Fixed issue

src/hnsw.c

@@ -18,7 +18,7 @@
 #endif
 
 int			hnsw_ef_search;
-bool		hnsw_streaming;
+int			hnsw_time_budget;
 int			hnsw_lock_tranche_id;
 static relopt_kind hnsw_relopt_kind;
 
@@ -69,12 +69,9 @@ 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);
 
-	/* TODO Figure out name */
-	DefineCustomBoolVariable("hnsw.streaming", "Use streaming mode",
-							 NULL, &hnsw_streaming,
-							 HNSW_DEFAULT_STREAMING, PGC_USERSET, 0, NULL, NULL, NULL);
-
-	/* TODO Add option for limiting iterative search */
+	DefineCustomIntVariable("hnsw.time_budget", "Sets the time budget for search",
+							NULL, &hnsw_time_budget,
+							-1, -1, INT_MAX, PGC_USERSET, GUC_UNIT_MS, NULL, NULL, NULL);
 
 	MarkGUCPrefixReserved("hnsw");
 }
@@ -134,8 +131,6 @@ hnswcostestimate(PlannerInfo *root, IndexPath *path, double loop_count,
 	/* Account for number of tuples (or entry level), m, and ef_search */
 	costs.numIndexTuples = (entryLevel + 2) * m;
 
-	/* TODO Adjust for selectivity for iterative scans */
-
 	genericcostestimate(root, path, loop_count, &costs);
 
 	/* Use total cost since most work happens before first tuple is returned */

src/hnsw.h

@@ -12,10 +12,6 @@
 #include "utils/sampling.h"
 #include "vector.h"
 
-#ifdef HNSW_BENCH
-#include "portability/instr_time.h"
-#endif
-
 #define HNSW_MAX_DIM 2000
 #define HNSW_MAX_NNZ 1000
 
@@ -46,7 +42,6 @@
 #define HNSW_DEFAULT_EF_SEARCH	40
 #define HNSW_MIN_EF_SEARCH		1
 #define HNSW_MAX_EF_SEARCH		1000
-#define HNSW_DEFAULT_STREAMING	false
 
 /* Tuple types */
 #define HNSW_ELEMENT_TUPLE_TYPE  1
@@ -73,21 +68,6 @@
 #define HnswPageGetOpaque(page)	((HnswPageOpaque) PageGetSpecialPointer(page))
 #define HnswPageGetMeta(page)	((HnswMetaPageData *) PageGetContents(page))
 
-#ifdef HNSW_BENCH
-#define HnswBench(name, code) \
-	do { \
-		instr_time	start; \
-		instr_time	duration; \
-		INSTR_TIME_SET_CURRENT(start); \
-		(code); \
-		INSTR_TIME_SET_CURRENT(duration); \
-		INSTR_TIME_SUBTRACT(duration, start); \
-		elog(INFO, "%s: %.3f ms", name, INSTR_TIME_GET_MILLISEC(duration)); \
-	} while (0)
-#else
-#define HnswBench(name, code) (code)
-#endif
-
 #if PG_VERSION_NUM >= 150000
 #define RandomDouble() pg_prng_double(&pg_global_prng_state)
 #define SeedRandom(seed) pg_prng_seed(&pg_global_prng_state, seed)
@@ -126,7 +106,7 @@
 
 /* Variables */
 extern int	hnsw_ef_search;
-extern bool hnsw_streaming;
+extern int	hnsw_time_budget;
 extern int	hnsw_lock_tranche_id;
 
 typedef struct HnswElementData HnswElementData;
@@ -150,7 +130,6 @@ struct HnswElementData
 	uint8		heaptidsLength;
 	uint8		level;
 	uint8		deleted;
-	uint8		version;
 	uint32		hash;
 	HnswNeighborsPtr neighbors;
 	BlockNumber blkno;
@@ -177,16 +156,12 @@ struct HnswNeighborArray
 	HnswCandidate items[FLEXIBLE_ARRAY_MEMBER];
 };
 
-typedef struct HnswSearchCandidate
+typedef struct HnswPairingHeapNode
 {
+	HnswCandidate *inner;
 	pairingheap_node c_node;
 	pairingheap_node w_node;
-	HnswElementPtr element;
-	float		distance;
-}			HnswSearchCandidate;
-
-#define HnswGetSearchCandidate(membername, ptr) pairingheap_container(HnswSearchCandidate, membername, ptr)
-#define HnswGetSearchCandidateConst(membername, ptr) pairingheap_const_container(HnswSearchCandidate, membername, ptr)
+}			HnswPairingHeapNode;
 
 /* HNSW index options */
 typedef struct HnswOptions
@@ -331,10 +306,10 @@ typedef struct HnswElementTupleData
 	uint8		type;
 	uint8		level;
 	uint8		deleted;
-	uint8		version;
+	uint8		unused;
 	ItemPointerData heaptids[HNSW_HEAPTIDS];
 	ItemPointerData neighbortid;
-	uint16		unused;
+	uint16		unused2;
 	Vector		data;
 }			HnswElementTupleData;
 
@@ -343,31 +318,20 @@ typedef HnswElementTupleData * HnswElementTuple;
 typedef struct HnswNeighborTupleData
 {
 	uint8		type;
-	uint8		version;
+	uint8		unused;
 	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 struct HnswScanOpaqueData
 {
 	const		HnswTypeInfo *typeInfo;
 	bool		first;
 	List	   *w;
-	visited_hash v;
-	pairingheap *discarded;
-	Datum		q;
-	int			m;
-	int64		tuples;
 	MemoryContext tmpCtx;
+	instr_time	start;
 
 	/* Support functions */
 	FmgrInfo   *procinfo;
@@ -412,14 +376,14 @@ bool		HnswCheckNorm(FmgrInfo *procinfo, Oid collation, Datum value);
 Buffer		HnswNewBuffer(Relation index, ForkNumber forkNum);
 void		HnswInitPage(Buffer buf, Page page);
 void		HnswInit(void);
-List	   *HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool inserting, HnswElement skipElement, visited_hash * v, pairingheap **discarded, bool initVisited);
+List	   *HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool inserting, HnswElement skipElement, instr_time *start);
 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);
-HnswSearchCandidate *HnswEntryCandidate(char *base, HnswElement em, Datum q, Relation rel, FmgrInfo *procinfo, Oid collation, bool loadVec);
+HnswCandidate *HnswEntryCandidate(char *base, HnswElement em, Datum q, Relation rel, FmgrInfo *procinfo, Oid collation, bool loadVec);
 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);

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, uint8 *tupleVersion)
+HnswFreeOffset(Relation index, Buffer buf, Page page, HnswElement element, Size etupSize, Size ntupSize, Buffer *nbuf, Page *npage, OffsetNumber *freeOffno, OffsetNumber *freeNeighborOffno, BlockNumber *newInsertPage)
 {
 	OffsetNumber offno;
 	OffsetNumber maxoffno = PageGetMaxOffsetNumber(page);
@@ -98,7 +98,6 @@ HnswFreeOffset(Relation index, Buffer buf, Page page, HnswElement element, Size
 			{
 				*freeOffno = offno;
 				*freeNeighborOffno = neighborOffno;
-				*tupleVersion = etup->version;
 				return true;
 			}
 			else if (*nbuf != buf)
@@ -154,7 +153,6 @@ AddElementOnDisk(Relation index, HnswElement e, int m, BlockNumber insertPage, B
 	OffsetNumber freeOffno = InvalidOffsetNumber;
 	OffsetNumber freeNeighborOffno = InvalidOffsetNumber;
 	BlockNumber newInsertPage = InvalidBlockNumber;
-	uint8		tupleVersion;
 	char	   *base = NULL;
 
 	/* Calculate sizes */
@@ -204,7 +202,7 @@ 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, &tupleVersion))
+		if (HnswFreeOffset(index, buf, page, e, etupSize, ntupSize, &nbuf, &npage, &freeOffno, &freeNeighborOffno, &newInsertPage))
 		{
 			if (nbuf != buf)
 			{
@@ -214,10 +212,6 @@ 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;
 		}
 

src/hnswscan.c

@@ -3,6 +3,7 @@
 #include "access/relscan.h"
 #include "hnsw.h"
 #include "pgstat.h"
+#include "portability/instr_time.h"
 #include "storage/bufmgr.h"
 #include "storage/lmgr.h"
 #include "utils/memutils.h"
@@ -22,13 +23,11 @@ GetScanItems(IndexScanDesc scan, Datum q)
 	int			m;
 	HnswElement entryPoint;
 	char	   *base = NULL;
+	instr_time *start = hnsw_time_budget == -1 ? NULL : &so->start;
 
 	/* Get m and entry point */
 	HnswGetMetaPageInfo(index, &m, &entryPoint);
 
-	so->q = q;
-	so->m = m;
-
 	if (entryPoint == NULL)
 		return NIL;
 
@@ -36,44 +35,11 @@ GetScanItems(IndexScanDesc scan, Datum q)
 
 	for (int lc = entryPoint->level; lc >= 1; lc--)
 	{
-		w = HnswSearchLayer(base, q, ep, 1, lc, index, procinfo, collation, m, false, NULL, NULL, NULL, true);
+		w = HnswSearchLayer(base, q, ep, 1, lc, index, procinfo, collation, m, false, NULL, start);
 		ep = w;
 	}
 
-	return HnswSearchLayer(base, q, ep, hnsw_ef_search, 0, index, procinfo, collation, m, false, NULL, &so->v, &so->discarded, true);
-}
-
-/*
- * Resume scan at ground level with discarded candidates
- */
-static List *
-ResumeScanItems(IndexScanDesc scan)
-{
-	HnswScanOpaque so = (HnswScanOpaque) scan->opaque;
-	Relation	index = scan->indexRelation;
-	FmgrInfo   *procinfo = so->procinfo;
-	Oid			collation = so->collation;
-	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 *hc;
-
-		if (pairingheap_is_empty(so->discarded))
-			break;
-
-		hc = HnswGetSearchCandidate(w_node, pairingheap_remove_first(so->discarded));
-
-		ep = lappend(ep, hc);
-	}
-
-	return HnswSearchLayer(base, so->q, ep, batch_size, 0, index, procinfo, collation, so->m, false, NULL, &so->v, &so->discarded, false);
+	return HnswSearchLayer(base, q, ep, hnsw_ef_search, 0, index, procinfo, collation, m, false, NULL, start);
 }
 
 /*
@@ -126,6 +92,9 @@ hnswbeginscan(Relation index, int nkeys, int norderbys)
 	so->normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
 	so->collation = index->rd_indcollation[0];
 
+	if (hnsw_time_budget != -1)
+		INSTR_TIME_SET_CURRENT(so->start);
+
 	scan->opaque = so;
 
 	return scan;
@@ -139,13 +108,7 @@ hnswrescan(IndexScanDesc scan, ScanKey keys, int nkeys, ScanKey orderbys, int no
 {
 	HnswScanOpaque so = (HnswScanOpaque) scan->opaque;
 
-	if (!so->first)
-	{
-		pairingheap_reset(so->discarded);
-		tidhash_reset(so->v.tids);
-	}
 	so->first = true;
-	so->tuples = 0;
 	MemoryContextReset(so->tmpCtx);
 
 	if (keys && scan->numberOfKeys > 0)
@@ -195,7 +158,7 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
 		 */
 		LockPage(scan->indexRelation, HNSW_SCAN_LOCK, ShareLock);
 
-		HnswBench("scan iteration", so->w = GetScanItems(scan, value));
+		so->w = GetScanItems(scan, value);
 
 		/* Release shared lock */
 		UnlockPage(scan->indexRelation, HNSW_SCAN_LOCK, ShareLock);
@@ -203,83 +166,24 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
 		so->first = false;
 
 #if defined(HNSW_MEMORY)
-		elog(INFO, "memory: %zu KB", MemoryContextMemAllocated(so->tmpCtx, false) / 1024);
+		elog(INFO, "memory: %zu MB", MemoryContextMemAllocated(so->tmpCtx, false) / (1024 * 1024));
 #endif
 	}
 
-	for (;;)
+	while (list_length(so->w) > 0)
 	{
 		char	   *base = NULL;
-		HnswSearchCandidate *hc;
-		HnswElement element;
+		HnswCandidate *hc = llast(so->w);
+		HnswElement element = HnswPtrAccess(base, hc->element);
 		ItemPointer heaptid;
 
-		if (list_length(so->w) == 0)
-		{
-			if (!hnsw_streaming)
-				break;
-
-			/* Prevent scans from consuming too much memory */
-			if (MemoryContextMemAllocated(so->tmpCtx, false) > (Size) work_mem * 1024L)
-			{
-				if (pairingheap_is_empty(so->discarded))
-				{
-					ereport(NOTICE,
-							(errmsg("hnsw iterative search 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);
-
-				HnswBench("scan iteration", 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;
-		}
-
-		hc = llast(so->w);
-		element = HnswPtrAccess(base, hc->element);
-
 		/* Move to next element if no valid heap TIDs */
 		if (element->heaptidsLength == 0)
 		{
 			so->w = list_delete_last(so->w);
-
-			/* Mark memory as free for next iteration */
-			if (hnsw_streaming)
-			{
-				pfree(element);
-				pfree(hc);
-			}
-
 			continue;
 		}
 
-		so->tuples++;
-
 		heaptid = &element->heaptids[--element->heaptidsLength];
 
 		MemoryContextSwitchTo(oldCtx);

src/hnswutils.c

@@ -9,6 +9,7 @@
 #include "fmgr.h"
 #include "hnsw.h"
 #include "lib/pairingheap.h"
+#include "portability/instr_time.h"
 #include "sparsevec.h"
 #include "storage/bufmgr.h"
 #include "utils/datum.h"
@@ -100,6 +101,13 @@ 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;
@@ -246,8 +254,6 @@ 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);
 
@@ -400,7 +406,6 @@ HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element)
 	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)
@@ -443,7 +448,6 @@ HnswSetNeighborTuple(char *base, HnswNeighborTuple ntup, HnswElement e, int m)
 	}
 
 	ntup->count = idx;
-	ntup->version = e->version;
 }
 
 /*
@@ -517,7 +521,6 @@ 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;
@@ -606,10 +609,10 @@ GetElementDistance(char *base, HnswElement element, Datum q, FmgrInfo *procinfo,
 /*
  * Create a candidate for the entry point
  */
-HnswSearchCandidate *
+HnswCandidate *
 HnswEntryCandidate(char *base, HnswElement entryPoint, Datum q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec)
 {
-	HnswSearchCandidate *hc = palloc(sizeof(HnswSearchCandidate));
+	HnswCandidate *hc = palloc(sizeof(HnswCandidate));
 
 	HnswPtrStore(base, hc->element, entryPoint);
 	if (index == NULL)
@@ -619,31 +622,19 @@ HnswEntryCandidate(char *base, HnswElement entryPoint, Datum q, Relation index,
 	return hc;
 }
 
+#define HnswGetPairingHeapCandidate(membername, ptr) (pairingheap_container(HnswPairingHeapNode, membername, ptr)->inner)
+#define HnswGetPairingHeapCandidateConst(membername, ptr) (pairingheap_const_container(HnswPairingHeapNode, membername, ptr)->inner)
+
 /*
  * Compare candidate distances
  */
 static int
 CompareNearestCandidates(const pairingheap_node *a, const pairingheap_node *b, void *arg)
 {
-	if (HnswGetSearchCandidateConst(c_node, a)->distance < HnswGetSearchCandidateConst(c_node, b)->distance)
+	if (HnswGetPairingHeapCandidateConst(c_node, a)->distance < HnswGetPairingHeapCandidateConst(c_node, b)->distance)
 		return 1;
 
-	if (HnswGetSearchCandidateConst(c_node, a)->distance > HnswGetSearchCandidateConst(c_node, b)->distance)
-		return -1;
-
-	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)
+	if (HnswGetPairingHeapCandidateConst(c_node, a)->distance > HnswGetPairingHeapCandidateConst(c_node, b)->distance)
 		return -1;
 
 	return 0;
@@ -655,15 +646,27 @@ CompareNearestDiscardedCandidates(const pairingheap_node *a, const pairingheap_n
 static int
 CompareFurthestCandidates(const pairingheap_node *a, const pairingheap_node *b, void *arg)
 {
-	if (HnswGetSearchCandidateConst(w_node, a)->distance < HnswGetSearchCandidateConst(w_node, b)->distance)
+	if (HnswGetPairingHeapCandidateConst(w_node, a)->distance < HnswGetPairingHeapCandidateConst(w_node, b)->distance)
 		return -1;
 
-	if (HnswGetSearchCandidateConst(w_node, a)->distance > HnswGetSearchCandidateConst(w_node, b)->distance)
+	if (HnswGetPairingHeapCandidateConst(w_node, a)->distance > HnswGetPairingHeapCandidateConst(w_node, b)->distance)
 		return 1;
 
 	return 0;
 }
 
+/*
+ * Create a pairing heap node for a candidate
+ */
+static HnswPairingHeapNode *
+CreatePairingHeapNode(HnswCandidate * c)
+{
+	HnswPairingHeapNode *node = palloc(sizeof(HnswPairingHeapNode));
+
+	node->inner = c;
+	return node;
+}
+
 /*
  * Init visited
  */
@@ -764,30 +767,20 @@ HnswLoadUnvisitedFromDisk(HnswElement element, HnswUnvisited * unvisited, int *u
 	int			start;
 	ItemPointerData indextids[HNSW_MAX_M * 2];
 
-	*unvisitedLength = 0;
-
 	buf = ReadBuffer(index, element->neighborPage);
 	LockBuffer(buf, BUFFER_LOCK_SHARE);
 	page = BufferGetPage(buf);
 
 	ntup = (HnswNeighborTuple) PageGetItem(page, PageGetItemId(page, element->neighborOffno));
-
-	/*
-	 * Ensure the neighbor tuple has not been deleted or replaced between
-	 * index scan iterations
-	 */
-	if (ntup->version != element->version)
-	{
-		UnlockReleaseBuffer(buf);
-		return;
-	}
+	start = (element->level - lc) * m;
 
 	/* Copy to minimize lock time */
-	start = (element->level - lc) * m;
 	memcpy(&indextids, ntup->indextids + start, lm * sizeof(ItemPointerData));
 
 	UnlockReleaseBuffer(buf);
 
+	*unvisitedLength = 0;
+
 	for (int i = 0; i < lm; i++)
 	{
 		ItemPointer indextid = &indextids[i];
@@ -807,13 +800,13 @@ HnswLoadUnvisitedFromDisk(HnswElement element, HnswUnvisited * unvisited, int *u
  * Algorithm 2 from paper
  */
 List *
-HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool inserting, HnswElement skipElement, visited_hash * v, pairingheap **discarded, bool initVisited)
+HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool inserting, HnswElement skipElement, instr_time *start)
 {
 	List	   *w = NIL;
 	pairingheap *C = pairingheap_allocate(CompareNearestCandidates, NULL);
 	pairingheap *W = pairingheap_allocate(CompareFurthestCandidates, NULL);
 	int			wlen = 0;
-	visited_hash vh;
+	visited_hash v;
 	ListCell   *lc2;
 	HnswNeighborArray *localNeighborhood = NULL;
 	Size		neighborhoodSize = 0;
@@ -821,19 +814,7 @@ HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, F
 	HnswUnvisited *unvisited = palloc(lm * sizeof(HnswUnvisited));
 	int			unvisitedLength;
 
-	if (v == NULL)
-	{
-		v = &vh;
-		initVisited = true;
-	}
-
-	if (initVisited)
-	{
-		InitVisited(base, v, index, ef, m);
-
-		if (discarded != NULL)
-			*discarded = pairingheap_allocate(CompareNearestDiscardedCandidates, NULL);
-	}
+	InitVisited(base, &v, index, ef, m);
 
 	/* Create local memory for neighborhood if needed */
 	if (index == NULL)
@@ -845,14 +826,15 @@ HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, F
 	/* Add entry points to v, C, and W */
 	foreach(lc2, ep)
 	{
-		HnswSearchCandidate *hc = (HnswSearchCandidate *) lfirst(lc2);
+		HnswCandidate *hc = (HnswCandidate *) lfirst(lc2);
 		bool		found;
+		HnswPairingHeapNode *node;
 
-		if (initVisited)
-			AddToVisited(base, v, hc->element, index, &found);
+		AddToVisited(base, &v, hc->element, index, &found);
 
-		pairingheap_add(C, &hc->c_node);
-		pairingheap_add(W, &hc->w_node);
+		node = CreatePairingHeapNode(hc);
+		pairingheap_add(C, &node->c_node);
+		pairingheap_add(W, &node->w_node);
 
 		/*
 		 * Do not count elements being deleted towards ef when vacuuming. It
@@ -865,28 +847,40 @@ HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, F
 
 	while (!pairingheap_is_empty(C))
 	{
-		HnswSearchCandidate *c = HnswGetSearchCandidate(c_node, pairingheap_remove_first(C));
-		HnswSearchCandidate *f = HnswGetSearchCandidate(w_node, pairingheap_first(W));
+		HnswCandidate *c = HnswGetPairingHeapCandidate(c_node, pairingheap_remove_first(C));
+		HnswCandidate *f = HnswGetPairingHeapCandidate(w_node, pairingheap_first(W));
 		HnswElement cElement;
 
+		/* Check time budget */
+		if (start != NULL)
+		{
+			instr_time	duration;
+
+			INSTR_TIME_SET_CURRENT(duration);
+			INSTR_TIME_SUBTRACT(duration, *start);
+			if (INSTR_TIME_GET_MILLISEC(duration) >= hnsw_time_budget)
+				break;
+		}
+
 		if (c->distance > f->distance)
 			break;
 
 		cElement = HnswPtrAccess(base, c->element);
 
 		if (index == NULL)
-			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);
 
 		for (int i = 0; i < unvisitedLength; i++)
 		{
 			HnswElement eElement;
-			HnswSearchCandidate *e;
+			HnswCandidate *e;
+			HnswPairingHeapNode *node;
 			float		eDistance;
 			bool		alwaysAdd = wlen < ef;
 
-			f = HnswGetSearchCandidate(w_node, pairingheap_first(W));
+			f = HnswGetPairingHeapCandidate(w_node, pairingheap_first(W));
 
 			if (index == NULL)
 			{
@@ -901,33 +895,29 @@ HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, F
 
 				/* Avoid any allocations if not adding */
 				eElement = NULL;
-				HnswLoadElementImpl(blkno, offno, &eDistance, &q, index, procinfo, collation, inserting, alwaysAdd || discarded != NULL ? NULL : &f->distance, &eElement);
+				HnswLoadElementImpl(blkno, offno, &eDistance, &q, index, procinfo, collation, inserting, alwaysAdd ? NULL : &f->distance, &eElement);
+
+				if (eElement == NULL)
+					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);
-				}
-
+			if (!(eDistance < f->distance || alwaysAdd))
 				continue;
-			}
+
+			Assert(!eElement->deleted);
 
 			/* Make robust to issues */
 			if (eElement->level < lc)
 				continue;
 
 			/* Create a new candidate */
-			e = palloc(sizeof(HnswSearchCandidate));
+			e = palloc(sizeof(HnswCandidate));
 			HnswPtrStore(base, e->element, eElement);
 			e->distance = eDistance;
-			pairingheap_add(C, &e->c_node);
-			pairingheap_add(W, &e->w_node);
+
+			node = CreatePairingHeapNode(e);
+			pairingheap_add(C, &node->c_node);
+			pairingheap_add(W, &node->w_node);
 
 			/*
 			 * Do not count elements being deleted towards ef when vacuuming.
@@ -940,12 +930,7 @@ HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, F
 
 				/* No need to decrement wlen */
 				if (wlen > ef)
-				{
-					HnswSearchCandidate *d = HnswGetSearchCandidate(w_node, pairingheap_remove_first(W));
-
-					if (discarded != NULL)
-						pairingheap_add(*discarded, &d->w_node);
-				}
+					pairingheap_remove_first(W);
 			}
 		}
 	}
@@ -953,7 +938,7 @@ HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, F
 	/* Add each element of W to w */
 	while (!pairingheap_is_empty(W))
 	{
-		HnswSearchCandidate *hc = HnswGetSearchCandidate(w_node, pairingheap_remove_first(W));
+		HnswCandidate *hc = HnswGetPairingHeapCandidate(w_node, pairingheap_remove_first(W));
 
 		w = lappend(w, hc);
 	}
@@ -1318,7 +1303,7 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
 	/* 1st phase: greedy search to insert level */
 	for (int lc = entryLevel; lc >= level + 1; lc--)
 	{
-		w = HnswSearchLayer(base, q, ep, 1, lc, index, procinfo, collation, m, true, skipElement, NULL, NULL, true);
+		w = HnswSearchLayer(base, q, ep, 1, lc, index, procinfo, collation, m, true, skipElement, NULL);
 		ep = w;
 	}
 
@@ -1334,27 +1319,16 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
 	{
 		int			lm = HnswGetLayerM(m, lc);
 		List	   *neighbors;
-		List	   *lw = NIL;
-		ListCell   *lc2;
+		List	   *lw;
 
-		w = HnswSearchLayer(base, q, ep, efConstruction, lc, index, procinfo, collation, m, true, skipElement, NULL, NULL, true);
-
-		/* Convert search candidates to candidates */
-		foreach(lc2, w)
-		{
-			HnswSearchCandidate *sc = lfirst(lc2);
-			HnswCandidate *hc = palloc(sizeof(HnswCandidate));
-
-			hc->element = sc->element;
-			hc->distance = sc->distance;
-
-			lw = lappend(lw, hc);
-		}
+		w = HnswSearchLayer(base, q, ep, efConstruction, lc, index, procinfo, collation, m, true, skipElement, NULL);
 
 		/* Elements being deleted or skipped can help with search */
 		/* but should be removed before selecting neighbors */
 		if (index != NULL)
-			lw = RemoveElements(base, lw, skipElement);
+			lw = RemoveElements(base, w, skipElement);
+		else
+			lw = w;
 
 		/*
 		 * Candidates are sorted, but not deterministically. Could set

src/hnswvacuum.c

@@ -527,14 +527,6 @@ 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

test/t/039_hnsw_streaming.pl

@@ -1,43 +0,0 @@
-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;");
-$node->safe_psql("postgres", "CREATE TABLE tst (i int4, v vector($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 = $node->safe_psql("postgres", qq(
-	SET enable_seqscan = off;
-	SET hnsw.streaming = on;
-	SET work_mem = '8MB';
-	SELECT COUNT(*) FROM (SELECT v FROM tst WHERE i % 10000 = 0 ORDER BY v <-> (SELECT v FROM tst LIMIT 1) LIMIT 11) t;
-));
-is($count, 10);
-
-my ($ret, $stdout, $stderr) = $node->psql("postgres", qq(
-	SET enable_seqscan = off;
-	SET hnsw.streaming = on;
-	SET work_mem = '2MB';
-	SELECT COUNT(*) FROM (SELECT v FROM tst WHERE i % 10000 = 0 ORDER BY v <-> (SELECT v FROM tst LIMIT 1) LIMIT 11) t;
-));
-like($stderr, qr/iterative search exceeded work_mem after \d+ tuples/);
-
-done_testing();

test/t/040_hnsw_streaming_recall.pl

@@ -1,131 +0,0 @@
-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.streaming = 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.streaming = 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();