Updated number of parallel workers for IVFFlat index builds

This reverts commit 14b278dec9.

.github/workflows/build.yml

@@ -28,7 +28,7 @@ jobs:
           dev-files: true
       - run: make
         env:
-          PG_CFLAGS: -Wall -Wextra -Werror -Wno-unused-parameter -Wno-sign-compare
+          PG_CFLAGS: -DUSE_ASSERT_CHECKING -Wall -Wextra -Werror -Wno-unused-parameter -Wno-sign-compare
       - run: |
           export PG_CONFIG=`which pg_config`
           sudo --preserve-env=PG_CONFIG make install
@@ -49,7 +49,7 @@ jobs:
           postgres-version: 14
       - run: make
         env:
-          PG_CFLAGS: -Wall -Wextra -Werror -Wno-unused-parameter
+          PG_CFLAGS: -DUSE_ASSERT_CHECKING -Wall -Wextra -Werror -Wno-unused-parameter
       - run: make install
       - run: make installcheck
       - if: ${{ failure() }}
@@ -97,4 +97,15 @@ jobs:
           sudo -u postgres make installcheck
           sudo -u postgres make prove_installcheck
         env:
-          PG_CFLAGS: -Wall -Wextra -Werror -Wno-unused-parameter -Wno-sign-compare
+          PG_CFLAGS: -DUSE_ASSERT_CHECKING -Wall -Wextra -Werror -Wno-unused-parameter -Wno-sign-compare
+  valgrind:
+    if: ${{ !startsWith(github.ref_name, 'mac') && !startsWith(github.ref_name, 'windows') }}
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: ankane/setup-postgres-valgrind@v1
+        with:
+          postgres-version: 16
+      - run: make
+      - run: sudo --preserve-env=PG_CONFIG make install
+      - run: make installcheck

CHANGELOG.md

@@ -1,10 +1,7 @@
-## 0.7.0 (unreleased)
-
-- Added support for inline filtering with HNSW
-
 ## 0.6.1 (unreleased)
 
 - Fixed error with `ANALYZE` and vectors with different dimensions
+- Fixed error with `shared_preload_libraries`
 
 ## 0.6.0 (2024-01-29)
 

Makefile

@@ -71,11 +71,9 @@ PG_MAJOR ?= 16
 .PHONY: docker
 
 docker:
-	docker build --pull --no-cache --build-arg PG_MAJOR=$(PG_MAJOR) -t pgvector/pgvector:pg$(PG_MAJOR) .
-	docker build --build-arg PG_MAJOR=$(PG_MAJOR) -t pgvector/pgvector:$(EXTVERSION)-pg$(PG_MAJOR) .
+	docker build --pull --no-cache --build-arg PG_MAJOR=$(PG_MAJOR) -t pgvector/pgvector:pg$(PG_MAJOR) -t pgvector/pgvector:$(EXTVERSION)-pg$(PG_MAJOR) .
 
 .PHONY: docker-release
 
 docker-release:
-	docker buildx build --push --pull --no-cache --platform linux/amd64,linux/arm64 --build-arg PG_MAJOR=$(PG_MAJOR) -t pgvector/pgvector:pg$(PG_MAJOR) .
-	docker buildx build --push --platform linux/amd64,linux/arm64 --build-arg PG_MAJOR=$(PG_MAJOR) -t pgvector/pgvector:$(EXTVERSION)-pg$(PG_MAJOR) .
+	docker buildx build --push --pull --no-cache --platform linux/amd64,linux/arm64 --build-arg PG_MAJOR=$(PG_MAJOR) -t pgvector/pgvector:pg$(PG_MAJOR) -t pgvector/pgvector:$(EXTVERSION)-pg$(PG_MAJOR) .

README.md

@@ -377,12 +377,6 @@ Create an index on one [or more](https://www.postgresql.org/docs/current/indexes
 CREATE INDEX ON items (category_id);
 ```
 
-Or a composite HNSW index for approximate search (added in 0.7.0)
-
-```sql
-CREATE INDEX ON items USING hnsw (embedding vector_l2_ops, category_id);
-```
-
 Or a [partial index](https://www.postgresql.org/docs/current/indexes-partial.html) on the vector column for approximate search
 
 ```sql
@@ -733,7 +727,7 @@ pkg install postgresql15-pg_vector
 or the port with:
 
 ```sh
-cd /usr/ports/databases/pg_vector
+cd /usr/ports/databases/pgvector
 make install
 ```
 

sql/vector--0.6.1--0.7.0.sql

@@ -1,34 +0,0 @@
--- complain if script is sourced in psql, rather than via CREATE EXTENSION
-\echo Use "ALTER EXTENSION vector UPDATE TO '0.7.0'" to load this file. \quit
-
-CREATE OPERATOR CLASS vector_bigint_ops
-	DEFAULT FOR TYPE bigint USING hnsw AS
-	OPERATOR 2 < ,
-	OPERATOR 3 <= ,
-	OPERATOR 4 = ,
-	OPERATOR 5 >= ,
-	OPERATOR 6 > ;
-
-CREATE OPERATOR CLASS vector_integer_ops
-	DEFAULT FOR TYPE integer USING hnsw AS
-	OPERATOR 2 < ,
-	OPERATOR 3 <= ,
-	OPERATOR 4 = ,
-	OPERATOR 5 >= ,
-	OPERATOR 6 > ;
-
-CREATE OPERATOR CLASS vector_text_ops
-	DEFAULT FOR TYPE text USING hnsw AS
-	OPERATOR 2 < ,
-	OPERATOR 3 <= ,
-	OPERATOR 4 = ,
-	OPERATOR 5 >= ,
-	OPERATOR 6 > ;
-
-CREATE OPERATOR CLASS vector_uuid_ops
-	DEFAULT FOR TYPE uuid USING hnsw AS
-	OPERATOR 2 < ,
-	OPERATOR 3 <= ,
-	OPERATOR 4 = ,
-	OPERATOR 5 >= ,
-	OPERATOR 6 > ;

sql/vector.sql

@@ -290,37 +290,3 @@ CREATE OPERATOR CLASS vector_cosine_ops
 	OPERATOR 1 <=> (vector, vector) FOR ORDER BY float_ops,
 	FUNCTION 1 vector_negative_inner_product(vector, vector),
 	FUNCTION 2 vector_norm(vector);
-
--- hnsw attributes
-
-CREATE OPERATOR CLASS vector_bigint_ops
-	DEFAULT FOR TYPE bigint USING hnsw AS
-	OPERATOR 2 < ,
-	OPERATOR 3 <= ,
-	OPERATOR 4 = ,
-	OPERATOR 5 >= ,
-	OPERATOR 6 > ;
-
-CREATE OPERATOR CLASS vector_integer_ops
-	DEFAULT FOR TYPE integer USING hnsw AS
-	OPERATOR 2 < ,
-	OPERATOR 3 <= ,
-	OPERATOR 4 = ,
-	OPERATOR 5 >= ,
-	OPERATOR 6 > ;
-
-CREATE OPERATOR CLASS vector_text_ops
-	DEFAULT FOR TYPE text USING hnsw AS
-	OPERATOR 2 < ,
-	OPERATOR 3 <= ,
-	OPERATOR 4 = ,
-	OPERATOR 5 >= ,
-	OPERATOR 6 > ;
-
-CREATE OPERATOR CLASS vector_uuid_ops
-	DEFAULT FOR TYPE uuid USING hnsw AS
-	OPERATOR 2 < ,
-	OPERATOR 3 <= ,
-	OPERATOR 4 = ,
-	OPERATOR 5 >= ,
-	OPERATOR 6 > ;

src/hnsw.c

@@ -8,6 +8,7 @@
 #include "commands/progress.h"
 #include "commands/vacuum.h"
 #include "hnsw.h"
+#include "miscadmin.h"
 #include "utils/guc.h"
 #include "utils/selfuncs.h"
 
@@ -28,7 +29,7 @@ static relopt_kind hnsw_relopt_kind;
  * this grows bigger, we should use a shmem_request_hook and
  * RequestAddinShmemSpace() to pre-reserve space for this.
  */
-static void
+void
 HnswInitLockTranche(void)
 {
 	int		   *tranche_ids;
@@ -53,7 +54,8 @@ HnswInitLockTranche(void)
 void
 HnswInit(void)
 {
-	HnswInitLockTranche();
+	if (!process_shared_preload_libraries_in_progress)
+		HnswInitLockTranche();
 
 	hnsw_relopt_kind = add_reloption_kind();
 	add_int_reloption(hnsw_relopt_kind, "m", "Max number of connections",
@@ -200,7 +202,7 @@ hnswhandler(PG_FUNCTION_ARGS)
 	amroutine->amcanorderbyop = true;
 	amroutine->amcanbackward = false;	/* can change direction mid-scan */
 	amroutine->amcanunique = false;
-	amroutine->amcanmulticol = true;
+	amroutine->amcanmulticol = false;
 	amroutine->amoptionalkey = true;
 	amroutine->amsearcharray = false;
 	amroutine->amsearchnulls = false;

src/hnsw.h

@@ -128,7 +128,6 @@ HnswPtrDeclare(HnswElementData, HnswElementRelptr, HnswElementPtr);
 HnswPtrDeclare(HnswNeighborArray, HnswNeighborArrayRelptr, HnswNeighborArrayPtr);
 HnswPtrDeclare(HnswNeighborArrayPtr, HnswNeighborsRelptr, HnswNeighborsPtr);
 HnswPtrDeclare(char, DatumRelptr, DatumPtr);
-HnswPtrDeclare(IndexTupleData, IndexTupleRelptr, IndexTuplePtr);
 
 typedef struct HnswElementData
 {
@@ -144,7 +143,6 @@ typedef struct HnswElementData
 	OffsetNumber neighborOffno;
 	BlockNumber neighborPage;
 	DatumPtr	value;
-	IndexTuplePtr itup;
 	LWLock		lock;
 }			HnswElementData;
 
@@ -372,7 +370,7 @@ bool		HnswNormValue(FmgrInfo *procinfo, Oid collation, Datum *value, Vector * re
 Buffer		HnswNewBuffer(Relation index, ForkNumber forkNum);
 void		HnswInitPage(Buffer buf, Page page);
 void		HnswInit(void);
-List	   *HnswSearchLayer(char *base, Datum q, IndexScanDesc scan, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool inserting, HnswElement skipElement);
+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);
@@ -386,14 +384,12 @@ void		HnswAddHeapTid(HnswElement element, ItemPointer heaptid);
 void		HnswInitNeighbors(char *base, HnswElement element, int m, HnswAllocator * alloc);
 bool		HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull, ItemPointer heap_tid, bool building);
 void		HnswUpdateNeighborsOnDisk(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement e, int m, bool checkExisting, bool building);
-void		HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHeaptids, bool loadVec, Relation index);
-void		HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec, IndexScanDesc scan, bool *matches);
-void		HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element, bool useIndexTuple);
+void		HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHeaptids, bool loadVec);
+void		HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec);
+void		HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element);
 void		HnswUpdateConnection(char *base, HnswElement element, HnswCandidate * hc, int lm, int lc, int *updateIdx, Relation index, FmgrInfo *procinfo, Oid collation);
 void		HnswLoadNeighbors(HnswElement element, Relation index, int m);
-TupleDesc	HnswTupleDesc(Relation index);
-IndexTuple	HnswFormIndexTuple(Relation index, TupleDesc tupdesc, Datum value, Datum *values, bool *isnull);
-bool		HnswElementIsDuplicate(char *base, HnswElement a, HnswElement b, Relation index);
+void		HnswInitLockTranche(void);
 PGDLLEXPORT void HnswParallelBuildMain(dsm_segment *seg, shm_toc *toc);
 
 /* Index access methods */

src/hnswbuild.c

@@ -157,7 +157,6 @@ CreateGraphPages(HnswBuildState * buildstate)
 	Page		page;
 	HnswElementPtr iter = buildstate->graph->head;
 	char	   *base = buildstate->hnswarea;
-	bool		useIndexTuple = IndexRelationGetNumberOfAttributes(index) > 1;
 
 	/* Calculate sizes */
 	maxSize = HNSW_MAX_SIZE;
@@ -178,7 +177,6 @@ CreateGraphPages(HnswBuildState * buildstate)
 		Size		ntupSize;
 		Size		combinedSize;
 		Pointer		valuePtr = HnswPtrAccess(base, element->value);
-		IndexTuple	itup = HnswPtrAccess(base, element->itup);
 
 		/* Update iterator */
 		iter = element->next;
@@ -187,7 +185,7 @@ CreateGraphPages(HnswBuildState * buildstate)
 		MemSet(etup, 0, HNSW_TUPLE_ALLOC_SIZE);
 
 		/* Calculate sizes */
-		etupSize = HNSW_ELEMENT_TUPLE_SIZE(useIndexTuple ? IndexTupleSize(itup) : VARSIZE_ANY(valuePtr));
+		etupSize = HNSW_ELEMENT_TUPLE_SIZE(VARSIZE_ANY(valuePtr));
 		ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(element->level, buildstate->m);
 		combinedSize = etupSize + ntupSize + sizeof(ItemIdData);
 
@@ -195,7 +193,7 @@ CreateGraphPages(HnswBuildState * buildstate)
 		if (etupSize > HNSW_TUPLE_ALLOC_SIZE)
 			elog(ERROR, "index tuple too large");
 
-		HnswSetElementTuple(base, etup, element, useIndexTuple);
+		HnswSetElementTuple(base, etup, element);
 
 		/* Keep element and neighbors on the same page if possible */
 		if (PageGetFreeSpace(page) < etupSize || (combinedSize <= maxSize && PageGetFreeSpace(page) < combinedSize))
@@ -336,17 +334,19 @@ AddDuplicateInMemory(HnswElement element, HnswElement dup)
  * Find duplicate element
  */
 static bool
-FindDuplicateInMemory(char *base, HnswElement element, Relation index)
+FindDuplicateInMemory(char *base, HnswElement element)
 {
 	HnswNeighborArray *neighbors = HnswGetNeighbors(base, element, 0);
+	Datum		value = HnswGetValue(base, element);
 
 	for (int i = 0; i < neighbors->length; i++)
 	{
 		HnswCandidate *neighbor = &neighbors->items[i];
 		HnswElement neighborElement = HnswPtrAccess(base, neighbor->element);
+		Datum		neighborValue = HnswGetValue(base, neighborElement);
 
 		/* Exit early since ordered by distance */
-		if (!HnswElementIsDuplicate(base, element, neighborElement, index))
+		if (!datumIsEqual(value, neighborValue, false, -1))
 			return false;
 
 		/* Check for space */
@@ -406,7 +406,7 @@ UpdateGraphInMemory(FmgrInfo *procinfo, Oid collation, HnswElement element, int
 	char	   *base = buildstate->hnswarea;
 
 	/* Look for duplicate */
-	if (FindDuplicateInMemory(base, element, buildstate->index))
+	if (FindDuplicateInMemory(base, element))
 		return;
 
 	/* Add element */
@@ -471,14 +471,10 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
 	HnswGraph  *graph = buildstate->graph;
 	HnswElement element;
 	HnswAllocator *allocator = &buildstate->allocator;
-	IndexTuple	itup;
-	Size		itupSize;
-	IndexTuple	itupPtr;
+	Size		valueSize;
 	Pointer		valuePtr;
 	LWLock	   *flushLock = &graph->flushLock;
 	char	   *base = buildstate->hnswarea;
-	TupleDesc	tupdesc = HnswTupleDesc(index);
-	bool		unused;
 
 	/* Detoast once for all calls */
 	Datum		value = PointerGetDatum(PG_DETOAST_DATUM(values[0]));
@@ -491,8 +487,7 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
 	}
 
 	/* Get datum size */
-	itup = HnswFormIndexTuple(index, tupdesc, value, values, isnull);
-	itupSize = IndexTupleSize(itup);
+	valueSize = VARSIZE_ANY(DatumGetPointer(value));
 
 	/* Ensure graph not flushed when inserting */
 	LWLockAcquire(flushLock, LW_SHARED);
@@ -539,7 +534,7 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
 
 	/* Ok, we can proceed to allocate the element */
 	element = HnswInitElement(base, heaptid, buildstate->m, buildstate->ml, buildstate->maxLevel, allocator);
-	itupPtr = HnswAlloc(allocator, itupSize);
+	valuePtr = HnswAlloc(allocator, valueSize);
 
 	/*
 	 * We have now allocated the space needed for the element, so we don't
@@ -548,10 +543,8 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
 	 */
 	LWLockRelease(&graph->allocatorLock);
 
-	/* Copy the index tuple */
-	memcpy(itupPtr, itup, itupSize);
-	HnswPtrStore(base, element->itup, itupPtr);
-	valuePtr = DatumGetPointer(index_getattr(itupPtr, 1, tupdesc, &unused));
+	/* Copy the datum */
+	memcpy(valuePtr, DatumGetPointer(value), valueSize);
 	HnswPtrStore(base, element->value, valuePtr);
 
 	/* Create a lock for the element */
@@ -608,6 +601,9 @@ BuildCallback(Relation index, CALLBACK_ITEM_POINTER, Datum *values,
 static void
 InitGraph(HnswGraph * graph, char *base, long memoryTotal)
 {
+	/* Initialize the lock tranche if needed */
+	HnswInitLockTranche();
+
 	HnswPtrStore(base, graph->head, (HnswElement) NULL);
 	HnswPtrStore(base, graph->entryPoint, (HnswElement) NULL);
 	graph->memoryUsed = 0;
@@ -676,19 +672,6 @@ InitBuildState(HnswBuildState * buildstate, Relation heap, Relation index, Index
 	buildstate->efConstruction = HnswGetEfConstruction(index);
 	buildstate->dimensions = TupleDescAttr(index->rd_att, 0)->atttypmod;
 
-	/* For now */
-	if (IndexRelationGetNumberOfKeyAttributes(index) > 3)
-		elog(ERROR, "index cannot have more than three columns");
-
-	if (!OidIsValid(index_getprocid(index, 1, HNSW_DISTANCE_PROC)))
-		elog(ERROR, "first column must be a vector");
-
-	for (int i = 1; i < IndexRelationGetNumberOfKeyAttributes(index); i++)
-	{
-		if (OidIsValid(index_getprocid(index, i + 1, HNSW_DISTANCE_PROC)))
-			elog(ERROR, "column %d cannot be a vector", i + 1);
-	}
-
 	/* Require column to have dimensions to be indexed */
 	if (buildstate->dimensions < 0)
 		elog(ERROR, "column does not have dimensions");
@@ -994,6 +977,14 @@ HnswBeginParallel(HnswBuildState * buildstate, bool isconcurrent, int request)
 	/* Report less than allocated so never fails */
 	InitGraph(&hnswshared->graphData, hnswarea, esthnswarea - 1024 * 1024);
 
+	/*
+	 * Avoid base address for relptr for Postgres < 14.5
+	 * https://github.com/postgres/postgres/commit/7201cd18627afc64850537806da7f22150d1a83b
+	 */
+#if PG_VERSION_NUM < 140005
+	hnswshared->graphData.memoryUsed += MAXALIGN(1);
+#endif
+
 	shm_toc_insert(pcxt->toc, PARALLEL_KEY_HNSW_SHARED, hnswshared);
 	shm_toc_insert(pcxt->toc, PARALLEL_KEY_HNSW_AREA, hnswarea);
 

src/hnswinsert.c

@@ -136,12 +136,9 @@ AddElementOnDisk(Relation index, HnswElement e, int m, BlockNumber insertPage, B
 	OffsetNumber freeNeighborOffno = InvalidOffsetNumber;
 	BlockNumber newInsertPage = InvalidBlockNumber;
 	char	   *base = NULL;
-	bool		useIndexTuple = IndexRelationGetNumberOfAttributes(index) > 1;
-	Pointer		valuePtr = HnswPtrAccess(base, e->value);
-	IndexTuple	itup = HnswPtrAccess(base, e->itup);
 
 	/* Calculate sizes */
-	etupSize = HNSW_ELEMENT_TUPLE_SIZE(useIndexTuple ? IndexTupleSize(itup) : VARSIZE_ANY(valuePtr));
+	etupSize = HNSW_ELEMENT_TUPLE_SIZE(VARSIZE_ANY(HnswPtrAccess(base, e->value)));
 	ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(e->level, m);
 	combinedSize = etupSize + ntupSize + sizeof(ItemIdData);
 	maxSize = HNSW_MAX_SIZE;
@@ -149,7 +146,7 @@ AddElementOnDisk(Relation index, HnswElement e, int m, BlockNumber insertPage, B
 
 	/* Prepare element tuple */
 	etup = palloc0(etupSize);
-	HnswSetElementTuple(base, etup, e, useIndexTuple);
+	HnswSetElementTuple(base, etup, e);
 
 	/* Prepare neighbor tuple */
 	ntup = palloc0(ntupSize);
@@ -507,14 +504,16 @@ FindDuplicateOnDisk(Relation index, HnswElement element, bool building)
 {
 	char	   *base = NULL;
 	HnswNeighborArray *neighbors = HnswGetNeighbors(base, element, 0);
+	Datum		value = HnswGetValue(base, element);
 
 	for (int i = 0; i < neighbors->length; i++)
 	{
 		HnswCandidate *neighbor = &neighbors->items[i];
 		HnswElement neighborElement = HnswPtrAccess(base, neighbor->element);
+		Datum		neighborValue = HnswGetValue(base, neighborElement);
 
 		/* Exit early since ordered by distance */
-		if (!HnswElementIsDuplicate(base, element, neighborElement, index))
+		if (!datumIsEqual(value, neighborValue, false, -1))
 			return false;
 
 		if (AddDuplicateOnDisk(index, element, neighborElement, building))
@@ -565,10 +564,6 @@ HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull,
 	Oid			collation = index->rd_indcollation[0];
 	LOCKMODE	lockmode = ShareLock;
 	char	   *base = NULL;
-	TupleDesc	tupdesc = HnswTupleDesc(index);
-	bool		unused;
-	IndexTuple	itup;
-	Pointer		valuePtr;
 
 	/*
 	 * Get a shared lock. This allows vacuum to ensure no in-flight inserts
@@ -582,10 +577,7 @@ HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull,
 
 	/* Create an element */
 	element = HnswInitElement(base, heap_tid, m, HnswGetMl(m), HnswGetMaxLevel(m), NULL);
-	itup = HnswFormIndexTuple(index, tupdesc, value, values, isnull);
-	HnswPtrStore(base, element->itup, itup);
-	valuePtr = DatumGetPointer(index_getattr(itup, 1, tupdesc, &unused));
-	HnswPtrStore(base, element->value, valuePtr);
+	HnswPtrStore(base, element->value, DatumGetPointer(value));
 
 	/* Prevent concurrent inserts when likely updating entry point */
 	if (entryPoint == NULL || element->level > entryPoint->level)

src/hnswscan.c

@@ -33,12 +33,11 @@ GetScanItems(IndexScanDesc scan, Datum q)
 
 	for (int lc = entryPoint->level; lc >= 1; lc--)
 	{
-		w = HnswSearchLayer(base, q, NULL, ep, 1, lc, index, procinfo, collation, m, false, NULL);
+		w = HnswSearchLayer(base, q, ep, 1, lc, index, procinfo, collation, m, false, NULL);
 		ep = w;
 	}
 
-	/* Only pass scan to check matches for layer 0 */
-	return HnswSearchLayer(base, q, scan, ep, hnsw_ef_search, 0, index, procinfo, collation, m, false, NULL);
+	return HnswSearchLayer(base, q, ep, hnsw_ef_search, 0, index, procinfo, collation, m, false, NULL);
 }
 
 /*
@@ -203,7 +202,7 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
 		MemoryContextSwitchTo(oldCtx);
 
 		scan->xs_heaptid = *heaptid;
-		scan->xs_recheck = scan->numberOfKeys > 0;
+		scan->xs_recheck = false;
 		scan->xs_recheckorderby = false;
 		return true;
 	}

src/hnswutils.c

@@ -3,7 +3,6 @@
 #include <math.h>
 
 #include "access/generic_xlog.h"
-#include "access/relscan.h"
 #include "hnsw.h"
 #include "lib/pairingheap.h"
 #include "storage/bufmgr.h"
@@ -12,10 +11,6 @@
 #include "utils/rel.h"
 #include "vector.h"
 
-#if PG_VERSION_NUM < 130000
-#define TYPSTORAGE_PLAIN 'p'
-#endif
-
 #if PG_VERSION_NUM >= 130000
 #include "common/hashfn.h"
 #else
@@ -300,82 +295,6 @@ HnswInitElementFromBlock(BlockNumber blkno, OffsetNumber offno)
 	return element;
 }
 
-/*
- * Get the tuple descriptor
- */
-TupleDesc
-HnswTupleDesc(Relation index)
-{
-	TupleDesc	tupdesc = CreateTupleDescCopyConstr(RelationGetDescr(index));
-
-	/* Prevent compression */
-	TupleDescAttr(tupdesc, 0)->attstorage = TYPSTORAGE_PLAIN;
-
-	return tupdesc;
-}
-
-/*
- * Form an index tuple
- */
-IndexTuple
-HnswFormIndexTuple(Relation index, TupleDesc tupdesc, Datum value, Datum *values, bool *isnull)
-{
-	Size		size = sizeof(Datum) * IndexRelationGetNumberOfAttributes(index);
-	Datum	   *newValues = palloc(size);
-
-	memcpy(newValues, values, size);
-	newValues[0] = value;
-
-	return index_form_tuple(tupdesc, newValues, isnull);
-}
-
-/*
- * Check if elements are duplicates
- */
-bool
-HnswElementIsDuplicate(char *base, HnswElement a, HnswElement b, Relation index)
-{
-	if (IndexRelationGetNumberOfAttributes(index) == 1)
-	{
-		Datum		value = HnswGetValue(base, a);
-		Datum		value2 = HnswGetValue(base, b);
-
-		return datumIsEqual(value, value2, false, -1);
-	}
-	else
-	{
-		TupleDesc	tupdesc = RelationGetDescr(index);
-		IndexTuple	itup = HnswPtrAccess(base, a->itup);
-		IndexTuple	itup2 = HnswPtrAccess(base, b->itup);
-
-		for (int i = 0; i < tupdesc->natts; i++)
-		{
-			Datum		value;
-			Datum		value2;
-			bool		isnull;
-			bool		isnull2;
-
-			value = index_getattr(itup, i + 1, tupdesc, &isnull);
-			value2 = index_getattr(itup2, i + 1, tupdesc, &isnull2);
-
-			if (isnull || isnull2)
-			{
-				if (isnull != isnull2)
-					return false;
-			}
-			else
-			{
-				Form_pg_attribute att = TupleDescAttr(tupdesc, i);
-
-				if (!datumIsEqual(value, value2, att->attbyval, att->attlen))
-					return false;
-			}
-		}
-
-		return true;
-	}
-}
-
 /*
  * Get the metapage info
  */
@@ -485,8 +404,10 @@ HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, Bloc
  * Set element tuple, except for neighbor info
  */
 void
-HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element, bool useIndexTuple)
+HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element)
 {
+	Pointer		valuePtr = HnswPtrAccess(base, element->value);
+
 	etup->type = HNSW_ELEMENT_TUPLE_TYPE;
 	etup->level = element->level;
 	etup->deleted = 0;
@@ -497,19 +418,7 @@ HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element, bool
 		else
 			ItemPointerSetInvalid(&etup->heaptids[i]);
 	}
-
-	if (useIndexTuple)
-	{
-		IndexTuple	itup = HnswPtrAccess(base, element->itup);
-
-		memcpy(&etup->data, itup, IndexTupleSize(itup));
-	}
-	else
-	{
-		Pointer		valuePtr = HnswPtrAccess(base, element->value);
-
-		memcpy(&etup->data, valuePtr, VARSIZE_ANY(valuePtr));
-	}
+	memcpy(&etup->data, valuePtr, VARSIZE_ANY(valuePtr));
 }
 
 /*
@@ -613,7 +522,7 @@ HnswLoadNeighbors(HnswElement element, Relation index, int m)
  * Load an element from a tuple
  */
 void
-HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHeaptids, bool loadVec, Relation index)
+HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHeaptids, bool loadVec)
 {
 	element->level = etup->level;
 	element->deleted = etup->deleted;
@@ -636,64 +545,17 @@ HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHe
 	if (loadVec)
 	{
 		char	   *base = NULL;
+		Datum		value = datumCopy(PointerGetDatum(&etup->data), false, -1);
 
-		if (IndexRelationGetNumberOfAttributes(index) > 1)
-		{
-			TupleDesc	tupdesc = RelationGetDescr(index);
-			bool		unused;
-			IndexTuple	itup = CopyIndexTuple((IndexTuple) &etup->data);
-			Datum		value = index_getattr(itup, 1, tupdesc, &unused);
-
-			HnswPtrStore(base, element->itup, itup);
-			HnswPtrStore(base, element->value, DatumGetPointer(value));
-		}
-		else
-		{
-			Datum		value = datumCopy(PointerGetDatum(&etup->data), false, -1);
-
-			HnswPtrStore(base, element->value, DatumGetPointer(value));
-		}
+		HnswPtrStore(base, element->value, DatumGetPointer(value));
 	}
 }
 
-/*
- * Check if an element matches
- */
-static bool
-HnswCheckMatches(Relation index, HnswElementTuple etup, IndexScanDesc scan)
-{
-	if (scan == NULL)
-		return true;
-
-	for (int i = 0; i < scan->numberOfKeys; i++)
-	{
-		IndexTuple	itup = (IndexTuple) &etup->data;
-		TupleDesc	tupdesc = RelationGetDescr(index);
-		ScanKey		key = &scan->keyData[i];
-		bool		isnull;
-		Datum		value = index_getattr(itup, key->sk_attno, tupdesc, &isnull);
-		bool		attnull = key->sk_flags & SK_ISNULL;
-
-		if (isnull || attnull)
-		{
-			if (isnull != attnull)
-				return false;
-		}
-		else
-		{
-			if (!DatumGetBool(FunctionCall2Coll(&key->sk_func, key->sk_collation, value, key->sk_argument)))
-				return false;
-		}
-	}
-
-	return true;
-}
-
 /*
  * Load an element and optionally get its distance from q
  */
 void
-HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec, IndexScanDesc scan, bool *matches)
+HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec)
 {
 	Buffer		buf;
 	Page		page;
@@ -709,29 +571,11 @@ HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation index,
 	Assert(HnswIsElementTuple(etup));
 
 	/* Load element */
-	HnswLoadElementFromTuple(element, etup, true, loadVec, index);
+	HnswLoadElementFromTuple(element, etup, true, loadVec);
 
 	/* Calculate distance */
 	if (distance != NULL)
-	{
-		Datum		value;
-
-		if (IndexRelationGetNumberOfAttributes(index) > 1)
-		{
-			IndexTuple	itup = (IndexTuple) &etup->data;
-			TupleDesc	tupdesc = RelationGetDescr(index);
-			bool		unused;
-
-			value = index_getattr(itup, 1, tupdesc, &unused);
-		}
-		else
-			value = PointerGetDatum(&etup->data);
-
-		*distance = (float) DatumGetFloat8(FunctionCall2Coll(procinfo, collation, *q, value));
-	}
-
-	if (matches != NULL)
-		*matches = HnswCheckMatches(index, etup, scan);
+		*distance = (float) DatumGetFloat8(FunctionCall2Coll(procinfo, collation, *q, PointerGetDatum(&etup->data)));
 
 	UnlockReleaseBuffer(buf);
 }
@@ -760,7 +604,7 @@ HnswEntryCandidate(char *base, HnswElement entryPoint, Datum q, Relation index,
 	if (index == NULL)
 		hc->distance = GetCandidateDistance(base, hc, q, procinfo, collation);
 	else
-		HnswLoadElement(entryPoint, &hc->distance, &q, index, procinfo, collation, loadVec, NULL, NULL);
+		HnswLoadElement(entryPoint, &hc->distance, &q, index, procinfo, collation, loadVec);
 	return hc;
 }
 
@@ -878,14 +722,12 @@ CountElement(char *base, HnswElement skipElement, HnswCandidate * hc)
  * Algorithm 2 from paper
  */
 List *
-HnswSearchLayer(char *base, Datum q, IndexScanDesc scan, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool inserting, HnswElement skipElement)
+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;
-	uint64		additional = 0;
-	uint64		maxAdditional = (scan != NULL && scan->numberOfKeys > 0) ? 100 * ef : 0;
 	visited_hash v;
 	ListCell   *lc2;
 	HnswNeighborArray *neighborhoodData = NULL;
@@ -957,18 +799,14 @@ HnswSearchLayer(char *base, Datum q, IndexScanDesc scan, List *ep, int ef, int l
 			if (!visited)
 			{
 				float		eDistance;
-				bool		eMatches;
 				HnswElement eElement = HnswPtrAccess(base, e->element);
 
 				f = ((HnswPairingHeapNode *) pairingheap_first(W))->inner;
 
 				if (index == NULL)
-				{
 					eDistance = GetCandidateDistance(base, e, q, procinfo, collation);
-					eMatches = true;
-				}
 				else
-					HnswLoadElement(eElement, &eDistance, &q, index, procinfo, collation, inserting, scan, &eMatches);
+					HnswLoadElement(eElement, &eDistance, &q, index, procinfo, collation, inserting);
 
 				Assert(!eElement->deleted);
 
@@ -987,16 +825,6 @@ HnswSearchLayer(char *base, Datum q, IndexScanDesc scan, List *ep, int ef, int l
 					pairingheap_add(C, &(CreatePairingHeapNode(ec)->ph_node));
 					pairingheap_add(W, &(CreatePairingHeapNode(ec)->ph_node));
 
-					/*
-					 * Do not count elements that do not match filter towards
-					 * ef
-					 */
-					if (!eMatches)
-					{
-						if ((++additional) <= maxAdditional)
-							continue;
-					}
-
 					/*
 					 * Do not count elements being deleted towards ef when
 					 * vacuuming. It would be ideal to do this for inserts as
@@ -1271,7 +1099,7 @@ HnswUpdateConnection(char *base, HnswElement element, HnswCandidate * hc, int lm
 				HnswElement hc3Element = HnswPtrAccess(base, hc3->element);
 
 				if (HnswPtrIsNull(base, hc3Element->value))
-					HnswLoadElement(hc3Element, &hc3->distance, &q, index, procinfo, collation, true, NULL, NULL);
+					HnswLoadElement(hc3Element, &hc3->distance, &q, index, procinfo, collation, true);
 				else
 					hc3->distance = GetCandidateDistance(base, hc3, q, procinfo, collation);
 
@@ -1393,7 +1221,7 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
 	/* 1st phase: greedy search to insert level */
 	for (int lc = entryLevel; lc >= level + 1; lc--)
 	{
-		w = HnswSearchLayer(base, q, NULL, ep, 1, lc, index, procinfo, collation, m, true, skipElement);
+		w = HnswSearchLayer(base, q, ep, 1, lc, index, procinfo, collation, m, true, skipElement);
 		ep = w;
 	}
 
@@ -1411,7 +1239,7 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
 		List	   *neighbors;
 		List	   *lw;
 
-		w = HnswSearchLayer(base, q, NULL, ep, efConstruction, lc, index, procinfo, collation, m, true, skipElement);
+		w = HnswSearchLayer(base, q, ep, efConstruction, lc, index, procinfo, collation, m, true, skipElement);
 
 		/* Elements being deleted or skipped can help with search */
 		/* but should be removed before selecting neighbors */

src/hnswvacuum.c

@@ -256,7 +256,7 @@ RepairGraphEntryPoint(HnswVacuumState * vacuumstate)
 		LockPage(index, HNSW_UPDATE_LOCK, ShareLock);
 
 		/* Load element */
-		HnswLoadElement(highestPoint, NULL, NULL, index, vacuumstate->procinfo, vacuumstate->collation, true, NULL, NULL);
+		HnswLoadElement(highestPoint, NULL, NULL, index, vacuumstate->procinfo, vacuumstate->collation, true);
 
 		/* 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, vacuumstate->procinfo, vacuumstate->collation, true, NULL, NULL);
+			HnswLoadElement(entryPoint, NULL, NULL, index, vacuumstate->procinfo, vacuumstate->collation, true);
 
 			if (NeedsUpdated(vacuumstate, entryPoint))
 			{
@@ -370,7 +370,7 @@ RepairGraph(HnswVacuumState * vacuumstate)
 
 			/* Create an element */
 			element = HnswInitElementFromBlock(blkno, offno);
-			HnswLoadElementFromTuple(element, etup, false, true, index);
+			HnswLoadElementFromTuple(element, etup, false, true);
 
 			elements = lappend(elements, element);
 		}
@@ -440,7 +440,6 @@ MarkDeleted(HnswVacuumState * vacuumstate)
 	BlockNumber insertPage = InvalidBlockNumber;
 	Relation	index = vacuumstate->index;
 	BufferAccessStrategy bas = vacuumstate->bas;
-	bool		useIndexTuple = IndexRelationGetNumberOfAttributes(index);
 
 	/*
 	 * Wait for index scans to complete. Scans before this point may contain
@@ -522,18 +521,7 @@ MarkDeleted(HnswVacuumState * vacuumstate)
 
 			/* Overwrite element */
 			etup->deleted = 1;
-			if (useIndexTuple)
-			{
-				IndexTuple	itup = (IndexTuple) &etup->data;
-
-				MemSet(itup, 0, IndexTupleSize(itup));
-			}
-			else
-			{
-				Vector	   *vec = (Vector *) (&etup->data);
-
-				MemSet(vec, 0, VARSIZE_ANY(vec));
-			}
+			MemSet(&etup->data, 0, VARSIZE_ANY(&etup->data));
 
 			/* Overwrite neighbors */
 			for (int i = 0; i < ntup->count; i++)

src/ivfbuild.c

@@ -904,6 +904,27 @@ IvfflatBeginParallel(IvfflatBuildState * buildstate, bool isconcurrent, int requ
 	WaitForParallelWorkersToAttach(pcxt);
 }
 
+/*
+ * Compute parallel workers
+ */
+static int
+ComputeParallelWorkers(Relation heap, Relation index)
+{
+	int			parallel_workers;
+
+	/* Make sure it's safe to use parallel workers */
+	parallel_workers = plan_create_index_workers(RelationGetRelid(heap), RelationGetRelid(index));
+	if (parallel_workers == 0)
+		return 0;
+
+	/* Use parallel_workers storage parameter on table if set */
+	parallel_workers = RelationGetParallelWorkers(heap, -1);
+	if (parallel_workers != -1)
+		return Min(parallel_workers, max_parallel_maintenance_workers);
+
+	return max_parallel_maintenance_workers;
+}
+
 /*
  * Scan table for tuples to index
  */
@@ -923,7 +944,7 @@ AssignTuples(IvfflatBuildState * buildstate)
 
 	/* Calculate parallel workers */
 	if (buildstate->heap != NULL)
-		parallel_workers = plan_create_index_workers(RelationGetRelid(buildstate->heap), RelationGetRelid(buildstate->index));
+		parallel_workers = ComputeParallelWorkers(buildstate->heap, buildstate->index);
 
 	/* Attempt to launch parallel worker scan when required */
 	if (parallel_workers > 0)

test/t/020_hnsw_filtering.pl

@@ -1,154 +0,0 @@
-use strict;
-use warnings;
-use PostgresNode;
-use TestLib;
-use Test::More;
-
-my $node;
-my @queries = ();
-my @cs = ();
-my @expected;
-my $limit = 20;
-my $dim = 3;
-my $array_sql = join(",", ('random()') x $dim);
-my $nc = 50;
-my @types = ("int4", "int8", "text", "uuid", "varchar");
-my $type = $types[rand(@types)];
-
-sub cast_c
-{
-	my ($c) = @_;
-
-	if ($type eq "uuid")
-	{
-		return "('00000000-0000-0000-0000-0000000000' || LPAD(($c)::text, 2, '0'))::uuid";
-	}
-	else
-	{
-		return "($c)::$type";
-	}
-}
-
-sub test_recall
-{
-	my ($min, $operator) = @_;
-	my $correct = 0;
-	my $total = 0;
-
-	my $explain = $node->safe_psql("postgres", qq(
-		SET enable_seqscan = off;
-		EXPLAIN ANALYZE SELECT i FROM tst WHERE c = @{[cast_c($cs[0])]} ORDER BY v $operator '$queries[0]' LIMIT $limit;
-	));
-	like($explain, qr/Index Cond/);
-
-	for my $i (0 .. $#queries)
-	{
-		my $actual = $node->safe_psql("postgres", qq(
-			SET enable_seqscan = off;
-			SELECT i FROM tst WHERE c = @{[cast_c($cs[$i])]} ORDER BY v $operator '$queries[$i]' LIMIT $limit;
-		));
-		my @actual_ids = split("\n", $actual);
-		my %actual_set = map { $_ => 1 } @actual_ids;
-
-		is(scalar(@actual_ids), $limit);
-
-		my @expected_ids = split("\n", $expected[$i]);
-
-		foreach (@expected_ids)
-		{
-			if (exists($actual_set{$_}))
-			{
-				$correct++;
-			}
-			$total++;
-		}
-	}
-
-	cmp_ok($correct / $total, ">=", $min, $operator);
-}
-
-# Initialize node
-$node = get_new_node('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), c $type, c2 $type);");
-$node->safe_psql("postgres", qq(
-	INSERT INTO tst SELECT i, ARRAY[$array_sql], @{[cast_c("i % $nc")]}, @{[cast_c("i % $nc")]} FROM generate_series(1, 10000) i;
-));
-$node->safe_psql("postgres", "CREATE INDEX ON tst USING hnsw (v vector_l2_ops, c, c2);");
-$node->safe_psql("postgres", qq(
-	INSERT INTO tst SELECT i, ARRAY[$array_sql], @{[cast_c("i % $nc")]}, @{[cast_c("i % $nc")]} FROM generate_series(1, 10000) i;
-));
-$node->safe_psql("postgres", "ANALYZE tst;");
-
-# Generate queries
-for (1 .. 20)
-{
-	my @r = ();
-	for (1 .. $dim)
-	{
-		push(@r, rand());
-	}
-	push(@queries, "[" . join(",", @r) . "]");
-	push(@cs, int(rand() * $nc));
-}
-
-# Get exact results
-@expected = ();
-for my $i (0 .. $#queries)
-{
-	my $res = $node->safe_psql("postgres", qq(
-		SET enable_indexscan = off;
-		SELECT i FROM tst WHERE c = @{[cast_c($cs[$i])]} ORDER BY v <-> '$queries[$i]' LIMIT $limit;
-	));
-	push(@expected, $res);
-}
-
-# Test recall
-test_recall(0.99, '<->');
-
-# Test no conditions
-my $explain = $node->safe_psql("postgres", qq(
-	EXPLAIN ANALYZE SELECT i FROM tst ORDER BY v <-> '$queries[0]' LIMIT $limit;
-));
-like($explain, qr/Index Scan/);
-
-# Test range
-$explain = $node->safe_psql("postgres", qq(
-	EXPLAIN ANALYZE SELECT i FROM tst WHERE c >= @{[cast_c(1)]} AND c <= @{[cast_c(3)]} ORDER BY v <-> '$queries[0]' LIMIT $limit;
-));
-like($explain, qr/Index Cond: \(\(\S+ >= \S+\) AND \(\S+ <= \S+\)\)/);
-
-# Test multiple conditions
-$explain = $node->safe_psql("postgres", qq(
-	EXPLAIN ANALYZE SELECT i FROM tst WHERE c = @{[cast_c($cs[0])]} AND c2 = @{[cast_c($cs[0])]} ORDER BY v <-> '$queries[0]' LIMIT $limit;
-));
-like($explain, qr/Index Cond: \(\(\S+ = \S+\) AND \(\S+ = \S+\)\)/);
-
-# Test no order
-$explain = $node->safe_psql("postgres", qq(
-	EXPLAIN ANALYZE SELECT i FROM tst WHERE c = @{[cast_c($cs[0])]} LIMIT $limit;
-));
-like($explain, qr/Seq Scan/);
-
-# Test vacuum
-$node->safe_psql("postgres", "DELETE FROM tst WHERE c > @{[cast_c(5)]};");
-$node->safe_psql("postgres", "VACUUM tst;");
-
-# Test columns
-my ($ret, $stdout, $stderr) = $node->psql("postgres", "CREATE INDEX ON tst USING hnsw (c);");
-like($stderr, qr/first column must be a vector/);
-
-($ret, $stdout, $stderr) = $node->psql("postgres", "CREATE INDEX ON tst USING hnsw (c, v vector_l2_ops);");
-like($stderr, qr/first column must be a vector/);
-
-($ret, $stdout, $stderr) = $node->psql("postgres", "CREATE INDEX ON tst USING hnsw (v vector_l2_ops, c, c, c);");
-like($stderr, qr/index cannot have more than three columns/);
-
-($ret, $stdout, $stderr) = $node->psql("postgres", "CREATE INDEX ON tst USING hnsw (v vector_l2_ops, v vector_l2_ops);");
-like($stderr, qr/column 2 cannot be a vector/);
-
-done_testing();