Merge branch 'master' into hqann2

Co-authored-by: "Jonathan S. Katz" <jkatz@amazon.com>

.github/workflows/build.yml

@@ -49,7 +49,7 @@ jobs:
           - postgres: 16
             os: macos-14
           - postgres: 14
-            os: macos-12
+            os: macos-13
     steps:
       - uses: actions/checkout@v4
       - uses: ankane/setup-postgres@v1

CHANGELOG.md

@@ -1,6 +1,7 @@
 ## 0.8.0 (unreleased)
 
 - Added support for inline filtering with HNSW
+- Added support for iterative index scans
 - Added casts for arrays to `sparsevec`
 - Improved cost estimation
 - Improved performance of HNSW inserts and on-disk index builds

src/hnsw.c

@@ -18,7 +18,16 @@
 #define MarkGUCPrefixReserved(x) EmitWarningsOnPlaceholders(x)
 #endif
 
+static const struct config_enum_entry hnsw_iterative_search_options[] = {
+	{"off", HNSW_ITERATIVE_SEARCH_OFF, false},
+	{"on", HNSW_ITERATIVE_SEARCH_RELAXED, false},
+	{"strict", HNSW_ITERATIVE_SEARCH_STRICT, false},
+	{NULL, 0, false}
+};
+
 int			hnsw_ef_search;
+int			hnsw_iterative_search_max_tuples;
+int			hnsw_iterative_search;
 int			hnsw_lock_tranche_id;
 static relopt_kind hnsw_relopt_kind;
 
@@ -69,6 +78,15 @@ HnswInit(void)
 							"Valid range is 1..1000.", &hnsw_ef_search,
 							HNSW_DEFAULT_EF_SEARCH, HNSW_MIN_EF_SEARCH, HNSW_MAX_EF_SEARCH, PGC_USERSET, 0, NULL, NULL, NULL);
 
+	DefineCustomEnumVariable("hnsw.iterative_search", "Sets iterative search",
+							 NULL, &hnsw_iterative_search,
+							 HNSW_ITERATIVE_SEARCH_OFF, hnsw_iterative_search_options, PGC_USERSET, 0, NULL, NULL, NULL);
+
+	/* TODO Ensure ivfflat.max_probes uses same value for "all" */
+	DefineCustomIntVariable("hnsw.iterative_search_max_tuples", "Sets the max number of candidates to visit for iterative search",
+							"-1 means all", &hnsw_iterative_search_max_tuples,
+							-1, -1, INT_MAX, PGC_USERSET, 0, NULL, NULL, NULL);
+
 	MarkGUCPrefixReserved("hnsw");
 }
 

src/hnsw.h

@@ -89,6 +89,9 @@
 /* Ensure fits on page and in uint8 */
 #define HnswGetMaxLevel(m) Min(((BLCKSZ - MAXALIGN(SizeOfPageHeaderData) - MAXALIGN(sizeof(HnswPageOpaqueData)) - offsetof(HnswNeighborTupleData, indextids) - sizeof(ItemIdData)) / (sizeof(ItemPointerData)) / (m)) - 2, 255)
 
+#define HnswGetSearchCandidate(membername, ptr) pairingheap_container(HnswSearchCandidate, membername, ptr)
+#define HnswGetSearchCandidateConst(membername, ptr) pairingheap_const_container(HnswSearchCandidate, membername, ptr)
+
 #define HnswGetValue(base, element) PointerGetDatum(HnswPtrAccess(base, (element)->value))
 
 #if PG_VERSION_NUM < 140005
@@ -109,8 +112,17 @@
 
 /* Variables */
 extern int	hnsw_ef_search;
+extern int	hnsw_iterative_search;
+extern int	hnsw_iterative_search_max_tuples;
 extern int	hnsw_lock_tranche_id;
 
+typedef enum HnswIterativeSearchType
+{
+	HNSW_ITERATIVE_SEARCH_OFF,
+	HNSW_ITERATIVE_SEARCH_RELAXED,
+	HNSW_ITERATIVE_SEARCH_STRICT
+}			HnswIterativeSearchType;
+
 typedef struct HnswElementData HnswElementData;
 typedef struct HnswNeighborArray HnswNeighborArray;
 
@@ -133,6 +145,7 @@ struct HnswElementData
 	uint8		heaptidsLength;
 	uint8		level;
 	uint8		deleted;
+	uint8		version;
 	uint32		hash;
 	HnswNeighborsPtr neighbors;
 	BlockNumber blkno;
@@ -243,6 +256,20 @@ typedef struct HnswTypeInfo
 	void		(*checkValue) (Pointer v);
 }			HnswTypeInfo;
 
+typedef struct HnswSupport
+{
+	FmgrInfo   *procinfo[2];
+	FmgrInfo   *normprocinfo;
+	Oid		   *collation;
+}			HnswSupport;
+
+typedef struct HnswQuery
+{
+	Datum		value;
+	IndexTuple	itup;
+	ScanKeyData *keyData;
+}			HnswQuery;
+
 typedef struct HnswBuildState
 {
 	/* Info */
@@ -262,9 +289,7 @@ typedef struct HnswBuildState
 	double		reltuples;
 
 	/* Support functions */
-	FmgrInfo   *procinfo[2];
-	FmgrInfo   *normprocinfo;
-	Oid		   *collation;
+	HnswSupport support;
 
 	/* Variables */
 	HnswGraph	graphData;
@@ -314,10 +339,10 @@ typedef struct HnswElementTupleData
 	uint8		type;
 	uint8		level;
 	uint8		deleted;
-	uint8		unused;
+	uint8		version;
 	ItemPointerData heaptids[HNSW_HEAPTIDS];
 	ItemPointerData neighbortid;
-	uint16		unused2;
+	uint16		unused;
 	Vector		data;
 }			HnswElementTupleData;
 
@@ -326,24 +351,41 @@ typedef HnswElementTupleData * HnswElementTuple;
 typedef struct HnswNeighborTupleData
 {
 	uint8		type;
-	uint8		unused;
+	uint8		version;
 	uint16		count;
 	ItemPointerData indextids[FLEXIBLE_ARRAY_MEMBER];
 }			HnswNeighborTupleData;
 
 typedef HnswNeighborTupleData * HnswNeighborTuple;
 
+typedef union
+{
+	struct pointerhash_hash *pointers;
+	struct offsethash_hash *offsets;
+	struct tidhash_hash *tids;
+}			visited_hash;
+
+typedef union
+{
+	HnswElement element;
+	ItemPointerData indextid;
+}			HnswUnvisited;
+
 typedef struct HnswScanOpaqueData
 {
 	const		HnswTypeInfo *typeInfo;
 	bool		first;
 	List	   *w;
+	visited_hash v;
+	pairingheap *discarded;
+	HnswQuery	q;
+	int			m;
+	int64		tuples;
+	double		previousDistance;
 	MemoryContext tmpCtx;
 
 	/* Support functions */
-	FmgrInfo   *procinfo[2];
-	FmgrInfo   *normprocinfo;
-	Oid		   *collation;
+	HnswSupport support;
 }			HnswScanOpaqueData;
 
 typedef HnswScanOpaqueData * HnswScanOpaque;
@@ -361,8 +403,7 @@ typedef struct HnswVacuumState
 	int			efConstruction;
 
 	/* Support functions */
-	FmgrInfo   *procinfo[2];
-	Oid		   *collation;
+	HnswSupport support;
 
 	/* Variables */
 	struct tidhash_hash *deleted;
@@ -378,35 +419,36 @@ typedef struct HnswVacuumState
 int			HnswGetM(Relation index);
 int			HnswGetEfConstruction(Relation index);
 FmgrInfo   *HnswOptionalProcInfo(Relation index, uint16 procnum);
+void		HnswInitSupport(HnswSupport * support, Relation index);
 Datum		HnswNormValue(const HnswTypeInfo * typeInfo, Oid collation, Datum value);
-bool		HnswCheckNorm(FmgrInfo *procinfo, Oid collation, Datum value);
+bool		HnswCheckNorm(HnswSupport * support, Datum value);
 Buffer		HnswNewBuffer(Relation index, ForkNumber forkNum);
 void		HnswInitPage(Buffer buf, Page page);
 void		HnswInit(void);
-List	   *HnswSearchLayer(char *base, Datum q, IndexTuple qtup, ScanKeyData *keyData, List *ep, int ef, int lc, Relation index, FmgrInfo **procinfo, Oid *collation, int m, bool inserting, HnswElement skipElement, bool inMemory);
+List	   *HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation index, HnswSupport * support, int m, bool inserting, HnswElement skipElement, bool inMemory, visited_hash * v, pairingheap **discarded, bool initVisited, int64 *tuples);
 HnswElement HnswGetEntryPoint(Relation index);
 void		HnswGetMetaPageInfo(Relation index, int *m, HnswElement * entryPoint);
 void	   *HnswAlloc(HnswAllocator * allocator, Size size);
 HnswElement HnswInitElement(char *base, ItemPointer tid, int m, double ml, int maxLevel, HnswAllocator * alloc);
 HnswElement HnswInitElementFromBlock(BlockNumber blkno, OffsetNumber offno);
-void		HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, FmgrInfo **procinfo, Oid *collation, int m, int efConstruction, bool existing, bool inMemory);
-HnswSearchCandidate *HnswEntryCandidate(char *base, HnswElement em, Datum q, IndexTuple qtup, ScanKeyData *keyData, Relation rel, FmgrInfo **procinfo, Oid *collation, bool loadVec, bool inMemory);
+void		HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, HnswSupport * support, int m, int efConstruction, bool existing, bool inMemory);
+HnswSearchCandidate *HnswEntryCandidate(char *base, HnswElement em, HnswQuery * q, Relation rel, HnswSupport * support, bool loadVec, bool inMemory);
 void		HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, BlockNumber insertPage, ForkNumber forkNum, bool building);
 void		HnswSetNeighborTuple(char *base, HnswNeighborTuple ntup, HnswElement e, int m);
 void		HnswAddHeapTid(HnswElement element, ItemPointer heaptid);
 HnswNeighborArray *HnswInitNeighborArray(int lm, HnswAllocator * allocator);
 void		HnswInitNeighbors(char *base, HnswElement element, int m, HnswAllocator * alloc);
-bool		HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull, ItemPointer heap_tid, bool building);
-void		HnswUpdateNeighborsOnDisk(Relation index, FmgrInfo **procinfo, Oid *collation, HnswElement e, int m, bool checkExisting, bool building);
+bool		HnswInsertTupleOnDisk(Relation index, HnswSupport * support, IndexTuple itup, ItemPointer heaptid, bool building, TupleDesc tupdesc);
+void		HnswUpdateNeighborsOnDisk(Relation index, HnswSupport * support, HnswElement e, int m, bool checkExisting, bool building);
 void		HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHeaptids, bool loadVec, Relation index);
-void		HnswLoadElement(HnswElement element, double *distance, bool *matches, Datum *q, IndexTuple qtup, ScanKeyData *keyData, Relation index, FmgrInfo **procinfo, Oid *collation, bool loadVec, double *maxDistance);
+void		HnswLoadElement(HnswElement element, double *distance, bool *matches, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec, double *maxDistance);
 void		HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element, bool useIndexTuple);
-void		HnswUpdateConnection(char *base, HnswNeighborArray * neighbors, HnswElement newElement, float distance, int lm, int *updateIdx, Relation index, FmgrInfo **procinfo, Oid *collation);
+void		HnswUpdateConnection(char *base, HnswNeighborArray * neighbors, HnswElement newElement, float distance, int lm, int *updateIdx, Relation index, HnswSupport * support);
+bool		HnswFormIndexTuple(IndexTuple *out, Datum *values, bool *isnull, const HnswTypeInfo * typeInfo, HnswSupport * support, TupleDesc tupdesc);
 bool		HnswLoadNeighborTids(HnswElement element, ItemPointerData *indextids, Relation index, int m, int lm, int lc);
 void		HnswInitLockTranche(void);
 const		HnswTypeInfo *HnswGetTypeInfo(Relation index);
 PGDLLEXPORT void HnswParallelBuildMain(dsm_segment *seg, shm_toc *toc);
-void		HnswInitProcinfo(FmgrInfo **procinfo, Oid **collation, Relation index);
 Size		HnswGetElementTupleSize(char *base, HnswElement element, bool useIndexTuple);
 bool		HnswIndexTupleIsEqual(IndexTuple a, IndexTuple b, TupleDesc tupdesc);
 

src/hnswbuild.c

@@ -330,7 +330,6 @@ static bool
 FindDuplicateInMemory(char *base, HnswElement element, bool useIndexTuple, TupleDesc tupdesc)
 {
 	HnswNeighborArray *neighbors = HnswGetNeighbors(base, element, 0);
-	Datum		value = HnswGetValue(base, element);
 	IndexTuple	itup = HnswPtrAccess(base, element->itup);
 
 	for (int i = 0; i < neighbors->length; i++)
@@ -338,18 +337,9 @@ FindDuplicateInMemory(char *base, HnswElement element, bool useIndexTuple, Tuple
 		HnswCandidate *neighbor = &neighbors->items[i];
 		HnswElement neighborElement = HnswPtrAccess(base, neighbor->element);
 
-		if (useIndexTuple)
-		{
-			/* Exit early since ordered by distance */
-			if (!HnswIndexTupleIsEqual(itup, HnswPtrAccess(base, neighborElement->itup), tupdesc))
-				return false;
-		}
-		else
-		{
-			/* Exit early since ordered by distance */
-			if (!datumIsEqual(value, HnswGetValue(base, neighborElement), false, -1))
-				return false;
-		}
+		/* Exit early since ordered by distance */
+		if (!HnswIndexTupleIsEqual(itup, HnswPtrAccess(base, neighborElement->itup), tupdesc))
+			return false;
 
 		/* Check for space */
 		if (AddDuplicateInMemory(element, neighborElement))
@@ -375,7 +365,7 @@ AddElementInMemory(char *base, HnswGraph * graph, HnswElement element)
  * Update neighbors
  */
 static void
-UpdateNeighborsInMemory(char *base, Relation index, FmgrInfo **procinfo, Oid *collation, HnswElement e, int m)
+UpdateNeighborsInMemory(char *base, Relation index, HnswSupport * support, HnswElement e, int m)
 {
 	for (int lc = e->level; lc >= 0; lc--)
 	{
@@ -397,7 +387,7 @@ UpdateNeighborsInMemory(char *base, Relation index, FmgrInfo **procinfo, Oid *co
 			Assert(neighborElement);
 
 			LWLockAcquire(&neighborElement->lock, LW_EXCLUSIVE);
-			HnswUpdateConnection(base, HnswGetNeighbors(base, neighborElement, lc), e, hc->distance, lm, NULL, index, procinfo, collation);
+			HnswUpdateConnection(base, HnswGetNeighbors(base, neighborElement, lc), e, hc->distance, lm, NULL, index, support);
 			LWLockRelease(&neighborElement->lock);
 		}
 	}
@@ -407,7 +397,7 @@ UpdateNeighborsInMemory(char *base, Relation index, FmgrInfo **procinfo, Oid *co
  * Update graph in memory
  */
 static void
-UpdateGraphInMemory(FmgrInfo **procinfo, Oid *collation, HnswElement element, int m, int efConstruction, HnswElement entryPoint, HnswBuildState * buildstate)
+UpdateGraphInMemory(HnswSupport * support, HnswElement element, int m, int efConstruction, HnswElement entryPoint, HnswBuildState * buildstate)
 {
 	HnswGraph  *graph = buildstate->graph;
 	char	   *base = buildstate->hnswarea;
@@ -420,7 +410,7 @@ UpdateGraphInMemory(FmgrInfo **procinfo, Oid *collation, HnswElement element, in
 	AddElementInMemory(base, graph, element);
 
 	/* Update neighbors */
-	UpdateNeighborsInMemory(base, buildstate->index, procinfo, collation, element, m);
+	UpdateNeighborsInMemory(base, buildstate->index, support, element, m);
 
 	/* Update entry point if needed (already have lock) */
 	if (entryPoint == NULL || element->level > entryPoint->level)
@@ -434,9 +424,8 @@ static void
 InsertTupleInMemory(HnswBuildState * buildstate, HnswElement element)
 {
 	Relation	index = buildstate->index;
-	FmgrInfo  **procinfo = buildstate->procinfo;
-	Oid		   *collation = buildstate->collation;
 	HnswGraph  *graph = buildstate->graph;
+	HnswSupport *support = &buildstate->support;
 	HnswElement entryPoint;
 	LWLock	   *entryLock = &graph->entryLock;
 	LWLock	   *entryWaitLock = &graph->entryWaitLock;
@@ -468,10 +457,10 @@ InsertTupleInMemory(HnswBuildState * buildstate, HnswElement element)
 	}
 
 	/* Find neighbors for element */
-	HnswFindElementNeighbors(base, element, entryPoint, index, procinfo, collation, m, efConstruction, false, true);
+	HnswFindElementNeighbors(base, element, entryPoint, index, support, m, efConstruction, false, true);
 
 	/* Update graph in memory */
-	UpdateGraphInMemory(procinfo, collation, element, m, efConstruction, entryPoint, buildstate);
+	UpdateGraphInMemory(support, element, m, efConstruction, entryPoint, buildstate);
 
 	/* Release entry lock */
 	LWLockRelease(entryLock);
@@ -483,38 +472,24 @@ InsertTupleInMemory(HnswBuildState * buildstate, HnswElement element)
 static bool
 InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, HnswBuildState * buildstate)
 {
-	const		HnswTypeInfo *typeInfo = buildstate->typeInfo;
 	HnswGraph  *graph = buildstate->graph;
 	HnswElement element;
 	HnswAllocator *allocator = &buildstate->allocator;
-	Size		valueSize;
-	Pointer		valuePtr;
+	HnswSupport *support = &buildstate->support;
 	LWLock	   *flushLock = &graph->flushLock;
 	char	   *base = buildstate->hnswarea;
-	bool		useIndexTuple = buildstate->useIndexTuple;
 	TupleDesc	tupdesc = buildstate->tupdesc;
 	IndexTuple	itup;
 	Size		itupSize;
-	IndexTuple	itupPtr;
+	IndexTuple	itupShared;
+	bool		unused;
 
-	/* Detoast once for all calls */
-	Datum		value = PointerGetDatum(PG_DETOAST_DATUM(values[0]));
+	/* Form index tuple */
+	if (!HnswFormIndexTuple(&itup, values, isnull, buildstate->typeInfo, support, tupdesc))
+		return false;
 
-	/* Check value */
-	if (typeInfo->checkValue != NULL)
-		typeInfo->checkValue(DatumGetPointer(value));
-
-	/* Normalize if needed */
-	if (buildstate->normprocinfo != NULL)
-	{
-		if (!HnswCheckNorm(buildstate->normprocinfo, buildstate->collation[0], value))
-			return false;
-
-		value = HnswNormValue(typeInfo, buildstate->collation[0], value);
-	}
-
-	/* Get datum size */
-	valueSize = VARSIZE_ANY(DatumGetPointer(value));
+	/* Get tuple size */
+	itupSize = IndexTupleSize(itup);
 
 	/* Ensure graph not flushed when inserting */
 	LWLockAcquire(flushLock, LW_SHARED);
@@ -524,7 +499,7 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
 	{
 		LWLockRelease(flushLock);
 
-		return HnswInsertTupleOnDisk(index, value, values, isnull, heaptid, true);
+		return HnswInsertTupleOnDisk(index, support, itup, heaptid, true, tupdesc);
 	}
 
 	/*
@@ -556,22 +531,12 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
 
 		LWLockRelease(flushLock);
 
-		return HnswInsertTupleOnDisk(index, value, values, isnull, heaptid, true);
+		return HnswInsertTupleOnDisk(index, support, itup, heaptid, true, tupdesc);
 	}
 
 	/* Ok, we can proceed to allocate the element */
 	element = HnswInitElement(base, heaptid, buildstate->m, buildstate->ml, buildstate->maxLevel, allocator);
-
-	if (useIndexTuple)
-	{
-		/* TODO fix */
-		values[0] = value;
-		itup = index_form_tuple(tupdesc, values, isnull);
-		itupSize = IndexTupleSize(itup);
-		itupPtr = HnswAlloc(allocator, itupSize);
-	}
-	else
-		valuePtr = HnswAlloc(allocator, valueSize);
+	itupShared = HnswAlloc(allocator, itupSize);
 
 	/*
 	 * We have now allocated the space needed for the element, so we don't
@@ -580,20 +545,10 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
 	 */
 	LWLockRelease(&graph->allocatorLock);
 
-	/* Copy the datum */
-	if (useIndexTuple)
-	{
-		bool		unused;
-
-		memcpy(itupPtr, itup, itupSize);
-		HnswPtrStore(base, element->itup, itupPtr);
-		HnswPtrStore(base, element->value, DatumGetPointer(index_getattr(itupPtr, 1, tupdesc, &unused)));
-	}
-	else
-	{
-		memcpy(valuePtr, DatumGetPointer(value), valueSize);
-		HnswPtrStore(base, element->value, valuePtr);
-	}
+	/* Copy the tuple */
+	memcpy(itupShared, itup, itupSize);
+	HnswPtrStore(base, element->itup, itupShared);
+	HnswPtrStore(base, element->value, DatumGetPointer(index_getattr(itupShared, 1, tupdesc, &unused)));
 
 	/* Create a lock for the element */
 	LWLockInitialize(&element->lock, hnsw_lock_tranche_id);
@@ -753,8 +708,7 @@ InitBuildState(HnswBuildState * buildstate, Relation heap, Relation index, Index
 	buildstate->indtuples = 0;
 
 	/* Get support functions */
-	HnswInitProcinfo(buildstate->procinfo, &buildstate->collation, index);
-	buildstate->normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
+	HnswInitSupport(&buildstate->support, index);
 
 	InitGraph(&buildstate->graphData, NULL, (Size) maintenance_work_mem * 1024L);
 	buildstate->graph = &buildstate->graphData;

src/hnswinsert.c

@@ -36,7 +36,7 @@ GetInsertPage(Relation index)
  * Check for a free offset
  */
 static bool
-HnswFreeOffset(Relation index, Buffer buf, Page page, HnswElement element, Size etupSize, Size ntupSize, Buffer *nbuf, Page *npage, OffsetNumber *freeOffno, OffsetNumber *freeNeighborOffno, BlockNumber *newInsertPage)
+HnswFreeOffset(Relation index, Buffer buf, Page page, HnswElement element, Size etupSize, Size ntupSize, Buffer *nbuf, Page *npage, OffsetNumber *freeOffno, OffsetNumber *freeNeighborOffno, BlockNumber *newInsertPage, uint8 *tupleVersion)
 {
 	OffsetNumber offno;
 	OffsetNumber maxoffno = PageGetMaxOffsetNumber(page);
@@ -98,6 +98,7 @@ HnswFreeOffset(Relation index, Buffer buf, Page page, HnswElement element, Size
 			{
 				*freeOffno = offno;
 				*freeNeighborOffno = neighborOffno;
+				*tupleVersion = etup->version;
 				return true;
 			}
 			else if (*nbuf != buf)
@@ -153,6 +154,7 @@ AddElementOnDisk(Relation index, HnswElement e, int m, BlockNumber insertPage, B
 	OffsetNumber freeOffno = InvalidOffsetNumber;
 	OffsetNumber freeNeighborOffno = InvalidOffsetNumber;
 	BlockNumber newInsertPage = InvalidBlockNumber;
+	uint8		tupleVersion;
 	char	   *base = NULL;
 	bool		useIndexTuple = HnswUseIndexTuple(index);
 
@@ -203,7 +205,7 @@ AddElementOnDisk(Relation index, HnswElement e, int m, BlockNumber insertPage, B
 		}
 
 		/* Next, try space from a deleted element */
-		if (HnswFreeOffset(index, buf, page, e, etupSize, ntupSize, &nbuf, &npage, &freeOffno, &freeNeighborOffno, &newInsertPage))
+		if (HnswFreeOffset(index, buf, page, e, etupSize, ntupSize, &nbuf, &npage, &freeOffno, &freeNeighborOffno, &newInsertPage, &tupleVersion))
 		{
 			if (nbuf != buf)
 			{
@@ -213,6 +215,10 @@ AddElementOnDisk(Relation index, HnswElement e, int m, BlockNumber insertPage, B
 					npage = GenericXLogRegisterBuffer(state, nbuf, 0);
 			}
 
+			/* Set tuple version */
+			etup->version = tupleVersion;
+			ntup->version = tupleVersion;
+
 			break;
 		}
 
@@ -369,7 +375,7 @@ HnswLoadNeighbors(HnswElement element, Relation index, int m, int lm, int lc)
  * Load elements for insert
  */
 static void
-LoadElementsForInsert(HnswNeighborArray * neighbors, Datum q, IndexTuple qtup, int *idx, Relation index, FmgrInfo **procinfo, Oid *collation)
+LoadElementsForInsert(HnswNeighborArray * neighbors, HnswQuery * q, int *idx, Relation index, HnswSupport * support)
 {
 	char	   *base = NULL;
 
@@ -380,7 +386,7 @@ LoadElementsForInsert(HnswNeighborArray * neighbors, Datum q, IndexTuple qtup, i
 		double		distance;
 		bool		matches;
 
-		HnswLoadElement(element, &distance, &matches, &q, qtup, NULL, index, procinfo, collation, true, NULL);
+		HnswLoadElement(element, &distance, &matches, q, index, support, true, NULL);
 		hc->distance = distance;
 
 		/* Prune element if being deleted */
@@ -396,7 +402,7 @@ LoadElementsForInsert(HnswNeighborArray * neighbors, Datum q, IndexTuple qtup, i
  * Get update index
  */
 static int
-GetUpdateIndex(HnswElement element, HnswElement newElement, float distance, int m, int lm, int lc, Relation index, FmgrInfo **procinfo, Oid *collation, MemoryContext updateCtx)
+GetUpdateIndex(HnswElement element, HnswElement newElement, float distance, int m, int lm, int lc, Relation index, HnswSupport * support, MemoryContext updateCtx)
 {
 	char	   *base = NULL;
 	int			idx = -1;
@@ -421,13 +427,16 @@ GetUpdateIndex(HnswElement element, HnswElement newElement, float distance, int
 		idx = -2;
 	else
 	{
-		Datum		q = HnswGetValue(base, element);
-		IndexTuple	qtup = HnswPtrAccess(base, element->itup);;
+		HnswQuery	q;
 
-		LoadElementsForInsert(neighbors, q, qtup, &idx, index, procinfo, collation);
+		q.value = HnswGetValue(base, element);
+		q.itup = HnswPtrAccess(base, element->itup);
+		q.keyData = NULL;
+
+		LoadElementsForInsert(neighbors, &q, &idx, index, support);
 
 		if (idx == -1)
-			HnswUpdateConnection(base, neighbors, newElement, distance, lm, &idx, index, procinfo, collation);
+			HnswUpdateConnection(base, neighbors, newElement, distance, lm, &idx, index, support);
 	}
 
 	MemoryContextSwitchTo(oldCtx);
@@ -532,7 +541,7 @@ UpdateNeighborOnDisk(HnswElement element, HnswElement newElement, int idx, int m
  * Update neighbors
  */
 void
-HnswUpdateNeighborsOnDisk(Relation index, FmgrInfo **procinfo, Oid *collation, HnswElement e, int m, bool checkExisting, bool building)
+HnswUpdateNeighborsOnDisk(Relation index, HnswSupport * support, HnswElement e, int m, bool checkExisting, bool building)
 {
 	char	   *base = NULL;
 
@@ -555,7 +564,7 @@ HnswUpdateNeighborsOnDisk(Relation index, FmgrInfo **procinfo, Oid *collation, H
 			HnswElement neighborElement = HnswPtrAccess(base, hc->element);
 			int			idx;
 
-			idx = GetUpdateIndex(neighborElement, e, hc->distance, m, lm, lc, index, procinfo, collation, updateCtx);
+			idx = GetUpdateIndex(neighborElement, e, hc->distance, m, lm, lc, index, support, updateCtx);
 
 			/* New element was not selected as a neighbor */
 			if (idx == -1)
@@ -628,13 +637,12 @@ AddDuplicateOnDisk(Relation index, HnswElement element, HnswElement dup, bool bu
  * Find duplicate element
  */
 static bool
-FindDuplicateOnDisk(Relation index, HnswElement element, bool building)
+FindDuplicateOnDisk(Relation index, HnswElement element, bool building, TupleDesc tupdesc)
 {
 	char	   *base = NULL;
 	HnswNeighborArray *neighbors = HnswGetNeighbors(base, element, 0);
 	Datum		value = HnswGetValue(base, element);
 	IndexTuple	itup = HnswPtrAccess(base, element->itup);
-	TupleDesc	tupdesc = RelationGetDescr(index);
 
 	for (int i = 0; i < neighbors->length; i++)
 	{
@@ -665,12 +673,12 @@ FindDuplicateOnDisk(Relation index, HnswElement element, bool building)
  * Update graph on disk
  */
 static void
-UpdateGraphOnDisk(Relation index, FmgrInfo **procinfo, Oid *collation, HnswElement element, int m, int efConstruction, HnswElement entryPoint, bool building)
+UpdateGraphOnDisk(Relation index, HnswSupport * support, HnswElement element, int m, int efConstruction, HnswElement entryPoint, bool building, TupleDesc tupdesc)
 {
 	BlockNumber newInsertPage = InvalidBlockNumber;
 
 	/* Look for duplicate */
-	if (FindDuplicateOnDisk(index, element, building))
+	if (FindDuplicateOnDisk(index, element, building, tupdesc))
 		return;
 
 	/* Add element */
@@ -681,7 +689,7 @@ UpdateGraphOnDisk(Relation index, FmgrInfo **procinfo, Oid *collation, HnswEleme
 		HnswUpdateMetaPage(index, 0, NULL, newInsertPage, MAIN_FORKNUM, building);
 
 	/* Update neighbors */
-	HnswUpdateNeighborsOnDisk(index, procinfo, collation, element, m, false, building);
+	HnswUpdateNeighborsOnDisk(index, support, element, m, false, building);
 
 	/* Update entry point if needed */
 	if (entryPoint == NULL || element->level > entryPoint->level)
@@ -692,18 +700,15 @@ UpdateGraphOnDisk(Relation index, FmgrInfo **procinfo, Oid *collation, HnswEleme
  * Insert a tuple into the index
  */
 bool
-HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull, ItemPointer heap_tid, bool building)
+HnswInsertTupleOnDisk(Relation index, HnswSupport * support, IndexTuple itup, ItemPointer heaptid, bool building, TupleDesc tupdesc)
 {
 	HnswElement entryPoint;
 	HnswElement element;
 	int			m;
 	int			efConstruction = HnswGetEfConstruction(index);
-	FmgrInfo   *procinfo[2];
-	Oid		   *collation;
 	LOCKMODE	lockmode = ShareLock;
 	char	   *base = NULL;
-
-	HnswInitProcinfo(procinfo, &collation, index);
+	bool		unused;
 
 	/*
 	 * Get a shared lock. This allows vacuum to ensure no in-flight inserts
@@ -716,24 +721,9 @@ HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull,
 	HnswGetMetaPageInfo(index, &m, &entryPoint);
 
 	/* Create an element */
-	element = HnswInitElement(base, heap_tid, m, HnswGetMl(m), HnswGetMaxLevel(m), NULL);
-	if (HnswUseIndexTuple(index))
-	{
-		/* TODO no toast */
-		TupleDesc	tupdesc = RelationGetDescr(index);
-		IndexTuple	itup;
-		bool		unused;
-
-		/* TODO fix */
-		values[0] = value;
-		itup = index_form_tuple(tupdesc, values, isnull);
-
-		HnswPtrStore(base, element->itup, itup);
-		HnswPtrStore(base, element->value, DatumGetPointer(index_getattr(itup, 1, tupdesc, &unused)));
-
-	}
-	else
-		HnswPtrStore(base, element->value, DatumGetPointer(value));
+	element = HnswInitElement(base, heaptid, m, HnswGetMl(m), HnswGetMaxLevel(m), NULL);
+	HnswPtrStore(base, element->itup, itup);
+	HnswPtrStore(base, element->value, DatumGetPointer(index_getattr(itup, 1, tupdesc, &unused)));
 
 	/* Prevent concurrent inserts when likely updating entry point */
 	if (entryPoint == NULL || element->level > entryPoint->level)
@@ -750,10 +740,10 @@ HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull,
 	}
 
 	/* Find neighbors for element */
-	HnswFindElementNeighbors(base, element, entryPoint, index, procinfo, collation, m, efConstruction, false, false);
+	HnswFindElementNeighbors(base, element, entryPoint, index, support, m, efConstruction, false, false);
 
 	/* Update graph on disk */
-	UpdateGraphOnDisk(index, procinfo, collation, element, m, efConstruction, entryPoint, building);
+	UpdateGraphOnDisk(index, support, element, m, efConstruction, entryPoint, building, tupdesc);
 
 	/* Release lock */
 	UnlockPage(index, HNSW_UPDATE_LOCK, lockmode);
@@ -765,31 +755,20 @@ HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull,
  * Insert a tuple into the index
  */
 static void
-HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid)
+HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid)
 {
-	Datum		value;
+	IndexTuple	itup;
 	const		HnswTypeInfo *typeInfo = HnswGetTypeInfo(index);
-	FmgrInfo   *normprocinfo;
-	Oid		   *collation = index->rd_indcollation;
+	TupleDesc	tupdesc = RelationGetDescr(index);
+	HnswSupport support;
 
-	/* Detoast once for all calls */
-	value = PointerGetDatum(PG_DETOAST_DATUM(values[0]));
+	HnswInitSupport(&support, index);
 
-	/* Check value */
-	if (typeInfo->checkValue != NULL)
-		typeInfo->checkValue(DatumGetPointer(value));
+	/* Form index tuple */
+	if (!HnswFormIndexTuple(&itup, values, isnull, typeInfo, &support, tupdesc))
+		return;
 
-	/* Normalize if needed */
-	normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
-	if (normprocinfo != NULL)
-	{
-		if (!HnswCheckNorm(normprocinfo, collation[0], value))
-			return;
-
-		value = HnswNormValue(typeInfo, collation[0], value);
-	}
-
-	HnswInsertTupleOnDisk(index, value, values, isnull, heap_tid, false);
+	HnswInsertTupleOnDisk(index, &support, itup, heaptid, false, tupdesc);
 }
 
 /*

src/hnswscan.c

@@ -5,41 +5,78 @@
 #include "pgstat.h"
 #include "storage/bufmgr.h"
 #include "storage/lmgr.h"
+#include "utils/float.h"
 #include "utils/memutils.h"
 
 /*
  * Algorithm 5 from paper
  */
 static List *
-GetScanItems(IndexScanDesc scan, Datum q)
+GetScanItems(IndexScanDesc scan, Datum value)
 {
 	HnswScanOpaque so = (HnswScanOpaque) scan->opaque;
 	Relation	index = scan->indexRelation;
-	FmgrInfo  **procinfo = so->procinfo;
-	Oid		   *collation = so->collation;
+	HnswSupport *support = &so->support;
 	List	   *ep;
 	List	   *w;
 	int			m;
 	HnswElement entryPoint;
 	char	   *base = NULL;
 	bool		inMemory = false;
-	ScanKeyData *keyData = scan->keyData;
+	HnswQuery  *q = &so->q;
+
+	q->value = value;
+	q->itup = NULL;
+	q->keyData = scan->keyData;
 
 	/* Get m and entry point */
 	HnswGetMetaPageInfo(index, &m, &entryPoint);
 
+	so->m = m;
+
 	if (entryPoint == NULL)
 		return NIL;
 
-	ep = list_make1(HnswEntryCandidate(base, entryPoint, q, NULL, keyData, index, procinfo, collation, false, inMemory));
+	ep = list_make1(HnswEntryCandidate(base, entryPoint, q, index, support, false, inMemory));
 
 	for (int lc = entryPoint->level; lc >= 1; lc--)
 	{
-		w = HnswSearchLayer(base, q, NULL, keyData, ep, 1, lc, index, procinfo, collation, m, false, NULL, inMemory);
+		w = HnswSearchLayer(base, q, ep, 1, lc, index, support, m, false, NULL, inMemory, NULL, NULL, true, NULL);
 		ep = w;
 	}
 
-	return HnswSearchLayer(base, q, NULL, keyData, ep, hnsw_ef_search, 0, index, procinfo, collation, m, false, NULL, inMemory);
+	return HnswSearchLayer(base, q, ep, hnsw_ef_search, 0, index, support, m, false, NULL, inMemory, &so->v, hnsw_iterative_search != HNSW_ITERATIVE_SEARCH_OFF ? &so->discarded : NULL, true, &so->tuples);
+}
+
+/*
+ * Resume scan at ground level with discarded candidates
+ */
+static List *
+ResumeScanItems(IndexScanDesc scan)
+{
+	HnswScanOpaque so = (HnswScanOpaque) scan->opaque;
+	Relation	index = scan->indexRelation;
+	List	   *ep = NIL;
+	char	   *base = NULL;
+	int			batch_size = hnsw_ef_search;
+
+	if (pairingheap_is_empty(so->discarded))
+		return NIL;
+
+	/* Get next batch of candidates */
+	for (int i = 0; i < batch_size; i++)
+	{
+		HnswSearchCandidate *sc;
+
+		if (pairingheap_is_empty(so->discarded))
+			break;
+
+		sc = HnswGetSearchCandidate(w_node, pairingheap_remove_first(so->discarded));
+
+		ep = lappend(ep, sc);
+	}
+
+	return HnswSearchLayer(base, &so->q, ep, batch_size, 0, index, &so->support, so->m, false, NULL, false, &so->v, &so->discarded, false, &so->tuples);
 }
 
 /*
@@ -62,8 +99,8 @@ GetScanValue(IndexScanDesc scan)
 		Assert(!VARATT_IS_EXTENDED(DatumGetPointer(value)));
 
 		/* Normalize if needed */
-		if (so->normprocinfo != NULL)
-			value = HnswNormValue(so->typeInfo, so->collation[0], value);
+		if (so->support.normprocinfo != NULL)
+			value = HnswNormValue(so->typeInfo, so->support.collation[0], value);
 	}
 
 	return value;
@@ -83,13 +120,14 @@ hnswbeginscan(Relation index, int nkeys, int norderbys)
 	so = (HnswScanOpaque) palloc(sizeof(HnswScanOpaqueData));
 	so->typeInfo = HnswGetTypeInfo(index);
 	so->first = true;
+	so->v.tids = NULL;
+	so->discarded = NULL;
 	so->tmpCtx = AllocSetContextCreate(CurrentMemoryContext,
 									   "Hnsw scan temporary context",
 									   ALLOCSET_DEFAULT_SIZES);
 
 	/* Set support functions */
-	HnswInitProcinfo(so->procinfo, &so->collation, index);
-	so->normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
+	HnswInitSupport(&so->support, index);
 
 	scan->opaque = so;
 
@@ -104,7 +142,15 @@ hnswrescan(IndexScanDesc scan, ScanKey keys, int nkeys, ScanKey orderbys, int no
 {
 	HnswScanOpaque so = (HnswScanOpaque) scan->opaque;
 
+	if (so->v.tids != NULL)
+		tidhash_reset(so->v.tids);
+
+	if (so->discarded != NULL)
+		pairingheap_reset(so->discarded);
+
 	so->first = true;
+	so->tuples = 0;
+	so->previousDistance = -get_float8_infinity();
 	MemoryContextReset(so->tmpCtx);
 
 	if (keys && scan->numberOfKeys > 0)
@@ -166,22 +212,100 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
 #endif
 	}
 
-	while (list_length(so->w) > 0)
+	for (;;)
 	{
 		char	   *base = NULL;
-		HnswSearchCandidate *hc = llast(so->w);
-		HnswElement element = HnswPtrAccess(base, hc->element);
+		HnswSearchCandidate *sc;
+		HnswElement element;
 		ItemPointer heaptid;
 
+		if (list_length(so->w) == 0)
+		{
+			if (hnsw_iterative_search == HNSW_ITERATIVE_SEARCH_OFF)
+				break;
+
+			/* Empty index */
+			if (so->discarded == NULL)
+				break;
+
+			/* Reached max number of additional tuples */
+			if (hnsw_iterative_search_max_tuples != -1 && so->tuples >= hnsw_iterative_search_max_tuples)
+			{
+				if (pairingheap_is_empty(so->discarded))
+					break;
+
+				/* Return remaining tuples */
+				so->w = lappend(so->w, HnswGetSearchCandidate(w_node, pairingheap_remove_first(so->discarded)));
+			}
+			/* Prevent scans from consuming too much memory */
+			else if (MemoryContextMemAllocated(so->tmpCtx, false) > (Size) work_mem * 1024L)
+			{
+				if (pairingheap_is_empty(so->discarded))
+				{
+					ereport(DEBUG1,
+							(errmsg("hnsw index scan exceeded work_mem after " INT64_FORMAT " tuples", so->tuples),
+							 errhint("Increase work_mem to scan more tuples.")));
+
+					break;
+				}
+
+				/* Return remaining tuples */
+				so->w = lappend(so->w, HnswGetSearchCandidate(w_node, pairingheap_remove_first(so->discarded)));
+			}
+			else
+			{
+				/*
+				 * Locking ensures when neighbors are read, the elements they
+				 * reference will not be deleted (and replaced) during the
+				 * iteration.
+				 *
+				 * Elements loaded into memory on previous iterations may have
+				 * been deleted (and replaced), so when reading neighbors, the
+				 * element version must be checked.
+				 */
+				LockPage(scan->indexRelation, HNSW_SCAN_LOCK, ShareLock);
+
+				so->w = ResumeScanItems(scan);
+
+				UnlockPage(scan->indexRelation, HNSW_SCAN_LOCK, ShareLock);
+
+#if defined(HNSW_MEMORY)
+				elog(INFO, "memory: %zu KB", MemoryContextMemAllocated(so->tmpCtx, false) / 1024);
+#endif
+			}
+
+			if (list_length(so->w) == 0)
+				break;
+		}
+
+		sc = llast(so->w);
+		element = HnswPtrAccess(base, sc->element);
+
 		/* Move to next element if no valid heap TIDs */
-		if (!hc->matches || element->heaptidsLength == 0)
+		if (!sc->matches || element->heaptidsLength == 0)
 		{
 			so->w = list_delete_last(so->w);
+
+			/* Mark memory as free for next iteration */
+			if (hnsw_iterative_search != HNSW_ITERATIVE_SEARCH_OFF)
+			{
+				pfree(element);
+				pfree(sc);
+			}
+
 			continue;
 		}
 
 		heaptid = &element->heaptids[--element->heaptidsLength];
 
+		if (hnsw_iterative_search == HNSW_ITERATIVE_SEARCH_STRICT)
+		{
+			if (sc->distance < so->previousDistance)
+				continue;
+
+			so->previousDistance = sc->distance;
+		}
+
 		MemoryContextSwitchTo(oldCtx);
 
 		scan->xs_heaptid = *heaptid;

src/hnswutils.c

@@ -100,19 +100,6 @@ hash_offset(Size offset)
 #define SH_DEFINE
 #include "lib/simplehash.h"
 
-typedef union
-{
-	pointerhash_hash *pointers;
-	offsethash_hash *offsets;
-	tidhash_hash *tids;
-}			visited_hash;
-
-typedef union
-{
-	HnswElement element;
-	ItemPointerData indextid;
-}			HnswUnvisited;
-
 /*
  * Get the max number of connections in an upper layer for each element in the index
  */
@@ -154,17 +141,18 @@ HnswOptionalProcInfo(Relation index, uint16 procnum)
 }
 
 /*
- * Init procinfo
+ * Init support functions
  */
 void
-HnswInitProcinfo(FmgrInfo **procinfo, Oid **collation, Relation index)
+HnswInitSupport(HnswSupport * support, Relation index)
 {
-	procinfo[0] = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
+	support->procinfo[0] = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
 
 	if (IndexRelationGetNumberOfKeyAttributes(index) > 1)
-		procinfo[1] = index_getprocinfo(index, 2, HNSW_ATTRIBUTE_DISTANCE_PROC);
+		support->procinfo[1] = index_getprocinfo(index, 2, HNSW_ATTRIBUTE_DISTANCE_PROC);
 
-	*collation = index->rd_indcollation;
+	support->collation = index->rd_indcollation;
+	support->normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
 }
 
 /*
@@ -204,9 +192,9 @@ HnswNormValue(const HnswTypeInfo * typeInfo, Oid collation, Datum value)
  * Check if non-zero norm
  */
 bool
-HnswCheckNorm(FmgrInfo *procinfo, Oid collation, Datum value)
+HnswCheckNorm(HnswSupport * support, Datum value)
 {
-	return DatumGetFloat8(FunctionCall1Coll(procinfo, collation, value)) > 0;
+	return DatumGetFloat8(FunctionCall1Coll(support->normprocinfo, support->collation[0], value)) > 0;
 }
 
 /*
@@ -322,6 +310,8 @@ HnswInitElement(char *base, ItemPointer heaptid, int m, double ml, int maxLevel,
 
 	element->level = level;
 	element->deleted = 0;
+	/* Start at one to make it easier to find issues */
+	element->version = 1;
 
 	HnswInitNeighbors(base, element, m, allocator);
 
@@ -465,6 +455,39 @@ HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, Bloc
 	UnlockReleaseBuffer(buf);
 }
 
+/*
+ * Form index tuple
+ */
+bool
+HnswFormIndexTuple(IndexTuple *out, Datum *values, bool *isnull, const HnswTypeInfo * typeInfo, HnswSupport * support, TupleDesc tupdesc)
+{
+	Datum		newValues[2];
+
+	/* Detoast once for all calls */
+	Datum		value = PointerGetDatum(PG_DETOAST_DATUM(values[0]));
+
+	/* Check value */
+	if (typeInfo->checkValue != NULL)
+		typeInfo->checkValue(DatumGetPointer(value));
+
+	/* Normalize if needed */
+	if (support->normprocinfo != NULL)
+	{
+		if (!HnswCheckNorm(support, value))
+			return false;
+
+		value = HnswNormValue(typeInfo, support->collation[0], value);
+	}
+
+	newValues[0] = value;
+	for (int i = 1; i < tupdesc->natts; i++)
+		newValues[i] = values[i];
+
+	*out = index_form_tuple(tupdesc, newValues, isnull);
+
+	return true;
+}
+
 /*
  * Set element tuple, except for neighbor info
  */
@@ -474,6 +497,7 @@ HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element, bool
 	etup->type = HNSW_ELEMENT_TUPLE_TYPE;
 	etup->level = element->level;
 	etup->deleted = 0;
+	etup->version = element->version;
 	for (int i = 0; i < HNSW_HEAPTIDS; i++)
 	{
 		if (i < element->heaptidsLength)
@@ -528,6 +552,7 @@ HnswSetNeighborTuple(char *base, HnswNeighborTuple ntup, HnswElement e, int m)
 	}
 
 	ntup->count = idx;
+	ntup->version = e->version;
 }
 
 /*
@@ -538,6 +563,7 @@ HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHe
 {
 	element->level = etup->level;
 	element->deleted = etup->deleted;
+	element->version = etup->version;
 	element->neighborPage = ItemPointerGetBlockNumber(&etup->neighbortid);
 	element->neighborOffno = ItemPointerGetOffsetNumber(&etup->neighbortid);
 	element->heaptidsLength = 0;
@@ -593,14 +619,14 @@ AttributeDistance(double e)
  * Calculate the distance between values
  */
 static double
-HnswGetDistance(IndexTuple itup, Datum vec, Datum q, IndexTuple qtup, ScanKeyData *keyData, Relation index, FmgrInfo **procinfo, Oid *collation, bool *matches)
+HnswGetDistance(IndexTuple itup, Datum vec, HnswQuery * q, Relation index, HnswSupport * support, bool *matches)
 {
 	double		g;
 
-	if (DatumGetPointer(q) == NULL)
+	if (DatumGetPointer(q->value) == NULL)
 		g = 0;
 	else
-		g = DatumGetFloat8(FunctionCall2Coll(procinfo[0], collation[0], q, vec));
+		g = DatumGetFloat8(FunctionCall2Coll(support->procinfo[0], support->collation[0], q->value, vec));
 
 	Assert(PointerIsValid(matches));
 	*matches = true;
@@ -611,14 +637,14 @@ HnswGetDistance(IndexTuple itup, Datum vec, Datum q, IndexTuple qtup, ScanKeyDat
 		double		e = 0.0;
 		TupleDesc	tupdesc = RelationGetDescr(index);
 
-		if (keyData)
+		if (q->keyData)
 		{
 			/* TODO need to pass length of key data */
 			int			keyCount = 1;
 
 			for (int i = 0; i < keyCount; i++)
 			{
-				ScanKey		key = &keyData[i];
+				ScanKey		key = &q->keyData[i];
 				bool		isnull;
 				Datum		value = index_getattr(itup, key->sk_attno, tupdesc, &isnull);
 				bool		attnull = key->sk_flags & SK_ISNULL;
@@ -633,7 +659,7 @@ HnswGetDistance(IndexTuple itup, Datum vec, Datum q, IndexTuple qtup, ScanKeyDat
 				}
 				else if (!DatumGetBool(FunctionCall2Coll(&key->sk_func, key->sk_collation, value, key->sk_argument)))
 				{
-					double		ei = fabs(DatumGetFloat8(FunctionCall2Coll(procinfo[key->sk_attno - 1], collation[key->sk_attno - 1], value, key->sk_argument)));
+					double		ei = fabs(DatumGetFloat8(FunctionCall2Coll(support->procinfo[key->sk_attno - 1], support->collation[key->sk_attno - 1], value, key->sk_argument)));
 
 					if (ei > 0)
 						e += ei;
@@ -647,7 +673,7 @@ HnswGetDistance(IndexTuple itup, Datum vec, Datum q, IndexTuple qtup, ScanKeyDat
 
 			return w * g + AttributeDistance(e);
 		}
-		else if (qtup)
+		else if (q->itup)
 		{
 			int			keyCount = IndexRelationGetNumberOfKeyAttributes(index) - 1;
 
@@ -656,7 +682,7 @@ HnswGetDistance(IndexTuple itup, Datum vec, Datum q, IndexTuple qtup, ScanKeyDat
 				bool		isnull;
 				bool		attnull;
 				Datum		value = index_getattr(itup, i + 2, tupdesc, &isnull);
-				Datum		value2 = index_getattr(qtup, i + 2, tupdesc, &attnull);
+				Datum		value2 = index_getattr(q->itup, i + 2, tupdesc, &attnull);
 
 				if (isnull || attnull)
 				{
@@ -664,7 +690,7 @@ HnswGetDistance(IndexTuple itup, Datum vec, Datum q, IndexTuple qtup, ScanKeyDat
 						e += 1000;
 				}
 				else
-					e += fabs(DatumGetFloat8(FunctionCall2Coll(procinfo[i + 1], collation[i + 1], value, value2)));
+					e += fabs(DatumGetFloat8(FunctionCall2Coll(support->procinfo[i + 1], support->collation[i + 1], value, value2)));
 			}
 
 			return w * g + AttributeDistance(e);
@@ -678,7 +704,7 @@ HnswGetDistance(IndexTuple itup, Datum vec, Datum q, IndexTuple qtup, ScanKeyDat
  * Load an element and optionally get its distance from q
  */
 static void
-HnswLoadElementImpl(BlockNumber blkno, OffsetNumber offno, double *distance, bool *matches, Datum *q, IndexTuple qtup, ScanKeyData *keyData, Relation index, FmgrInfo **procinfo, Oid *collation, bool loadVec, double *maxDistance, HnswElement * element)
+HnswLoadElementImpl(BlockNumber blkno, OffsetNumber offno, double *distance, bool *matches, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec, double *maxDistance, HnswElement * element)
 {
 	Buffer		buf;
 	Page		page;
@@ -712,7 +738,7 @@ HnswLoadElementImpl(BlockNumber blkno, OffsetNumber offno, double *distance, boo
 			value = PointerGetDatum(&etup->data);
 		}
 
-		*distance = HnswGetDistance(itup, value, *q, qtup, keyData, index, procinfo, collation, matches);
+		*distance = HnswGetDistance(itup, value, q, index, support, matches);
 	}
 
 	/* Load element */
@@ -731,42 +757,39 @@ HnswLoadElementImpl(BlockNumber blkno, OffsetNumber offno, double *distance, boo
  * Load an element and optionally get its distance from q
  */
 void
-HnswLoadElement(HnswElement element, double *distance, bool *matches, Datum *q, IndexTuple qtup, ScanKeyData *keyData, Relation index, FmgrInfo **procinfo, Oid *collation, bool loadVec, double *maxDistance)
+HnswLoadElement(HnswElement element, double *distance, bool *matches, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec, double *maxDistance)
 {
-	HnswLoadElementImpl(element->blkno, element->offno, distance, matches, q, qtup, keyData, index, procinfo, collation, loadVec, maxDistance, &element);
+	HnswLoadElementImpl(element->blkno, element->offno, distance, matches, q, index, support, loadVec, maxDistance, &element);
 }
 
 /*
  * Get the distance for an element
  */
 static double
-GetElementDistance(char *base, HnswElement element, bool *matches, Datum q, IndexTuple qtup, ScanKeyData *keyData, Relation index, FmgrInfo **procinfo, Oid *collation)
+GetElementDistance(char *base, HnswElement element, bool *matches, HnswQuery * q, Relation index, HnswSupport * support)
 {
 	Datum		value = HnswGetValue(base, element);
 	IndexTuple	itup = HnswPtrAccess(base, element->itup);
 
-	return HnswGetDistance(itup, value, q, qtup, keyData, index, procinfo, collation, matches);
+	return HnswGetDistance(itup, value, q, index, support, matches);
 }
 
 /*
  * Create a candidate for the entry point
  */
 HnswSearchCandidate *
-HnswEntryCandidate(char *base, HnswElement entryPoint, Datum q, IndexTuple qtup, ScanKeyData *keyData, Relation index, FmgrInfo **procinfo, Oid *collation, bool loadVec, bool inMemory)
+HnswEntryCandidate(char *base, HnswElement entryPoint, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec, bool inMemory)
 {
 	HnswSearchCandidate *sc = palloc(sizeof(HnswSearchCandidate));
 
 	HnswPtrStore(base, sc->element, entryPoint);
 	if (inMemory)
-		sc->distance = GetElementDistance(base, entryPoint, &sc->matches, q, qtup, keyData, index, procinfo, collation);
+		sc->distance = GetElementDistance(base, entryPoint, &sc->matches, q, index, support);
 	else
-		HnswLoadElement(entryPoint, &sc->distance, &sc->matches, &q, qtup, keyData, index, procinfo, collation, loadVec, NULL);
+		HnswLoadElement(entryPoint, &sc->distance, &sc->matches, q, index, support, loadVec, NULL);
 	return sc;
 }
 
-#define HnswGetSearchCandidate(membername, ptr) pairingheap_container(HnswSearchCandidate, membername, ptr)
-#define HnswGetSearchCandidateConst(membername, ptr) pairingheap_const_container(HnswSearchCandidate, membername, ptr)
-
 /*
  * Compare candidate distances
  */
@@ -782,6 +805,21 @@ CompareNearestCandidates(const pairingheap_node *a, const pairingheap_node *b, v
 	return 0;
 }
 
+/*
+ * Compare discarded candidate distances
+ */
+static int
+CompareNearestDiscardedCandidates(const pairingheap_node *a, const pairingheap_node *b, void *arg)
+{
+	if (HnswGetSearchCandidateConst(w_node, a)->distance < HnswGetSearchCandidateConst(w_node, b)->distance)
+		return 1;
+
+	if (HnswGetSearchCandidateConst(w_node, a)->distance > HnswGetSearchCandidateConst(w_node, b)->distance)
+		return -1;
+
+	return 0;
+}
+
 /*
  * Compare candidate distances
  */
@@ -902,8 +940,11 @@ HnswLoadNeighborTids(HnswElement element, ItemPointerData *indextids, Relation i
 
 	ntup = (HnswNeighborTuple) PageGetItem(page, PageGetItemId(page, element->neighborOffno));
 
-	/* Ensure expected neighbors */
-	if (ntup->count != (element->level + 2) * m)
+	/*
+	 * Ensure the neighbor tuple has not been deleted or replaced between
+	 * index scan iterations
+	 */
+	if (ntup->version != element->version || ntup->count != (element->level + 2) * m)
 	{
 		UnlockReleaseBuffer(buf);
 		return false;
@@ -949,13 +990,13 @@ HnswLoadUnvisitedFromDisk(HnswElement element, HnswUnvisited * unvisited, int *u
  * Algorithm 2 from paper
  */
 List *
-HnswSearchLayer(char *base, Datum q, IndexTuple qtup, ScanKeyData *keyData, List *ep, int ef, int lc, Relation index, FmgrInfo **procinfo, Oid *collation, int m, bool inserting, HnswElement skipElement, bool inMemory)
+HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation index, HnswSupport * support, int m, bool inserting, HnswElement skipElement, bool inMemory, visited_hash * v, pairingheap **discarded, bool initVisited, int64 *tuples)
 {
 	List	   *w = NIL;
 	pairingheap *C = pairingheap_allocate(CompareNearestCandidates, NULL);
 	pairingheap *W = pairingheap_allocate(CompareFurthestCandidates, NULL);
 	int			wlen = 0;
-	visited_hash v;
+	visited_hash vh;
 	ListCell   *lc2;
 	HnswNeighborArray *localNeighborhood = NULL;
 	Size		neighborhoodSize = 0;
@@ -963,9 +1004,21 @@ HnswSearchLayer(char *base, Datum q, IndexTuple qtup, ScanKeyData *keyData, List
 	HnswUnvisited *unvisited = palloc(lm * sizeof(HnswUnvisited));
 	int			unvisitedLength;
 	uint64		additional = 0;
-	uint64		maxAdditional = keyData && lc == 0 ? 10000 : 0;
+	uint64		maxAdditional = q->keyData && lc == 0 ? 10000 : 0;
 
-	InitVisited(base, &v, inMemory, ef, m);
+	if (v == NULL)
+	{
+		v = &vh;
+		initVisited = true;
+	}
+
+	if (initVisited)
+	{
+		InitVisited(base, v, inMemory, ef, m);
+
+		if (discarded != NULL)
+			*discarded = pairingheap_allocate(CompareNearestDiscardedCandidates, NULL);
+	}
 
 	/* Create local memory for neighborhood if needed */
 	if (inMemory)
@@ -980,7 +1033,13 @@ HnswSearchLayer(char *base, Datum q, IndexTuple qtup, ScanKeyData *keyData, List
 		HnswSearchCandidate *sc = (HnswSearchCandidate *) lfirst(lc2);
 		bool		found;
 
-		AddToVisited(base, &v, sc->element, inMemory, &found);
+		if (initVisited)
+		{
+			AddToVisited(base, v, sc->element, inMemory, &found);
+
+			if (tuples != NULL)
+				(*tuples)++;
+		}
 
 		pairingheap_add(C, &sc->c_node);
 		pairingheap_add(W, &sc->w_node);
@@ -1010,9 +1069,12 @@ HnswSearchLayer(char *base, Datum q, IndexTuple qtup, ScanKeyData *keyData, List
 		cElement = HnswPtrAccess(base, c->element);
 
 		if (inMemory)
-			HnswLoadUnvisitedFromMemory(base, cElement, unvisited, &unvisitedLength, &v, lc, localNeighborhood, neighborhoodSize);
+			HnswLoadUnvisitedFromMemory(base, cElement, unvisited, &unvisitedLength, v, lc, localNeighborhood, neighborhoodSize);
 		else
-			HnswLoadUnvisitedFromDisk(cElement, unvisited, &unvisitedLength, &v, index, m, lm, lc);
+			HnswLoadUnvisitedFromDisk(cElement, unvisited, &unvisitedLength, v, index, m, lm, lc);
+
+		if (tuples != NULL)
+			(*tuples) += unvisitedLength;
 
 		for (int i = 0; i < unvisitedLength; i++)
 		{
@@ -1027,7 +1089,7 @@ HnswSearchLayer(char *base, Datum q, IndexTuple qtup, ScanKeyData *keyData, List
 			if (inMemory)
 			{
 				eElement = unvisited[i].element;
-				eDistance = GetElementDistance(base, eElement, &eMatches, q, qtup, keyData, index, procinfo, collation);
+				eDistance = GetElementDistance(base, eElement, &eMatches, q, index, support);
 			}
 			else
 			{
@@ -1037,16 +1099,25 @@ HnswSearchLayer(char *base, Datum q, IndexTuple qtup, ScanKeyData *keyData, List
 
 				/* Avoid any allocations if not adding */
 				eElement = NULL;
-				HnswLoadElementImpl(blkno, offno, &eDistance, &eMatches, &q, qtup, keyData, index, procinfo, collation, inserting, alwaysAdd ? NULL : &f->distance, &eElement);
+				HnswLoadElementImpl(blkno, offno, &eDistance, &eMatches, q, index, support, inserting, alwaysAdd || discarded != NULL ? NULL : &f->distance, &eElement);
 
 				if (eElement == NULL)
 					continue;
 			}
 
-			if (!(eDistance < f->distance || alwaysAdd))
-				continue;
+			if (eElement == NULL || !(eDistance < f->distance || alwaysAdd))
+			{
+				if (discarded != NULL)
+				{
+					/* Create a new candidate */
+					e = palloc(sizeof(HnswSearchCandidate));
+					HnswPtrStore(base, e->element, eElement);
+					e->distance = eDistance;
+					pairingheap_add(*discarded, &e->w_node);
+				}
 
-			Assert(!eElement->deleted);
+				continue;
+			}
 
 			/* Make robust to issues */
 			if (eElement->level < lc)
@@ -1075,7 +1146,12 @@ HnswSearchLayer(char *base, Datum q, IndexTuple qtup, ScanKeyData *keyData, List
 
 				/* No need to decrement wlen */
 				if (wlen > ef)
-					pairingheap_remove_first(W);
+				{
+					HnswSearchCandidate *d = HnswGetSearchCandidate(w_node, pairingheap_remove_first(W));
+
+					if (discarded != NULL)
+						pairingheap_add(*discarded, &d->w_node);
+				}
 			}
 		}
 	}
@@ -1143,13 +1219,16 @@ CompareCandidateDistancesOffset(const ListCell *a, const ListCell *b)
  * Check if an element is closer to q than any element from R
  */
 static bool
-CheckElementCloser(char *base, HnswCandidate * e, List *r, Relation index, FmgrInfo **procinfo, Oid *collation)
+CheckElementCloser(char *base, HnswCandidate * e, List *r, Relation index, HnswSupport * support)
 {
 	HnswElement eElement = HnswPtrAccess(base, e->element);
-	Datum		eValue = HnswGetValue(base, eElement);
-	IndexTuple	etup = HnswPtrAccess(base, eElement->itup);
+	HnswQuery	q;
 	ListCell   *lc2;
 
+	q.value = HnswGetValue(base, eElement);
+	q.itup = HnswPtrAccess(base, eElement->itup);
+	q.keyData = NULL;
+
 	foreach(lc2, r)
 	{
 		HnswCandidate *ri = lfirst(lc2);
@@ -1157,7 +1236,7 @@ CheckElementCloser(char *base, HnswCandidate * e, List *r, Relation index, FmgrI
 		Datum		riValue = HnswGetValue(base, riElement);
 		IndexTuple	ritup = HnswPtrAccess(base, riElement->itup);
 		bool		matches;
-		float		distance = HnswGetDistance(etup, eValue, riValue, ritup, NULL, index, procinfo, collation, &matches);
+		float		distance = HnswGetDistance(ritup, riValue, &q, index, support, &matches);
 
 		if (distance <= e->distance)
 			return false;
@@ -1170,7 +1249,7 @@ CheckElementCloser(char *base, HnswCandidate * e, List *r, Relation index, FmgrI
  * Algorithm 4 from paper
  */
 static List *
-SelectNeighbors(char *base, List *c, int lm, Relation index, FmgrInfo **procinfo, Oid *collation, bool *closerSet, HnswCandidate * newCandidate, HnswCandidate * *pruned, bool sortCandidates)
+SelectNeighbors(char *base, List *c, int lm, Relation index, HnswSupport * support, bool *closerSet, HnswCandidate * newCandidate, HnswCandidate * *pruned, bool sortCandidates)
 {
 	List	   *r = NIL;
 	List	   *w = list_copy(c);
@@ -1204,7 +1283,7 @@ SelectNeighbors(char *base, List *c, int lm, Relation index, FmgrInfo **procinfo
 
 		/* Use previous state of r and wd to skip work when possible */
 		if (mustCalculate)
-			e->closer = CheckElementCloser(base, e, r, index, procinfo, collation);
+			e->closer = CheckElementCloser(base, e, r, index, support);
 		else if (list_length(added) > 0)
 		{
 			/* Keep Valgrind happy for in-memory, parallel builds */
@@ -1217,8 +1296,7 @@ SelectNeighbors(char *base, List *c, int lm, Relation index, FmgrInfo **procinfo
 			 */
 			if (e->closer)
 			{
-				e->closer = CheckElementCloser(base, e, added, index, procinfo, collation);
-
+				e->closer = CheckElementCloser(base, e, added, index, support);
 				if (!e->closer)
 					removedAny = true;
 			}
@@ -1230,7 +1308,7 @@ SelectNeighbors(char *base, List *c, int lm, Relation index, FmgrInfo **procinfo
 				 */
 				if (removedAny)
 				{
-					e->closer = CheckElementCloser(base, e, r, index, procinfo, collation);
+					e->closer = CheckElementCloser(base, e, r, index, support);
 					if (e->closer)
 						added = lappend(added, e);
 				}
@@ -1238,7 +1316,7 @@ SelectNeighbors(char *base, List *c, int lm, Relation index, FmgrInfo **procinfo
 		}
 		else if (e == newCandidate)
 		{
-			e->closer = CheckElementCloser(base, e, r, index, procinfo, collation);
+			e->closer = CheckElementCloser(base, e, r, index, support);
 			if (e->closer)
 				added = lappend(added, e);
 		}
@@ -1289,7 +1367,7 @@ AddConnections(char *base, HnswElement element, List *neighbors, int lc)
  * Update connections
  */
 void
-HnswUpdateConnection(char *base, HnswNeighborArray * neighbors, HnswElement newElement, float distance, int lm, int *updateIdx, Relation index, FmgrInfo **procinfo, Oid *collation)
+HnswUpdateConnection(char *base, HnswNeighborArray * neighbors, HnswElement newElement, float distance, int lm, int *updateIdx, Relation index, HnswSupport * support)
 {
 	HnswCandidate newHc;
 
@@ -1315,7 +1393,7 @@ HnswUpdateConnection(char *base, HnswNeighborArray * neighbors, HnswElement newE
 			c = lappend(c, &neighbors->items[i]);
 		c = lappend(c, &newHc);
 
-		SelectNeighbors(base, c, lm, index, procinfo, collation, &neighbors->closerSet, &newHc, &pruned, true);
+		SelectNeighbors(base, c, lm, index, support, &neighbors->closerSet, &newHc, &pruned, true);
 
 		/* Should not happen */
 		if (pruned == NULL)
@@ -1386,17 +1464,20 @@ PrecomputeHash(char *base, HnswElement element)
  * Algorithm 1 from paper
  */
 void
-HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, FmgrInfo **procinfo, Oid *collation, int m, int efConstruction, bool existing, bool inMemory)
+HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, HnswSupport * support, int m, int efConstruction, bool existing, bool inMemory)
 {
 	List	   *ep;
 	List	   *w;
 	int			level = element->level;
 	int			entryLevel;
-	Datum		q = HnswGetValue(base, element);
-	IndexTuple	qtup = HnswPtrAccess(base, element->itup);
-	ScanKeyData *keyData = NULL;
+	HnswQuery	q;
+
 	HnswElement skipElement = existing ? element : NULL;
 
+	q.value = HnswGetValue(base, element);
+	q.itup = HnswPtrAccess(base, element->itup);
+	q.keyData = NULL;
+
 	/* Precompute hash */
 	if (inMemory)
 		PrecomputeHash(base, element);
@@ -1406,13 +1487,13 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
 		return;
 
 	/* Get entry point and level */
-	ep = list_make1(HnswEntryCandidate(base, entryPoint, q, qtup, keyData, index, procinfo, collation, true, inMemory));
+	ep = list_make1(HnswEntryCandidate(base, entryPoint, &q, index, support, true, inMemory));
 	entryLevel = entryPoint->level;
 
 	/* 1st phase: greedy search to insert level */
 	for (int lc = entryLevel; lc >= level + 1; lc--)
 	{
-		w = HnswSearchLayer(base, q, qtup, keyData, ep, 1, lc, index, procinfo, collation, m, true, skipElement, inMemory);
+		w = HnswSearchLayer(base, &q, ep, 1, lc, index, support, m, true, skipElement, inMemory, NULL, NULL, true, NULL);
 		ep = w;
 	}
 
@@ -1431,7 +1512,7 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
 		List	   *lw = NIL;
 		ListCell   *lc2;
 
-		w = HnswSearchLayer(base, q, qtup, keyData, ep, efConstruction, lc, index, procinfo, collation, m, true, skipElement, inMemory);
+		w = HnswSearchLayer(base, &q, ep, efConstruction, lc, index, support, m, true, skipElement, inMemory, NULL, NULL, true, NULL);
 
 		/* Convert search candidates to candidates */
 		foreach(lc2, w)
@@ -1455,7 +1536,7 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
 		 * sortCandidates to true for in-memory builds to enable closer
 		 * caching, but there does not seem to be a difference in performance.
 		 */
-		neighbors = SelectNeighbors(base, lw, lm, index, procinfo, collation, &HnswGetNeighbors(base, element, lc)->closerSet, NULL, NULL, false);
+		neighbors = SelectNeighbors(base, lw, lm, index, support, &HnswGetNeighbors(base, element, lc)->closerSet, NULL, NULL, false);
 
 		AddConnections(base, element, neighbors, lc);
 

src/hnswvacuum.c

@@ -184,13 +184,12 @@ static void
 RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswElement entryPoint)
 {
 	Relation	index = vacuumstate->index;
+	HnswSupport *support = &vacuumstate->support;
 	Buffer		buf;
 	Page		page;
 	GenericXLogState *state;
 	int			m = vacuumstate->m;
 	int			efConstruction = vacuumstate->efConstruction;
-	FmgrInfo  **procinfo = vacuumstate->procinfo;
-	Oid		   *collation = vacuumstate->collation;
 	BufferAccessStrategy bas = vacuumstate->bas;
 	HnswNeighborTuple ntup = vacuumstate->ntup;
 	Size		ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(element->level, m);
@@ -205,7 +204,7 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
 	element->heaptidsLength = 0;
 
 	/* Find neighbors for element, skipping itself */
-	HnswFindElementNeighbors(base, element, entryPoint, index, procinfo, collation, m, efConstruction, true, false);
+	HnswFindElementNeighbors(base, element, entryPoint, index, support, m, efConstruction, true, false);
 
 	/* Zero memory for each element */
 	MemSet(ntup, 0, HNSW_TUPLE_ALLOC_SIZE);
@@ -229,7 +228,7 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
 	UnlockReleaseBuffer(buf);
 
 	/* Update neighbors */
-	HnswUpdateNeighborsOnDisk(index, procinfo, collation, element, m, true, false);
+	HnswUpdateNeighborsOnDisk(index, support, element, m, true, false);
 }
 
 /*
@@ -239,6 +238,7 @@ static void
 RepairGraphEntryPoint(HnswVacuumState * vacuumstate)
 {
 	Relation	index = vacuumstate->index;
+	HnswSupport *support = &vacuumstate->support;
 	HnswElement highestPoint = &vacuumstate->highestPoint;
 	HnswElement entryPoint;
 	MemoryContext oldCtx = MemoryContextSwitchTo(vacuumstate->tmpCtx);
@@ -256,7 +256,7 @@ RepairGraphEntryPoint(HnswVacuumState * vacuumstate)
 		LockPage(index, HNSW_UPDATE_LOCK, ShareLock);
 
 		/* Load element */
-		HnswLoadElement(highestPoint, NULL, NULL, NULL, NULL, NULL, index, vacuumstate->procinfo, vacuumstate->collation, true, NULL);
+		HnswLoadElement(highestPoint, NULL, NULL, NULL, index, support, true, NULL);
 
 		/* Repair if needed */
 		if (NeedsUpdated(vacuumstate, highestPoint))
@@ -294,7 +294,7 @@ RepairGraphEntryPoint(HnswVacuumState * vacuumstate)
 			 * is outdated, this can remove connections at higher levels in
 			 * the graph until they are repaired, but this should be fine.
 			 */
-			HnswLoadElement(entryPoint, NULL, NULL, NULL, NULL, NULL, index, vacuumstate->procinfo, vacuumstate->collation, true, NULL);
+			HnswLoadElement(entryPoint, NULL, NULL, NULL, index, support, true, NULL);
 
 			if (NeedsUpdated(vacuumstate, entryPoint))
 			{
@@ -535,6 +535,14 @@ MarkDeleted(HnswVacuumState * vacuumstate)
 			for (int i = 0; i < ntup->count; i++)
 				ItemPointerSetInvalid(&ntup->indextids[i]);
 
+			/* Increment version */
+			/* This is used to avoid incorrect reads for iterative scans */
+			/* Reserve some bits for future use */
+			etup->version++;
+			if (etup->version > 15)
+				etup->version = 1;
+			ntup->version = etup->version;
+
 			/*
 			 * We modified the tuples in place, no need to call
 			 * PageIndexTupleOverwrite
@@ -581,12 +589,13 @@ InitVacuumState(HnswVacuumState * vacuumstate, IndexVacuumInfo *info, IndexBulkD
 	vacuumstate->callback_state = callback_state;
 	vacuumstate->efConstruction = HnswGetEfConstruction(index);
 	vacuumstate->bas = GetAccessStrategy(BAS_BULKREAD);
-	HnswInitProcinfo(vacuumstate->procinfo, &vacuumstate->collation, index);
 	vacuumstate->ntup = palloc0(HNSW_TUPLE_ALLOC_SIZE);
 	vacuumstate->tmpCtx = AllocSetContextCreate(CurrentMemoryContext,
 												"Hnsw vacuum temporary context",
 												ALLOCSET_DEFAULT_SIZES);
 
+	HnswInitSupport(&vacuumstate->support, index);
+
 	/* Get m from metapage */
 	HnswGetMetaPageInfo(index, &vacuumstate->m, NULL);
 

src/ivfbuild.c

@@ -138,7 +138,7 @@ SampleRows(IvfflatBuildState * buildstate)
  * Add tuple to sort
  */
 static void
-AddTupleToSort(Relation index, ItemPointer tid, Datum *values, IvfflatBuildState * buildstate)
+AddTupleToSort(Relation index, ItemPointer tid, Datum *values, bool *isnull, IvfflatBuildState * buildstate)
 {
 	double		distance;
 	double		minDistance = DBL_MAX;
@@ -184,6 +184,11 @@ AddTupleToSort(Relation index, ItemPointer tid, Datum *values, IvfflatBuildState
 	slot->tts_isnull[1] = false;
 	slot->tts_values[2] = value;
 	slot->tts_isnull[2] = false;
+	for (int i = 1; i < buildstate->tupdesc->natts; i++)
+	{
+		slot->tts_values[2 + i] = values[i];
+		slot->tts_isnull[2 + i] = isnull[i];
+	}
 	ExecStoreVirtualTuple(slot);
 
 	/*
@@ -215,7 +220,7 @@ BuildCallback(Relation index, ItemPointer tid, Datum *values,
 	oldCtx = MemoryContextSwitchTo(buildstate->tmpCtx);
 
 	/* Add tuple to sort */
-	AddTupleToSort(index, tid, values, buildstate);
+	AddTupleToSort(index, tid, values, isnull, buildstate);
 
 	/* Reset memory context */
 	MemoryContextSwitchTo(oldCtx);
@@ -226,19 +231,20 @@ BuildCallback(Relation index, ItemPointer tid, Datum *values,
  * Get index tuple from sort state
  */
 static inline void
-GetNextTuple(Tuplesortstate *sortstate, TupleDesc tupdesc, TupleTableSlot *slot, IndexTuple *itup, int *list)
+GetNextTuple(Tuplesortstate *sortstate, TupleDesc tupdesc, TupleTableSlot *slot, Datum *values, bool *isnull, IndexTuple *itup, int *list)
 {
-	Datum		value;
-	bool		isnull;
-
 	if (tuplesort_gettupleslot(sortstate, true, false, slot, NULL))
 	{
-		*list = DatumGetInt32(slot_getattr(slot, 1, &isnull));
-		value = slot_getattr(slot, 3, &isnull);
+		bool		unused;
+
+		*list = DatumGetInt32(slot_getattr(slot, 1, &unused));
+
+		for (int i = 0; i < tupdesc->natts; i++)
+			values[i] = slot_getattr(slot, 3 + i, &isnull[i]);
 
 		/* Form the index tuple */
-		*itup = index_form_tuple(tupdesc, &value, &isnull);
-		(*itup)->t_tid = *((ItemPointer) DatumGetPointer(slot_getattr(slot, 2, &isnull)));
+		*itup = index_form_tuple(tupdesc, values, isnull);
+		(*itup)->t_tid = *((ItemPointer) DatumGetPointer(slot_getattr(slot, 2, &unused)));
 	}
 	else
 		*list = -1;
@@ -254,14 +260,16 @@ InsertTuples(Relation index, IvfflatBuildState * buildstate, ForkNumber forkNum)
 	IndexTuple	itup = NULL;	/* silence compiler warning */
 	int64		inserted = 0;
 
-	TupleTableSlot *slot = MakeSingleTupleTableSlot(buildstate->tupdesc, &TTSOpsMinimalTuple);
-	TupleDesc	tupdesc = RelationGetDescr(index);
+	TupleTableSlot *slot = MakeSingleTupleTableSlot(buildstate->sortdesc, &TTSOpsMinimalTuple);
+	TupleDesc	tupdesc = buildstate->tupdesc;
+	Datum	   *values = palloc(tupdesc->natts * sizeof(Datum));
+	bool	   *isnull = palloc(tupdesc->natts * sizeof(bool));
 
 	pgstat_progress_update_param(PROGRESS_CREATEIDX_SUBPHASE, PROGRESS_IVFFLAT_PHASE_LOAD);
 
 	pgstat_progress_update_param(PROGRESS_CREATEIDX_TUPLES_TOTAL, buildstate->indtuples);
 
-	GetNextTuple(buildstate->sortstate, tupdesc, slot, &itup, &list);
+	GetNextTuple(buildstate->sortstate, tupdesc, slot, values, isnull, &itup, &list);
 
 	for (int i = 0; i < buildstate->centers->length; i++)
 	{
@@ -297,7 +305,7 @@ InsertTuples(Relation index, IvfflatBuildState * buildstate, ForkNumber forkNum)
 
 			pgstat_progress_update_param(PROGRESS_CREATEIDX_TUPLES_DONE, ++inserted);
 
-			GetNextTuple(buildstate->sortstate, tupdesc, slot, &itup, &list);
+			GetNextTuple(buildstate->sortstate, tupdesc, slot, values, isnull, &itup, &list);
 		}
 
 		insertPage = BufferGetBlockNumber(buf);
@@ -307,6 +315,9 @@ InsertTuples(Relation index, IvfflatBuildState * buildstate, ForkNumber forkNum)
 		/* Set the start and insert pages */
 		IvfflatUpdateList(index, buildstate->listInfo[i], insertPage, InvalidBlockNumber, startPage, forkNum);
 	}
+
+	pfree(values);
+	pfree(isnull);
 }
 
 /*
@@ -319,6 +330,7 @@ InitBuildState(IvfflatBuildState * buildstate, Relation heap, Relation index, In
 	buildstate->index = index;
 	buildstate->indexInfo = indexInfo;
 	buildstate->typeInfo = IvfflatGetTypeInfo(index);
+	buildstate->tupdesc = RelationGetDescr(index);
 
 	buildstate->lists = IvfflatGetLists(index);
 	buildstate->dimensions = TupleDescAttr(index->rd_att, 0)->atttypmod;
@@ -356,12 +368,13 @@ InitBuildState(IvfflatBuildState * buildstate, Relation heap, Relation index, In
 				 errmsg("dimensions must be greater than one for this opclass")));
 
 	/* Create tuple description for sorting */
-	buildstate->tupdesc = CreateTemplateTupleDesc(3);
-	TupleDescInitEntry(buildstate->tupdesc, (AttrNumber) 1, "list", INT4OID, -1, 0);
-	TupleDescInitEntry(buildstate->tupdesc, (AttrNumber) 2, "tid", TIDOID, -1, 0);
-	TupleDescInitEntry(buildstate->tupdesc, (AttrNumber) 3, "vector", RelationGetDescr(index)->attrs[0].atttypid, -1, 0);
+	buildstate->sortdesc = CreateTemplateTupleDesc(2 + buildstate->tupdesc->natts);
+	TupleDescInitEntry(buildstate->sortdesc, (AttrNumber) 1, "list", INT4OID, -1, 0);
+	TupleDescInitEntry(buildstate->sortdesc, (AttrNumber) 2, "tid", TIDOID, -1, 0);
+	for (int i = 0; i < buildstate->tupdesc->natts; i++)
+		TupleDescInitEntry(buildstate->sortdesc, (AttrNumber) (3 + i), NULL, buildstate->tupdesc->attrs[i].atttypid, -1, 0);
 
-	buildstate->slot = MakeSingleTupleTableSlot(buildstate->tupdesc, &TTSOpsVirtual);
+	buildstate->slot = MakeSingleTupleTableSlot(buildstate->sortdesc, &TTSOpsVirtual);
 
 	buildstate->centers = VectorArrayInit(buildstate->lists, buildstate->dimensions, buildstate->typeInfo->itemSize(buildstate->dimensions));
 	buildstate->listInfo = palloc(sizeof(ListInfo) * buildstate->lists);
@@ -633,7 +646,7 @@ IvfflatParallelScanAndSort(IvfflatSpool * ivfspool, IvfflatShared * ivfshared, S
 	InitBuildState(&buildstate, ivfspool->heap, ivfspool->index, indexInfo);
 	memcpy(buildstate.centers->items, ivfcenters, buildstate.centers->itemsize * buildstate.centers->maxlen);
 	buildstate.centers->length = buildstate.centers->maxlen;
-	ivfspool->sortstate = InitBuildSortState(buildstate.tupdesc, sortmem, coordinate);
+	ivfspool->sortstate = InitBuildSortState(buildstate.sortdesc, sortmem, coordinate);
 	buildstate.sortstate = ivfspool->sortstate;
 	scan = table_beginscan_parallel(ivfspool->heap,
 									ParallelTableScanFromIvfflatShared(ivfshared));
@@ -950,7 +963,7 @@ AssignTuples(IvfflatBuildState * buildstate)
 	}
 
 	/* Begin serial/leader tuplesort */
-	buildstate->sortstate = InitBuildSortState(buildstate->tupdesc, maintenance_work_mem, coordinate);
+	buildstate->sortstate = InitBuildSortState(buildstate->sortdesc, maintenance_work_mem, coordinate);
 
 	/* Add tuples to sort */
 	if (buildstate->heap != NULL)

src/ivfflat.c

@@ -17,8 +17,16 @@
 #endif
 
 int			ivfflat_probes;
+int			ivfflat_iterative_search;
+int			ivfflat_iterative_search_max_probes;
 static relopt_kind ivfflat_relopt_kind;
 
+static const struct config_enum_entry ivfflat_iterative_search_options[] = {
+	{"off", IVFFLAT_ITERATIVE_SEARCH_OFF, false},
+	{"on", IVFFLAT_ITERATIVE_SEARCH_RELAXED, false},
+	{NULL, 0, false}
+};
+
 /*
  * Initialize index options and variables
  */
@@ -33,6 +41,14 @@ IvfflatInit(void)
 							"Valid range is 1..lists.", &ivfflat_probes,
 							IVFFLAT_DEFAULT_PROBES, IVFFLAT_MIN_LISTS, IVFFLAT_MAX_LISTS, PGC_USERSET, 0, NULL, NULL, NULL);
 
+	DefineCustomEnumVariable("ivfflat.iterative_search", "Sets whether to use iterative search",
+							 NULL, &ivfflat_iterative_search,
+							 IVFFLAT_ITERATIVE_SEARCH_OFF, ivfflat_iterative_search_options, PGC_USERSET, 0, NULL, NULL, NULL);
+
+	DefineCustomIntVariable("ivfflat.iterative_search_max_probes", "Sets the max number of probes for iterative search",
+							"Zero sets to the number of lists", &ivfflat_iterative_search_max_probes,
+							0, 0, IVFFLAT_MAX_LISTS, PGC_USERSET, 0, NULL, NULL, NULL);
+
 	MarkGUCPrefixReserved("ivfflat");
 }
 

src/ivfflat.h

@@ -80,6 +80,14 @@
 
 /* Variables */
 extern int	ivfflat_probes;
+extern int	ivfflat_iterative_search;
+extern int	ivfflat_iterative_search_max_probes;
+
+typedef enum IvfflatIterativeSearchType
+{
+	IVFFLAT_ITERATIVE_SEARCH_OFF,
+	IVFFLAT_ITERATIVE_SEARCH_RELAXED
+}			IvfflatIterativeSearchType;
 
 typedef struct VectorArrayData
 {
@@ -165,6 +173,7 @@ typedef struct IvfflatBuildState
 	Relation	index;
 	IndexInfo  *indexInfo;
 	const		IvfflatTypeInfo *typeInfo;
+	TupleDesc	tupdesc;
 
 	/* Settings */
 	int			dimensions;
@@ -198,7 +207,7 @@ typedef struct IvfflatBuildState
 
 	/* Sorting */
 	Tuplesortstate *sortstate;
-	TupleDesc	tupdesc;
+	TupleDesc	sortdesc;
 	TupleTableSlot *slot;
 
 	/* Memory */
@@ -247,8 +256,10 @@ typedef struct IvfflatScanOpaqueData
 {
 	const		IvfflatTypeInfo *typeInfo;
 	int			probes;
+	int			maxProbes;
 	int			dimensions;
 	bool		first;
+	Datum		value;
 
 	/* Sorting */
 	Tuplesortstate *sortstate;
@@ -265,6 +276,8 @@ typedef struct IvfflatScanOpaqueData
 
 	/* Lists */
 	pairingheap *listQueue;
+	BlockNumber *listPages;
+	int			listIndex;
 	IvfflatScanList lists[FLEXIBLE_ARRAY_MEMBER];	/* must come last */
 }			IvfflatScanOpaqueData;
 

src/ivfinsert.c

@@ -78,6 +78,8 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid, R
 	BlockNumber insertPage = InvalidBlockNumber;
 	ListInfo	listInfo;
 	BlockNumber originalInsertPage;
+	TupleDesc	tupdesc = RelationGetDescr(index);
+	Datum	   *newValues = palloc(tupdesc->natts * sizeof(Datum));
 
 	/* Detoast once for all calls */
 	value = PointerGetDatum(PG_DETOAST_DATUM(values[0]));
@@ -98,12 +100,16 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid, R
 	IvfflatGetMetaPageInfo(index, NULL, NULL);
 
 	/* Find the insert page - sets the page and list info */
-	FindInsertPage(index, values, &insertPage, &listInfo);
+	FindInsertPage(index, &value, &insertPage, &listInfo);
 	Assert(BlockNumberIsValid(insertPage));
 	originalInsertPage = insertPage;
 
+	newValues[0] = value;
+	for (int i = 1; i < tupdesc->natts; i++)
+		newValues[i] = values[i];
+
 	/* Form tuple */
-	itup = index_form_tuple(RelationGetDescr(index), &value, isnull);
+	itup = index_form_tuple(tupdesc, newValues, isnull);
 	itup->t_tid = *heap_tid;
 
 	/* Get tuple size */

src/ivfscan.c

@@ -65,7 +65,7 @@ GetScanLists(IndexScanDesc scan, Datum value)
 			/* Use procinfo from the index instead of scan key for performance */
 			distance = DatumGetFloat8(so->distfunc(so->procinfo, so->collation, PointerGetDatum(&list->center), value));
 
-			if (listCount < so->probes)
+			if (listCount < so->maxProbes)
 			{
 				IvfflatScanList *scanlist;
 
@@ -78,7 +78,7 @@ GetScanLists(IndexScanDesc scan, Datum value)
 				pairingheap_add(so->listQueue, &scanlist->ph_node);
 
 				/* Calculate max distance */
-				if (listCount == so->probes)
+				if (listCount == so->maxProbes)
 					maxDistance = GetScanList(pairingheap_first(so->listQueue))->distance;
 			}
 			else if (distance < maxDistance)
@@ -102,6 +102,11 @@ GetScanLists(IndexScanDesc scan, Datum value)
 
 		UnlockReleaseBuffer(cbuf);
 	}
+
+	for (int i = listCount - 1; i >= 0; i--)
+		so->listPages[i] = GetScanList(pairingheap_remove_first(so->listQueue))->startPage;
+
+	Assert(pairingheap_is_empty(so->listQueue));
 }
 
 /*
@@ -114,11 +119,14 @@ GetScanItems(IndexScanDesc scan, Datum value)
 	TupleDesc	tupdesc = RelationGetDescr(scan->indexRelation);
 	double		tuples = 0;
 	TupleTableSlot *slot = so->vslot;
+	int			batchProbes = 0;
+
+	tuplesort_reset(so->sortstate);
 
 	/* Search closest probes lists */
-	while (!pairingheap_is_empty(so->listQueue))
+	while (so->listIndex < so->maxProbes && (++batchProbes) <= so->probes)
 	{
-		BlockNumber searchPage = GetScanList(pairingheap_remove_first(so->listQueue))->startPage;
+		BlockNumber searchPage = so->listPages[so->listIndex++];
 
 		/* Search all entry pages for list */
 		while (BlockNumberIsValid(searchPage))
@@ -166,13 +174,17 @@ GetScanItems(IndexScanDesc scan, Datum value)
 		}
 	}
 
-	if (tuples < 100)
+	if (tuples < 100 && ivfflat_iterative_search == IVFFLAT_ITERATIVE_SEARCH_OFF)
 		ereport(DEBUG1,
 				(errmsg("index scan found few tuples"),
 				 errdetail("Index may have been created with little data."),
 				 errhint("Recreate the index and possibly decrease lists.")));
 
 	tuplesort_performsort(so->sortstate);
+
+#if defined(IVFFLAT_MEMORY)
+	elog(INFO, "memory: %zu MB", MemoryContextMemAllocated(CurrentMemoryContext, true) / (1024 * 1024));
+#endif
 }
 
 /*
@@ -240,6 +252,7 @@ ivfflatbeginscan(Relation index, int nkeys, int norderbys)
 	int			lists;
 	int			dimensions;
 	int			probes = ivfflat_probes;
+	int			maxProbes;
 
 	scan = RelationGetIndexScan(index, nkeys, norderbys);
 
@@ -249,10 +262,21 @@ ivfflatbeginscan(Relation index, int nkeys, int norderbys)
 	if (probes > lists)
 		probes = lists;
 
-	so = (IvfflatScanOpaque) palloc(offsetof(IvfflatScanOpaqueData, lists) + probes * sizeof(IvfflatScanList));
+	if (ivfflat_iterative_search != IVFFLAT_ITERATIVE_SEARCH_OFF)
+	{
+		if (ivfflat_iterative_search_max_probes == 0)
+			maxProbes = lists;
+		else
+			maxProbes = Min(ivfflat_iterative_search_max_probes, lists);
+	}
+	else
+		maxProbes = probes;
+
+	so = (IvfflatScanOpaque) palloc(offsetof(IvfflatScanOpaqueData, lists) + maxProbes * sizeof(IvfflatScanList));
 	so->typeInfo = IvfflatGetTypeInfo(index);
 	so->first = true;
 	so->probes = probes;
+	so->maxProbes = maxProbes;
 	so->dimensions = dimensions;
 
 	/* Set support functions */
@@ -280,6 +304,8 @@ ivfflatbeginscan(Relation index, int nkeys, int norderbys)
 	so->bas = GetAccessStrategy(BAS_BULKREAD);
 
 	so->listQueue = pairingheap_allocate(CompareLists, scan);
+	so->listPages = palloc(maxProbes * sizeof(BlockNumber));
+	so->listIndex = 0;
 
 	scan->opaque = so;
 
@@ -294,11 +320,9 @@ ivfflatrescan(IndexScanDesc scan, ScanKey keys, int nkeys, ScanKey orderbys, int
 {
 	IvfflatScanOpaque so = (IvfflatScanOpaque) scan->opaque;
 
-	if (!so->first)
-		tuplesort_reset(so->sortstate);
-
 	so->first = true;
 	pairingheap_reset(so->listQueue);
+	so->listIndex = 0;
 
 	if (keys && scan->numberOfKeys > 0)
 		memmove(scan->keyData, keys, scan->numberOfKeys * sizeof(ScanKeyData));
@@ -314,6 +338,8 @@ bool
 ivfflatgettuple(IndexScanDesc scan, ScanDirection dir)
 {
 	IvfflatScanOpaque so = (IvfflatScanOpaque) scan->opaque;
+	ItemPointer heaptid;
+	bool		isnull;
 
 	/*
 	 * Index can be used to scan backward, but Postgres doesn't support
@@ -341,28 +367,25 @@ ivfflatgettuple(IndexScanDesc scan, ScanDirection dir)
 		IvfflatBench("GetScanLists", GetScanLists(scan, value));
 		IvfflatBench("GetScanItems", GetScanItems(scan, value));
 		so->first = false;
+		so->value = value;
 
-#if defined(IVFFLAT_MEMORY)
-		elog(INFO, "memory: %zu MB", MemoryContextMemAllocated(CurrentMemoryContext, true) / (1024 * 1024));
-#endif
-
-		/* Clean up if we allocated a new value */
-		if (value != scan->orderByData->sk_argument)
-			pfree(DatumGetPointer(value));
+		/* TODO clean up if we allocated a new value */
 	}
 
-	if (tuplesort_gettupleslot(so->sortstate, true, false, so->mslot, NULL))
+	while (!tuplesort_gettupleslot(so->sortstate, true, false, so->mslot, NULL))
 	{
-		bool		isnull;
-		ItemPointer heaptid = (ItemPointer) DatumGetPointer(slot_getattr(so->mslot, 2, &isnull));
+		if (so->listIndex == so->maxProbes)
+			return false;
 
-		scan->xs_heaptid = *heaptid;
-		scan->xs_recheck = false;
-		scan->xs_recheckorderby = false;
-		return true;
+		IvfflatBench("GetScanItems", GetScanItems(scan, so->value));
 	}
 
-	return false;
+	heaptid = (ItemPointer) DatumGetPointer(slot_getattr(so->mslot, 2, &isnull));
+
+	scan->xs_heaptid = *heaptid;
+	scan->xs_recheck = false;
+	scan->xs_recheckorderby = false;
+	return true;
 }
 
 /*
@@ -374,6 +397,7 @@ ivfflatendscan(IndexScanDesc scan)
 	IvfflatScanOpaque so = (IvfflatScanOpaque) scan->opaque;
 
 	pairingheap_free(so->listQueue);
+	pfree(so->listPages);
 	tuplesort_end(so->sortstate);
 	FreeAccessStrategy(so->bas);
 	FreeTupleDesc(so->tupdesc);

src/ivfvacuum.c

@@ -26,7 +26,7 @@ ivfflatbulkdelete(IndexVacuumInfo *info, IndexBulkDeleteResult *stats,
 		Page		cpage;
 		OffsetNumber coffno;
 		OffsetNumber cmaxoffno;
-		BlockNumber startPages[MaxOffsetNumber];
+		BlockNumber listPages[MaxOffsetNumber];
 		ListInfo	listInfo;
 
 		cbuf = ReadBuffer(index, blkno);
@@ -40,7 +40,7 @@ ivfflatbulkdelete(IndexVacuumInfo *info, IndexBulkDeleteResult *stats,
 		{
 			IvfflatList list = (IvfflatList) PageGetItem(cpage, PageGetItemId(cpage, coffno));
 
-			startPages[coffno - FirstOffsetNumber] = list->startPage;
+			listPages[coffno - FirstOffsetNumber] = list->startPage;
 		}
 
 		listInfo.blkno = blkno;
@@ -50,7 +50,7 @@ ivfflatbulkdelete(IndexVacuumInfo *info, IndexBulkDeleteResult *stats,
 
 		for (coffno = FirstOffsetNumber; coffno <= cmaxoffno; coffno = OffsetNumberNext(coffno))
 		{
-			BlockNumber searchPage = startPages[coffno - FirstOffsetNumber];
+			BlockNumber searchPage = listPages[coffno - FirstOffsetNumber];
 			BlockNumber insertPage = InvalidBlockNumber;
 
 			/* Iterate over entry pages */

test/t/002_ivfflat_vacuum.pl

@@ -6,13 +6,7 @@ use Test::More;
 
 my $dim = 3;
 
-my @r = ();
-for (1 .. $dim)
-{
-	my $v = int(rand(1000)) + 1;
-	push(@r, "i % $v");
-}
-my $array_sql = join(", ", @r);
+my $array_sql = join(",", ('random()') x $dim);
 
 # Initialize node
 my $node = PostgreSQL::Test::Cluster->new('node');
@@ -23,19 +17,20 @@ $node->start;
 $node->safe_psql("postgres", "CREATE EXTENSION vector;");
 $node->safe_psql("postgres", "CREATE TABLE tst (i int4, v vector($dim));");
 $node->safe_psql("postgres",
-	"INSERT INTO tst SELECT i % 10, ARRAY[$array_sql] FROM generate_series(1, 100000) i;"
+	"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(1, 100000) i;"
 );
 $node->safe_psql("postgres", "CREATE INDEX ON tst USING ivfflat (v vector_l2_ops);");
 
 # Get size
 my $size = $node->safe_psql("postgres", "SELECT pg_total_relation_size('tst_v_idx');");
 
+# Store values
+$node->safe_psql("postgres", "CREATE TABLE tmp AS SELECT * FROM tst;");
+
 # Delete all, vacuum, and insert same data
 $node->safe_psql("postgres", "DELETE FROM tst;");
 $node->safe_psql("postgres", "VACUUM tst;");
-$node->safe_psql("postgres",
-	"INSERT INTO tst SELECT i % 10, ARRAY[$array_sql] FROM generate_series(1, 100000) i;"
-);
+$node->safe_psql("postgres", "INSERT INTO tst SELECT * FROM tmp;");
 
 # Check size
 my $new_size = $node->safe_psql("postgres", "SELECT pg_total_relation_size('tst_v_idx');");

test/t/041_ivfflat_iterative_search.pl

@@ -0,0 +1,54 @@
+use strict;
+use warnings FATAL => 'all';
+use PostgreSQL::Test::Cluster;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+my $dim = 3;
+my $array_sql = join(",", ('random()') x $dim);
+
+# Initialize node
+my $node = PostgreSQL::Test::Cluster->new('node');
+$node->init;
+$node->start;
+
+# Create table
+$node->safe_psql("postgres", "CREATE EXTENSION vector;");
+$node->safe_psql("postgres", "CREATE TABLE tst (i int4 PRIMARY KEY, v vector($dim));");
+$node->safe_psql("postgres",
+	"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(1, 100000) i;"
+);
+$node->safe_psql("postgres", "CREATE INDEX ON tst USING ivfflat (v vector_l2_ops);");
+
+my $count = $node->safe_psql("postgres", qq(
+	SET enable_seqscan = off;
+	SET ivfflat.probes = 10;
+	SET ivfflat.iterative_search = on;
+	SELECT COUNT(*) FROM (SELECT v FROM tst WHERE i % 10000 = 0 ORDER BY v <-> (SELECT v FROM tst LIMIT 1) LIMIT 11) t;
+));
+is($count, 10);
+
+foreach ((30, 50, 70))
+{
+	my $max_probes = $_;
+	my $expected = $max_probes / 10;
+	my $sum = 0;
+
+	for my $i (1 .. 20)
+	{
+		$count = $node->safe_psql("postgres", qq(
+			SET enable_seqscan = off;
+			SET ivfflat.probes = 10;
+			SET ivfflat.iterative_search = on;
+			SET ivfflat.iterative_search_max_probes = $max_probes;
+			SELECT COUNT(*) FROM (SELECT v FROM tst WHERE i % 10000 = 0 ORDER BY v <-> (SELECT v FROM tst WHERE i = $i) LIMIT 11) t;
+		));
+		$sum += $count;
+	}
+
+	my $avg = $sum / 20;
+	cmp_ok($avg, '>', $expected - 2);
+	cmp_ok($avg, '<', $expected + 2);
+}
+
+done_testing();

test/t/042_ivfflat_iterative_search_recall.pl

@@ -0,0 +1,125 @@
+use strict;
+use warnings FATAL => 'all';
+use PostgreSQL::Test::Cluster;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+my $node;
+my @queries = ();
+my @expected;
+my $limit = 20;
+my @cs = (100, 1000);
+
+sub test_recall
+{
+	my ($c, $probes, $min, $operator) = @_;
+	my $correct = 0;
+	my $total = 0;
+
+	my $explain = $node->safe_psql("postgres", qq(
+		SET enable_seqscan = off;
+		SET ivfflat.probes = $probes;
+		SET ivfflat.iterative_search = on;
+		EXPLAIN ANALYZE SELECT i FROM tst WHERE i % $c = 0 ORDER BY v $operator '$queries[0]' LIMIT $limit;
+	));
+	like($explain, qr/Index Scan using idx on tst/);
+
+	for my $i (0 .. $#queries)
+	{
+		my $actual = $node->safe_psql("postgres", qq(
+			SET enable_seqscan = off;
+			SET ivfflat.probes = $probes;
+			SET ivfflat.iterative_search = on;
+			SELECT i FROM tst WHERE i % $c = 0 ORDER BY v $operator '$queries[$i]' LIMIT $limit;
+		));
+		my @actual_ids = split("\n", $actual);
+
+		my @expected_ids = split("\n", $expected[$i]);
+		my %expected_set = map { $_ => 1 } @expected_ids;
+
+		foreach (@actual_ids)
+		{
+			if (exists($expected_set{$_}))
+			{
+				$correct++;
+			}
+		}
+
+		$total += $limit;
+	}
+
+	cmp_ok($correct / $total, ">=", $min, $operator);
+}
+
+# Initialize node
+$node = PostgreSQL::Test::Cluster->new('node');
+$node->init;
+$node->start;
+
+# Create table
+$node->safe_psql("postgres", "CREATE EXTENSION vector;");
+$node->safe_psql("postgres", "CREATE TABLE tst (i int4, v vector(3));");
+$node->safe_psql("postgres",
+	"INSERT INTO tst SELECT i, ARRAY[random(), random(), random()] FROM generate_series(1, 100000) i;"
+);
+
+# Generate queries
+for (1 .. 20)
+{
+	my $r1 = rand();
+	my $r2 = rand();
+	my $r3 = rand();
+	push(@queries, "[$r1,$r2,$r3]");
+}
+
+# Check each index type
+my @operators = ("<->", "<=>");
+my @opclasses = ("vector_l2_ops", "vector_cosine_ops");
+
+for my $i (0 .. $#operators)
+{
+	my $operator = $operators[$i];
+	my $opclass = $opclasses[$i];
+
+	$node->safe_psql("postgres", "CREATE INDEX idx ON tst USING ivfflat (v $opclass);");
+
+	foreach (@cs)
+	{
+		my $c = $_;
+
+		# Get exact results
+		@expected = ();
+		foreach (@queries)
+		{
+			my $res = $node->safe_psql("postgres", qq(
+				SET enable_indexscan = off;
+				WITH top AS (
+					SELECT v $operator '$_' AS distance FROM tst WHERE i % $c = 0 ORDER BY distance LIMIT $limit
+				)
+				SELECT i FROM tst WHERE (v $operator '$_') <= (SELECT MAX(distance) FROM top)
+			));
+			push(@expected, $res);
+		}
+
+		if ($c == 100)
+		{
+			test_recall($c, 1, 0.58, $operator);
+			test_recall($c, 10, 0.98, $operator);
+		}
+		else
+		{
+			if ($operator eq "<->")
+			{
+				test_recall($c, 1, 0.80, $operator);
+			}
+			else
+			{
+				test_recall($c, 1, 0.88, $operator);
+			}
+		}
+	}
+
+	$node->safe_psql("postgres", "DROP INDEX idx;");
+}
+
+done_testing();

test/t/043_hnsw_iterative_search.pl

@@ -0,0 +1,67 @@
+use strict;
+use warnings FATAL => 'all';
+use PostgreSQL::Test::Cluster;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+my $dim = 3;
+my $array_sql = join(",", ('random()') x $dim);
+
+# Initialize node
+my $node = PostgreSQL::Test::Cluster->new('node');
+$node->init;
+$node->start;
+
+# Create table
+$node->safe_psql("postgres", "CREATE EXTENSION vector;");
+$node->safe_psql("postgres", "CREATE TABLE tst (i int4 PRIMARY KEY, v vector($dim));");
+$node->safe_psql("postgres",
+	"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(1, 100000) i;"
+);
+$node->safe_psql("postgres", qq(
+	SET maintenance_work_mem = '128MB';
+	SET max_parallel_maintenance_workers = 2;
+	CREATE INDEX ON tst USING hnsw (v vector_l2_ops)
+));
+
+my $count = $node->safe_psql("postgres", qq(
+	SET enable_seqscan = off;
+	SET hnsw.iterative_search = on;
+	SET work_mem = '8MB';
+	SELECT COUNT(*) FROM (SELECT v FROM tst WHERE i % 10000 = 0 ORDER BY v <-> (SELECT v FROM tst LIMIT 1) LIMIT 11) t;
+));
+is($count, 10);
+
+foreach ((30000, 50000, 70000))
+{
+	my $max_tuples = $_;
+	my $expected = $max_tuples / 10000;
+	my $sum = 0;
+
+	for my $i (1 .. 20)
+	{
+		$count = $node->safe_psql("postgres", qq(
+			SET enable_seqscan = off;
+			SET hnsw.iterative_search = on;
+			SET hnsw.iterative_search_max_tuples = $max_tuples;
+			SET work_mem = '8MB';
+			SELECT COUNT(*) FROM (SELECT v FROM tst WHERE i % 10000 = 0 ORDER BY v <-> (SELECT v FROM tst WHERE i = $i) LIMIT 11) t;
+		));
+		$sum += $count;
+	}
+
+	my $avg = $sum / 20;
+	cmp_ok($avg, '>', $expected - 2);
+	cmp_ok($avg, '<', $expected + 2);
+}
+
+my ($ret, $stdout, $stderr) = $node->psql("postgres", qq(
+	SET enable_seqscan = off;
+	SET hnsw.iterative_search = on;
+	SET client_min_messages = debug1;
+	SET work_mem = '2MB';
+	SELECT COUNT(*) FROM (SELECT v FROM tst WHERE i % 10000 = 0 ORDER BY v <-> (SELECT v FROM tst LIMIT 1) LIMIT 11) t;
+));
+like($stderr, qr/hnsw index scan exceeded work_mem after \d+ tuples/);
+
+done_testing();

test/t/044_hnsw_iterative_search_recall.pl

@@ -0,0 +1,131 @@
+use strict;
+use warnings FATAL => 'all';
+use PostgreSQL::Test::Cluster;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+my $node;
+my @queries = ();
+my @expected;
+my $limit = 20;
+my $dim = 3;
+my $array_sql = join(",", ('random()') x $dim);
+my @cs = (100, 1000);
+
+sub test_recall
+{
+	my ($c, $ef_search, $min, $operator) = @_;
+	my $correct = 0;
+	my $total = 0;
+
+	my $explain = $node->safe_psql("postgres", qq(
+		SET enable_seqscan = off;
+		SET hnsw.ef_search = $ef_search;
+		SET hnsw.iterative_search = on;
+		EXPLAIN ANALYZE SELECT i FROM tst WHERE i % $c = 0 ORDER BY v $operator '$queries[0]' LIMIT $limit;
+	));
+	like($explain, qr/Index Scan using idx on tst/);
+
+	for my $i (0 .. $#queries)
+	{
+		my $actual = $node->safe_psql("postgres", qq(
+			SET enable_seqscan = off;
+			SET hnsw.ef_search = $ef_search;
+			SET hnsw.iterative_search = on;
+			SELECT i FROM tst WHERE i % $c = 0 ORDER BY v $operator '$queries[$i]' LIMIT $limit;
+		));
+		my @actual_ids = split("\n", $actual);
+
+		my @expected_ids = split("\n", $expected[$i]);
+		my %expected_set = map { $_ => 1 } @expected_ids;
+
+		foreach (@actual_ids)
+		{
+			if (exists($expected_set{$_}))
+			{
+				$correct++;
+			}
+		}
+
+		$total += $limit;
+	}
+
+	cmp_ok($correct / $total, ">=", $min, $operator);
+}
+
+# Initialize node
+$node = PostgreSQL::Test::Cluster->new('node');
+$node->init;
+$node->start;
+
+# Create table
+$node->safe_psql("postgres", "CREATE EXTENSION vector;");
+$node->safe_psql("postgres", "CREATE TABLE tst (i int4, v vector($dim));");
+$node->safe_psql("postgres",
+	"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(1, 100000) i;"
+);
+
+# Generate queries
+for (1 .. 20)
+{
+	my @r = ();
+	for (1 .. $dim)
+	{
+		push(@r, rand());
+	}
+	push(@queries, "[" . join(",", @r) . "]");
+}
+
+# Check each index type
+my @operators = ("<->", "<=>");
+my @opclasses = ("vector_l2_ops", "vector_cosine_ops");
+
+for my $i (0 .. $#operators)
+{
+	my $operator = $operators[$i];
+	my $opclass = $opclasses[$i];
+
+	$node->safe_psql("postgres", qq(
+		SET maintenance_work_mem = '128MB';
+		CREATE INDEX idx ON tst USING hnsw (v $opclass);
+	));
+
+	foreach (@cs)
+	{
+		my $c = $_;
+
+		# Get exact results
+		@expected = ();
+		foreach (@queries)
+		{
+			my $res = $node->safe_psql("postgres", qq(
+				SET enable_indexscan = off;
+				WITH top AS (
+					SELECT v $operator '$_' AS distance FROM tst WHERE i % $c = 0 ORDER BY distance LIMIT $limit
+				)
+				SELECT i FROM tst WHERE (v $operator '$_') <= (SELECT MAX(distance) FROM top)
+			));
+			push(@expected, $res);
+		}
+
+		if ($c == 100)
+		{
+			test_recall($c, 40, 0.99, $operator);
+		}
+		else
+		{
+			if ($operator eq "<->")
+			{
+				test_recall($c, 40, 0.99, $operator);
+			}
+			else
+			{
+				test_recall($c, 40, 0.99, $operator);
+			}
+		}
+	}
+
+	$node->safe_psql("postgres", "DROP INDEX idx;");
+}
+
+done_testing();

test/t/045_hnsw_hqann.pl

@@ -11,7 +11,7 @@ my @expected;
 my $limit = 20;
 my $dim = 3;
 my $array_sql = join(",", ('random()') x $dim);
-my $nc = 50;
+my $nc = 1000;
 
 sub test_recall
 {
@@ -79,15 +79,19 @@ for (1 .. 20)
 @expected = ();
 for my $i (0 .. $#queries)
 {
-	my $res = $node->safe_psql("postgres", "SELECT i FROM tst WHERE c = $cs[$i] ORDER BY v <-> '$queries[$i]' LIMIT $limit;");
+	my $res = $node->safe_psql("postgres", "SELECT i FROM tst WHERE c = $cs[$i] ORDER BY v <=> '$queries[$i]' LIMIT $limit;");
 	push(@expected, $res);
 }
 
 # Add index
-$node->safe_psql("postgres", "CREATE INDEX ON tst USING hnsw (v vector_l2_ops, c);");
+$node->safe_psql("postgres", qq(
+	SET maintenance_work_mem = '256MB';
+	SET max_parallel_maintenance_workers = 2;
+	CREATE INDEX ON tst USING hnsw (v vector_cosine_ops, c);
+));
 
 # Test recall
-test_recall(0.99, '<->');
+test_recall(0.99, '<=>');
 
 # Test vacuum
 $node->safe_psql("postgres", "DELETE FROM tst WHERE c > 5;");
@@ -97,13 +101,13 @@ $node->safe_psql("postgres", "VACUUM tst;");
 my ($ret, $stdout, $stderr) = $node->psql("postgres", "CREATE INDEX ON tst USING hnsw (c);");
 like($stderr, qr/first column must be a vector/);
 
-($ret, $stdout, $stderr) = $node->psql("postgres", "CREATE INDEX ON tst USING hnsw (c, v vector_l2_ops);");
+($ret, $stdout, $stderr) = $node->psql("postgres", "CREATE INDEX ON tst USING hnsw (c, v vector_cosine_ops);");
 like($stderr, qr/first column must be a vector/);
 
-($ret, $stdout, $stderr) = $node->psql("postgres", "CREATE INDEX ON tst USING hnsw (v vector_l2_ops, c, c);");
+($ret, $stdout, $stderr) = $node->psql("postgres", "CREATE INDEX ON tst USING hnsw (v vector_cosine_ops, c, c);");
 like($stderr, qr/index cannot have more than two columns/);
 
-($ret, $stdout, $stderr) = $node->psql("postgres", "CREATE INDEX ON tst USING hnsw (v vector_l2_ops, v vector_l2_ops);");
+($ret, $stdout, $stderr) = $node->psql("postgres", "CREATE INDEX ON tst USING hnsw (v vector_cosine_ops, v vector_cosine_ops);");
 like($stderr, qr/column 2 cannot be a vector/);
 
 done_testing();