Added search parameters to EXPLAIN [skip ci]

This reverts commit 7043cce893.

.github/workflows/build.yml

@@ -8,8 +8,8 @@ jobs:
       fail-fast: false
       matrix:
         include:
-          # - postgres: 18
+          - postgres: 18
-          #   os: ubuntu-24.04
+            os: ubuntu-24.04
           - postgres: 17
             os: ubuntu-24.04
           - postgres: 16
@@ -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

README.md

@@ -451,67 +451,77 @@ Use [partitioning](https://www.postgresql.org/docs/current/ddl-partitioning.html
 CREATE TABLE items (embedding vector(3), category_id int) PARTITION BY LIST(category_id);
 ```
 
-## Iterative Search [unreleased]
+## Iterative Index Scans
 
-*Added in 0.8.0*
+*Unreleased*
 
-With approximate indexes, you can end up with less results than expected due to filtering conditions in the query.
+With approximate indexes, queries with filtering can return less results (due to post-filtering). Starting with 0.8.0, you can enable iterative index scans. If too few results from the initial scan match the filters, the scan will resume until enough results are found (or it reaches `hnsw.max_scan_tuples` or `ivfflat.max_probes`). This can significantly improve recall.
 
-Starting with 0.8.0, you can enable iterative search. If too few results from the initial index scan match the query filters, it will resume scanning until enough results are found. This can significantly improve recall (at the cost of speed).
+There are two modes for iterative scans: strict and relaxed.
 
-```tsql
+Strict ensures results are in the exact order by distance
-SET hnsw.streaming = on;
--- or
-SET ivfflat.streaming = on;
-```
-
-However, there are some important caveats.
-
-### Iterative Caveats
-
-With iterative search, it’s possible for rows to be slightly out of order by distance. For strict ordering, use:
 
 ```sql
-WITH approx_order AS MATERIALIZED (
+SET hnsw.iterative_scan = strict_order;
-    SELECT *, embedding <-> '[1,2,3]' AS distance FROM items WHERE ... ORDER BY distance LIMIT 5
-) SELECT * FROM approx_order ORDER BY distance;
 ```
 
-For distance filters, use a CTE and place the filter outside it.
+Relaxed allows results to be slightly out of order by distance, but provides better recall
 
 ```sql
-WITH approx_order AS MATERIALIZED (
+SET hnsw.iterative_scan = relaxed_order;
-    SELECT *, embedding <-> '[1,2,3]' AS distance FROM items WHERE ... ORDER BY distance LIMIT 5
+# or
-) SELECT * FROM approx_order WHERE distance < 0.1 ORDER BY distance;
+SET ivfflat.iterative_scan = relaxed_order;
 ```
 
-### Iterative Options
+With relaxed ordering, you can use a [materialized CTE](https://www.postgresql.org/docs/current/queries-with.html#QUERIES-WITH-CTE-MATERIALIZATION) to get strict ordering
 
-Since scanning a large portion of the index is expensive, there are options to control when the scan ends.
+```sql
+WITH relaxed_results AS MATERIALIZED (
+    SELECT id, embedding <-> '[1,2,3]' AS distance FROM items WHERE category_id = 123 ORDER BY distance LIMIT 5
+) SELECT * FROM relaxed_results ORDER BY distance;
+```
+
+For queries that filter by distance, use a materialized CTE and place the distance filter outside of it for best performance (due to the [current behavior](https://www.postgresql.org/message-id/flat/CAOdR5yGUoMQ6j7M5hNUXrySzaqZVGf_Ne%2B8fwZMRKTFxU1nbJg%40mail.gmail.com) of the Postgres executor)
+
+```sql
+WITH nearest_results AS MATERIALIZED (
+    SELECT id, embedding <-> '[1,2,3]' AS distance FROM items ORDER BY distance LIMIT 5
+) SELECT * FROM nearest_results WHERE distance < 5 ORDER BY distance;
+```
+
+Note: Place any other filters inside the CTE
+
+### Iterative Scan Options
+
+Since scanning a large portion of an approximate index is expensive, there are options to control when a scan ends
 
 #### HNSW
 
-Specify the max number of additional tuples visited
+Specify the max number of tuples to visit (20,000 by default)
 
 ```sql
-SET hnsw.ef_stream = 10000;
+SET hnsw.max_scan_tuples = 20000;
 ```
 
-The scan will also end if reaches `work_mem`. You can see when this happens by enabling debug messages.
+Note: This is approximate and does not affect the initial scan
+
+Specify the max amount of memory to use, as a multiple of `work_mem` (1 by default)
+
+```sql
+SET hnsw.scan_mem_multiplier = 2;
+```
+
+You can see when increasing this is needed by enabling debug messages
 
 ```sql
 SET client_min_messages = debug1;
 ```
 
+which will show when a scan reaches the memory limit
+
 ```text
-DEBUG:  hnsw index scan exceeded work_mem after 10000 tuples
+DEBUG:  hnsw index scan reached memory limit after 20000 tuples
-HINT:  Increase work_mem to scan more tuples.
+HINT:  Increase hnsw.scan_mem_multiplier to scan more tuples.
-```
-
-If the server has enough memory, you can adjust this with:
-
-```sql
-SET work_mem = '8MB';
 ```
 
 #### IVFFlat
@@ -522,6 +532,8 @@ Specify the max number of probes
 SET ivfflat.max_probes = 100;
 ```
 
+Note: If this is lower than `ivfflat.probes`, `ivfflat.probes` will be used
+
 ## Half-Precision Vectors
 
 *Added in 0.7.0*

src/hnsw.c

@@ -18,18 +18,17 @@
 #define MarkGUCPrefixReserved(x) EmitWarningsOnPlaceholders(x)
 #endif
 
-static const struct config_enum_entry hnsw_iterative_search_options[] = {
+static const struct config_enum_entry hnsw_iterative_scan_options[] = {
-	{"off", HNSW_ITERATIVE_SEARCH_OFF, false},
+	{"off", HNSW_ITERATIVE_SCAN_OFF, false},
-	{"strict", HNSW_ITERATIVE_SEARCH_STRICT, false},
+	{"relaxed_order", HNSW_ITERATIVE_SCAN_RELAXED, false},
-	{"relaxed", HNSW_ITERATIVE_SEARCH_RELAXED, false},
+	{"strict_order", HNSW_ITERATIVE_SCAN_STRICT, false},
-	/* TODO Change to strict before merging */
-	{"on", HNSW_ITERATIVE_SEARCH_RELAXED, false},
 	{NULL, 0, false}
 };
 
 int			hnsw_ef_search;
-int			hnsw_max_iterative_tuples;
+int			hnsw_iterative_scan;
-int			hnsw_iterative_search;
+int			hnsw_max_scan_tuples;
+double		hnsw_scan_mem_multiplier;
 int			hnsw_lock_tranche_id;
 static relopt_kind hnsw_relopt_kind;
 
@@ -78,18 +77,21 @@ HnswInit(void)
 
 	DefineCustomIntVariable("hnsw.ef_search", "Sets the size of the dynamic candidate list for search",
 							"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);
+							HNSW_DEFAULT_EF_SEARCH, HNSW_MIN_EF_SEARCH, HNSW_MAX_EF_SEARCH, PGC_USERSET, GUC_EXPLAIN, NULL, NULL, NULL);
 
-	/* TODO Change name */
+	DefineCustomEnumVariable("hnsw.iterative_scan", "Sets the mode for iterative scans",
-	DefineCustomEnumVariable("hnsw.streaming", "Iterative search mode",
+							 NULL, &hnsw_iterative_scan,
-							 NULL, &hnsw_iterative_search,
+							 HNSW_ITERATIVE_SCAN_OFF, hnsw_iterative_scan_options, PGC_USERSET, GUC_EXPLAIN, NULL, NULL, NULL);
-							 HNSW_ITERATIVE_SEARCH_OFF, hnsw_iterative_search_options, PGC_USERSET, 0, NULL, NULL, NULL);
 
-	/* TODO Change name */
+	/* This is approximate and does not affect the initial scan */
-	/* TODO Ensure ivfflat.max_probes uses same value for "all" */
+	DefineCustomIntVariable("hnsw.max_scan_tuples", "Sets the max number of tuples to visit for iterative scans",
-	DefineCustomIntVariable("hnsw.ef_stream", "Sets the max number of additional candidates to visit for streaming search",
+							NULL, &hnsw_max_scan_tuples,
-							"-1 means all", &hnsw_max_iterative_tuples,
+							20000, 1, INT_MAX, PGC_USERSET, GUC_EXPLAIN, NULL, NULL, NULL);
-							HNSW_DEFAULT_EF_STREAM, HNSW_MIN_EF_STREAM, HNSW_MAX_EF_STREAM, PGC_USERSET, 0, NULL, NULL, NULL);
+
+	/* Same range as hash_mem_multiplier */
+	DefineCustomRealVariable("hnsw.scan_mem_multiplier", "Sets the multiple of work_mem to use for iterative scans",
+							 NULL, &hnsw_scan_mem_multiplier,
+							 1, 1, 1000, PGC_USERSET, GUC_EXPLAIN, NULL, NULL, NULL);
 
 	MarkGUCPrefixReserved("hnsw");
 }
@@ -135,6 +137,10 @@ hnswcostestimate(PlannerInfo *root, IndexPath *path, double loop_count,
 		*indexSelectivity = 0;
 		*indexCorrelation = 0;
 		*indexPages = 0;
+#if PG_VERSION_NUM >= 180000
+		/* See "On disable_cost" thread on pgsql-hackers */
+		path->path.disabled_nodes = 2;
+#endif
 		return;
 	}
 

src/hnsw.h

@@ -42,9 +42,6 @@
 #define HNSW_DEFAULT_EF_SEARCH	40
 #define HNSW_MIN_EF_SEARCH		1
 #define HNSW_MAX_EF_SEARCH		1000
-#define HNSW_DEFAULT_EF_STREAM	-1
-#define HNSW_MIN_EF_STREAM		-1
-#define HNSW_MAX_EF_STREAM		INT_MAX
 
 /* Tuple types */
 #define HNSW_ELEMENT_TUPLE_TYPE  1
@@ -112,16 +109,17 @@
 
 /* Variables */
 extern int	hnsw_ef_search;
-extern int	hnsw_max_iterative_tuples;
+extern int	hnsw_iterative_scan;
-extern int	hnsw_iterative_search;
+extern int	hnsw_max_scan_tuples;
+extern double hnsw_scan_mem_multiplier;
 extern int	hnsw_lock_tranche_id;
 
-typedef enum HnswIterativeSearchType
+typedef enum HnswIterativeScanMode
 {
-	HNSW_ITERATIVE_SEARCH_OFF,
+	HNSW_ITERATIVE_SCAN_OFF,
-	HNSW_ITERATIVE_SEARCH_STRICT,
+	HNSW_ITERATIVE_SCAN_RELAXED,
-	HNSW_ITERATIVE_SEARCH_RELAXED
+	HNSW_ITERATIVE_SCAN_STRICT
-}			HnswIterativeSearchType;
+}			HnswIterativeScanMode;
 
 typedef struct HnswElementData HnswElementData;
 typedef struct HnswNeighborArray HnswNeighborArray;
@@ -375,6 +373,7 @@ typedef struct HnswScanOpaqueData
 	int			m;
 	int64		tuples;
 	double		previousDistance;
+	Size		maxMemory;
 	MemoryContext tmpCtx;
 
 	/* Support functions */

src/hnswscan.c

@@ -41,7 +41,7 @@ GetScanItems(IndexScanDesc scan, Datum value)
 		ep = w;
 	}
 
-	return HnswSearchLayer(base, q, ep, hnsw_ef_search, 0, index, support, m, false, NULL, &so->v, hnsw_iterative_search != HNSW_ITERATIVE_SEARCH_OFF ? &so->discarded : NULL, true, &so->tuples);
+	return HnswSearchLayer(base, q, ep, hnsw_ef_search, 0, index, support, m, false, NULL, &so->v, hnsw_iterative_scan != HNSW_ITERATIVE_SCAN_OFF ? &so->discarded : NULL, true, &so->tuples);
 }
 
 /*
@@ -102,6 +102,17 @@ GetScanValue(IndexScanDesc scan)
 	return value;
 }
 
+#if defined(HNSW_MEMORY)
+/*
+ * Show memory usage
+ */
+static void
+ShowMemoryUsage(HnswScanOpaque so)
+{
+	elog(INFO, "memory: %zu KB, tuples: " INT64_FORMAT, MemoryContextMemAllocated(so->tmpCtx, false) / 1024, so->tuples);
+}
+#endif
+
 /*
  * Prepare for an index scan
  */
@@ -110,21 +121,29 @@ hnswbeginscan(Relation index, int nkeys, int norderbys)
 {
 	IndexScanDesc scan;
 	HnswScanOpaque so;
+	double		maxMemory;
 
 	scan = RelationGetIndexScan(index, nkeys, 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 */
 	HnswInitSupport(&so->support, index);
 
+	/*
+	 * Use a lower max allocation size than default to allow scanning more
+	 * tuples for iterative search before exceeding work_mem
+	 */
+	so->tmpCtx = AllocSetContextCreate(CurrentMemoryContext,
+									   "Hnsw scan temporary context",
+									   0, 8 * 1024, 256 * 1024);
+
+	/* Calculate max memory */
+	/* Add 256 extra bytes to fill last block when close */
+	maxMemory = (double) work_mem * hnsw_scan_mem_multiplier * 1024.0 + 256;
+	so->maxMemory = Min(maxMemory, (double) SIZE_MAX);
+
 	scan->opaque = so;
 
 	return scan;
@@ -138,13 +157,10 @@ 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;
+	/* v and discarded are allocated in tmpCtx */
+	so->v.tids = NULL;
+	so->discarded = NULL;
 	so->tuples = 0;
 	so->previousDistance = -get_float8_infinity();
 	MemoryContextReset(so->tmpCtx);
@@ -204,7 +220,7 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
 		so->first = false;
 
 #if defined(HNSW_MEMORY)
-		elog(INFO, "memory: %zu KB", MemoryContextMemAllocated(so->tmpCtx, false) / 1024);
+		ShowMemoryUsage(so);
 #endif
 	}
 
@@ -217,15 +233,15 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
 
 		if (list_length(so->w) == 0)
 		{
-			if (hnsw_iterative_search == HNSW_ITERATIVE_SEARCH_OFF)
+			if (hnsw_iterative_scan == HNSW_ITERATIVE_SCAN_OFF)
 				break;
 
 			/* Empty index */
 			if (so->discarded == NULL)
 				break;
 
-			/* Reached max number of additional tuples */
+			/* Reached max number of tuples */
-			if (hnsw_max_iterative_tuples != -1 && so->tuples >= hnsw_ef_search + hnsw_max_iterative_tuples)
+			if (so->tuples >= hnsw_max_scan_tuples)
 			{
 				if (pairingheap_is_empty(so->discarded))
 					break;
@@ -234,13 +250,13 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
 				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)
+			else if (MemoryContextMemAllocated(so->tmpCtx, false) > so->maxMemory)
 			{
 				if (pairingheap_is_empty(so->discarded))
 				{
 					ereport(DEBUG1,
-							(errmsg("hnsw index scan exceeded work_mem after " INT64_FORMAT " tuples", so->tuples),
+							(errmsg("hnsw index scan reached memory limit after " INT64_FORMAT " tuples", so->tuples),
-							 errhint("Increase work_mem to scan more tuples.")));
+							 errhint("Increase hnsw.scan_mem_multiplier to scan more tuples.")));
 
 					break;
 				}
@@ -266,7 +282,7 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
 				UnlockPage(scan->indexRelation, HNSW_SCAN_LOCK, ShareLock);
 
 #if defined(HNSW_MEMORY)
-				elog(INFO, "memory: %zu KB", MemoryContextMemAllocated(so->tmpCtx, false) / 1024);
+				ShowMemoryUsage(so);
 #endif
 			}
 
@@ -283,7 +299,7 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
 			so->w = list_delete_last(so->w);
 
 			/* Mark memory as free for next iteration */
-			if (hnsw_iterative_search != HNSW_ITERATIVE_SEARCH_OFF)
+			if (hnsw_iterative_scan != HNSW_ITERATIVE_SCAN_OFF)
 			{
 				pfree(element);
 				pfree(sc);
@@ -294,7 +310,7 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
 
 		heaptid = &element->heaptids[--element->heaptidsLength];
 
-		if (hnsw_iterative_search == HNSW_ITERATIVE_SEARCH_STRICT)
+		if (hnsw_iterative_scan == HNSW_ITERATIVE_SCAN_STRICT)
 		{
 			if (sc->distance < so->previousDistance)
 				continue;

src/hnswutils.c

@@ -581,21 +581,34 @@ GetElementDistance(char *base, HnswElement element, HnswQuery * q, HnswSupport *
 	return HnswGetDistance(q->value, value, support);
 }
 
+/*
+ * Allocate a search candidate
+ */
+static HnswSearchCandidate *
+HnswInitSearchCandidate(char *base, HnswElement element, double distance)
+{
+	HnswSearchCandidate *sc = palloc(sizeof(HnswSearchCandidate));
+
+	HnswPtrStore(base, sc->element, element);
+	sc->distance = distance;
+	return sc;
+}
+
 /*
  * Create a candidate for the entry point
  */
 HnswSearchCandidate *
 HnswEntryCandidate(char *base, HnswElement entryPoint, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec)
 {
-	HnswSearchCandidate *sc = palloc(sizeof(HnswSearchCandidate));
 	bool		inMemory = index == NULL;
+	double		distance;
 
-	HnswPtrStore(base, sc->element, entryPoint);
 	if (inMemory)
-		sc->distance = GetElementDistance(base, entryPoint, q, support);
+		distance = GetElementDistance(base, entryPoint, q, support);
 	else
-		HnswLoadElement(entryPoint, &sc->distance, q, index, support, loadVec, NULL);
+		HnswLoadElement(entryPoint, &distance, q, index, support, loadVec, NULL);
-	return sc;
+
+	return HnswInitSearchCandidate(base, entryPoint, distance);
 }
 
 /*
@@ -844,6 +857,7 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
 		{
 			AddToVisited(base, v, sc->element, inMemory, &found);
 
+			/* OK to count elements instead of tuples */
 			if (tuples != NULL)
 				(*tuples)++;
 		}
@@ -876,6 +890,7 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
 		else
 			HnswLoadUnvisitedFromDisk(cElement, unvisited, &unvisitedLength, v, index, m, lm, lc);
 
+		/* OK to count elements instead of tuples */
 		if (tuples != NULL)
 			(*tuples) += unvisitedLength;
 
@@ -912,9 +927,7 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
 				if (discarded != NULL)
 				{
 					/* Create a new candidate */
-					e = palloc(sizeof(HnswSearchCandidate));
+					e = HnswInitSearchCandidate(base, eElement, eDistance);
-					HnswPtrStore(base, e->element, eElement);
-					e->distance = eDistance;
 					pairingheap_add(*discarded, &e->w_node);
 				}
 
@@ -926,9 +939,7 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
 				continue;
 
 			/* Create a new candidate */
-			e = palloc(sizeof(HnswSearchCandidate));
+			e = HnswInitSearchCandidate(base, eElement, eDistance);
-			HnswPtrStore(base, e->element, eElement);
-			e->distance = eDistance;
 			pairingheap_add(C, &e->c_node);
 			pairingheap_add(W, &e->w_node);
 

src/ivfbuild.c

@@ -228,11 +228,11 @@ BuildCallback(Relation index, ItemPointer tid, Datum *values,
 static inline void
 GetNextTuple(Tuplesortstate *sortstate, TupleDesc tupdesc, TupleTableSlot *slot, IndexTuple *itup, int *list)
 {
+	if (tuplesort_gettupleslot(sortstate, true, false, slot, NULL))
+	{
 		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);
 
@@ -254,8 +254,8 @@ InsertTuples(Relation index, IvfflatBuildState * buildstate, ForkNumber forkNum)
 	IndexTuple	itup = NULL;	/* silence compiler warning */
 	int64		inserted = 0;
 
-	TupleTableSlot *slot = MakeSingleTupleTableSlot(buildstate->tupdesc, &TTSOpsMinimalTuple);
+	TupleTableSlot *slot = MakeSingleTupleTableSlot(buildstate->sortdesc, &TTSOpsMinimalTuple);
-	TupleDesc	tupdesc = RelationGetDescr(index);
+	TupleDesc	tupdesc = buildstate->tupdesc;
 
 	pgstat_progress_update_param(PROGRESS_CREATEIDX_SUBPHASE, PROGRESS_IVFFLAT_PHASE_LOAD);
 
@@ -319,6 +319,7 @@ 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 +357,12 @@ 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);
+	buildstate->sortdesc = CreateTemplateTupleDesc(3);
-	TupleDescInitEntry(buildstate->tupdesc, (AttrNumber) 1, "list", INT4OID, -1, 0);
+	TupleDescInitEntry(buildstate->sortdesc, (AttrNumber) 1, "list", INT4OID, -1, 0);
-	TupleDescInitEntry(buildstate->tupdesc, (AttrNumber) 2, "tid", TIDOID, -1, 0);
+	TupleDescInitEntry(buildstate->sortdesc, (AttrNumber) 2, "tid", TIDOID, -1, 0);
-	TupleDescInitEntry(buildstate->tupdesc, (AttrNumber) 3, "vector", RelationGetDescr(index)->attrs[0].atttypid, -1, 0);
+	TupleDescInitEntry(buildstate->sortdesc, (AttrNumber) 3, "vector", buildstate->tupdesc->attrs[0].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 +634,7 @@ 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 +951,7 @@ 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_scan;
+int			ivfflat_max_probes;
 static relopt_kind ivfflat_relopt_kind;
 
+static const struct config_enum_entry ivfflat_iterative_scan_options[] = {
+	{"off", IVFFLAT_ITERATIVE_SCAN_OFF, false},
+	{"relaxed_order", IVFFLAT_ITERATIVE_SCAN_RELAXED, false},
+	{NULL, 0, false}
+};
+
 /*
  * Initialize index options and variables
  */
@@ -31,7 +39,16 @@ IvfflatInit(void)
 
 	DefineCustomIntVariable("ivfflat.probes", "Sets the number of probes",
 							"Valid range is 1..lists.", &ivfflat_probes,
-							IVFFLAT_DEFAULT_PROBES, IVFFLAT_MIN_LISTS, IVFFLAT_MAX_LISTS, PGC_USERSET, 0, NULL, NULL, NULL);
+							IVFFLAT_DEFAULT_PROBES, IVFFLAT_MIN_LISTS, IVFFLAT_MAX_LISTS, PGC_USERSET, GUC_EXPLAIN, NULL, NULL, NULL);
+
+	DefineCustomEnumVariable("ivfflat.iterative_scan", "Sets the mode for iterative scans",
+							 NULL, &ivfflat_iterative_scan,
+							 IVFFLAT_ITERATIVE_SCAN_OFF, ivfflat_iterative_scan_options, PGC_USERSET, GUC_EXPLAIN, NULL, NULL, NULL);
+
+	/* If this is less than probes, probes is used */
+	DefineCustomIntVariable("ivfflat.max_probes", "Sets the max number of probes for iterative scans",
+							NULL, &ivfflat_max_probes,
+							IVFFLAT_MAX_LISTS, IVFFLAT_MIN_LISTS, IVFFLAT_MAX_LISTS, PGC_USERSET, GUC_EXPLAIN, NULL, NULL, NULL);
 
 	MarkGUCPrefixReserved("ivfflat");
 }
@@ -82,6 +99,10 @@ ivfflatcostestimate(PlannerInfo *root, IndexPath *path, double loop_count,
 		*indexSelectivity = 0;
 		*indexCorrelation = 0;
 		*indexPages = 0;
+#if PG_VERSION_NUM >= 180000
+		/* See "On disable_cost" thread on pgsql-hackers */
+		path->path.disabled_nodes = 2;
+#endif
 		return;
 	}
 

src/ivfflat.h

@@ -80,6 +80,14 @@
 
 /* Variables */
 extern int	ivfflat_probes;
+extern int	ivfflat_iterative_scan;
+extern int	ivfflat_max_probes;
+
+typedef enum IvfflatIterativeScanMode
+{
+	IVFFLAT_ITERATIVE_SCAN_OFF,
+	IVFFLAT_ITERATIVE_SCAN_RELAXED
+}			IvfflatIterativeScanMode;
 
 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 +256,11 @@ typedef struct IvfflatScanOpaqueData
 {
 	const		IvfflatTypeInfo *typeInfo;
 	int			probes;
+	int			maxProbes;
 	int			dimensions;
 	bool		first;
+	Datum		value;
+	MemoryContext tmpCtx;
 
 	/* Sorting */
 	Tuplesortstate *sortstate;
@@ -265,7 +277,9 @@ typedef struct IvfflatScanOpaqueData
 
 	/* Lists */
 	pairingheap *listQueue;
-	IvfflatScanList lists[FLEXIBLE_ARRAY_MEMBER];	/* must come last */
+	BlockNumber *listPages;
+	int			listIndex;
+	IvfflatScanList *lists;
 }			IvfflatScanOpaqueData;
 
 typedef IvfflatScanOpaqueData * IvfflatScanOpaque;

src/ivfinsert.c

@@ -98,7 +98,7 @@ 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;
 

src/ivfscan.c

@@ -10,10 +10,7 @@
 #include "miscadmin.h"
 #include "pgstat.h"
 #include "storage/bufmgr.h"
-
-#ifdef IVFFLAT_MEMORY
 #include "utils/memutils.h"
-#endif
 
 #define GetScanList(ptr) pairingheap_container(IvfflatScanList, ph_node, ptr)
 #define GetScanListConst(ptr) pairingheap_const_container(IvfflatScanList, ph_node, ptr)
@@ -65,7 +62,7 @@ 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 +75,7 @@ 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 +99,11 @@ 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 +116,14 @@ 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 +171,17 @@ GetScanItems(IndexScanDesc scan, Datum value)
 		}
 	}
 
-	if (tuples < 100)
+	if (tuples < 100 && ivfflat_iterative_scan == IVFFLAT_ITERATIVE_SCAN_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
 }
 
 /*
@@ -209,7 +218,13 @@ GetScanValue(IndexScanDesc scan)
 
 		/* Normalize if needed */
 		if (so->normprocinfo != NULL)
+		{
+			MemoryContext oldCtx = MemoryContextSwitchTo(so->tmpCtx);
+
 			value = IvfflatNormValue(so->typeInfo, so->collation, value);
+
+			MemoryContextSwitchTo(oldCtx);
+		}
 	}
 
 	return value;
@@ -240,19 +255,30 @@ ivfflatbeginscan(Relation index, int nkeys, int norderbys)
 	int			lists;
 	int			dimensions;
 	int			probes = ivfflat_probes;
+	int			maxProbes;
+	MemoryContext oldCtx;
 
 	scan = RelationGetIndexScan(index, nkeys, norderbys);
 
 	/* Get lists and dimensions from metapage */
 	IvfflatGetMetaPageInfo(index, &lists, &dimensions);
 
+	if (ivfflat_iterative_scan != IVFFLAT_ITERATIVE_SCAN_OFF)
+		maxProbes = Max(ivfflat_max_probes, probes);
+	else
+		maxProbes = probes;
+
 	if (probes > lists)
 		probes = lists;
 
-	so = (IvfflatScanOpaque) palloc(offsetof(IvfflatScanOpaqueData, lists) + probes * sizeof(IvfflatScanList));
+	if (maxProbes > lists)
+		maxProbes = lists;
+
+	so = (IvfflatScanOpaque) palloc(sizeof(IvfflatScanOpaqueData));
 	so->typeInfo = IvfflatGetTypeInfo(index);
 	so->first = true;
 	so->probes = probes;
+	so->maxProbes = maxProbes;
 	so->dimensions = dimensions;
 
 	/* Set support functions */
@@ -260,6 +286,12 @@ ivfflatbeginscan(Relation index, int nkeys, int norderbys)
 	so->normprocinfo = IvfflatOptionalProcInfo(index, IVFFLAT_NORM_PROC);
 	so->collation = index->rd_indcollation[0];
 
+	so->tmpCtx = AllocSetContextCreate(CurrentMemoryContext,
+									   "Ivfflat scan temporary context",
+									   ALLOCSET_DEFAULT_SIZES);
+
+	oldCtx = MemoryContextSwitchTo(so->tmpCtx);
+
 	/* Create tuple description for sorting */
 	so->tupdesc = CreateTemplateTupleDesc(2);
 	TupleDescInitEntry(so->tupdesc, (AttrNumber) 1, "distance", FLOAT8OID, -1, 0);
@@ -280,6 +312,11 @@ 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;
+	so->lists = palloc(maxProbes * sizeof(IvfflatScanList));
+
+	MemoryContextSwitchTo(oldCtx);
 
 	scan->opaque = so;
 
@@ -294,11 +331,9 @@ 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 +349,8 @@ 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 +378,23 @@ 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));
 	}
 
-	if (tuplesort_gettupleslot(so->sortstate, true, false, so->mslot, NULL))
+	while (!tuplesort_gettupleslot(so->sortstate, true, false, so->mslot, NULL))
 	{
-		bool		isnull;
+		if (so->listIndex == so->maxProbes)
-		ItemPointer heaptid = (ItemPointer) DatumGetPointer(slot_getattr(so->mslot, 2, &isnull));
+			return false;
+
+		IvfflatBench("GetScanItems", GetScanItems(scan, so->value));
+	}
+
+	heaptid = (ItemPointer) DatumGetPointer(slot_getattr(so->mslot, 2, &isnull));
 
 	scan->xs_heaptid = *heaptid;
 	scan->xs_recheck = false;
 	scan->xs_recheckorderby = false;
 	return true;
-	}
-
-	return false;
 }
 
 /*
@@ -373,12 +405,10 @@ ivfflatendscan(IndexScanDesc scan)
 {
 	IvfflatScanOpaque so = (IvfflatScanOpaque) scan->opaque;
 
-	pairingheap_free(so->listQueue);
+	/* Free any temporary files */
 	tuplesort_end(so->sortstate);
-	FreeAccessStrategy(so->bas);
-	FreeTupleDesc(so->tupdesc);
 
-	/* TODO Free vslot and mslot without freeing TupleDesc */
+	MemoryContextDelete(so->tmpCtx);
 
 	pfree(so);
 	scan->opaque = NULL;

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/expected/hnsw_vector.out

@@ -99,6 +99,32 @@ SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <+> (SELECT NULL::vector)) t2
      4
 (1 row)
 
+DROP TABLE t;
+-- iterative
+CREATE TABLE t (val vector(3));
+INSERT INTO t (val) VALUES ('[0,0,0]'), ('[1,2,3]'), ('[1,1,1]'), (NULL);
+CREATE INDEX ON t USING hnsw (val vector_l2_ops);
+SET hnsw.iterative_scan = strict_order;
+SET hnsw.ef_search = 1;
+SELECT * FROM t ORDER BY val <-> '[3,3,3]';
+   val   
+---------
+ [1,2,3]
+ [1,1,1]
+ [0,0,0]
+(3 rows)
+
+SET hnsw.iterative_scan = relaxed_order;
+SELECT * FROM t ORDER BY val <-> '[3,3,3]';
+   val   
+---------
+ [1,2,3]
+ [1,1,1]
+ [0,0,0]
+(3 rows)
+
+RESET hnsw.iterative_scan;
+RESET hnsw.ef_search;
 DROP TABLE t;
 -- unlogged
 CREATE UNLOGGED TABLE t (val vector(3));
@@ -139,4 +165,29 @@ SET hnsw.ef_search = 0;
 ERROR:  0 is outside the valid range for parameter "hnsw.ef_search" (1 .. 1000)
 SET hnsw.ef_search = 1001;
 ERROR:  1001 is outside the valid range for parameter "hnsw.ef_search" (1 .. 1000)
+SHOW hnsw.iterative_scan;
+ hnsw.iterative_scan 
+---------------------
+ off
+(1 row)
+
+SET hnsw.iterative_scan = on;
+ERROR:  invalid value for parameter "hnsw.iterative_scan": "on"
+HINT:  Available values: off, relaxed_order, strict_order.
+SHOW hnsw.max_scan_tuples;
+ hnsw.max_scan_tuples 
+----------------------
+ 20000
+(1 row)
+
+SET hnsw.max_scan_tuples = 0;
+ERROR:  0 is outside the valid range for parameter "hnsw.max_scan_tuples" (1 .. 2147483647)
+SHOW hnsw.scan_mem_multiplier;
+ hnsw.scan_mem_multiplier 
+--------------------------
+ 1
+(1 row)
+
+SET hnsw.scan_mem_multiplier = 0;
+ERROR:  0 is outside the valid range for parameter "hnsw.scan_mem_multiplier" (1 .. 1000)
 DROP TABLE t;

test/expected/ivfflat_vector.out

@@ -81,6 +81,37 @@ SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <=> (SELECT NULL::vector)) t2
      3
 (1 row)
 
+DROP TABLE t;
+-- iterative
+CREATE TABLE t (val vector(3));
+INSERT INTO t (val) VALUES ('[0,0,0]'), ('[1,2,3]'), ('[1,1,1]'), (NULL);
+CREATE INDEX ON t USING ivfflat (val vector_l2_ops) WITH (lists = 3);
+SET ivfflat.iterative_scan = relaxed_order;
+SELECT * FROM t ORDER BY val <-> '[3,3,3]';
+   val   
+---------
+ [1,2,3]
+ [1,1,1]
+ [0,0,0]
+(3 rows)
+
+SET ivfflat.max_probes = 1;
+SELECT * FROM t ORDER BY val <-> '[3,3,3]';
+   val   
+---------
+ [1,2,3]
+(1 row)
+
+SET ivfflat.max_probes = 2;
+SELECT * FROM t ORDER BY val <-> '[3,3,3]';
+   val   
+---------
+ [1,2,3]
+ [1,1,1]
+(2 rows)
+
+RESET ivfflat.iterative_scan;
+RESET ivfflat.max_probes;
 DROP TABLE t;
 -- unlogged
 CREATE UNLOGGED TABLE t (val vector(3));
@@ -109,4 +140,27 @@ SHOW ivfflat.probes;
  1
 (1 row)
 
+SET ivfflat.probes = 0;
+ERROR:  0 is outside the valid range for parameter "ivfflat.probes" (1 .. 32768)
+SET ivfflat.probes = 32769;
+ERROR:  32769 is outside the valid range for parameter "ivfflat.probes" (1 .. 32768)
+SHOW ivfflat.iterative_scan;
+ ivfflat.iterative_scan 
+------------------------
+ off
+(1 row)
+
+SET ivfflat.iterative_scan = on;
+ERROR:  invalid value for parameter "ivfflat.iterative_scan": "on"
+HINT:  Available values: off, relaxed_order.
+SHOW ivfflat.max_probes;
+ ivfflat.max_probes 
+--------------------
+ 32768
+(1 row)
+
+SET ivfflat.max_probes = 0;
+ERROR:  0 is outside the valid range for parameter "ivfflat.max_probes" (1 .. 32768)
+SET ivfflat.max_probes = 32769;
+ERROR:  32769 is outside the valid range for parameter "ivfflat.max_probes" (1 .. 32768)
 DROP TABLE t;

test/sql/hnsw_vector.sql

@@ -57,6 +57,23 @@ SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <+> (SELECT NULL::vector)) t2
 
 DROP TABLE t;
 
+-- iterative
+
+CREATE TABLE t (val vector(3));
+INSERT INTO t (val) VALUES ('[0,0,0]'), ('[1,2,3]'), ('[1,1,1]'), (NULL);
+CREATE INDEX ON t USING hnsw (val vector_l2_ops);
+
+SET hnsw.iterative_scan = strict_order;
+SET hnsw.ef_search = 1;
+SELECT * FROM t ORDER BY val <-> '[3,3,3]';
+
+SET hnsw.iterative_scan = relaxed_order;
+SELECT * FROM t ORDER BY val <-> '[3,3,3]';
+
+RESET hnsw.iterative_scan;
+RESET hnsw.ef_search;
+DROP TABLE t;
+
 -- unlogged
 
 CREATE UNLOGGED TABLE t (val vector(3));
@@ -81,4 +98,16 @@ SHOW hnsw.ef_search;
 SET hnsw.ef_search = 0;
 SET hnsw.ef_search = 1001;
 
+SHOW hnsw.iterative_scan;
+
+SET hnsw.iterative_scan = on;
+
+SHOW hnsw.max_scan_tuples;
+
+SET hnsw.max_scan_tuples = 0;
+
+SHOW hnsw.scan_mem_multiplier;
+
+SET hnsw.scan_mem_multiplier = 0;
+
 DROP TABLE t;

test/sql/ivfflat_vector.sql

@@ -44,6 +44,25 @@ SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <=> (SELECT NULL::vector)) t2
 
 DROP TABLE t;
 
+-- iterative
+
+CREATE TABLE t (val vector(3));
+INSERT INTO t (val) VALUES ('[0,0,0]'), ('[1,2,3]'), ('[1,1,1]'), (NULL);
+CREATE INDEX ON t USING ivfflat (val vector_l2_ops) WITH (lists = 3);
+
+SET ivfflat.iterative_scan = relaxed_order;
+SELECT * FROM t ORDER BY val <-> '[3,3,3]';
+
+SET ivfflat.max_probes = 1;
+SELECT * FROM t ORDER BY val <-> '[3,3,3]';
+
+SET ivfflat.max_probes = 2;
+SELECT * FROM t ORDER BY val <-> '[3,3,3]';
+
+RESET ivfflat.iterative_scan;
+RESET ivfflat.max_probes;
+DROP TABLE t;
+
 -- unlogged
 
 CREATE UNLOGGED TABLE t (val vector(3));
@@ -62,4 +81,16 @@ CREATE INDEX ON t USING ivfflat (val vector_l2_ops) WITH (lists = 32769);
 
 SHOW ivfflat.probes;
 
+SET ivfflat.probes = 0;
+SET ivfflat.probes = 32769;
+
+SHOW ivfflat.iterative_scan;
+
+SET ivfflat.iterative_scan = on;
+
+SHOW ivfflat.max_probes;
+
+SET ivfflat.max_probes = 0;
+SET ivfflat.max_probes = 32769;
+
 DROP TABLE t;

test/t/002_ivfflat_vacuum.pl

@@ -6,13 +6,7 @@ use Test::More;
 
 my $dim = 3;
 
-my @r = ();
+my $array_sql = join(",", ('random()') x $dim);
-for (1 .. $dim)
-{
-	my $v = int(rand(1000)) + 1;
-	push(@r, "i % $v");
-}
-my $array_sql = join(", ", @r);
 
 # 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",
+$node->safe_psql("postgres", "INSERT INTO tst SELECT * FROM tmp;");
-	"INSERT INTO tst SELECT i % 10, ARRAY[$array_sql] FROM generate_series(1, 100000) i;"
-);
 
 # Check size
 my $new_size = $node->safe_psql("postgres", "SELECT pg_total_relation_size('tst_v_idx');");

test/t/041_ivfflat_iterative_scan.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 = $node->safe_psql("postgres", qq(
+	SET enable_seqscan = off;
+	SET ivfflat.probes = 10;
+	SET ivfflat.iterative_scan = relaxed_order;
+	SELECT COUNT(*) FROM (SELECT v FROM tst WHERE i % 10000 = 0 ORDER BY v <-> (SELECT v FROM tst LIMIT 1) LIMIT 11) t;
+));
+is($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_scan = relaxed_order;
+			SET ivfflat.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_scan_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_scan = relaxed_order;
+		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_scan = relaxed_order;
+			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 $c");
+}
+
+# Initialize node
+$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, 0.57, $operator);
+			test_recall($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_scan.pl

@@ -26,25 +26,26 @@ $node->safe_psql("postgres", qq(
 
 my $count = $node->safe_psql("postgres", qq(
 	SET enable_seqscan = off;
-	SET hnsw.streaming = on;
+	SET hnsw.iterative_scan = relaxed_order;
-	SET work_mem = '8MB';
+	SET hnsw.max_scan_tuples = 100000;
+	SET hnsw.scan_mem_multiplier = 2;
 	SELECT COUNT(*) FROM (SELECT v FROM tst WHERE i % 10000 = 0 ORDER BY v <-> (SELECT v FROM tst LIMIT 1) LIMIT 11) t;
 ));
 is($count, 10);
 
 foreach ((30000, 50000, 70000))
 {
-	my $ef_stream = $_;
+	my $max_tuples = $_;
-	my $expected = $ef_stream / 10000;
+	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.streaming = on;
+			SET hnsw.iterative_scan = relaxed_order;
-			SET hnsw.ef_stream = $ef_stream;
+			SET hnsw.max_scan_tuples = $max_tuples;
-			SET work_mem = '8MB';
+			SET hnsw.scan_mem_multiplier = 2;
 			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;
@@ -57,11 +58,11 @@ foreach ((30000, 50000, 70000))
 
 my ($ret, $stdout, $stderr) = $node->psql("postgres", qq(
 	SET enable_seqscan = off;
-	SET hnsw.streaming = on;
+	SET hnsw.iterative_scan = relaxed_order;
 	SET client_min_messages = debug1;
-	SET work_mem = '2MB';
+	SET work_mem = '1MB';
 	SELECT COUNT(*) FROM (SELECT v FROM tst WHERE i % 10000 = 0 ORDER BY v <-> (SELECT v FROM tst LIMIT 1) LIMIT 11) t;
 ));
-like($stderr, qr/hnsw index scan exceeded work_mem after \d+ tuples/);
+like($stderr, qr/hnsw index scan reached memory limit after \d+ tuples/);
 
 done_testing();

test/t/044_hnsw_iterative_scan_recall.pl

@@ -10,18 +10,18 @@ my @expected;
 my $limit = 20;
 my $dim = 3;
 my $array_sql = join(",", ('random()') x $dim);
-my @cs = (100, 1000);
+my @cs = (50, 500);
 
 sub test_recall
 {
-	my ($c, $ef_search, $min, $operator) = @_;
+	my ($c, $ef_search, $min, $operator, $mode) = @_;
 	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;
+		SET hnsw.iterative_scan = $mode;
 		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/);
@@ -31,7 +31,7 @@ sub test_recall
 		my $actual = $node->safe_psql("postgres", qq(
 			SET enable_seqscan = off;
 			SET hnsw.ef_search = $ef_search;
-			SET hnsw.streaming = on;
+			SET hnsw.iterative_scan = $mode;
 			SELECT i FROM tst WHERE i % $c = 0 ORDER BY v $operator '$queries[$i]' LIMIT $limit;
 		));
 		my @actual_ids = split("\n", $actual);
@@ -50,7 +50,7 @@ sub test_recall
 		$total += $limit;
 	}
 
-	cmp_ok($correct / $total, ">=", $min, $operator);
+	cmp_ok($correct / $total, ">=", $min, "$operator $mode $c");
 }
 
 # Initialize node
@@ -62,7 +62,7 @@ $node->start;
 $node->safe_psql("postgres", "CREATE EXTENSION vector;");
 $node->safe_psql("postgres", "CREATE TABLE tst (i int4, v vector($dim));");
 $node->safe_psql("postgres",
-	"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(1, 100000) i;"
+	"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(1, 50000) i;"
 );
 
 # Generate queries
@@ -108,21 +108,8 @@ for my $i (0 .. $#operators)
 			push(@expected, $res);
 		}
 
-		if ($c == 100)
+		test_recall($c, 40, 0.99, $operator, "strict_order");
-		{
+		test_recall($c, 40, 0.99, $operator, "relaxed_order");
-			test_recall($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;");