty(buf);
 		GenericXLogFinish(state);
 		UnlockReleaseBuffer(buf);
 	}

src/hnswinsert.c

@@ -135,7 +135,7 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
 	etupSize = HNSW_ELEMENT_TUPLE_SIZE(dimensions);
 	ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(e->level, m);
 	combinedSize = etupSize + ntupSize + sizeof(ItemIdData);
-	maxSize = HNSW_MAX_SIZE;
+	maxSize = BLCKSZ - MAXALIGN(SizeOfPageHeaderData) - MAXALIGN(sizeof(HnswPageOpaqueData));
 	minCombinedSize = etupSize + HNSW_NEIGHBOR_TUPLE_SIZE(0, m) + sizeof(ItemIdData);
 
 	/* Prepare element tuple */
@@ -202,6 +202,8 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
 			HnswInsertAppendPage(index, &newbuf, &newpage, state, page);
 
 			/* Commit */
+			MarkBufferDirty(newbuf);
+			MarkBufferDirty(buf);
 			GenericXLogFinish(state);
 
 			/* Unlock previous buffer */
@@ -268,6 +270,9 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
 	}
 
 	/* Commit */
+	MarkBufferDirty(buf);
+	if (nbuf != buf)
+		MarkBufferDirty(nbuf);
 	GenericXLogFinish(state);
 	UnlockReleaseBuffer(buf);
 	if (nbuf != buf)
@@ -324,7 +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
@@ -386,6 +391,7 @@ HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswE
 					elog(ERROR, "failed to add index item to \"%s\"", RelationGetRelationName(index));
 
 				/* Commit */
+				MarkBufferDirty(buf);
 				GenericXLogFinish(state);
 			}
 			else
@@ -439,6 +445,7 @@ HnswAddDuplicate(Relation index, HnswElement element, HnswElement dup)
 		elog(ERROR, "failed to add index item to \"%s\"", RelationGetRelationName(index));
 
 	/* Commit */
+	MarkBufferDirty(buf);
 	GenericXLogFinish(state);
 	UnlockReleaseBuffer(buf);
 
@@ -485,8 +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;
@@ -503,6 +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
@@ -510,12 +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",
@@ -160,13 +130,20 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
 		if (scan->orderByData == NULL)
 			elog(ERROR, "cannot scan hnsw index without order");
 
-		/* Requires MVCC-compliant snapshot as not able to maintain a pin */
+		if (scan->orderByData->sk_flags & SK_ISNULL)
-		/* https://www.postgresql.org/docs/current/index-locking.html */
+			value = PointerGetDatum(InitVector(GetDimensions(scan->indexRelation)));
-		if (!IsMVCCSnapshot(scan->xs_snapshot))
+		else
-			elog(ERROR, "non-MVCC snapshots are not supported with hnsw");
+		{
+			value = scan->orderByData->sk_argument;
 
-		/* Get scan value */
+			/* Value should not be compressed or toasted */
-		value = GetScanValue(scan);
+			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
@@ -185,27 +162,41 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
 	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);
+
+		/*
+		 * An index scan must maintain a pin on the index page holding the
+		 * item last returned by amgettuple
+		 *
+		 * https://www.postgresql.org/docs/current/index-locking.html
+		 */
+		so->buf = ReadBuffer(scan->indexRelation, indexblkno);
+
 		scan->xs_recheckorderby = false;
 		return true;
 	}
@@ -222,6 +213,10 @@ hnswendscan(IndexScanDesc scan)
 {
 	HnswScanOpaque so = (HnswScanOpaque) scan->opaque;
 
+	/* Release pin */
+	if (BufferIsValid(so->buf))
+		ReleaseBuffer(so->buf);
+
 	MemoryContextDelete(so->tmpCtx);
 
 	pfree(so);

src/hnswutils.c

@@ -38,12 +38,12 @@ HnswGetEfConstruction(Relation index)
  * Get proc
  */
 FmgrInfo *
-HnswOptionalProcInfo(Relation index, uint16 procnum)
+HnswOptionalProcInfo(Relation rel, uint16 procnum)
 {
-	if (!OidIsValid(index_getprocid(index, 1, procnum)))
+	if (!OidIsValid(index_getprocid(rel, 1, procnum)))
 		return NULL;
 
-	return index_getprocinfo(index, 1, procnum);
+	return index_getprocinfo(rel, 1, procnum);
 }
 
 /*
@@ -117,6 +117,7 @@ HnswInitRegisterPage(Relation index, Buffer *buf, Page *page, GenericXLogState *
 void
 HnswCommitBuffer(Buffer buf, GenericXLogState *state)
 {
+	MarkBufferDirty(buf);
 	GenericXLogFinish(state);
 	UnlockReleaseBuffer(buf);
 }
@@ -139,21 +140,9 @@ HnswInitNeighbors(HnswElement element, int m)
 		a = &element->neighbors[lc];
 		a->length = 0;
 		a->items = palloc(sizeof(HnswCandidate) * lm);
-		a->closerSet = false;
 	}
 }
 
-/*
- * Free neighbors
- */
-static void
-HnswFreeNeighbors(HnswElement element)
-{
-	for (int lc = 0; lc <= element->level; lc++)
-		pfree(element->neighbors[lc].items);
-	pfree(element->neighbors);
-}
-
 /*
  * Allocate an element
  */
@@ -185,8 +174,10 @@ HnswInitElement(ItemPointer heaptid, int m, double ml, int maxLevel)
 void
 HnswFreeElement(HnswElement element)
 {
-	HnswFreeNeighbors(element);
 	list_free_deep(element->heaptids);
+	for (int lc = 0; lc <= element->level; lc++)
+		pfree(element->neighbors[lc].items);
+	pfree(element->neighbors);
 	pfree(element->vec);
 	pfree(element);
 }
@@ -219,43 +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;
 }
@@ -364,9 +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));
@@ -407,7 +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;
@@ -416,7 +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);
 }
@@ -569,7 +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;
 
@@ -624,7 +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];
@@ -693,34 +667,6 @@ HnswSearchLayer(Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *pro
 	return w;
 }
 
-/*
- * Compare candidate distances
- */
-static int
-#if PG_VERSION_NUM >= 130000
-CompareCandidateDistances(const ListCell *a, const ListCell *b)
-#else
-CompareCandidateDistances(const void *a, const void *b)
-#endif
-{
-	HnswCandidate *hca = lfirst((ListCell *) a);
-	HnswCandidate *hcb = lfirst((ListCell *) b);
-
-	if (hca->distance < hcb->distance)
-		return 1;
-
-	if (hca->distance > hcb->distance)
-		return -1;
-
-	if (hca->element < hcb->element)
-		return 1;
-
-	if (hca->element > hcb->element)
-		return -1;
-
-	return 0;
-}
-
 /*
  * Calculate the distance between elements
  */
@@ -777,77 +723,33 @@ CheckElementCloser(HnswCandidate * e, List *r, int lc, FmgrInfo *procinfo, Oid c
  * Algorithm 4 from paper
  */
 static List *
-SelectNeighbors(List *c, int m, int lc, FmgrInfo *procinfo, Oid collation, HnswElement e2, HnswCandidate * newCandidate, HnswCandidate * *pruned, bool sortCandidates)
+SelectNeighbors(List *c, int m, int lc, FmgrInfo *procinfo, Oid collation, HnswCandidate * *pruned)
 {
 	List	   *r = NIL;
 	List	   *w = list_copy(c);
 	pairingheap *wd;
-	bool		mustCalculate = !e2->neighbors[lc].closerSet;
-	List	   *added = NIL;
-	bool		removedAny = false;
 
 	if (list_length(w) <= m)
 		return w;
 
 	wd = pairingheap_allocate(CompareNearestCandidates, NULL);
 
-	/* Ensure order of candidates is deterministic for closer caching */
-	if (sortCandidates)
-		list_sort(w, CompareCandidateDistances);
-
 	while (list_length(w) > 0 && list_length(r) < m)
 	{
 		/* Assumes w is already ordered desc */
 		HnswCandidate *e = llast(w);
+		bool		closer;
 
 		w = list_delete_last(w);
 
-		/* Use previous state of r and wd to skip work when possible */
+		closer = CheckElementCloser(e, r, lc, procinfo, collation);
-		if (mustCalculate)
-			e->closer = CheckElementCloser(e, r, lc, procinfo, collation);
-		else if (list_length(added) > 0)
-		{
-			/*
-			 * If the current candidate was closer, we only need to compare it
-			 * with the other candidates that we have added.
-			 */
-			if (e->closer)
-			{
-				e->closer = CheckElementCloser(e, added, lc, procinfo, collation);
 
-				if (!e->closer)
+		if (closer)
-					removedAny = true;
-			}
-			else
-			{
-				/*
-				 * If we have removed any candidates from closer, a candidate
-				 * that was not closer earlier might now be.
-				 */
-				if (removedAny)
-				{
-					e->closer = CheckElementCloser(e, r, lc, procinfo, collation);
-					if (e->closer)
-						added = lappend(added, e);
-				}
-			}
-		}
-		else if (e == newCandidate)
-		{
-			e->closer = CheckElementCloser(e, r, lc, procinfo, collation);
-			if (e->closer)
-				added = lappend(added, e);
-		}
-
-		if (e->closer)
 			r = lappend(r, e);
 		else
 			pairingheap_add(wd, &(CreatePairingHeapNode(e)->ph_node));
 	}
 
-	/* Cached value can only be used in future if sorted deterministically */
-	e2->neighbors[lc].closerSet = sortCandidates;
-
 	/* Keep pruned connections */
 	while (!pairingheap_is_empty(wd) && list_length(r) < m)
 		r = lappend(r, ((HnswPairingHeapNode *) pairingheap_remove_first(wd))->inner);
@@ -901,6 +803,28 @@ AddConnections(HnswElement element, List *neighbors, int m, int lc)
 		a->items[a->length++] = *((HnswCandidate *) lfirst(lc2));
 }
 
+/*
+ * Compare candidate distances
+ */
+static int
+#if PG_VERSION_NUM >= 130000
+CompareCandidateDistances(const ListCell *a, const ListCell *b)
+#else
+CompareCandidateDistances(const void *a, const void *b)
+#endif
+{
+	HnswCandidate *hca = lfirst((ListCell *) a);
+	HnswCandidate *hcb = lfirst((ListCell *) b);
+
+	if (hca->distance < hcb->distance)
+		return 1;
+
+	if (hca->distance > hcb->distance)
+		return -1;
+
+	return 0;
+}
+
 /*
  * Update connections
  */
@@ -954,12 +878,13 @@ HnswUpdateConnection(HnswElement element, HnswCandidate * hc, int m, int lc, int
 		{
 			List	   *c = NIL;
 
-			/* Add candidates */
+			/* Add and sort candidates */
 			for (int i = 0; i < currentNeighbors->length; i++)
 				c = lappend(c, &currentNeighbors->items[i]);
 			c = lappend(c, &hc2);
+			list_sort(c, CompareCandidateDistances);
 
-			SelectNeighbors(c, m, lc, procinfo, collation, hc->element, &hc2, &pruned, true);
+			SelectNeighbors(c, m, lc, procinfo, collation, &pruned);
 
 			/* Should not happen */
 			if (pruned == NULL)
@@ -1031,7 +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;
 	}
 
@@ -1049,7 +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 */
@@ -1058,12 +983,7 @@ HnswInsertElement(HnswElement element, HnswElement entryPoint, Relation index, F
 		else
 			lw = w;
 
-		/*
+		neighbors = SelectNeighbors(lw, lm, lc, procinfo, collation, NULL);
-		 * Candidates are sorted, but not deterministically. Could set
-		 * sortCandidates to true for in-memory builds to enable closer
-		 * caching, but there does not seem to be a difference in performance.
-		 */
-		neighbors = SelectNeighbors(lw, lm, lc, procinfo, collation, element, NULL, NULL, false);
 
 		AddConnections(element, neighbors, lm, lc);
 

src/hnswvacuum.c

@@ -128,7 +128,10 @@ RemoveHeapTids(HnswVacuumState * vacuumstate)
 		blkno = HnswPageGetOpaque(page)->nextblkno;
 
 		if (updated)
+		{
+			MarkBufferDirty(buf);
 			GenericXLogFinish(state);
+		}
 		else
 			GenericXLogAbort(state);
 
@@ -226,6 +229,7 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
 		elog(ERROR, "failed to add index item to \"%s\"", RelationGetRelationName(index));
 
 	/* Commit */
+	MarkBufferDirty(buf);
 	GenericXLogFinish(state);
 	UnlockReleaseBuffer(buf);
 
@@ -326,10 +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);
 
@@ -442,11 +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);
 
@@ -543,6 +540,9 @@ MarkDeleted(HnswVacuumState * vacuumstate)
 				elog(ERROR, "failed to add index item to \"%s\"", RelationGetRelationName(index));
 
 			/* Commit */
+			MarkBufferDirty(buf);
+			if (nbuf != buf)
+				MarkBufferDirty(nbuf);
 			GenericXLogFinish(state);
 			if (nbuf != buf)
 				UnlockReleaseBuffer(nbuf);
@@ -582,6 +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);
@@ -591,9 +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/ivfbuild.c

@@ -11,7 +11,6 @@
 #include "miscadmin.h"
 #include "storage/bufmgr.h"
 #include "tcop/tcopprot.h"
-#include "utils/datum.h"
 #include "utils/memutils.h"
 
 #if PG_VERSION_NUM >= 140000
@@ -66,18 +65,11 @@
 static void
 AddSample(Datum *values, IvfflatBuildState * buildstate)
 {
-	MemoryContext oldCtx;
+	VectorArray samples = buildstate->samples;
-	Datum		value;
+	int			targsamples = samples->maxlen;
-	int			targsamples = buildstate->targsamples;
-
-	/* Use memory context since detoast can allocate */
-	oldCtx = MemoryContextSwitchTo(buildstate->tmpCtx);
 
 	/* Detoast once for all calls */
-	value = PointerGetDatum(PG_DETOAST_DATUM(values[0]));
+	Datum		value = PointerGetDatum(PG_DETOAST_DATUM(values[0]));
-
-	/* Restore memory context */
-	MemoryContextSwitchTo(oldCtx);
 
 	/*
 	 * Normalize with KMEANS_NORM_PROC since spherical distance function
@@ -89,23 +81,18 @@ AddSample(Datum *values, IvfflatBuildState * buildstate)
 			return;
 	}
 
-	/* Copy datum */
+	if (samples->length < targsamples)
-	value = datumCopy(value, false, -1);
+	{
-
+		VectorArraySet(samples, samples->length, DatumGetVector(value));
-	/* Reset memory context */
+		samples->length++;
-	MemoryContextReset(buildstate->tmpCtx);
+	}
-
-	if (list_length(buildstate->samples) < targsamples)
-		buildstate->samples = lappend(buildstate->samples, DatumGetVector(value));
 	else
 	{
 		if (buildstate->rowstoskip < 0)
-			buildstate->rowstoskip = reservoir_get_next_S(&buildstate->rstate, list_length(buildstate->samples), targsamples);
+			buildstate->rowstoskip = reservoir_get_next_S(&buildstate->rstate, samples->length, targsamples);
 
 		if (buildstate->rowstoskip <= 0)
 		{
-			ListCell   *lc;
-
 #if PG_VERSION_NUM >= 150000
 			int			k = (int) (targsamples * sampler_random_fract(&buildstate->rstate.randstate));
 #else
@@ -113,8 +100,7 @@ AddSample(Datum *values, IvfflatBuildState * buildstate)
 #endif
 
 			Assert(k >= 0 && k < targsamples);
-			lc = list_nth_cell(buildstate->samples, k);
+			VectorArraySet(samples, k, DatumGetVector(value));
-			lfirst(lc) = DatumGetVector(value);
 		}
 
 		buildstate->rowstoskip -= 1;
@@ -129,13 +115,21 @@ SampleCallback(Relation index, CALLBACK_ITEM_POINTER, Datum *values,
 			   bool *isnull, bool tupleIsAlive, void *state)
 {
 	IvfflatBuildState *buildstate = (IvfflatBuildState *) state;
+	MemoryContext oldCtx;
 
 	/* Skip nulls */
 	if (isnull[0])
 		return;
 
+	/* Use memory context since detoast can allocate */
+	oldCtx = MemoryContextSwitchTo(buildstate->tmpCtx);
+
 	/* Add sample */
-	AddSample(values, buildstate);
+	AddSample(values, state);
+
+	/* Reset memory context */
+	MemoryContextSwitchTo(oldCtx);
+	MemoryContextReset(buildstate->tmpCtx);
 }
 
 /*
@@ -144,7 +138,7 @@ SampleCallback(Relation index, CALLBACK_ITEM_POINTER, Datum *values,
 static void
 SampleRows(IvfflatBuildState * buildstate)
 {
-	int			targsamples = buildstate->targsamples;
+	int			targsamples = buildstate->samples->maxlen;
 	BlockNumber totalblocks = RelationGetNumberOfBlocks(buildstate->heap);
 
 	buildstate->rowstoskip = -1;
@@ -455,13 +449,12 @@ ComputeCenters(IvfflatBuildState * buildstate)
 
 	/* Sample rows */
 	/* TODO Ensure within maintenance_work_mem */
-	buildstate->samples = NIL;
+	buildstate->samples = VectorArrayInit(numSamples, buildstate->dimensions);
-	buildstate->targsamples = numSamples;
 	if (buildstate->heap != NULL)
 	{
 		SampleRows(buildstate);
 
-		if (list_length(buildstate->samples) < buildstate->lists)
+		if (buildstate->samples->length < buildstate->lists)
 		{
 			ereport(NOTICE,
 					(errmsg("ivfflat index created with little data"),
@@ -474,7 +467,7 @@ ComputeCenters(IvfflatBuildState * buildstate)
 	IvfflatBench("k-means", IvfflatKmeans(buildstate->index, buildstate->samples, buildstate->centers));
 
 	/* Free samples before we allocate more memory */
-	list_free_deep(buildstate->samples);
+	VectorArrayFree(buildstate->samples);
 }
 
 /*
@@ -513,30 +506,29 @@ CreateListPages(Relation index, VectorArray centers, int dimensions,
 	Buffer		buf;
 	Page		page;
 	GenericXLogState *state;
-	Size		listSize;
+	OffsetNumber offno;
+	Size		itemsz;
 	IvfflatList list;
 
-	listSize = MAXALIGN(IVFFLAT_LIST_SIZE(dimensions));
+	itemsz = MAXALIGN(IVFFLAT_LIST_SIZE(dimensions));
-	list = palloc(listSize);
+	list = palloc(itemsz);
 
 	buf = IvfflatNewBuffer(index, forkNum);
 	IvfflatInitRegisterPage(index, &buf, &page, &state);
 
 	for (int i = 0; i < lists; i++)
 	{
-		OffsetNumber offno;
-
 		/* Load list */
 		list->startPage = InvalidBlockNumber;
 		list->insertPage = InvalidBlockNumber;
 		memcpy(&list->center, VectorArrayGet(centers, i), VECTOR_SIZE(dimensions));
 
 		/* Ensure free space */
-		if (PageGetFreeSpace(page) < listSize)
+		if (PageGetFreeSpace(page) < itemsz)
 			IvfflatAppendPage(index, &buf, &page, &state, forkNum);
 
 		/* Add the item */
-		offno = PageAddItem(page, (Item) list, listSize, InvalidOffsetNumber, false, false);
+		offno = PageAddItem(page, (Item) list, itemsz, InvalidOffsetNumber, false, false);
 		if (offno == InvalidOffsetNumber)
 			elog(ERROR, "failed to add index item to \"%s\"", RelationGetRelationName(index));
 

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

@@ -80,10 +80,6 @@
 #define RandomInt() random()
 #endif
 
-#if PG_VERSION_NUM < 130000
-#define list_sort(list, cmp) list_qsort(list, cmp)
-#endif
-
 /* Variables */
 extern int	ivfflat_probes;
 
@@ -182,8 +178,7 @@ typedef struct IvfflatBuildState
 	Oid			collation;
 
 	/* Variables */
-	List	   *samples;
+	VectorArray samples;
-	int			targsamples;
 	VectorArray centers;
 	ListInfo   *listInfo;
 	Vector	   *normvec;
@@ -249,8 +244,8 @@ typedef struct IvfflatScanList
 typedef struct IvfflatScanOpaqueData
 {
 	int			probes;
-	int			dimensions;
 	bool		first;
+	Buffer		buf;
 
 	/* Sorting */
 	Tuplesortstate *sortstate;
@@ -279,11 +274,10 @@ typedef IvfflatScanOpaqueData * IvfflatScanOpaque;
 VectorArray VectorArrayInit(int maxlen, int dimensions);
 void		VectorArrayFree(VectorArray arr);
 void		PrintVectorArray(char *msg, VectorArray arr);
-void		IvfflatKmeans(Relation index, List *samples, VectorArray centers);
+void		IvfflatKmeans(Relation index, VectorArray samples, VectorArray centers);
-FmgrInfo   *IvfflatOptionalProcInfo(Relation index, uint16 procnum);
+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/ivfinsert.c

@@ -11,37 +11,36 @@
  * Find the list that minimizes the distance function
  */
 static void
-FindInsertPage(Relation index, Datum *values, BlockNumber *insertPage, ListInfo * listInfo)
+FindInsertPage(Relation rel, Datum *values, BlockNumber *insertPage, ListInfo * listInfo)
 {
+	Buffer		cbuf;
+	Page		cpage;
+	IvfflatList list;
+	double		distance;
 	double		minDistance = DBL_MAX;
 	BlockNumber nextblkno = IVFFLAT_HEAD_BLKNO;
 	FmgrInfo   *procinfo;
 	Oid			collation;
+	OffsetNumber offno;
+	OffsetNumber maxoffno;
 
 	/* Avoid compiler warning */
 	listInfo->blkno = nextblkno;
 	listInfo->offno = FirstOffsetNumber;
 
-	procinfo = index_getprocinfo(index, 1, IVFFLAT_DISTANCE_PROC);
+	procinfo = index_getprocinfo(rel, 1, IVFFLAT_DISTANCE_PROC);
-	collation = index->rd_indcollation[0];
+	collation = rel->rd_indcollation[0];
 
 	/* Search all list pages */
 	while (BlockNumberIsValid(nextblkno))
 	{
-		Buffer		cbuf;
+		cbuf = ReadBuffer(rel, nextblkno);
-		Page		cpage;
-		OffsetNumber maxoffno;
-
-		cbuf = ReadBuffer(index, 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;
-			double		distance;
-
 			list = (IvfflatList) PageGetItem(cpage, PageGetItemId(cpage, offno));
 			distance = DatumGetFloat8(FunctionCall2Coll(procinfo, collation, values[0], PointerGetDatum(&list->center)));
 
@@ -64,7 +63,7 @@ FindInsertPage(Relation index, Datum *values, BlockNumber *insertPage, ListInfo
  * Insert a tuple into the index
  */
 static void
-InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid, Relation heapRel)
+InsertTuple(Relation rel, Datum *values, bool *isnull, ItemPointer heap_tid, Relation heapRel)
 {
 	IndexTuple	itup;
 	Datum		value;
@@ -81,33 +80,33 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid, R
 	value = PointerGetDatum(PG_DETOAST_DATUM(values[0]));
 
 	/* Normalize if needed */
-	normprocinfo = IvfflatOptionalProcInfo(index, IVFFLAT_NORM_PROC);
+	normprocinfo = IvfflatOptionalProcInfo(rel, IVFFLAT_NORM_PROC);
 	if (normprocinfo != NULL)
 	{
-		if (!IvfflatNormValue(normprocinfo, index->rd_indcollation[0], &value, NULL))
+		if (!IvfflatNormValue(normprocinfo, rel->rd_indcollation[0], &value, NULL))
 			return;
 	}
 
 	/* Find the insert page - sets the page and list info */
-	FindInsertPage(index, values, &insertPage, &listInfo);
+	FindInsertPage(rel, values, &insertPage, &listInfo);
 	Assert(BlockNumberIsValid(insertPage));
 	originalInsertPage = insertPage;
 
 	/* Form tuple */
-	itup = index_form_tuple(RelationGetDescr(index), &value, isnull);
+	itup = index_form_tuple(RelationGetDescr(rel), &value, isnull);
 	itup->t_tid = *heap_tid;
 
 	/* Get tuple size */
 	itemsz = MAXALIGN(IndexTupleSize(itup));
-	Assert(itemsz <= BLCKSZ - MAXALIGN(SizeOfPageHeaderData) - MAXALIGN(sizeof(IvfflatPageOpaqueData)) - sizeof(ItemIdData));
+	Assert(itemsz <= BLCKSZ - MAXALIGN(SizeOfPageHeaderData) - MAXALIGN(sizeof(IvfflatPageOpaqueData)));
 
 	/* Find a page to insert the item */
 	for (;;)
 	{
-		buf = ReadBuffer(index, insertPage);
+		buf = ReadBuffer(rel, insertPage);
 		LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
 
-		state = GenericXLogStart(index);
+		state = GenericXLogStart(rel);
 		page = GenericXLogRegisterBuffer(state, buf, 0);
 
 		if (PageGetFreeSpace(page) >= itemsz)
@@ -127,9 +126,9 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid, R
 			Page		newpage;
 
 			/* Add a new page */
-			LockRelationForExtension(index, ExclusiveLock);
+			LockRelationForExtension(rel, ExclusiveLock);
-			newbuf = IvfflatNewBuffer(index, MAIN_FORKNUM);
+			newbuf = IvfflatNewBuffer(rel, MAIN_FORKNUM);
-			UnlockRelationForExtension(index, ExclusiveLock);
+			UnlockRelationForExtension(rel, ExclusiveLock);
 
 			/* Init new page */
 			newpage = GenericXLogRegisterBuffer(state, newbuf, GENERIC_XLOG_FULL_IMAGE);
@@ -142,13 +141,15 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid, R
 			IvfflatPageGetOpaque(page)->nextblkno = insertPage;
 
 			/* Commit */
+			MarkBufferDirty(newbuf);
+			MarkBufferDirty(buf);
 			GenericXLogFinish(state);
 
 			/* Unlock previous buffer */
 			UnlockReleaseBuffer(buf);
 
 			/* Prepare new buffer */
-			state = GenericXLogStart(index);
+			state = GenericXLogStart(rel);
 			buf = newbuf;
 			page = GenericXLogRegisterBuffer(state, buf, 0);
 			break;
@@ -157,13 +158,13 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid, R
 
 	/* Add to next offset */
 	if (PageAddItem(page, (Item) itup, itemsz, InvalidOffsetNumber, false, false) == InvalidOffsetNumber)
-		elog(ERROR, "failed to add index item to \"%s\"", RelationGetRelationName(index));
+		elog(ERROR, "failed to add index item to \"%s\"", RelationGetRelationName(rel));
 
 	IvfflatCommitBuffer(buf, state);
 
 	/* Update the insert page */
 	if (insertPage != originalInsertPage)
-		IvfflatUpdateList(index, listInfo, insertPage, originalInsertPage, InvalidBlockNumber, MAIN_FORKNUM);
+		IvfflatUpdateList(rel, listInfo, insertPage, originalInsertPage, InvalidBlockNumber, MAIN_FORKNUM);
 }
 
 /*

src/ivfkmeans.c

@@ -12,38 +12,38 @@
  * https://theory.stanford.edu/~sergei/papers/kMeansPP-soda.pdf
  */
 static void
-InitCenters(Relation index, List *samples, VectorArray centers, float *lowerBound)
+InitCenters(Relation index, VectorArray samples, VectorArray centers, float *lowerBound)
 {
 	FmgrInfo   *procinfo;
 	Oid			collation;
 	int64		j;
-	float	   *weight = palloc(list_length(samples) * sizeof(float));
+	double		distance;
+	double		sum;
+	double		choice;
+	Vector	   *vec;
+	float	   *weight = palloc(samples->length * sizeof(float));
 	int			numCenters = centers->maxlen;
-	int			numSamples = list_length(samples);
+	int			numSamples = samples->length;
 
 	procinfo = index_getprocinfo(index, 1, IVFFLAT_KMEANS_DISTANCE_PROC);
 	collation = index->rd_indcollation[0];
 
 	/* Choose an initial center uniformly at random */
-	VectorArraySet(centers, 0, list_nth(samples, RandomInt() % list_length(samples)));
+	VectorArraySet(centers, 0, VectorArrayGet(samples, RandomInt() % samples->length));
 	centers->length++;
 
 	for (j = 0; j < numSamples; j++)
-		weight[j] = FLT_MAX;
+		weight[j] = DBL_MAX;
 
 	for (int i = 0; i < numCenters; i++)
 	{
-		double		sum;
-		double		choice;
-
 		CHECK_FOR_INTERRUPTS();
 
 		sum = 0.0;
 
 		for (j = 0; j < numSamples; j++)
 		{
-			Vector	   *vec = list_nth(samples, j);
+			vec = VectorArrayGet(samples, j);
-			double		distance;
 
 			/* Only need to compute distance for new center */
 			/* TODO Use triangle inequality to reduce distance calculations */
@@ -74,7 +74,7 @@ InitCenters(Relation index, List *samples, VectorArray centers, float *lowerBoun
 				break;
 		}
 
-		VectorArraySet(centers, i + 1, list_nth(samples, j));
+		VectorArraySet(centers, i + 1, VectorArrayGet(samples, j));
 		centers->length++;
 	}
 
@@ -106,41 +106,26 @@ CompareVectors(const void *a, const void *b)
 	return vector_cmp_internal((Vector *) a, (Vector *) b);
 }
 
-/*
- * Compare list vectors
- */
-static int
-#if PG_VERSION_NUM >= 130000
-CompareListVectors(const ListCell *a, const ListCell *b)
-#else
-CompareListVectors(const void *a, const void *b)
-#endif
-{
-	Vector	   *va = lfirst((ListCell *) a);
-	Vector	   *vb = lfirst((ListCell *) b);
-
-	return CompareVectors(va, vb);
-}
-
 /*
  * Quick approach if we have little data
  */
 static void
-QuickCenters(Relation index, List *samples, VectorArray centers)
+QuickCenters(Relation index, VectorArray samples, VectorArray centers)
 {
+	Vector	   *vec;
 	int			dimensions = centers->dim;
 	Oid			collation = index->rd_indcollation[0];
 	FmgrInfo   *normprocinfo = IvfflatOptionalProcInfo(index, IVFFLAT_KMEANS_NORM_PROC);
 
 	/* Copy existing vectors while avoiding duplicates */
-	if (list_length(samples) > 0)
+	if (samples->length > 0)
 	{
-		list_sort(samples, CompareListVectors);
+		qsort(samples->items, samples->length, VECTOR_SIZE(samples->dim), CompareVectors);
-		for (int i = 0; i < list_length(samples); i++)
+		for (int i = 0; i < samples->length; i++)
 		{
-			Vector	   *vec = list_nth(samples, i);
+			vec = VectorArrayGet(samples, i);
 
-			if (i == 0 || CompareVectors(vec, list_nth(samples, i - 1)) != 0)
+			if (i == 0 || CompareVectors(vec, VectorArrayGet(samples, i - 1)) != 0)
 			{
 				VectorArraySet(centers, centers->length, vec);
 				centers->length++;
@@ -151,7 +136,7 @@ QuickCenters(Relation index, List *samples, VectorArray centers)
 	/* Fill remaining with random data */
 	while (centers->length < centers->maxlen)
 	{
-		Vector	   *vec = VectorArrayGet(centers, centers->length);
+		vec = VectorArrayGet(centers, centers->length);
 
 		SET_VARSIZE(vec, VECTOR_SIZE(dimensions));
 		vec->dim = dimensions;
@@ -176,18 +161,19 @@ QuickCenters(Relation index, List *samples, VectorArray centers)
  * https://www.aaai.org/Papers/ICML/2003/ICML03-022.pdf
  */
 static void
-ElkanKmeans(Relation index, List *samples, VectorArray centers)
+ElkanKmeans(Relation index, VectorArray samples, VectorArray centers)
 {
 	FmgrInfo   *procinfo;
 	FmgrInfo   *normprocinfo;
 	Oid			collation;
 	Vector	   *vec;
 	Vector	   *newCenter;
+	int			iteration;
 	int64		j;
 	int64		k;
 	int			dimensions = centers->dim;
 	int			numCenters = centers->maxlen;
-	int			numSamples = list_length(samples);
+	int			numSamples = samples->length;
 	VectorArray newCenters;
 	int		   *centerCounts;
 	int		   *closestCenters;
@@ -196,9 +182,17 @@ ElkanKmeans(Relation index, List *samples, VectorArray centers)
 	float	   *s;
 	float	   *halfcdist;
 	float	   *newcdist;
+	int			changes;
+	double		minDistance;
+	int			closestCenter;
+	double		distance;
+	bool		rj;
+	bool		rjreset;
+	double		dxcx;
+	double		dxc;
 
 	/* Calculate allocation sizes */
-	Size		samplesSize = 0;
+	Size		samplesSize = VECTOR_ARRAY_SIZE(samples->maxlen, samples->dim);
 	Size		centersSize = VECTOR_ARRAY_SIZE(centers->maxlen, centers->dim);
 	Size		newCentersSize = VECTOR_ARRAY_SIZE(numCenters, dimensions);
 	Size		centerCountsSize = sizeof(int) * numCenters;
@@ -253,14 +247,14 @@ ElkanKmeans(Relation index, List *samples, VectorArray centers)
 	/* Assign each x to its closest initial center c(x) = argmin d(x,c) */
 	for (j = 0; j < numSamples; j++)
 	{
-		float		minDistance = FLT_MAX;
+		minDistance = DBL_MAX;
-		int			closestCenter = 0;
+		closestCenter = 0;
 
 		/* Find closest center */
 		for (k = 0; k < numCenters; k++)
 		{
 			/* TODO Use Lemma 1 in k-means++ initialization */
-			float		distance = lowerBound[j * numCenters + k];
+			distance = lowerBound[j * numCenters + k];
 
 			if (distance < minDistance)
 			{
@@ -274,14 +268,13 @@ ElkanKmeans(Relation index, List *samples, VectorArray centers)
 	}
 
 	/* Give 500 iterations to converge */
-	for (int iteration = 0; iteration < 500; iteration++)
+	for (iteration = 0; iteration < 500; iteration++)
 	{
-		int			changes = 0;
-		bool		rjreset;
-
 		/* Can take a while, so ensure we can interrupt */
 		CHECK_FOR_INTERRUPTS();
 
+		changes = 0;
+
 		/* Step 1: For all centers, compute distance */
 		for (j = 0; j < numCenters; j++)
 		{
@@ -289,8 +282,7 @@ ElkanKmeans(Relation index, List *samples, VectorArray centers)
 
 			for (k = j + 1; k < numCenters; k++)
 			{
-				float		distance = 0.5 * DatumGetFloat8(FunctionCall2Coll(procinfo, collation, PointerGetDatum(vec), PointerGetDatum(VectorArrayGet(centers, k))));
+				distance = 0.5 * DatumGetFloat8(FunctionCall2Coll(procinfo, collation, PointerGetDatum(vec), PointerGetDatum(VectorArrayGet(centers, k))));
-
 				halfcdist[j * numCenters + k] = distance;
 				halfcdist[k * numCenters + j] = distance;
 			}
@@ -299,12 +291,10 @@ ElkanKmeans(Relation index, List *samples, VectorArray centers)
 		/* For all centers c, compute s(c) */
 		for (j = 0; j < numCenters; j++)
 		{
-			float		minDistance = FLT_MAX;
+			minDistance = DBL_MAX;
 
 			for (k = 0; k < numCenters; k++)
 			{
-				float		distance;
-
 				if (j == k)
 					continue;
 
@@ -320,8 +310,6 @@ ElkanKmeans(Relation index, List *samples, VectorArray centers)
 
 		for (j = 0; j < numSamples; j++)
 		{
-			bool		rj;
-
 			/* Step 2: Identify all points x such that u(x) <= s(c(x)) */
 			if (upperBound[j] <= s[closestCenters[j]])
 				continue;
@@ -330,8 +318,6 @@ ElkanKmeans(Relation index, List *samples, VectorArray centers)
 
 			for (k = 0; k < numCenters; k++)
 			{
-				float		dxcx;
-
 				/* Step 3: For all remaining points x and centers c */
 				if (k == closestCenters[j])
 					continue;
@@ -342,7 +328,7 @@ ElkanKmeans(Relation index, List *samples, VectorArray centers)
 				if (upperBound[j] <= halfcdist[closestCenters[j] * numCenters + k])
 					continue;
 
-				vec = list_nth(samples, j);
+				vec = VectorArrayGet(samples, j);
 
 				/* Step 3a */
 				if (rj)
@@ -361,7 +347,7 @@ ElkanKmeans(Relation index, List *samples, VectorArray centers)
 				/* Step 3b */
 				if (dxcx > lowerBound[j * numCenters + k] || dxcx > halfcdist[closestCenters[j] * numCenters + k])
 				{
-					float		dxc = DatumGetFloat8(FunctionCall2Coll(procinfo, collation, PointerGetDatum(vec), PointerGetDatum(VectorArrayGet(centers, k))));
+					dxc = DatumGetFloat8(FunctionCall2Coll(procinfo, collation, PointerGetDatum(vec), PointerGetDatum(VectorArrayGet(centers, k))));
 
 					/* d(x,c) calculated */
 					lowerBound[j * numCenters + k] = dxc;
@@ -375,6 +361,7 @@ ElkanKmeans(Relation index, List *samples, VectorArray centers)
 
 						changes++;
 					}
+
 				}
 			}
 		}
@@ -391,9 +378,7 @@ ElkanKmeans(Relation index, List *samples, VectorArray centers)
 
 		for (j = 0; j < numSamples; j++)
 		{
-			int			closestCenter;
+			vec = VectorArrayGet(samples, j);
-
-			vec = list_nth(samples, j);
 			closestCenter = closestCenters[j];
 
 			/* Increment sum and count of closest center */
@@ -441,7 +426,7 @@ ElkanKmeans(Relation index, List *samples, VectorArray centers)
 		{
 			for (k = 0; k < numCenters; k++)
 			{
-				float		distance = lowerBound[j * numCenters + k] - newcdist[k];
+				distance = lowerBound[j * numCenters + k] - newcdist[k];
 
 				if (distance < 0)
 					distance = 0;
@@ -457,7 +442,7 @@ ElkanKmeans(Relation index, List *samples, VectorArray centers)
 
 		/* Step 7 */
 		for (j = 0; j < numCenters; j++)
-			VectorArraySet(centers, j, VectorArrayGet(newCenters, j));
+			memcpy(VectorArrayGet(centers, j), VectorArrayGet(newCenters, j), VECTOR_SIZE(dimensions));
 
 		if (changes == 0 && iteration != 0)
 			break;
@@ -480,6 +465,9 @@ static void
 CheckCenters(Relation index, VectorArray centers)
 {
 	FmgrInfo   *normprocinfo;
+	Oid			collation;
+	Vector	   *vec;
+	double		norm;
 
 	if (centers->length != centers->maxlen)
 		elog(ERROR, "Not enough centers. Please report a bug.");
@@ -487,7 +475,7 @@ CheckCenters(Relation index, VectorArray centers)
 	/* Ensure no NaN or infinite values */
 	for (int i = 0; i < centers->length; i++)
 	{
-		Vector	   *vec = VectorArrayGet(centers, i);
+		vec = VectorArrayGet(centers, i);
 
 		for (int j = 0; j < vec->dim; j++)
 		{
@@ -513,12 +501,11 @@ CheckCenters(Relation index, VectorArray centers)
 	normprocinfo = IvfflatOptionalProcInfo(index, IVFFLAT_NORM_PROC);
 	if (normprocinfo != NULL)
 	{
-		Oid			collation = index->rd_indcollation[0];
+		collation = index->rd_indcollation[0];
 
 		for (int i = 0; i < centers->length; i++)
 		{
-			double		norm = DatumGetFloat8(FunctionCall1Coll(normprocinfo, collation, PointerGetDatum(VectorArrayGet(centers, i))));
+			norm = DatumGetFloat8(FunctionCall1Coll(normprocinfo, collation, PointerGetDatum(VectorArrayGet(centers, i))));
-
 			if (norm == 0)
 				elog(ERROR, "Zero norm detected. Please report a bug.");
 		}
@@ -530,9 +517,9 @@ CheckCenters(Relation index, VectorArray centers)
  * We use spherical k-means for inner product and cosine
  */
 void
-IvfflatKmeans(Relation index, List *samples, VectorArray centers)
+IvfflatKmeans(Relation index, VectorArray samples, VectorArray centers)
 {
-	if (list_length(samples) <= centers->maxlen)
+	if (samples->length <= centers->maxlen)
 		QuickCenters(index, samples, centers);
 	else
 		ElkanKmeans(index, samples, centers);

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;
 
@@ -122,28 +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);
-
-				itup = (IndexTuple) PageGetItem(page, itemid);
 				datum = index_getattr(itup, 1, tupdesc, &isnull);
 
 				/*
@@ -157,6 +154,8 @@ GetScanItems(IndexScanDesc scan, 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);
 
 				tuplesort_puttupleslot(so->sortstate, slot);
@@ -181,6 +180,29 @@ GetScanItems(IndexScanDesc scan, Datum value)
 	tuplesort_performsort(so->sortstate);
 }
 
+/*
+ * Get dimensions from metapage
+ */
+static int
+GetDimensions(Relation index)
+{
+	Buffer		buf;
+	Page		page;
+	IvfflatMetaPage metap;
+	int			dimensions;
+
+	buf = ReadBuffer(index, IVFFLAT_METAPAGE_BLKNO);
+	LockBuffer(buf, BUFFER_LOCK_SHARE);
+	page = BufferGetPage(buf);
+	metap = IvfflatPageGetMeta(page);
+
+	dimensions = metap->dimensions;
+
+	UnlockReleaseBuffer(buf);
+
+	return dimensions;
+}
+
 /*
  * Prepare for an index scan
  */
@@ -190,7 +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};
@@ -198,17 +219,15 @@ 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;
 
 	so = (IvfflatScanOpaque) palloc(offsetof(IvfflatScanOpaqueData, lists) + probes * sizeof(IvfflatScanList));
+	so->buf = InvalidBuffer;
 	so->first = true;
 	so->probes = probes;
-	so->dimensions = dimensions;
 
 	/* Set support functions */
 	so->procinfo = index_getprocinfo(index, 1, IVFFLAT_DISTANCE_PROC);
@@ -217,12 +236,13 @@ ivfflatbeginscan(Relation index, int nkeys, int norderbys)
 
 	/* Create tuple description for sorting */
 #if PG_VERSION_NUM >= 120000
-	so->tupdesc = CreateTemplateTupleDesc(2);
+	so->tupdesc = CreateTemplateTupleDesc(3);
 #else
-	so->tupdesc = CreateTemplateTupleDesc(2, false);
+	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 */
 	so->sortstate = tuplesort_begin_heap(so->tupdesc, 1, attNums, sortOperators, sortCollations, nullsFirstFlags, work_mem, NULL, false);
@@ -288,13 +308,8 @@ ivfflatgettuple(IndexScanDesc scan, ScanDirection dir)
 		if (scan->orderByData == NULL)
 			elog(ERROR, "cannot scan ivfflat index without order");
 
-		/* Requires MVCC-compliant snapshot as not able to pin during sorting */
-		/* https://www.postgresql.org/docs/current/index-locking.html */
-		if (!IsMVCCSnapshot(scan->xs_snapshot))
-			elog(ERROR, "non-MVCC snapshots are not supported with ivfflat");
-
 		if (scan->orderByData->sk_flags & SK_ISNULL)
-			value = PointerGetDatum(InitVector(so->dimensions));
+			value = PointerGetDatum(InitVector(GetDimensions(scan->indexRelation)));
 		else
 		{
 			value = scan->orderByData->sk_argument;
@@ -319,14 +334,27 @@ ivfflatgettuple(IndexScanDesc scan, ScanDirection dir)
 
 	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
 
+		/* Unpin buffer */
+		if (BufferIsValid(so->buf))
+			ReleaseBuffer(so->buf);
+
+		/*
+		 * An index scan must maintain a pin on the index page holding the
+		 * item last returned by amgettuple
+		 *
+		 * https://www.postgresql.org/docs/current/index-locking.html
+		 */
+		so->buf = ReadBuffer(scan->indexRelation, indexblkno);
+
 		scan->xs_recheckorderby = false;
 		return true;
 	}
@@ -342,6 +370,10 @@ ivfflatendscan(IndexScanDesc scan)
 {
 	IvfflatScanOpaque so = (IvfflatScanOpaque) scan->opaque;
 
+	/* Release pin */
+	if (BufferIsValid(so->buf))
+		ReleaseBuffer(so->buf);
+
 	pairingheap_free(so->listQueue);
 	tuplesort_end(so->sortstate);
 

src/ivfutils.c

@@ -57,12 +57,12 @@ IvfflatGetLists(Relation index)
  * Get proc
  */
 FmgrInfo *
-IvfflatOptionalProcInfo(Relation index, uint16 procnum)
+IvfflatOptionalProcInfo(Relation rel, uint16 procnum)
 {
-	if (!OidIsValid(index_getprocid(index, 1, procnum)))
+	if (!OidIsValid(index_getprocid(rel, 1, procnum)))
 		return NULL;
 
-	return index_getprocinfo(index, 1, procnum);
+	return index_getprocinfo(rel, 1, procnum);
 }
 
 /*
@@ -136,6 +136,7 @@ IvfflatInitRegisterPage(Relation index, Buffer *buf, Page *page, GenericXLogStat
 void
 IvfflatCommitBuffer(Buffer buf, GenericXLogState *state)
 {
+	MarkBufferDirty(buf);
 	GenericXLogFinish(state);
 	UnlockReleaseBuffer(buf);
 }
@@ -159,6 +160,8 @@ IvfflatAppendPage(Relation index, Buffer *buf, Page *page, GenericXLogState **st
 	IvfflatInitPage(newbuf, newpage);
 
 	/* Commit */
+	MarkBufferDirty(*buf);
+	MarkBufferDirty(newbuf);
 	GenericXLogFinish(*state);
 
 	/* Unlock */
@@ -169,29 +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/ivfvacuum.c

@@ -107,6 +107,7 @@ ivfflatbulkdelete(IndexVacuumInfo *info, IndexBulkDeleteResult *stats,
 				{
 					/* Delete tuples */
 					PageIndexMultiDelete(page, deletable, ndeletable);
+					MarkBufferDirty(buf);
 					GenericXLogFinish(state);
 				}
 				else

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 = '0.5.1'
+default_version = '0.5.0'
 module_pathname = '$libdir/vector'
 relocatable = true