Use variable for sequential ratio [skip ci]

.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-13
+            os: macos-12
     steps:
       - uses: actions/checkout@v4
       - uses: ankane/setup-postgres@v1

CHANGELOG.md

@@ -1,10 +1,8 @@
-## 0.8.0 (2024-10-30)
+## 0.8.0 (unreleased)
 
-- Added support for iterative index scans
 - Added casts for arrays to `sparsevec`
-- Improved cost estimation for better index selection when filtering
+- Improved cost estimation
-- Improved performance of HNSW index scans
+- Reduced memory usage for HNSW index scans
-- Improved performance of HNSW inserts and on-disk index builds
 - Dropped support for Postgres 12
 
 ## 0.7.4 (2024-08-05)

META.json

@@ -2,7 +2,7 @@
 	"name": "vector",
 	"abstract": "Open-source vector similarity search for Postgres",
 	"description": "Supports L2 distance, inner product, and cosine distance",
-	"version": "0.8.0",
+	"version": "0.7.4",
 	"maintainer": [
 		"Andrew Kane <andrew@ankane.org>"
 	],
@@ -12,7 +12,7 @@
 	"prereqs": {
 		"runtime": {
 			"requires": {
-				"PostgreSQL": "13.0.0"
+				"PostgreSQL": "12.0.0"
 			}
 		}
 	},
@@ -20,7 +20,7 @@
 		"vector": {
 			"file": "sql/vector.sql",
 			"docfile": "README.md",
-			"version": "0.8.0",
+			"version": "0.7.4",
 			"abstract": "Open-source vector similarity search for Postgres"
 		}
 	},

Makefile

@@ -1,5 +1,5 @@
 EXTENSION = vector
-EXTVERSION = 0.8.0
+EXTVERSION = 0.7.4
 
 MODULE_big = vector
 DATA = $(wildcard sql/*--*--*.sql)

Makefile.win

@@ -1,5 +1,5 @@
 EXTENSION = vector
-EXTVERSION = 0.8.0
+EXTVERSION = 0.7.4
 
 DATA_built = sql\$(EXTENSION)--$(EXTVERSION).sql
 OBJS = src\bitutils.obj src\bitvec.obj src\halfutils.obj src\halfvec.obj src\hnsw.obj src\hnswbuild.obj src\hnswinsert.obj src\hnswscan.obj src\hnswutils.obj src\hnswvacuum.obj src\ivfbuild.obj src\ivfflat.obj src\ivfinsert.obj src\ivfkmeans.obj src\ivfscan.obj src\ivfutils.obj src\ivfvacuum.obj src\sparsevec.obj src\vector.obj

README.md

@@ -17,11 +17,11 @@ Plus [ACID](https://en.wikipedia.org/wiki/ACID) compliance, point-in-time recove
 
 ### Linux and Mac
 
-Compile and install the extension (supports Postgres 13+)
+Compile and install the extension (supports Postgres 12+)
 
 ```sh
 cd /tmp
-git clone --branch v0.8.0 https://github.com/pgvector/pgvector.git
+git clone --branch v0.7.4 https://github.com/pgvector/pgvector.git
 cd pgvector
 make
 make install # may need sudo
@@ -46,7 +46,7 @@ Then use `nmake` to build:
 ```cmd
 set "PGROOT=C:\Program Files\PostgreSQL\16"
 cd %TEMP%
-git clone --branch v0.8.0 https://github.com/pgvector/pgvector.git
+git clone --branch v0.7.4 https://github.com/pgvector/pgvector.git
 cd pgvector
 nmake /F Makefile.win
 nmake /F Makefile.win install
@@ -324,7 +324,7 @@ For a large number of workers, you may also need to increase `max_parallel_worke
 
 ### Indexing Progress
 
-Check [indexing progress](https://www.postgresql.org/docs/current/progress-reporting.html#CREATE-INDEX-PROGRESS-REPORTING)
+Check [indexing progress](https://www.postgresql.org/docs/current/progress-reporting.html#CREATE-INDEX-PROGRESS-REPORTING) with Postgres 12+
 
 ```sql
 SELECT phase, round(100.0 * blocks_done / nullif(blocks_total, 0), 1) AS "%" FROM pg_stat_progress_create_index;
@@ -410,7 +410,7 @@ For a large number of workers, you may also need to increase `max_parallel_worke
 
 ### Indexing Progress
 
-Check [indexing progress](https://www.postgresql.org/docs/current/progress-reporting.html#CREATE-INDEX-PROGRESS-REPORTING)
+Check [indexing progress](https://www.postgresql.org/docs/current/progress-reporting.html#CREATE-INDEX-PROGRESS-REPORTING) with Postgres 12+
 
 ```sql
 SELECT phase, round(100.0 * tuples_done / nullif(tuples_total, 0), 1) AS "%" FROM pg_stat_progress_create_index;
@@ -427,126 +427,30 @@ Note: `%` is only populated during the `loading tuples` phase
 
 ## Filtering
 
-There are a few ways to index nearest neighbor queries with a `WHERE` clause.
+There are a few ways to index nearest neighbor queries with a `WHERE` clause
 
 ```sql
 SELECT * FROM items WHERE category_id = 123 ORDER BY embedding <-> '[3,1,2]' LIMIT 5;
 ```
 
-A good place to start is creating an index on the filter column. This can provide fast, exact nearest neighbor search in many cases. Postgres has a number of [index types](https://www.postgresql.org/docs/current/indexes-types.html) for this: B-tree (default), hash, GiST, SP-GiST, GIN, and BRIN.
+Create an index on one [or more](https://www.postgresql.org/docs/current/indexes-multicolumn.html) of the `WHERE` columns for exact search
 
 ```sql
 CREATE INDEX ON items (category_id);
 ```
 
-For multiple columns, consider a [multicolumn index](https://www.postgresql.org/docs/current/indexes-multicolumn.html).
+Or a [partial index](https://www.postgresql.org/docs/current/indexes-partial.html) on the vector column for approximate search
-
-```sql
-CREATE INDEX ON items (location_id, category_id);
-```
-
-Exact indexes work well for conditions that match a low percentage of rows. Otherwise, [approximate indexes](#indexing) can work better.
-
-```sql
-CREATE INDEX ON items USING hnsw (embedding vector_l2_ops);
-```
-
-With approximate indexes, filtering is applied *after* the index is scanned. If a condition matches 10% of rows, with HNSW and the default `hnsw.ef_search` of 40, only 4 rows will match on average. For more rows, increase `hnsw.ef_search`.
-
-```sql
-SET hnsw.ef_search = 200;
-```
-
-Starting with 0.8.0, you can enable [iterative index scans](#iterative-index-scans), which will automatically scan more of the index when needed.
-
-```sql
-SET hnsw.iterative_scan = strict_order;
-```
-
-If filtering by only a few distinct values, consider [partial indexing](https://www.postgresql.org/docs/current/indexes-partial.html).
 
 ```sql
 CREATE INDEX ON items USING hnsw (embedding vector_l2_ops) WHERE (category_id = 123);
 ```
 
-If filtering by many different values, consider [partitioning](https://www.postgresql.org/docs/current/ddl-partitioning.html).
+Use [partitioning](https://www.postgresql.org/docs/current/ddl-partitioning.html) for approximate search on many different values of the `WHERE` columns
 
 ```sql
 CREATE TABLE items (embedding vector(3), category_id int) PARTITION BY LIST(category_id);
 ```
 
-## Iterative Index Scans
-
-*Added in 0.8.0*
-
-With approximate indexes, queries with filtering can return less results since filtering is applied *after* the index is scanned. Starting with 0.8.0, you can enable iterative index scans, which will automatically scan more of the index until enough results are found (or it reaches `hnsw.max_scan_tuples` or `ivfflat.max_probes`).
-
-Iterative scans can use strict or relaxed ordering.
-
-Strict ensures results are in the exact order by distance
-
-```sql
-SET hnsw.iterative_scan = strict_order;
-```
-
-Relaxed allows results to be slightly out of order by distance, but provides better recall
-
-```sql
-SET hnsw.iterative_scan = relaxed_order;
-# or
-SET ivfflat.iterative_scan = relaxed_order;
-```
-
-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
-
-```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 tuples to visit (20,000 by default)
-
-```sql
-SET hnsw.max_scan_tuples = 20000;
-```
-
-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;
-```
-
-Note: Try increasing this if increasing `hnsw.max_scan_tuples` does not improve recall
-
-#### IVFFlat
-
-Specify the max number of probes
-
-```sql
-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*
@@ -1153,7 +1057,7 @@ This adds pgvector to the [Postgres image](https://hub.docker.com/_/postgres) (r
 You can also build the image manually:
 
 ```sh
-git clone --branch v0.8.0 https://github.com/pgvector/pgvector.git
+git clone --branch v0.7.4 https://github.com/pgvector/pgvector.git
 cd pgvector
 docker build --pull --build-arg PG_MAJOR=17 -t myuser/pgvector .
 ```

src/hnsw.c

@@ -18,17 +18,7 @@
 #define MarkGUCPrefixReserved(x) EmitWarningsOnPlaceholders(x)
 #endif
 
-static const struct config_enum_entry hnsw_iterative_scan_options[] = {
-	{"off", HNSW_ITERATIVE_SCAN_OFF, false},
-	{"relaxed_order", HNSW_ITERATIVE_SCAN_RELAXED, false},
-	{"strict_order", HNSW_ITERATIVE_SCAN_STRICT, false},
-	{NULL, 0, false}
-};
-
 int			hnsw_ef_search;
-int			hnsw_iterative_scan;
-int			hnsw_max_scan_tuples;
-double		hnsw_scan_mem_multiplier;
 int			hnsw_lock_tranche_id;
 static relopt_kind hnsw_relopt_kind;
 
@@ -79,20 +69,6 @@ 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_scan", "Sets the mode for iterative scans",
-							 NULL, &hnsw_iterative_scan,
-							 HNSW_ITERATIVE_SCAN_OFF, hnsw_iterative_scan_options, PGC_USERSET, 0, NULL, NULL, NULL);
-
-	/* This is approximate and does not affect the initial scan */
-	DefineCustomIntVariable("hnsw.max_scan_tuples", "Sets the max number of tuples to visit for iterative scans",
-							NULL, &hnsw_max_scan_tuples,
-							20000, 1, INT_MAX, 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, 0, NULL, NULL, NULL);
-
 	MarkGUCPrefixReserved("hnsw");
 }
 
@@ -137,10 +113,6 @@ 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

@@ -88,9 +88,6 @@
 /* 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
@@ -109,18 +106,8 @@
 
 /* Variables */
 extern int	hnsw_ef_search;
-extern int	hnsw_iterative_scan;
-extern int	hnsw_max_scan_tuples;
-extern double hnsw_scan_mem_multiplier;
 extern int	hnsw_lock_tranche_id;
 
-typedef enum HnswIterativeScanMode
-{
-	HNSW_ITERATIVE_SCAN_OFF,
-	HNSW_ITERATIVE_SCAN_RELAXED,
-	HNSW_ITERATIVE_SCAN_STRICT
-}			HnswIterativeScanMode;
-
 typedef struct HnswElementData HnswElementData;
 typedef struct HnswNeighborArray HnswNeighborArray;
 
@@ -142,7 +129,6 @@ struct HnswElementData
 	uint8		heaptidsLength;
 	uint8		level;
 	uint8		deleted;
-	uint8		version;
 	uint32		hash;
 	HnswNeighborsPtr neighbors;
 	BlockNumber blkno;
@@ -174,7 +160,7 @@ typedef struct HnswSearchCandidate
 	pairingheap_node c_node;
 	pairingheap_node w_node;
 	HnswElementPtr element;
-	double		distance;
+	float		distance;
 }			HnswSearchCandidate;
 
 /* HNSW index options */
@@ -199,8 +185,8 @@ typedef struct HnswGraph
 
 	/* Allocations state */
 	LWLock		allocatorLock;
-	Size		memoryUsed;
+	long		memoryUsed;
-	Size		memoryTotal;
+	long		memoryTotal;
 
 	/* Flushed state */
 	LWLock		flushLock;
@@ -251,18 +237,6 @@ typedef struct HnswTypeInfo
 	void		(*checkValue) (Pointer v);
 }			HnswTypeInfo;
 
-typedef struct HnswSupport
-{
-	FmgrInfo   *procinfo;
-	FmgrInfo   *normprocinfo;
-	Oid			collation;
-}			HnswSupport;
-
-typedef struct HnswQuery
-{
-	Datum		value;
-}			HnswQuery;
-
 typedef struct HnswBuildState
 {
 	/* Info */
@@ -282,7 +256,9 @@ typedef struct HnswBuildState
 	double		reltuples;
 
 	/* Support functions */
-	HnswSupport support;
+	FmgrInfo   *procinfo;
+	FmgrInfo   *normprocinfo;
+	Oid			collation;
 
 	/* Variables */
 	HnswGraph	graphData;
@@ -330,10 +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;
 
@@ -342,42 +318,24 @@ 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 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;
-	Size		maxMemory;
 	MemoryContext tmpCtx;
 
 	/* Support functions */
-	HnswSupport support;
+	FmgrInfo   *procinfo;
+	FmgrInfo   *normprocinfo;
+	Oid			collation;
 }			HnswScanOpaqueData;
 
 typedef HnswScanOpaqueData * HnswScanOpaque;
@@ -395,7 +353,8 @@ typedef struct HnswVacuumState
 	int			efConstruction;
 
 	/* Support functions */
-	HnswSupport support;
+	FmgrInfo   *procinfo;
+	Oid			collation;
 
 	/* Variables */
 	struct tidhash_hash *deleted;
@@ -411,33 +370,30 @@ 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(HnswSupport * support, Datum value);
+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, HnswQuery * q, List *ep, int ef, int lc, Relation index, HnswSupport * support, int m, bool inserting, HnswElement skipElement, visited_hash * v, pairingheap **discarded, bool initVisited, int64 *tuples);
+List	   *HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool inserting, HnswElement skipElement);
 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, HnswSupport * support, int m, int efConstruction, bool existing);
+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, HnswQuery * q, Relation rel, HnswSupport * support, bool loadVec);
+HnswSearchCandidate *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);
-HnswNeighborArray *HnswInitNeighborArray(int lm, HnswAllocator * allocator);
 void		HnswInitNeighbors(char *base, HnswElement element, int m, HnswAllocator * alloc);
-bool		HnswInsertTupleOnDisk(Relation index, HnswSupport * support, Datum value, ItemPointer heaptid, bool building);
+bool		HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull, ItemPointer heap_tid, bool building);
-void		HnswUpdateNeighborsOnDisk(Relation index, HnswSupport * support, HnswElement e, int m, bool checkExisting, bool building);
+void		HnswUpdateNeighborsOnDisk(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement e, int m, bool checkExisting, bool building);
 void		HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHeaptids, bool loadVec);
-void		HnswLoadElement(HnswElement element, double *distance, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec, double *maxDistance);
+void		HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec, float *maxDistance);
-bool		HnswFormIndexValue(Datum *out, Datum *values, bool *isnull, const HnswTypeInfo * typeInfo, HnswSupport * support);
 void		HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element);
-void		HnswUpdateConnection(char *base, HnswNeighborArray * neighbors, HnswElement newElement, float distance, int lm, int *updateIdx, Relation index, HnswSupport * support);
+void		HnswUpdateConnection(char *base, HnswElement element, HnswCandidate * hc, int lm, int lc, int *updateIdx, Relation index, FmgrInfo *procinfo, Oid collation);
-bool		HnswLoadNeighborTids(HnswElement element, ItemPointerData *indextids, Relation index, int m, int lm, int lc);
+void		HnswLoadNeighbors(HnswElement element, Relation index, int m);
 void		HnswInitLockTranche(void);
 const		HnswTypeInfo *HnswGetTypeInfo(Relation index);
 PGDLLEXPORT void HnswParallelBuildMain(dsm_segment *seg, shm_toc *toc);

src/hnswbuild.c

@@ -366,7 +366,7 @@ AddElementInMemory(char *base, HnswGraph * graph, HnswElement element)
  * Update neighbors
  */
 static void
-UpdateNeighborsInMemory(char *base, HnswSupport * support, HnswElement e, int m)
+UpdateNeighborsInMemory(char *base, FmgrInfo *procinfo, Oid collation, HnswElement e, int m)
 {
 	for (int lc = e->level; lc >= 0; lc--)
 	{
@@ -388,7 +388,7 @@ UpdateNeighborsInMemory(char *base, HnswSupport * support, HnswElement e, int m)
 			Assert(neighborElement);
 
 			LWLockAcquire(&neighborElement->lock, LW_EXCLUSIVE);
-			HnswUpdateConnection(base, HnswGetNeighbors(base, neighborElement, lc), e, hc->distance, lm, NULL, NULL, support);
+			HnswUpdateConnection(base, e, hc, lm, lc, NULL, NULL, procinfo, collation);
 			LWLockRelease(&neighborElement->lock);
 		}
 	}
@@ -398,7 +398,7 @@ UpdateNeighborsInMemory(char *base, HnswSupport * support, HnswElement e, int m)
  * Update graph in memory
  */
 static void
-UpdateGraphInMemory(HnswSupport * support, HnswElement element, int m, int efConstruction, HnswElement entryPoint, HnswBuildState * buildstate)
+UpdateGraphInMemory(FmgrInfo *procinfo, Oid collation, HnswElement element, int m, int efConstruction, HnswElement entryPoint, HnswBuildState * buildstate)
 {
 	HnswGraph  *graph = buildstate->graph;
 	char	   *base = buildstate->hnswarea;
@@ -411,7 +411,7 @@ UpdateGraphInMemory(HnswSupport * support, HnswElement element, int m, int efCon
 	AddElementInMemory(base, graph, element);
 
 	/* Update neighbors */
-	UpdateNeighborsInMemory(base, support, element, m);
+	UpdateNeighborsInMemory(base, procinfo, collation, element, m);
 
 	/* Update entry point if needed (already have lock) */
 	if (entryPoint == NULL || element->level > entryPoint->level)
@@ -424,8 +424,9 @@ UpdateGraphInMemory(HnswSupport * support, HnswElement element, int m, int efCon
 static void
 InsertTupleInMemory(HnswBuildState * buildstate, HnswElement element)
 {
+	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;
@@ -457,10 +458,10 @@ InsertTupleInMemory(HnswBuildState * buildstate, HnswElement element)
 	}
 
 	/* Find neighbors for element */
-	HnswFindElementNeighbors(base, element, entryPoint, NULL, support, m, efConstruction, false);
+	HnswFindElementNeighbors(base, element, entryPoint, NULL, procinfo, collation, m, efConstruction, false);
 
 	/* Update graph in memory */
-	UpdateGraphInMemory(support, element, m, efConstruction, entryPoint, buildstate);
+	UpdateGraphInMemory(procinfo, collation, element, m, efConstruction, entryPoint, buildstate);
 
 	/* Release entry lock */
 	LWLockRelease(entryLock);
@@ -472,19 +473,30 @@ 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;
-	HnswSupport *support = &buildstate->support;
 	Size		valueSize;
 	Pointer		valuePtr;
 	LWLock	   *flushLock = &graph->flushLock;
 	char	   *base = buildstate->hnswarea;
-	Datum		value;
 
-	/* Form index value */
+	/* Detoast once for all calls */
-	if (!HnswFormIndexValue(&value, values, isnull, buildstate->typeInfo, support))
+	Datum		value = PointerGetDatum(PG_DETOAST_DATUM(values[0]));
-		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, value))
+			return false;
+
+		value = HnswNormValue(typeInfo, buildstate->collation, value);
+	}
 
 	/* Get datum size */
 	valueSize = VARSIZE_ANY(DatumGetPointer(value));
@@ -497,7 +509,7 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
 	{
 		LWLockRelease(flushLock);
 
-		return HnswInsertTupleOnDisk(index, support, value, heaptid, true);
+		return HnswInsertTupleOnDisk(index, value, values, isnull, heaptid, true);
 	}
 
 	/*
@@ -529,7 +541,7 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
 
 		LWLockRelease(flushLock);
 
-		return HnswInsertTupleOnDisk(index, support, value, heaptid, true);
+		return HnswInsertTupleOnDisk(index, value, values, isnull, heaptid, true);
 	}
 
 	/* Ok, we can proceed to allocate the element */
@@ -595,7 +607,7 @@ BuildCallback(Relation index, ItemPointer tid, Datum *values,
  * Initialize the graph
  */
 static void
-InitGraph(HnswGraph * graph, char *base, Size memoryTotal)
+InitGraph(HnswGraph * graph, char *base, long memoryTotal)
 {
 	/* Initialize the lock tranche if needed */
 	HnswInitLockTranche();
@@ -692,9 +704,11 @@ InitBuildState(HnswBuildState * buildstate, Relation heap, Relation index, Index
 	buildstate->indtuples = 0;
 
 	/* Get support functions */
-	HnswInitSupport(&buildstate->support, index);
+	buildstate->procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
+	buildstate->normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
+	buildstate->collation = index->rd_indcollation[0];
 
-	InitGraph(&buildstate->graphData, NULL, (Size) maintenance_work_mem * 1024L);
+	InitGraph(&buildstate->graphData, NULL, maintenance_work_mem * 1024L);
 	buildstate->graph = &buildstate->graphData;
 	buildstate->ml = HnswGetMl(buildstate->m);
 	buildstate->maxLevel = HnswGetMaxLevel(buildstate->m);

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;
 		}
 
@@ -340,107 +334,6 @@ AddElementOnDisk(Relation index, HnswElement e, int m, BlockNumber insertPage, B
 		*updatedInsertPage = newInsertPage;
 }
 
-/*
- * Load neighbors
- */
-static HnswNeighborArray *
-HnswLoadNeighbors(HnswElement element, Relation index, int m, int lm, int lc)
-{
-	char	   *base = NULL;
-	HnswNeighborArray *neighbors = HnswInitNeighborArray(lm, NULL);
-	ItemPointerData indextids[HNSW_MAX_M * 2];
-
-	if (!HnswLoadNeighborTids(element, indextids, index, m, lm, lc))
-		return neighbors;
-
-	for (int i = 0; i < lm; i++)
-	{
-		ItemPointer indextid = &indextids[i];
-		HnswElement e;
-		HnswCandidate *hc;
-
-		if (!ItemPointerIsValid(indextid))
-			break;
-
-		e = HnswInitElementFromBlock(ItemPointerGetBlockNumber(indextid), ItemPointerGetOffsetNumber(indextid));
-		hc = &neighbors->items[neighbors->length++];
-		HnswPtrStore(base, hc->element, e);
-	}
-
-	return neighbors;
-}
-
-/*
- * Load elements for insert
- */
-static void
-LoadElementsForInsert(HnswNeighborArray * neighbors, HnswQuery * q, int *idx, Relation index, HnswSupport * support)
-{
-	char	   *base = NULL;
-
-	for (int i = 0; i < neighbors->length; i++)
-	{
-		HnswCandidate *hc = &neighbors->items[i];
-		HnswElement element = HnswPtrAccess(base, hc->element);
-		double		distance;
-
-		HnswLoadElement(element, &distance, q, index, support, true, NULL);
-		hc->distance = distance;
-
-		/* Prune element if being deleted */
-		if (element->heaptidsLength == 0)
-		{
-			*idx = i;
-			break;
-		}
-	}
-}
-
-/*
- * Get update index
- */
-static int
-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;
-	HnswNeighborArray *neighbors;
-	MemoryContext oldCtx = MemoryContextSwitchTo(updateCtx);
-
-	/*
-	 * Get latest neighbors since they may have changed. Do not lock yet since
-	 * selecting neighbors can take time. Could use optimistic locking to
-	 * retry if another update occurs before getting exclusive lock.
-	 */
-	neighbors = HnswLoadNeighbors(element, index, m, lm, lc);
-
-	/*
-	 * Could improve performance for vacuuming by checking neighbors against
-	 * list of elements being deleted to find index. It's important to exclude
-	 * already deleted elements for this since they can be replaced at any
-	 * time.
-	 */
-
-	if (neighbors->length < lm)
-		idx = -2;
-	else
-	{
-		HnswQuery	q;
-
-		q.value = HnswGetValue(base, element);
-
-		LoadElementsForInsert(neighbors, &q, &idx, index, support);
-
-		if (idx == -1)
-			HnswUpdateConnection(base, neighbors, newElement, distance, lm, &idx, index, support);
-	}
-
-	MemoryContextSwitchTo(oldCtx);
-	MemoryContextReset(updateCtx);
-
-	return idx;
-}
-
 /*
  * Check if connection already exists
  */
@@ -461,94 +354,14 @@ ConnectionExists(HnswElement e, HnswNeighborTuple ntup, int startIdx, int lm)
 	return false;
 }
 
-/*
- * Update neighbor
- */
-static void
-UpdateNeighborOnDisk(HnswElement element, HnswElement newElement, int idx, int m, int lm, int lc, Relation index, bool checkExisting, bool building)
-{
-	Buffer		buf;
-	Page		page;
-	GenericXLogState *state;
-	HnswNeighborTuple ntup;
-	int			startIdx;
-	OffsetNumber offno = element->neighborOffno;
-
-	/* Register page */
-	buf = ReadBuffer(index, element->neighborPage);
-	LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
-	if (building)
-	{
-		state = NULL;
-		page = BufferGetPage(buf);
-	}
-	else
-	{
-		state = GenericXLogStart(index);
-		page = GenericXLogRegisterBuffer(state, buf, 0);
-	}
-
-	/* Get tuple */
-	ntup = (HnswNeighborTuple) PageGetItem(page, PageGetItemId(page, offno));
-
-	/* Calculate index for update */
-	startIdx = (element->level - lc) * m;
-
-	/* Check for existing connection */
-	if (checkExisting && ConnectionExists(newElement, ntup, startIdx, lm))
-		idx = -1;
-	else if (idx == -2)
-	{
-		/* Find free offset if still exists */
-		/* TODO Retry updating connections if not */
-		for (int j = 0; j < lm; j++)
-		{
-			if (!ItemPointerIsValid(&ntup->indextids[startIdx + j]))
-			{
-				idx = startIdx + j;
-				break;
-			}
-		}
-	}
-	else
-		idx += startIdx;
-
-	/* Make robust to issues */
-	if (idx >= 0 && idx < ntup->count)
-	{
-		ItemPointer indextid = &ntup->indextids[idx];
-
-		/* Update neighbor on the buffer */
-		ItemPointerSet(indextid, newElement->blkno, newElement->offno);
-
-		/* Commit */
-		if (building)
-			MarkBufferDirty(buf);
-		else
-			GenericXLogFinish(state);
-	}
-	else if (!building)
-		GenericXLogAbort(state);
-
-	UnlockReleaseBuffer(buf);
-}
-
 /*
  * Update neighbors
  */
 void
-HnswUpdateNeighborsOnDisk(Relation index, HnswSupport * support, HnswElement e, int m, bool checkExisting, bool building)
+HnswUpdateNeighborsOnDisk(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement e, int m, bool checkExisting, bool building)
 {
 	char	   *base = NULL;
 
-	/* Use separate memory context to improve performance for larger vectors */
-	MemoryContext updateCtx = GenerationContextCreate(CurrentMemoryContext,
-													  "Hnsw insert update context",
-#if PG_VERSION_NUM >= 150000
-													  128 * 1024, 128 * 1024,
-#endif
-													  128 * 1024);
-
 	for (int lc = e->level; lc >= 0; lc--)
 	{
 		int			lm = HnswGetLayerM(m, lc);
@@ -557,20 +370,96 @@ HnswUpdateNeighborsOnDisk(Relation index, HnswSupport * support, HnswElement e,
 		for (int i = 0; i < neighbors->length; i++)
 		{
 			HnswCandidate *hc = &neighbors->items[i];
+			Buffer		buf;
+			Page		page;
+			GenericXLogState *state;
+			HnswNeighborTuple ntup;
+			int			idx = -1;
+			int			startIdx;
 			HnswElement neighborElement = HnswPtrAccess(base, hc->element);
-			int			idx;
+			OffsetNumber offno = neighborElement->neighborOffno;
 
-			idx = GetUpdateIndex(neighborElement, e, hc->distance, m, lm, lc, index, support, updateCtx);
+			/*
+			 * Get latest neighbors since they may have changed. Do not lock
+			 * yet since selecting neighbors can take time. Could use
+			 * optimistic locking to retry if another update occurs before
+			 * getting exclusive lock.
+			 */
+			HnswLoadNeighbors(neighborElement, index, m);
+
+			/*
+			 * Could improve performance for vacuuming by checking neighbors
+			 * against list of elements being deleted to find index. It's
+			 * important to exclude already deleted elements for this since
+			 * they can be replaced at any time.
+			 */
+
+			/* Select neighbors */
+			HnswUpdateConnection(NULL, e, hc, lm, lc, &idx, index, procinfo, collation);
 
 			/* New element was not selected as a neighbor */
 			if (idx == -1)
 				continue;
 
-			UpdateNeighborOnDisk(neighborElement, e, idx, m, lm, lc, index, checkExisting, building);
+			/* Register page */
+			buf = ReadBuffer(index, neighborElement->neighborPage);
+			LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
+			if (building)
+			{
+				state = NULL;
+				page = BufferGetPage(buf);
+			}
+			else
+			{
+				state = GenericXLogStart(index);
+				page = GenericXLogRegisterBuffer(state, buf, 0);
+			}
+
+			/* Get tuple */
+			ntup = (HnswNeighborTuple) PageGetItem(page, PageGetItemId(page, offno));
+
+			/* Calculate index for update */
+			startIdx = (neighborElement->level - lc) * m;
+
+			/* Check for existing connection */
+			if (checkExisting && ConnectionExists(e, ntup, startIdx, lm))
+				idx = -1;
+			else if (idx == -2)
+			{
+				/* Find free offset if still exists */
+				/* TODO Retry updating connections if not */
+				for (int j = 0; j < lm; j++)
+				{
+					if (!ItemPointerIsValid(&ntup->indextids[startIdx + j]))
+					{
+						idx = startIdx + j;
+						break;
+					}
+				}
+			}
+			else
+				idx += startIdx;
+
+			/* Make robust to issues */
+			if (idx >= 0 && idx < ntup->count)
+			{
+				ItemPointer indextid = &ntup->indextids[idx];
+
+				/* Update neighbor on the buffer */
+				ItemPointerSet(indextid, e->blkno, e->offno);
+
+				/* Commit */
+				if (building)
+					MarkBufferDirty(buf);
+				else
+					GenericXLogFinish(state);
+			}
+			else if (!building)
+				GenericXLogAbort(state);
+
+			UnlockReleaseBuffer(buf);
 		}
 	}
-
-	MemoryContextDelete(updateCtx);
 }
 
 /*
@@ -660,7 +549,7 @@ FindDuplicateOnDisk(Relation index, HnswElement element, bool building)
  * Update graph on disk
  */
 static void
-UpdateGraphOnDisk(Relation index, HnswSupport * support, HnswElement element, int m, int efConstruction, HnswElement entryPoint, bool building)
+UpdateGraphOnDisk(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement element, int m, int efConstruction, HnswElement entryPoint, bool building)
 {
 	BlockNumber newInsertPage = InvalidBlockNumber;
 
@@ -676,7 +565,7 @@ UpdateGraphOnDisk(Relation index, HnswSupport * support, HnswElement element, in
 		HnswUpdateMetaPage(index, 0, NULL, newInsertPage, MAIN_FORKNUM, building);
 
 	/* Update neighbors */
-	HnswUpdateNeighborsOnDisk(index, support, element, m, false, building);
+	HnswUpdateNeighborsOnDisk(index, procinfo, collation, element, m, false, building);
 
 	/* Update entry point if needed */
 	if (entryPoint == NULL || element->level > entryPoint->level)
@@ -687,12 +576,14 @@ UpdateGraphOnDisk(Relation index, HnswSupport * support, HnswElement element, in
  * Insert a tuple into the index
  */
 bool
-HnswInsertTupleOnDisk(Relation index, HnswSupport * support, Datum value, ItemPointer heaptid, bool building)
+HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull, ItemPointer heap_tid, bool building)
 {
 	HnswElement entryPoint;
 	HnswElement element;
 	int			m;
 	int			efConstruction = HnswGetEfConstruction(index);
+	FmgrInfo   *procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
+	Oid			collation = index->rd_indcollation[0];
 	LOCKMODE	lockmode = ShareLock;
 	char	   *base = NULL;
 
@@ -707,7 +598,7 @@ HnswInsertTupleOnDisk(Relation index, HnswSupport * support, Datum value, ItemPo
 	HnswGetMetaPageInfo(index, &m, &entryPoint);
 
 	/* Create an element */
-	element = HnswInitElement(base, heaptid, m, HnswGetMl(m), HnswGetMaxLevel(m), NULL);
+	element = HnswInitElement(base, heap_tid, m, HnswGetMl(m), HnswGetMaxLevel(m), NULL);
 	HnswPtrStore(base, element->value, DatumGetPointer(value));
 
 	/* Prevent concurrent inserts when likely updating entry point */
@@ -725,10 +616,10 @@ HnswInsertTupleOnDisk(Relation index, HnswSupport * support, Datum value, ItemPo
 	}
 
 	/* Find neighbors for element */
-	HnswFindElementNeighbors(base, element, entryPoint, index, support, m, efConstruction, false);
+	HnswFindElementNeighbors(base, element, entryPoint, index, procinfo, collation, m, efConstruction, false);
 
 	/* Update graph on disk */
-	UpdateGraphOnDisk(index, support, element, m, efConstruction, entryPoint, building);
+	UpdateGraphOnDisk(index, procinfo, collation, element, m, efConstruction, entryPoint, building);
 
 	/* Release lock */
 	UnlockPage(index, HNSW_UPDATE_LOCK, lockmode);
@@ -740,19 +631,31 @@ HnswInsertTupleOnDisk(Relation index, HnswSupport * support, Datum value, ItemPo
  * Insert a tuple into the index
  */
 static void
-HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid)
+HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid)
 {
 	Datum		value;
 	const		HnswTypeInfo *typeInfo = HnswGetTypeInfo(index);
-	HnswSupport support;
+	FmgrInfo   *normprocinfo;
+	Oid			collation = index->rd_indcollation[0];
 
-	HnswInitSupport(&support, index);
+	/* Detoast once for all calls */
+	value = PointerGetDatum(PG_DETOAST_DATUM(values[0]));
 
-	/* Form index value */
+	/* Check value */
-	if (!HnswFormIndexValue(&value, values, isnull, typeInfo, &support))
+	if (typeInfo->checkValue != NULL)
-		return;
+		typeInfo->checkValue(DatumGetPointer(value));
 
-	HnswInsertTupleOnDisk(index, &support, value, heaptid, false);
+	/* Normalize if needed */
+	normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
+	if (normprocinfo != NULL)
+	{
+		if (!HnswCheckNorm(normprocinfo, collation, value))
+			return;
+
+		value = HnswNormValue(typeInfo, collation, value);
+	}
+
+	HnswInsertTupleOnDisk(index, value, values, isnull, heap_tid, false);
 }
 
 /*

src/hnswscan.c

@@ -5,74 +5,39 @@
 #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 value)
+GetScanItems(IndexScanDesc scan, Datum q)
 {
 	HnswScanOpaque so = (HnswScanOpaque) scan->opaque;
 	Relation	index = scan->indexRelation;
-	HnswSupport *support = &so->support;
+	FmgrInfo   *procinfo = so->procinfo;
+	Oid			collation = so->collation;
 	List	   *ep;
 	List	   *w;
 	int			m;
 	HnswElement entryPoint;
 	char	   *base = NULL;
-	HnswQuery  *q = &so->q;
 
 	/* Get m and entry point */
 	HnswGetMetaPageInfo(index, &m, &entryPoint);
 
-	q->value = value;
-	so->m = m;
-
 	if (entryPoint == NULL)
 		return NIL;
 
-	ep = list_make1(HnswEntryCandidate(base, entryPoint, q, index, support, false));
+	ep = list_make1(HnswEntryCandidate(base, entryPoint, q, index, procinfo, collation, false));
 
 	for (int lc = entryPoint->level; lc >= 1; lc--)
 	{
-		w = HnswSearchLayer(base, q, ep, 1, lc, index, support, m, false, NULL, NULL, NULL, true, NULL);
+		w = HnswSearchLayer(base, q, ep, 1, lc, index, procinfo, collation, m, false, NULL);
 		ep = w;
 	}
 
-	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);
+	return HnswSearchLayer(base, q, ep, hnsw_ef_search, 0, index, procinfo, collation, m, false, NULL);
-}
-
-/*
- * 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, &so->v, &so->discarded, false, &so->tuples);
 }
 
 /*
@@ -95,24 +60,13 @@ GetScanValue(IndexScanDesc scan)
 		Assert(!VARATT_IS_EXTENDED(DatumGetPointer(value)));
 
 		/* Normalize if needed */
-		if (so->support.normprocinfo != NULL)
+		if (so->normprocinfo != NULL)
-			value = HnswNormValue(so->typeInfo, so->support.collation, value);
+			value = HnswNormValue(so->typeInfo, so->collation, value);
 	}
 
 	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
  */
@@ -121,28 +75,20 @@ 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;
-	/* 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);
+									   ALLOCSET_DEFAULT_SIZES);
 
-	/* Calculate max memory */
+	/* Set support functions */
-	/* Add 256 extra bytes to fill last block when close */
+	so->procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
-	maxMemory = (double) work_mem * hnsw_scan_mem_multiplier * 1024.0 + 256;
+	so->normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
-	so->maxMemory = Min(maxMemory, (double) SIZE_MAX);
+	so->collation = index->rd_indcollation[0];
 
 	scan->opaque = so;
 
@@ -158,11 +104,6 @@ hnswrescan(IndexScanDesc scan, ScanKey keys, int nkeys, ScanKey orderbys, int no
 	HnswScanOpaque so = (HnswScanOpaque) scan->opaque;
 
 	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);
 
 	if (keys && scan->numberOfKeys > 0)
@@ -220,89 +161,26 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
 		so->first = false;
 
 #if defined(HNSW_MEMORY)
-		ShowMemoryUsage(so);
+		elog(INFO, "memory: %zu KB", MemoryContextMemAllocated(so->tmpCtx, false) / 1024);
 #endif
 	}
 
-	for (;;)
+	while (list_length(so->w) > 0)
 	{
 		char	   *base = NULL;
-		HnswSearchCandidate *sc;
+		HnswSearchCandidate *hc = llast(so->w);
-		HnswElement element;
+		HnswElement element = HnswPtrAccess(base, hc->element);
 		ItemPointer heaptid;
 
-		if (list_length(so->w) == 0)
-		{
-			if (hnsw_iterative_scan == HNSW_ITERATIVE_SCAN_OFF)
-				break;
-
-			/* Empty index */
-			if (so->discarded == NULL)
-				break;
-
-			/* Reached max number of tuples or memory limit */
-			if (so->tuples >= hnsw_max_scan_tuples || MemoryContextMemAllocated(so->tmpCtx, false) > so->maxMemory)
-			{
-				if (pairingheap_is_empty(so->discarded))
-					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)
-				ShowMemoryUsage(so);
-#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 (element->heaptidsLength == 0)
 		{
 			so->w = list_delete_last(so->w);
-
-			/* Mark memory as free for next iteration */
-			if (hnsw_iterative_scan != HNSW_ITERATIVE_SCAN_OFF)
-			{
-				pfree(element);
-				pfree(sc);
-			}
-
 			continue;
 		}
 
 		heaptid = &element->heaptids[--element->heaptidsLength];
 
-		if (hnsw_iterative_scan == HNSW_ITERATIVE_SCAN_STRICT)
-		{
-			if (sc->distance < so->previousDistance)
-				continue;
-
-			so->previousDistance = sc->distance;
-		}
-
 		MemoryContextSwitchTo(oldCtx);
 
 		scan->xs_heaptid = *heaptid;

src/hnswutils.c

@@ -100,6 +100,19 @@ 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
  */
@@ -140,17 +153,6 @@ HnswOptionalProcInfo(Relation index, uint16 procnum)
 	return index_getprocinfo(index, 1, procnum);
 }
 
-/*
- * Init support functions
- */
-void
-HnswInitSupport(HnswSupport * support, Relation index)
-{
-	support->procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
-	support->collation = index->rd_indcollation[0];
-	support->normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
-}
-
 /*
  * Normalize value
  */
@@ -164,9 +166,9 @@ HnswNormValue(const HnswTypeInfo * typeInfo, Oid collation, Datum value)
  * Check if non-zero norm
  */
 bool
-HnswCheckNorm(HnswSupport * support, Datum value)
+HnswCheckNorm(FmgrInfo *procinfo, Oid collation, Datum value)
 {
-	return DatumGetFloat8(FunctionCall1Coll(support->normprocinfo, support->collation, value)) > 0;
+	return DatumGetFloat8(FunctionCall1Coll(procinfo, collation, value)) > 0;
 }
 
 /*
@@ -195,7 +197,7 @@ HnswInitPage(Buffer buf, Page page)
 /*
  * Allocate a neighbor array
  */
-HnswNeighborArray *
+static HnswNeighborArray *
 HnswInitNeighborArray(int lm, HnswAllocator * allocator)
 {
 	HnswNeighborArray *a = HnswAlloc(allocator, HNSW_NEIGHBOR_ARRAY_SIZE(lm));
@@ -251,8 +253,6 @@ 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);
 
@@ -394,33 +394,6 @@ HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, Bloc
 	UnlockReleaseBuffer(buf);
 }
 
-/*
- * Form index value
- */
-bool
-HnswFormIndexValue(Datum *out, Datum *values, bool *isnull, const HnswTypeInfo * typeInfo, HnswSupport * support)
-{
-	/* 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, value);
-	}
-
-	*out = value;
-
-	return true;
-}
-
 /*
  * Set element tuple, except for neighbor info
  */
@@ -432,7 +405,6 @@ 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)
@@ -475,7 +447,69 @@ HnswSetNeighborTuple(char *base, HnswNeighborTuple ntup, HnswElement e, int m)
 	}
 
 	ntup->count = idx;
-	ntup->version = e->version;
+}
+
+/*
+ * Load neighbors from page
+ */
+static void
+LoadNeighborsFromPage(HnswElement element, Relation index, Page page, int m)
+{
+	char	   *base = NULL;
+
+	HnswNeighborTuple ntup = (HnswNeighborTuple) PageGetItem(page, PageGetItemId(page, element->neighborOffno));
+	int			neighborCount = (element->level + 2) * m;
+
+	Assert(HnswIsNeighborTuple(ntup));
+
+	HnswInitNeighbors(base, element, m, NULL);
+
+	/* Ensure expected neighbors */
+	if (ntup->count != neighborCount)
+		return;
+
+	for (int i = 0; i < neighborCount; i++)
+	{
+		HnswElement e;
+		int			level;
+		HnswCandidate *hc;
+		ItemPointer indextid;
+		HnswNeighborArray *neighbors;
+
+		indextid = &ntup->indextids[i];
+
+		if (!ItemPointerIsValid(indextid))
+			continue;
+
+		e = HnswInitElementFromBlock(ItemPointerGetBlockNumber(indextid), ItemPointerGetOffsetNumber(indextid));
+
+		/* Calculate level based on offset */
+		level = element->level - i / m;
+		if (level < 0)
+			level = 0;
+
+		neighbors = HnswGetNeighbors(base, element, level);
+		hc = &neighbors->items[neighbors->length++];
+		HnswPtrStore(base, hc->element, e);
+	}
+}
+
+/*
+ * Load neighbors
+ */
+void
+HnswLoadNeighbors(HnswElement element, Relation index, int m)
+{
+	Buffer		buf;
+	Page		page;
+
+	buf = ReadBuffer(index, element->neighborPage);
+	LockBuffer(buf, BUFFER_LOCK_SHARE);
+	page = BufferGetPage(buf);
+
+	LoadNeighborsFromPage(element, index, page, m);
+
+	UnlockReleaseBuffer(buf);
 }
 
 /*
@@ -486,7 +520,6 @@ 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;
@@ -512,20 +545,11 @@ HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHe
 	}
 }
 
-/*
- * Calculate the distance between values
- */
-static inline double
-HnswGetDistance(Datum a, Datum b, HnswSupport * support)
-{
-	return DatumGetFloat8(FunctionCall2Coll(support->procinfo, support->collation, a, b));
-}
-
 /*
  * Load an element and optionally get its distance from q
  */
 static void
-HnswLoadElementImpl(BlockNumber blkno, OffsetNumber offno, double *distance, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec, double *maxDistance, HnswElement * element)
+HnswLoadElementImpl(BlockNumber blkno, OffsetNumber offno, float *distance, Datum *q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec, float *maxDistance, HnswElement * element)
 {
 	Buffer		buf;
 	Page		page;
@@ -543,10 +567,10 @@ HnswLoadElementImpl(BlockNumber blkno, OffsetNumber offno, double *distance, Hns
 	/* Calculate distance */
 	if (distance != NULL)
 	{
-		if (DatumGetPointer(q->value) == NULL)
+		if (DatumGetPointer(*q) == NULL)
 			*distance = 0;
 		else
-			*distance = HnswGetDistance(q->value, PointerGetDatum(&etup->data), support);
+			*distance = (float) DatumGetFloat8(FunctionCall2Coll(procinfo, collation, *q, PointerGetDatum(&etup->data)));
 	}
 
 	/* Load element */
@@ -565,52 +589,41 @@ HnswLoadElementImpl(BlockNumber blkno, OffsetNumber offno, double *distance, Hns
  * Load an element and optionally get its distance from q
  */
 void
-HnswLoadElement(HnswElement element, double *distance, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec, double *maxDistance)
+HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec, float *maxDistance)
 {
-	HnswLoadElementImpl(element->blkno, element->offno, distance, q, index, support, loadVec, maxDistance, &element);
+	HnswLoadElementImpl(element->blkno, element->offno, distance, q, index, procinfo, collation, loadVec, maxDistance, &element);
 }
 
 /*
  * Get the distance for an element
  */
-static double
+static float
-GetElementDistance(char *base, HnswElement element, HnswQuery * q, HnswSupport * support)
+GetElementDistance(char *base, HnswElement element, Datum q, FmgrInfo *procinfo, Oid collation)
 {
 	Datum		value = HnswGetValue(base, element);
 
-	return HnswGetDistance(q->value, value, support);
+	return DatumGetFloat8(FunctionCall2Coll(procinfo, collation, q, value));
-}
-
-/*
- * 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)
+HnswEntryCandidate(char *base, HnswElement entryPoint, Datum q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec)
 {
-	bool		inMemory = index == NULL;
+	HnswSearchCandidate *hc = palloc(sizeof(HnswSearchCandidate));
-	double		distance;
 
-	if (inMemory)
+	HnswPtrStore(base, hc->element, entryPoint);
-		distance = GetElementDistance(base, entryPoint, q, support);
+	if (index == NULL)
+		hc->distance = GetElementDistance(base, entryPoint, q, procinfo, collation);
 	else
-		HnswLoadElement(entryPoint, &distance, q, index, support, loadVec, NULL);
+		HnswLoadElement(entryPoint, &hc->distance, &q, index, procinfo, collation, loadVec, NULL);
-
+	return hc;
-	return HnswInitSearchCandidate(base, entryPoint, distance);
 }
 
+#define HnswGetSearchCandidate(membername, ptr) pairingheap_container(HnswSearchCandidate, membername, ptr)
+#define HnswGetSearchCandidateConst(membername, ptr) pairingheap_const_container(HnswSearchCandidate, membername, ptr)
+
 /*
  * Compare candidate distances
  */
@@ -626,21 +639,6 @@ 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
  */
@@ -660,9 +658,9 @@ CompareFurthestCandidates(const pairingheap_node *a, const pairingheap_node *b,
  * Init visited
  */
 static inline void
-InitVisited(char *base, visited_hash * v, bool inMemory, int ef, int m)
+InitVisited(char *base, visited_hash * v, Relation index, int ef, int m)
 {
-	if (!inMemory)
+	if (index != NULL)
 		v->tids = tidhash_create(CurrentMemoryContext, ef * m * 2, NULL);
 	else if (base != NULL)
 		v->offsets = offsethash_create(CurrentMemoryContext, ef * m * 2, NULL);
@@ -674,9 +672,9 @@ InitVisited(char *base, visited_hash * v, bool inMemory, int ef, int m)
  * Add to visited
  */
 static inline void
-AddToVisited(char *base, visited_hash * v, HnswElementPtr elementPtr, bool inMemory, bool *found)
+AddToVisited(char *base, visited_hash * v, HnswElementPtr elementPtr, Relation index, bool *found)
 {
-	if (!inMemory)
+	if (index != NULL)
 	{
 		HnswElement element = HnswPtrAccess(base, elementPtr);
 		ItemPointerData indextid;
@@ -737,60 +735,45 @@ HnswLoadUnvisitedFromMemory(char *base, HnswElement element, HnswUnvisited * unv
 		HnswCandidate *hc = &localNeighborhood->items[i];
 		bool		found;
 
-		AddToVisited(base, v, hc->element, true, &found);
+		AddToVisited(base, v, hc->element, NULL, &found);
 
 		if (!found)
 			unvisited[(*unvisitedLength)++].element = HnswPtrAccess(base, hc->element);
 	}
 }
 
-/*
- * Load neighbor index TIDs
- */
-bool
-HnswLoadNeighborTids(HnswElement element, ItemPointerData *indextids, Relation index, int m, int lm, int lc)
-{
-	Buffer		buf;
-	Page		page;
-	HnswNeighborTuple ntup;
-	int			start;
-
-	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 || ntup->count != (element->level + 2) * m)
-	{
-		UnlockReleaseBuffer(buf);
-		return false;
-	}
-
-	/* Copy to minimize lock time */
-	start = (element->level - lc) * m;
-	memcpy(indextids, ntup->indextids + start, lm * sizeof(ItemPointerData));
-
-	UnlockReleaseBuffer(buf);
-	return true;
-}
-
 /*
  * Load unvisited neighbors from disk
  */
 static void
 HnswLoadUnvisitedFromDisk(HnswElement element, HnswUnvisited * unvisited, int *unvisitedLength, visited_hash * v, Relation index, int m, int lm, int lc)
 {
+	Buffer		buf;
+	Page		page;
+	HnswNeighborTuple ntup;
+	int			start;
 	ItemPointerData indextids[HNSW_MAX_M * 2];
 
-	*unvisitedLength = 0;
+	buf = ReadBuffer(index, element->neighborPage);
+	LockBuffer(buf, BUFFER_LOCK_SHARE);
+	page = BufferGetPage(buf);
 
-	if (!HnswLoadNeighborTids(element, indextids, index, m, lm, lc))
+	ntup = (HnswNeighborTuple) PageGetItem(page, PageGetItemId(page, element->neighborOffno));
+
+	/* Ensure expected neighbors */
+	if (ntup->count != (element->level + 2) * m)
+	{
+		UnlockReleaseBuffer(buf);
 		return;
+	}
+
+	/* 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++)
 	{
@@ -811,37 +794,24 @@ HnswLoadUnvisitedFromDisk(HnswElement element, HnswUnvisited * unvisited, int *u
  * Algorithm 2 from paper
  */
 List *
-HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation index, HnswSupport * support, int m, bool inserting, HnswElement skipElement, visited_hash * v, pairingheap **discarded, bool initVisited, int64 *tuples)
+HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool inserting, HnswElement skipElement)
 {
 	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;
 	int			lm = HnswGetLayerM(m, lc);
 	HnswUnvisited *unvisited = palloc(lm * sizeof(HnswUnvisited));
 	int			unvisitedLength;
-	bool		inMemory = index == NULL;
 
-	if (v == NULL)
+	InitVisited(base, &v, index, ef, m);
-	{
-		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)
+	if (index == NULL)
 	{
 		neighborhoodSize = HNSW_NEIGHBOR_ARRAY_SIZE(lm);
 		localNeighborhood = palloc(neighborhoodSize);
@@ -850,27 +820,20 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
 	/* Add entry points to v, C, and W */
 	foreach(lc2, ep)
 	{
-		HnswSearchCandidate *sc = (HnswSearchCandidate *) lfirst(lc2);
+		HnswSearchCandidate *hc = (HnswSearchCandidate *) lfirst(lc2);
 		bool		found;
 
-		if (initVisited)
+		AddToVisited(base, &v, hc->element, index, &found);
-		{
-			AddToVisited(base, v, sc->element, inMemory, &found);
 
-			/* OK to count elements instead of tuples */
+		pairingheap_add(C, &hc->c_node);
-			if (tuples != NULL)
+		pairingheap_add(W, &hc->w_node);
-				(*tuples)++;
-		}
-
-		pairingheap_add(C, &sc->c_node);
-		pairingheap_add(W, &sc->w_node);
 
 		/*
 		 * Do not count elements being deleted towards ef when vacuuming. It
 		 * would be ideal to do this for inserts as well, but this could
 		 * affect insert performance.
 		 */
-		if (CountElement(skipElement, HnswPtrAccess(base, sc->element)))
+		if (CountElement(skipElement, HnswPtrAccess(base, hc->element)))
 			wlen++;
 	}
 
@@ -885,28 +848,24 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
 
 		cElement = HnswPtrAccess(base, c->element);
 
-		if (inMemory)
+		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);
-
-		/* OK to count elements instead of tuples */
-		if (tuples != NULL)
-			(*tuples) += unvisitedLength;
 
 		for (int i = 0; i < unvisitedLength; i++)
 		{
 			HnswElement eElement;
 			HnswSearchCandidate *e;
-			double		eDistance;
+			float		eDistance;
 			bool		alwaysAdd = wlen < ef;
 
 			f = HnswGetSearchCandidate(w_node, pairingheap_first(W));
 
-			if (inMemory)
+			if (index == NULL)
 			{
 				eElement = unvisited[i].element;
-				eDistance = GetElementDistance(base, eElement, q, support);
+				eDistance = GetElementDistance(base, eElement, q, procinfo, collation);
 			}
 			else
 			{
@@ -916,30 +875,25 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
 
 				/* Avoid any allocations if not adding */
 				eElement = NULL;
-				HnswLoadElementImpl(blkno, offno, &eDistance, q, index, support, 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 (!(eDistance < f->distance || alwaysAdd))
-			{
-				if (discarded != NULL)
-				{
-					/* Create a new candidate */
-					e = HnswInitSearchCandidate(base, eElement, eDistance);
-					pairingheap_add(*discarded, &e->w_node);
-				}
-
 				continue;
-			}
+
+			Assert(!eElement->deleted);
 
 			/* Make robust to issues */
 			if (eElement->level < lc)
 				continue;
 
 			/* Create a new candidate */
-			e = HnswInitSearchCandidate(base, eElement, eDistance);
+			e = palloc(sizeof(HnswSearchCandidate));
+			HnswPtrStore(base, e->element, eElement);
+			e->distance = eDistance;
 			pairingheap_add(C, &e->c_node);
 			pairingheap_add(W, &e->w_node);
 
@@ -954,12 +908,7 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
 
 				/* 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);
-				}
 			}
 		}
 	}
@@ -967,9 +916,9 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
 	/* Add each element of W to w */
 	while (!pairingheap_is_empty(W))
 	{
-		HnswSearchCandidate *sc = HnswGetSearchCandidate(w_node, pairingheap_remove_first(W));
+		HnswSearchCandidate *hc = HnswGetSearchCandidate(w_node, pairingheap_remove_first(W));
 
-		w = lappend(w, sc);
+		w = lappend(w, hc);
 	}
 
 	return w;
@@ -1023,22 +972,32 @@ CompareCandidateDistancesOffset(const ListCell *a, const ListCell *b)
 	return 0;
 }
 
+/*
+ * Calculate the distance between elements
+ */
+static float
+HnswGetDistance(char *base, HnswElement a, HnswElement b, FmgrInfo *procinfo, Oid collation)
+{
+	Datum		aValue = HnswGetValue(base, a);
+	Datum		bValue = HnswGetValue(base, b);
+
+	return DatumGetFloat8(FunctionCall2Coll(procinfo, collation, aValue, bValue));
+}
+
 /*
  * Check if an element is closer to q than any element from R
  */
 static bool
-CheckElementCloser(char *base, HnswCandidate * e, List *r, HnswSupport * support)
+CheckElementCloser(char *base, HnswCandidate * e, List *r, FmgrInfo *procinfo, Oid collation)
 {
 	HnswElement eElement = HnswPtrAccess(base, e->element);
-	Datum		eValue = HnswGetValue(base, eElement);
 	ListCell   *lc2;
 
 	foreach(lc2, r)
 	{
 		HnswCandidate *ri = lfirst(lc2);
 		HnswElement riElement = HnswPtrAccess(base, ri->element);
-		Datum		riValue = HnswGetValue(base, riElement);
+		float		distance = HnswGetDistance(base, eElement, riElement, procinfo, collation);
-		float		distance = HnswGetDistance(eValue, riValue, support);
 
 		if (distance <= e->distance)
 			return false;
@@ -1051,14 +1010,15 @@ CheckElementCloser(char *base, HnswCandidate * e, List *r, HnswSupport * support
  * Algorithm 4 from paper
  */
 static List *
-SelectNeighbors(char *base, List *c, int lm, HnswSupport * support, bool *closerSet, HnswCandidate * newCandidate, HnswCandidate * *pruned, bool sortCandidates)
+SelectNeighbors(char *base, List *c, int lm, int lc, FmgrInfo *procinfo, Oid collation, HnswElement e2, HnswCandidate * newCandidate, HnswCandidate * *pruned, bool sortCandidates)
 {
 	List	   *r = NIL;
 	List	   *w = list_copy(c);
 	HnswCandidate **wd;
 	int			wdlen = 0;
 	int			wdoff = 0;
-	bool		mustCalculate = !(*closerSet);
+	HnswNeighborArray *neighbors = HnswGetNeighbors(base, e2, lc);
+	bool		mustCalculate = !neighbors->closerSet;
 	List	   *added = NIL;
 	bool		removedAny = false;
 
@@ -1085,7 +1045,7 @@ SelectNeighbors(char *base, List *c, int lm, HnswSupport * support, bool *closer
 
 		/* Use previous state of r and wd to skip work when possible */
 		if (mustCalculate)
-			e->closer = CheckElementCloser(base, e, r, support);
+			e->closer = CheckElementCloser(base, e, r, procinfo, collation);
 		else if (list_length(added) > 0)
 		{
 			/* Keep Valgrind happy for in-memory, parallel builds */
@@ -1098,7 +1058,7 @@ SelectNeighbors(char *base, List *c, int lm, HnswSupport * support, bool *closer
 			 */
 			if (e->closer)
 			{
-				e->closer = CheckElementCloser(base, e, added, support);
+				e->closer = CheckElementCloser(base, e, added, procinfo, collation);
 
 				if (!e->closer)
 					removedAny = true;
@@ -1111,7 +1071,7 @@ SelectNeighbors(char *base, List *c, int lm, HnswSupport * support, bool *closer
 				 */
 				if (removedAny)
 				{
-					e->closer = CheckElementCloser(base, e, r, support);
+					e->closer = CheckElementCloser(base, e, r, procinfo, collation);
 					if (e->closer)
 						added = lappend(added, e);
 				}
@@ -1119,7 +1079,7 @@ SelectNeighbors(char *base, List *c, int lm, HnswSupport * support, bool *closer
 		}
 		else if (e == newCandidate)
 		{
-			e->closer = CheckElementCloser(base, e, r, support);
+			e->closer = CheckElementCloser(base, e, r, procinfo, collation);
 			if (e->closer)
 				added = lappend(added, e);
 		}
@@ -1135,7 +1095,7 @@ SelectNeighbors(char *base, List *c, int lm, HnswSupport * support, bool *closer
 	}
 
 	/* Cached value can only be used in future if sorted deterministically */
-	*closerSet = sortCandidates;
+	neighbors->closerSet = sortCandidates;
 
 	/* Keep pruned connections */
 	while (wdoff < wdlen && list_length(r) < lm)
@@ -1170,16 +1130,18 @@ 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, HnswSupport * support)
+HnswUpdateConnection(char *base, HnswElement element, HnswCandidate * hc, int lm, int lc, int *updateIdx, Relation index, FmgrInfo *procinfo, Oid collation)
 {
-	HnswCandidate newHc;
+	HnswElement hce = HnswPtrAccess(base, hc->element);
+	HnswNeighborArray *currentNeighbors = HnswGetNeighbors(base, hce, lc);
+	HnswCandidate hc2;
 
-	HnswPtrStore(base, newHc.element, newElement);
+	HnswPtrStore(base, hc2.element, element);
-	newHc.distance = distance;
+	hc2.distance = hc->distance;
 
-	if (neighbors->length < lm)
+	if (currentNeighbors->length < lm)
 	{
-		neighbors->items[neighbors->length++] = newHc;
+		currentNeighbors->items[currentNeighbors->length++] = hc2;
 
 		/* Track update */
 		if (updateIdx != NULL)
@@ -1188,26 +1150,54 @@ HnswUpdateConnection(char *base, HnswNeighborArray * neighbors, HnswElement newE
 	else
 	{
 		/* Shrink connections */
-		List	   *c = NIL;
 		HnswCandidate *pruned = NULL;
 
-		/* Add candidates */
+		/* Load elements on insert */
-		for (int i = 0; i < neighbors->length; i++)
+		if (index != NULL)
-			c = lappend(c, &neighbors->items[i]);
+		{
-		c = lappend(c, &newHc);
+			Datum		q = HnswGetValue(base, hce);
 
-		SelectNeighbors(base, c, lm, support, &neighbors->closerSet, &newHc, &pruned, true);
+			for (int i = 0; i < currentNeighbors->length; i++)
+			{
+				HnswCandidate *hc3 = &currentNeighbors->items[i];
+				HnswElement hc3Element = HnswPtrAccess(base, hc3->element);
+
+				if (HnswPtrIsNull(base, hc3Element->value))
+					HnswLoadElement(hc3Element, &hc3->distance, &q, index, procinfo, collation, true, NULL);
+				else
+					hc3->distance = GetElementDistance(base, hc3Element, q, procinfo, collation);
+
+				/* Prune element if being deleted */
+				if (hc3Element->heaptidsLength == 0)
+				{
+					pruned = &currentNeighbors->items[i];
+					break;
+				}
+			}
+		}
 
-		/* Should not happen */
 		if (pruned == NULL)
-			return;
+		{
+			List	   *c = NIL;
+
+			/* Add candidates */
+			for (int i = 0; i < currentNeighbors->length; i++)
+				c = lappend(c, &currentNeighbors->items[i]);
+			c = lappend(c, &hc2);
+
+			SelectNeighbors(base, c, lm, lc, procinfo, collation, hce, &hc2, &pruned, true);
+
+			/* Should not happen */
+			if (pruned == NULL)
+				return;
+		}
 
 		/* Find and replace the pruned element */
-		for (int i = 0; i < neighbors->length; i++)
+		for (int i = 0; i < currentNeighbors->length; i++)
 		{
-			if (HnswPtrEqual(base, neighbors->items[i].element, pruned->element))
+			if (HnswPtrEqual(base, currentNeighbors->items[i].element, pruned->element))
 			{
-				neighbors->items[i] = newHc;
+				currentNeighbors->items[i] = hc2;
 
 				/* Track update */
 				if (updateIdx != NULL)
@@ -1267,20 +1257,17 @@ PrecomputeHash(char *base, HnswElement element)
  * Algorithm 1 from paper
  */
 void
-HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, HnswSupport * support, int m, int efConstruction, bool existing)
+HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, FmgrInfo *procinfo, Oid collation, int m, int efConstruction, bool existing)
 {
 	List	   *ep;
 	List	   *w;
 	int			level = element->level;
 	int			entryLevel;
-	HnswQuery	q;
+	Datum		q = HnswGetValue(base, element);
 	HnswElement skipElement = existing ? element : NULL;
-	bool		inMemory = index == NULL;
-
-	q.value = HnswGetValue(base, element);
 
 	/* Precompute hash */
-	if (inMemory)
+	if (index == NULL)
 		PrecomputeHash(base, element);
 
 	/* No neighbors if no entry point */
@@ -1288,13 +1275,13 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
 		return;
 
 	/* Get entry point and level */
-	ep = list_make1(HnswEntryCandidate(base, entryPoint, &q, index, support, true));
+	ep = list_make1(HnswEntryCandidate(base, entryPoint, q, index, procinfo, collation, true));
 	entryLevel = entryPoint->level;
 
 	/* 1st phase: greedy search to insert level */
 	for (int lc = entryLevel; lc >= level + 1; lc--)
 	{
-		w = HnswSearchLayer(base, &q, ep, 1, lc, index, support, m, true, skipElement, NULL, NULL, true, NULL);
+		w = HnswSearchLayer(base, q, ep, 1, lc, index, procinfo, collation, m, true, skipElement);
 		ep = w;
 	}
 
@@ -1313,7 +1300,7 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
 		List	   *lw = NIL;
 		ListCell   *lc2;
 
-		w = HnswSearchLayer(base, &q, ep, efConstruction, lc, index, support, m, true, skipElement, NULL, NULL, true, NULL);
+		w = HnswSearchLayer(base, q, ep, efConstruction, lc, index, procinfo, collation, m, true, skipElement);
 
 		/* Convert search candidates to candidates */
 		foreach(lc2, w)
@@ -1329,7 +1316,7 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
 
 		/* Elements being deleted or skipped can help with search */
 		/* but should be removed before selecting neighbors */
-		if (!inMemory)
+		if (index != NULL)
 			lw = RemoveElements(base, lw, skipElement);
 
 		/*
@@ -1337,7 +1324,7 @@ 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, support, &HnswGetNeighbors(base, element, lc)->closerSet, NULL, NULL, false);
+		neighbors = SelectNeighbors(base, lw, lm, lc, procinfo, collation, element, NULL, NULL, false);
 
 		AddConnections(base, element, neighbors, lc);
 

src/hnswvacuum.c

@@ -184,12 +184,13 @@ 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);
@@ -204,7 +205,7 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
 	element->heaptidsLength = 0;
 
 	/* Find neighbors for element, skipping itself */
-	HnswFindElementNeighbors(base, element, entryPoint, index, support, m, efConstruction, true);
+	HnswFindElementNeighbors(base, element, entryPoint, index, procinfo, collation, m, efConstruction, true);
 
 	/* Zero memory for each element */
 	MemSet(ntup, 0, HNSW_TUPLE_ALLOC_SIZE);
@@ -228,7 +229,7 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
 	UnlockReleaseBuffer(buf);
 
 	/* Update neighbors */
-	HnswUpdateNeighborsOnDisk(index, support, element, m, true, false);
+	HnswUpdateNeighborsOnDisk(index, procinfo, collation, element, m, true, false);
 }
 
 /*
@@ -238,7 +239,6 @@ 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, index, support, true, NULL);
+		HnswLoadElement(highestPoint, NULL, NULL, index, vacuumstate->procinfo, vacuumstate->collation, 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, index, support, true, NULL);
+			HnswLoadElement(entryPoint, NULL, NULL, index, vacuumstate->procinfo, vacuumstate->collation, true, NULL);
 
 			if (NeedsUpdated(vacuumstate, entryPoint))
 			{
@@ -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
@@ -581,13 +573,13 @@ InitVacuumState(HnswVacuumState * vacuumstate, IndexVacuumInfo *info, IndexBulkD
 	vacuumstate->callback_state = callback_state;
 	vacuumstate->efConstruction = HnswGetEfConstruction(index);
 	vacuumstate->bas = GetAccessStrategy(BAS_BULKREAD);
+	vacuumstate->procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
+	vacuumstate->collation = index->rd_indcollation[0];
 	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

@@ -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)
 {
+	Datum		value;
+	bool		isnull;
+
 	if (tuplesort_gettupleslot(sortstate, true, false, slot, NULL))
 	{
-		Datum		value;
-		bool		isnull;
-
 		*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->sortdesc, &TTSOpsMinimalTuple);
+	TupleTableSlot *slot = MakeSingleTupleTableSlot(buildstate->tupdesc, &TTSOpsMinimalTuple);
-	TupleDesc	tupdesc = buildstate->tupdesc;
+	TupleDesc	tupdesc = RelationGetDescr(index);
 
 	pgstat_progress_update_param(PROGRESS_CREATEIDX_SUBPHASE, PROGRESS_IVFFLAT_PHASE_LOAD);
 
@@ -319,7 +319,6 @@ 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;
@@ -357,12 +356,12 @@ InitBuildState(IvfflatBuildState * buildstate, Relation heap, Relation index, In
 				 errmsg("dimensions must be greater than one for this opclass")));
 
 	/* Create tuple description for sorting */
-	buildstate->sortdesc = CreateTemplateTupleDesc(3);
+	buildstate->tupdesc = CreateTemplateTupleDesc(3);
-	TupleDescInitEntry(buildstate->sortdesc, (AttrNumber) 1, "list", INT4OID, -1, 0);
+	TupleDescInitEntry(buildstate->tupdesc, (AttrNumber) 1, "list", INT4OID, -1, 0);
-	TupleDescInitEntry(buildstate->sortdesc, (AttrNumber) 2, "tid", TIDOID, -1, 0);
+	TupleDescInitEntry(buildstate->tupdesc, (AttrNumber) 2, "tid", TIDOID, -1, 0);
-	TupleDescInitEntry(buildstate->sortdesc, (AttrNumber) 3, "vector", buildstate->tupdesc->attrs[0].atttypid, -1, 0);
+	TupleDescInitEntry(buildstate->tupdesc, (AttrNumber) 3, "vector", RelationGetDescr(index)->attrs[0].atttypid, -1, 0);
 
-	buildstate->slot = MakeSingleTupleTableSlot(buildstate->sortdesc, &TTSOpsVirtual);
+	buildstate->slot = MakeSingleTupleTableSlot(buildstate->tupdesc, &TTSOpsVirtual);
 
 	buildstate->centers = VectorArrayInit(buildstate->lists, buildstate->dimensions, buildstate->typeInfo->itemSize(buildstate->dimensions));
 	buildstate->listInfo = palloc(sizeof(ListInfo) * buildstate->lists);
@@ -634,7 +633,7 @@ 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.sortdesc, sortmem, coordinate);
+	ivfspool->sortstate = InitBuildSortState(buildstate.tupdesc, sortmem, coordinate);
 	buildstate.sortstate = ivfspool->sortstate;
 	scan = table_beginscan_parallel(ivfspool->heap,
 									ParallelTableScanFromIvfflatShared(ivfshared));
@@ -951,7 +950,7 @@ AssignTuples(IvfflatBuildState * buildstate)
 	}
 
 	/* Begin serial/leader tuplesort */
-	buildstate->sortstate = InitBuildSortState(buildstate->sortdesc, maintenance_work_mem, coordinate);
+	buildstate->sortstate = InitBuildSortState(buildstate->tupdesc, maintenance_work_mem, coordinate);
 
 	/* Add tuples to sort */
 	if (buildstate->heap != NULL)

src/ivfflat.c

@@ -17,16 +17,8 @@
 #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
  */
@@ -41,15 +33,6 @@ 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_scan", "Sets the mode for iterative scans",
-							 NULL, &ivfflat_iterative_scan,
-							 IVFFLAT_ITERATIVE_SCAN_OFF, ivfflat_iterative_scan_options, PGC_USERSET, 0, 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, 0, NULL, NULL, NULL);
-
 	MarkGUCPrefixReserved("ivfflat");
 }
 
@@ -99,10 +82,6 @@ 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

@@ -80,14 +80,6 @@
 
 /* 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
 {
@@ -173,7 +165,6 @@ typedef struct IvfflatBuildState
 	Relation	index;
 	IndexInfo  *indexInfo;
 	const		IvfflatTypeInfo *typeInfo;
-	TupleDesc	tupdesc;
 
 	/* Settings */
 	int			dimensions;
@@ -207,7 +198,7 @@ typedef struct IvfflatBuildState
 
 	/* Sorting */
 	Tuplesortstate *sortstate;
-	TupleDesc	sortdesc;
+	TupleDesc	tupdesc;
 	TupleTableSlot *slot;
 
 	/* Memory */
@@ -256,11 +247,8 @@ typedef struct IvfflatScanOpaqueData
 {
 	const		IvfflatTypeInfo *typeInfo;
 	int			probes;
-	int			maxProbes;
 	int			dimensions;
 	bool		first;
-	Datum		value;
-	MemoryContext tmpCtx;
 
 	/* Sorting */
 	Tuplesortstate *sortstate;
@@ -277,9 +265,7 @@ typedef struct IvfflatScanOpaqueData
 
 	/* Lists */
 	pairingheap *listQueue;
-	BlockNumber *listPages;
+	IvfflatScanList lists[FLEXIBLE_ARRAY_MEMBER];	/* must come last */
-	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, &value, &insertPage, &listInfo);
+	FindInsertPage(index, values, &insertPage, &listInfo);
 	Assert(BlockNumberIsValid(insertPage));
 	originalInsertPage = insertPage;
 

src/ivfscan.c

@@ -10,7 +10,10 @@
 #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)
@@ -62,7 +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->maxProbes)
+			if (listCount < so->probes)
 			{
 				IvfflatScanList *scanlist;
 
@@ -75,7 +78,7 @@ GetScanLists(IndexScanDesc scan, Datum value)
 				pairingheap_add(so->listQueue, &scanlist->ph_node);
 
 				/* Calculate max distance */
-				if (listCount == so->maxProbes)
+				if (listCount == so->probes)
 					maxDistance = GetScanList(pairingheap_first(so->listQueue))->distance;
 			}
 			else if (distance < maxDistance)
@@ -99,11 +102,6 @@ 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));
 }
 
 /*
@@ -114,15 +112,13 @@ GetScanItems(IndexScanDesc scan, Datum value)
 {
 	IvfflatScanOpaque so = (IvfflatScanOpaque) scan->opaque;
 	TupleDesc	tupdesc = RelationGetDescr(scan->indexRelation);
+	double		tuples = 0;
 	TupleTableSlot *slot = so->vslot;
-	int			batchProbes = 0;
-
-	tuplesort_reset(so->sortstate);
 
 	/* Search closest probes lists */
-	while (so->listIndex < so->maxProbes && (++batchProbes) <= so->probes)
+	while (!pairingheap_is_empty(so->listQueue))
 	{
-		BlockNumber searchPage = so->listPages[so->listIndex++];
+		BlockNumber searchPage = GetScanList(pairingheap_remove_first(so->listQueue))->startPage;
 
 		/* Search all entry pages for list */
 		while (BlockNumberIsValid(searchPage))
@@ -160,6 +156,8 @@ GetScanItems(IndexScanDesc scan, Datum value)
 				ExecStoreVirtualTuple(slot);
 
 				tuplesort_puttupleslot(so->sortstate, slot);
+
+				tuples++;
 			}
 
 			searchPage = IvfflatPageGetOpaque(page)->nextblkno;
@@ -168,11 +166,13 @@ GetScanItems(IndexScanDesc scan, Datum value)
 		}
 	}
 
-	tuplesort_performsort(so->sortstate);
+	if (tuples < 100)
+		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.")));
 
-#if defined(IVFFLAT_MEMORY)
+	tuplesort_performsort(so->sortstate);
-	elog(INFO, "memory: %zu MB", MemoryContextMemAllocated(CurrentMemoryContext, true) / (1024 * 1024));
-#endif
 }
 
 /*
@@ -209,13 +209,7 @@ 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;
@@ -246,30 +240,19 @@ 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;
 
-	if (maxProbes > lists)
+	so = (IvfflatScanOpaque) palloc(offsetof(IvfflatScanOpaqueData, lists) + probes * sizeof(IvfflatScanList));
-		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 */
@@ -277,12 +260,6 @@ 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);
@@ -303,11 +280,6 @@ 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;
 
@@ -322,9 +294,11 @@ 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));
@@ -340,8 +314,6 @@ 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
@@ -369,23 +341,28 @@ 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));
 	}
 
-	while (!tuplesort_gettupleslot(so->sortstate, true, false, so->mslot, NULL))
+	if (tuplesort_gettupleslot(so->sortstate, true, false, so->mslot, NULL))
 	{
-		if (so->listIndex == so->maxProbes)
+		bool		isnull;
-			return false;
+		ItemPointer heaptid = (ItemPointer) DatumGetPointer(slot_getattr(so->mslot, 2, &isnull));
 
-		IvfflatBench("GetScanItems", GetScanItems(scan, so->value));
+		scan->xs_heaptid = *heaptid;
+		scan->xs_recheck = false;
+		scan->xs_recheckorderby = false;
+		return true;
 	}
 
-	heaptid = (ItemPointer) DatumGetPointer(slot_getattr(so->mslot, 2, &isnull));
+	return false;
-
-	scan->xs_heaptid = *heaptid;
-	scan->xs_recheck = false;
-	scan->xs_recheckorderby = false;
-	return true;
 }
 
 /*
@@ -396,10 +373,12 @@ ivfflatendscan(IndexScanDesc scan)
 {
 	IvfflatScanOpaque so = (IvfflatScanOpaque) scan->opaque;
 
-	/* Free any temporary files */
+	pairingheap_free(so->listQueue);
 	tuplesort_end(so->sortstate);
+	FreeAccessStrategy(so->bas);
+	FreeTupleDesc(so->tupdesc);
 
-	MemoryContextDelete(so->tmpCtx);
+	/* TODO Free vslot and mslot without freeing TupleDesc */
 
 	pfree(so);
 	scan->opaque = NULL;

src/ivfvacuum.c

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

src/sparsevec.c

@@ -4,7 +4,6 @@
 #include <math.h>
 
 #include "catalog/pg_type.h"
-#include "common/shortest_dec.h"
 #include "common/string.h"
 #include "fmgr.h"
 #include "halfutils.h"
@@ -13,10 +12,17 @@
 #include "sparsevec.h"
 #include "utils/array.h"
 #include "utils/builtins.h"
-#include "utils/float.h"
 #include "utils/lsyscache.h"
 #include "vector.h"
 
+#if PG_VERSION_NUM >= 120000
+#include "common/shortest_dec.h"
+#include "utils/float.h"
+#else
+#include <float.h>
+#include "utils/builtins.h"
+#endif
+
 typedef struct SparseInputElement
 {
 	int32		index;

test/expected/hnsw_vector.out

@@ -99,32 +99,6 @@ 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));
@@ -165,31 +139,4 @@ 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)
-SET hnsw.scan_mem_multiplier = 1001;
-ERROR:  1001 is outside the valid range for parameter "hnsw.scan_mem_multiplier" (1 .. 1000)
 DROP TABLE t;

test/expected/ivfflat_vector.out

@@ -81,37 +81,6 @@ 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));
@@ -140,27 +109,4 @@ 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

@@ -57,23 +57,6 @@ 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));
@@ -98,17 +81,4 @@ 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;
-SET hnsw.scan_mem_multiplier = 1001;
-
 DROP TABLE t;

test/sql/ivfflat_vector.sql

@@ -44,25 +44,6 @@ 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));
@@ -81,16 +62,4 @@ 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

@@ -6,7 +6,13 @@ use Test::More;
 
 my $dim = 3;
 
-my $array_sql = join(",", ('random()') x $dim);
+my @r = ();
+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');
@@ -17,20 +23,19 @@ $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 % 10, 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 * FROM tmp;");
+$node->safe_psql("postgres",
+	"INSERT INTO tst SELECT i % 10, ARRAY[$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

@@ -1,54 +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;");
-$node->safe_psql("postgres", "CREATE TABLE tst (i int4 PRIMARY KEY, v vector($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

@@ -1,125 +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 $limit = 20;
-my @cs = (100, 1000);
-
-sub test_recall
-{
-	my ($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

@@ -1,59 +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;");
-$node->safe_psql("postgres", "CREATE TABLE tst (i int4 PRIMARY KEY, v vector($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 = $node->safe_psql("postgres", qq(
-	SET enable_seqscan = off;
-	SET hnsw.iterative_scan = relaxed_order;
-	SET hnsw.max_scan_tuples = 100000;
-	SET hnsw.scan_mem_multiplier = 2;
-	SELECT COUNT(*) FROM (SELECT v FROM tst WHERE i % 10000 = 0 ORDER BY v <-> (SELECT v FROM tst LIMIT 1) LIMIT 11) t;
-));
-is($count, 10);
-
-foreach ((30000, 50000, 70000))
-{
-	my $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_scan = relaxed_order;
-			SET hnsw.max_scan_tuples = $max_tuples;
-			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;
-	}
-
-	my $avg = $sum / 20;
-	cmp_ok($avg, '>', $expected - 2);
-	cmp_ok($avg, '<', $expected + 2);
-}
-
-done_testing();

test/t/044_hnsw_iterative_scan_recall.pl

@@ -1,118 +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 $dim);
-my @cs = (50, 500);
-
-sub test_recall
-{
-	my ($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.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/);
-
-	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_scan = $mode;
-			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 $mode $c");
-}
-
-# Initialize node
-$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($dim));");
-$node->safe_psql("postgres",
-	"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(1, 50000) 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, $res);
-		}
-
-		test_recall($c, 40, 0.99, $operator, "strict_order");
-		test_recall($c, 40, 0.99, $operator, "relaxed_order");
-	}
-
-	$node->safe_psql("postgres", "DROP INDEX idx;");
-}
-
-done_testing();

vector.control

@@ -1,4 +1,4 @@
 comment = 'vector data type and ivfflat and hnsw access methods'
-default_version = '0.8.0'
+default_version = '0.7.4'
 module_pathname = '$libdir/vector'
 relocatable = true