Improved test [skip ci]

There are no references to anything that's in generic_xlog.h in the
header files.

.github/workflows/build.yml

@@ -20,8 +20,6 @@ jobs:
             os: ubuntu-20.04
           - postgres: 12
             os: ubuntu-20.04
-          - postgres: 11
-            os: ubuntu-20.04
     steps:
       - uses: actions/checkout@v4
       - uses: ankane/setup-postgres@v1
@@ -62,7 +60,7 @@ jobs:
           wget -q https://github.com/postgres/postgres/archive/refs/tags/REL_14_5.tar.gz
           tar xf REL_14_5.tar.gz
       - run: make prove_installcheck PROVE_FLAGS="-I ./postgres-REL_14_5/src/test/perl" PERL5LIB="/Users/runner/perl5/lib/perl5"
-      - run: make clean && /usr/local/opt/llvm@15/bin/scan-build --status-bugs make
+      - run: make clean && /usr/local/opt/llvm@15/bin/scan-build --status-bugs make PG_CFLAGS="-DUSE_ASSERT_CHECKING"
   windows:
     runs-on: windows-latest
     if: ${{ !startsWith(github.ref_name, 'mac') }}
@@ -83,10 +81,10 @@ jobs:
     if: ${{ !startsWith(github.ref_name, 'mac') && !startsWith(github.ref_name, 'windows') }}
     runs-on: ubuntu-latest
     container:
-      image: debian:11
+      image: debian:12
       options: --platform linux/386
     steps:
-      - run: apt-get update && apt-get install -y build-essential git libipc-run-perl postgresql-13 postgresql-server-dev-13 sudo
+      - run: apt-get update && apt-get install -y build-essential git libipc-run-perl postgresql-15 postgresql-server-dev-15 sudo
       - run: service postgresql start
       - run: |
           git clone https://github.com/${{ github.repository }}.git pgvector

CHANGELOG.md

@@ -1,11 +1,17 @@
-## 0.5.2 (unreleased)
+## 0.6.0 (unreleased)
 
+If upgrading with Postgres < 13, see [this note](https://github.com/pgvector/pgvector#060).
+
+- Changed storage for vector from `extended` to `external`
 - Improved performance of HNSW
-- Added support for on-disk parallel index builds for HNSW
+- Added support for parallel index builds for HNSW
+- Added `hamming_distance` function
+- Added validation for GUC parameters
 - Reduced memory usage for HNSW index builds
 - Reduced WAL generation for HNSW index builds
 - Fixed error with logical replication
 - Fixed `invalid memory alloc request size` error with HNSW index build
+- Dropped support for Postgres 11
 
 ## 0.5.1 (2023-10-10)
 

META.json

@@ -12,7 +12,7 @@
 	"prereqs": {
 		"runtime": {
 			"requires": {
-				"PostgreSQL": "11.0.0"
+				"PostgreSQL": "12.0.0"
 			}
 		}
 	},

README.md

@@ -729,6 +729,16 @@ SELECT extversion FROM pg_extension WHERE extname = 'vector';
 
 ## Upgrade Notes
 
+### 0.6.0 [unreleased]
+
+If upgrading with Postgres < 13, remove this line from `sql/vector--0.5.1--0.6.0.sql`:
+
+```sql
+ALTER TYPE vector SET (STORAGE = external);
+```
+
+Then run `make install` and `ALTER EXTENSION vector UPDATE;`.
+
 ### 0.4.0
 
 If upgrading with Postgres < 13, remove this line from `sql/vector--0.3.2--0.4.0.sql`:

sql/vector--0.5.1--0.6.0.sql

@@ -0,0 +1,8 @@
+-- complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "ALTER EXTENSION vector UPDATE TO '0.6.0'" to load this file. \quit
+
+-- remove this single line for Postgres < 13
+ALTER TYPE vector SET (STORAGE = external);
+
+CREATE FUNCTION hamming_distance(bytea, bytea) RETURNS float8
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;

sql/vector.sql

@@ -26,7 +26,7 @@ CREATE TYPE vector (
 	TYPMOD_IN = vector_typmod_in,
 	RECEIVE   = vector_recv,
 	SEND      = vector_send,
-	STORAGE   = extended
+	STORAGE   = external
 );
 
 -- functions
@@ -290,3 +290,8 @@ 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);
+
+-- bytea functions
+
+CREATE FUNCTION hamming_distance(bytea, bytea) RETURNS float8
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;

src/hnsw.c

@@ -4,25 +4,57 @@
 #include <math.h>
 
 #include "access/amapi.h"
+#include "access/reloptions.h"
+#include "commands/progress.h"
 #include "commands/vacuum.h"
 #include "hnsw.h"
 #include "utils/guc.h"
 #include "utils/selfuncs.h"
 
-#if PG_VERSION_NUM >= 120000
+#if PG_VERSION_NUM < 150000
-#include "commands/progress.h"
+#define MarkGUCPrefixReserved(x) EmitWarningsOnPlaceholders(x)
 #endif
 
 int			hnsw_ef_search;
-bool		hnsw_enable_parallel_build;
+int			hnsw_lock_tranche_id;
 static relopt_kind hnsw_relopt_kind;
 
+/*
+ * Assign a tranche ID for our LWLocks. This only needs to be done by one
+ * backend, as the tranche ID is remembered in shared memory.
+ *
+ * This shared memory area is very small, so we just allocate it from the
+ * "slop" that PostgreSQL reserves for small allocations like this. If
+ * this grows bigger, we should use a shmem_request_hook and
+ * RequestAddinShmemSpace() to pre-reserve space for this.
+ */
+static void
+HnswInitLockTranche(void)
+{
+	int		   *tranche_ids;
+	bool		found;
+
+	LWLockAcquire(AddinShmemInitLock, LW_EXCLUSIVE);
+	tranche_ids = ShmemInitStruct("hnsw LWLock ids",
+								  sizeof(int) * 1,
+								  &found);
+	if (!found)
+		tranche_ids[0] = LWLockNewTrancheId();
+	hnsw_lock_tranche_id = tranche_ids[0];
+	LWLockRelease(AddinShmemInitLock);
+
+	/* Per-backend registration of the tranche ID */
+	LWLockRegisterTranche(hnsw_lock_tranche_id, "HnswBuild");
+}
+
 /*
  * Initialize index options and variables
  */
 void
 HnswInit(void)
 {
+	HnswInitLockTranche();
+
 	hnsw_relopt_kind = add_reloption_kind();
 	add_int_reloption(hnsw_relopt_kind, "m", "Max number of connections",
 					  HNSW_DEFAULT_M, HNSW_MIN_M, HNSW_MAX_M
@@ -41,16 +73,12 @@ 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);
 
-	/* Behind a variable for now since can be slower than building in memory */
+	MarkGUCPrefixReserved("hnsw");
-	DefineCustomBoolVariable("hnsw.enable_parallel_build", "Enables or disables building indexes in parallel",
-							 NULL, &hnsw_enable_parallel_build,
-							 false, PGC_USERSET, 0, NULL, NULL, NULL);
 }
 
 /*
  * Get the name of index build phase
  */
-#if PG_VERSION_NUM >= 120000
 static char *
 hnswbuildphasename(int64 phasenum)
 {
@@ -64,7 +92,6 @@ hnswbuildphasename(int64 phasenum)
 			return NULL;
 	}
 }
-#endif
 
 /*
  * Estimate the cost of an index scan
@@ -79,9 +106,6 @@ hnswcostestimate(PlannerInfo *root, IndexPath *path, double loop_count,
 	int			m;
 	int			entryLevel;
 	Relation	index;
-#if PG_VERSION_NUM < 120000
-	List	   *qinfos;
-#endif
 
 	/* Never use index without order */
 	if (path->indexorderbys == NULL)
@@ -94,20 +118,6 @@ hnswcostestimate(PlannerInfo *root, IndexPath *path, double loop_count,
 		return;
 	}
 
-	/*
-	 * Do not use index if no limit or limit + offset > ef_search unless
-	 * enable_seqscan = off
-	 */
-	if (root->limit_tuples < 0 || root->limit_tuples > hnsw_ef_search)
-	{
-		*indexStartupCost = 1.0e10 - 1;
-		*indexTotalCost = 1.0e10 - 1;
-		*indexSelectivity = 0;
-		*indexCorrelation = 0;
-		*indexPages = 0;
-		return;
-	}
-
 	MemSet(&costs, 0, sizeof(costs));
 
 	index = index_open(path->indexinfo->indexoid, NoLock);
@@ -121,12 +131,7 @@ hnswcostestimate(PlannerInfo *root, IndexPath *path, double loop_count,
 	/* Account for number of tuples (or entry level), m, and ef_search */
 	costs.numIndexTuples = (entryLevel + 2) * m;
 
-#if PG_VERSION_NUM >= 120000
 	genericcostestimate(root, path, loop_count, &costs);
-#else
-	qinfos = deconstruct_indexquals(path);
-	genericcostestimate(root, path, loop_count, qinfos, &costs);
-#endif
 
 	/* Use total cost since most work happens before first tuple is returned */
 	*indexStartupCost = costs.indexTotalCost;
@@ -220,9 +225,7 @@ hnswhandler(PG_FUNCTION_ARGS)
 	amroutine->amcostestimate = hnswcostestimate;
 	amroutine->amoptions = hnswoptions;
 	amroutine->amproperty = NULL;	/* TODO AMPROP_DISTANCE_ORDERABLE */
-#if PG_VERSION_NUM >= 120000
 	amroutine->ambuildphasename = hnswbuildphasename;
-#endif
 	amroutine->amvalidate = hnswvalidate;
 #if PG_VERSION_NUM >= 140000
 	amroutine->amadjustmembers = NULL;

src/hnsw.h

@@ -3,21 +3,17 @@
 
 #include "postgres.h"
 
-#include "access/generic_xlog.h"
+#include "access/genam.h"
 #include "access/parallel.h"
-#include "access/reloptions.h"
+#include "lib/pairingheap.h"
-#include "lib/ilist.h"
 #include "nodes/execnodes.h"
 #include "port.h"				/* for random() */
+#include "utils/relptr.h"
 #include "utils/sampling.h"
 #include "vector.h"
 
-#if PG_VERSION_NUM < 110000
-#error "Requires PostgreSQL 11+"
-#endif
-
 #if PG_VERSION_NUM < 120000
-#include "access/relscan.h"
+#error "Requires PostgreSQL 12+"
 #endif
 
 #define HNSW_MAX_DIM 2000
@@ -96,33 +92,62 @@
 /* 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 HnswGetNeighbors(element, lc) (AssertMacro((element)->level >= (lc)), &(element)->neighbors[lc])
+#define HnswGetValue(base, element) PointerGetDatum(HnswPtrAccess(base, (element)->value))
+
+#if PG_VERSION_NUM < 140005
+#define relptr_offset(rp) ((rp).relptr_off - 1)
+#endif
+
+/* Pointer macros */
+#define HnswPtrAccess(base, hp) ((base) == NULL ? (hp).ptr : relptr_access(base, (hp).relptr))
+#define HnswPtrStore(base, hp, value) ((base) == NULL ? (void) ((hp).ptr = (value)) : (void) relptr_store(base, (hp).relptr, value))
+#define HnswPtrIsNull(base, hp) ((base) == NULL ? (hp).ptr == NULL : relptr_is_null((hp).relptr))
+#define HnswPtrEqual(base, hp1, hp2) ((base) == NULL ? (hp1).ptr == (hp2).ptr : relptr_offset((hp1).relptr) == relptr_offset((hp2).relptr))
+
+/* For code paths dedicated to each type */
+#define HnswPtrPointer(hp) (hp).ptr
+#define HnswPtrOffset(hp) relptr_offset((hp).relptr)
 
 /* Variables */
 extern int	hnsw_ef_search;
-extern bool hnsw_enable_parallel_build;
+extern int	hnsw_lock_tranche_id;
+
+typedef struct HnswElementData HnswElementData;
+typedef struct HnswNeighborArray HnswNeighborArray;
+
+#define HnswPtrDeclare(type, relptrtype, ptrtype) \
+	relptr_declare(type, relptrtype); \
+	typedef union { type *ptr; relptrtype relptr; } ptrtype;
+
+/* Pointers that can be absolute or relative */
+/* Use char for DatumPtr so works with Pointer */
+HnswPtrDeclare(HnswElementData, HnswElementRelptr, HnswElementPtr);
+HnswPtrDeclare(HnswNeighborArray, HnswNeighborArrayRelptr, HnswNeighborArrayPtr);
+HnswPtrDeclare(HnswNeighborArrayPtr, HnswNeighborsRelptr, HnswNeighborsPtr);
+HnswPtrDeclare(char, DatumRelptr, DatumPtr);
 
 typedef struct HnswElementData
 {
-	slist_node	next;
+	HnswElementPtr next;
 	ItemPointerData heaptids[HNSW_HEAPTIDS];
 	uint8		heaptidsLength;
 	uint8		level;
 	uint8		deleted;
 	uint32		hash;
-	struct HnswNeighborArray *neighbors;
+	HnswNeighborsPtr neighbors;
 	BlockNumber blkno;
 	OffsetNumber offno;
 	OffsetNumber neighborOffno;
 	BlockNumber neighborPage;
-	Datum		value;
+	DatumPtr	value;
+	LWLock		lock;
 }			HnswElementData;
 
 typedef HnswElementData * HnswElement;
 
 typedef struct HnswCandidate
 {
-	HnswElement element;
+	HnswElementPtr element;
 	float		distance;
 	bool		closer;
 }			HnswCandidate;
@@ -131,7 +156,7 @@ typedef struct HnswNeighborArray
 {
 	int			length;
 	bool		closerSet;
-	HnswCandidate *items;
+	HnswCandidate items[FLEXIBLE_ARRAY_MEMBER];
 }			HnswNeighborArray;
 
 typedef struct HnswPairingHeapNode
@@ -150,19 +175,24 @@ typedef struct HnswOptions
 
 typedef struct HnswGraph
 {
-	slist_head	elements;
+	/* Graph state */
-	HnswElement entryPoint;
+	slock_t		lock;
+	HnswElementPtr head;
+	double		indtuples;
+
+	/* Entry state */
+	LWLock		entryLock;
+	HnswElementPtr entryPoint;
+
+	/* Allocations state */
+	LWLock		allocatorLock;
 	long		memoryUsed;
 	long		memoryTotal;
-	bool		flushed;
-	double		indtuples;
-}			HnswGraph;
 
-typedef struct HnswSpool
+	/* Flushed state */
-{
+	LWLock		flushLock;
-	Relation	heap;
+	bool		flushed;
-	Relation	index;
+}			HnswGraph;
-}			HnswSpool;
 
 typedef struct HnswShared
 {
@@ -170,7 +200,6 @@ typedef struct HnswShared
 	Oid			heaprelid;
 	Oid			indexrelid;
 	bool		isconcurrent;
-	int			scantuplesortstates;
 
 	/* Worker progress */
 	ConditionVariable workersdonecv;
@@ -182,16 +211,10 @@ typedef struct HnswShared
 	int			nparticipantsdone;
 	double		reltuples;
 	HnswGraph	graphData;
-
-#if PG_VERSION_NUM < 120000
-	ParallelHeapScanDescData heapdesc;	/* must come last */
-#endif
 }			HnswShared;
 
-#if PG_VERSION_NUM >= 120000
 #define ParallelTableScanFromHnswShared(shared) \
 	(ParallelTableScanDesc) ((char *) (shared) + BUFFERALIGN(sizeof(HnswShared)))
-#endif
 
 typedef struct HnswLeader
 {
@@ -199,8 +222,15 @@ typedef struct HnswLeader
 	int			nparticipanttuplesorts;
 	HnswShared *hnswshared;
 	Snapshot	snapshot;
+	char	   *hnswarea;
 }			HnswLeader;
 
+typedef struct HnswAllocator
+{
+	void	   *(*alloc) (Size size, void *state);
+	void	   *state;
+}			HnswAllocator;
+
 typedef struct HnswBuildState
 {
 	/* Info */
@@ -233,10 +263,12 @@ typedef struct HnswBuildState
 	/* Memory */
 	MemoryContext graphCtx;
 	MemoryContext tmpCtx;
+	HnswAllocator allocator;
 
 	/* Parallel builds */
 	HnswLeader *hnswleader;
 	HnswShared *hnswshared;
+	char	   *hnswarea;
 }			HnswBuildState;
 
 typedef struct HnswMetaPageData
@@ -335,23 +367,24 @@ 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(Datum q, 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);
-HnswElement HnswInitElement(ItemPointer tid, int m, double ml, int maxLevel);
+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		HnswInsertElement(HnswElement element, HnswElement entryPoint, Relation index, FmgrInfo *procinfo, Oid collation, 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);
-HnswCandidate *HnswEntryCandidate(HnswElement em, Datum q, Relation rel, FmgrInfo *procinfo, Oid collation, bool loadVec);
+HnswCandidate *HnswEntryCandidate(char *base, HnswElement em, Datum q, Relation rel, FmgrInfo *procinfo, Oid collation, bool loadVec);
 void		HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, BlockNumber insertPage, ForkNumber forkNum, bool building);
-void		HnswSetNeighborTuple(HnswNeighborTuple ntup, HnswElement e, int m);
+void		HnswSetNeighborTuple(char *base, HnswNeighborTuple ntup, HnswElement e, int m);
 void		HnswAddHeapTid(HnswElement element, ItemPointer heaptid);
-void		HnswInitNeighbors(HnswElement element, int m);
+void		HnswInitNeighbors(char *base, HnswElement element, int m, HnswAllocator * alloc);
-bool		HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid, Relation heapRel, bool building);
+bool		HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull, ItemPointer heap_tid, Relation heapRel, bool building);
-void		HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, 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, float *distance, Datum *q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec);
-void		HnswSetElementTuple(HnswElementTuple etup, HnswElement element);
+void		HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element);
-void		HnswUpdateConnection(HnswElement element, HnswCandidate * hc, int m, int lc, int *updateIdx, Relation index, FmgrInfo *procinfo, Oid collation);
+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);
 PGDLLEXPORT void HnswParallelBuildMain(dsm_segment *seg, shm_toc *toc);
 
@@ -371,6 +404,16 @@ void		hnswrescan(IndexScanDesc scan, ScanKey keys, int nkeys, ScanKey orderbys,
 bool		hnswgettuple(IndexScanDesc scan, ScanDirection dir);
 void		hnswendscan(IndexScanDesc scan);
 
+static inline HnswNeighborArray *
+HnswGetNeighbors(char *base, HnswElement element, int lc)
+{
+	HnswNeighborArrayPtr *neighborList = HnswPtrAccess(base, element->neighbors);
+
+	Assert(element->level >= lc);
+
+	return HnswPtrAccess(base, neighborList[lc]);
+}
+
 /* Hash tables */
 typedef struct TidHashEntry
 {
@@ -398,4 +441,17 @@ typedef struct PointerHashEntry
 #define SH_DECLARE
 #include "lib/simplehash.h"
 
+typedef struct OffsetHashEntry
+{
+	Size		offset;
+	char		status;
+}			OffsetHashEntry;
+
+#define SH_PREFIX offsethash
+#define SH_ELEMENT_TYPE OffsetHashEntry
+#define SH_KEY_TYPE Size
+#define SH_SCOPE extern
+#define SH_DECLARE
+#include "lib/simplehash.h"
+
 #endif

src/hnswbuild.c

@@ -1,14 +1,53 @@
+/*
+ * The HNSW build happens in two phases:
+ *
+ * 1. In-memory phase
+ *
+ * In this first phase, the graph is held completely in memory. When the graph
+ * is fully built, or we run out of memory reserved for the build (determined
+ * by maintenance_work_mem), we materialize the graph to disk (see
+ * FlushPages()), and switch to the on-disk phase.
+ *
+ * In a parallel build, a large contiguous chunk of shared memory is allocated
+ * to hold the graph. Each worker process has its own HnswBuildState struct in
+ * private memory, which contains information that doesn't change throughout
+ * the build, and pointers to the shared structs in shared memory. The shared
+ * memory area is mapped to a different address in each worker process, and
+ * 'HnswBuildState.hnswarea' points to the beginning of the shared area in the
+ * worker process's address space. All pointers used in the graph are
+ * "relative pointers", stored as an offset from 'hnswarea'.
+ *
+ * Each element is protected by an LWLock. It must be held when reading or
+ * modifying the element's neighbors or 'heaptids'.
+ *
+ * In a non-parallel build, the graph is held in backend-private memory. All
+ * the elements are allocated in a dedicated memory context, 'graphCtx', and
+ * the pointers used in the graph are regular pointers.
+ *
+ * 2. On-disk phase
+ *
+ * In the on-disk phase, the index is built by inserting each vector to the
+ * index one by one, just like on INSERT. The only difference is that we don't
+ * WAL-log the individual inserts. If the graph fit completely in memory and
+ * was fully built in the in-memory phase, the on-disk phase is skipped.
+ *
+ * After we have finished building the graph, we perform one more scan through
+ * the index and write all the pages to the WAL.
+ */
 #include "postgres.h"
 
 #include <math.h>
 
 #include "access/parallel.h"
+#include "access/table.h"
+#include "access/tableam.h"
 #include "access/xact.h"
+#include "access/xloginsert.h"
 #include "catalog/index.h"
+#include "commands/progress.h"
 #include "hnsw.h"
 #include "miscadmin.h"
-#include "lib/pairingheap.h"
+#include "optimizer/optimizer.h"
-#include "nodes/pg_list.h"
 #include "storage/bufmgr.h"
 #include "tcop/tcopprot.h"
 #include "utils/datum.h"
@@ -16,15 +55,8 @@
 
 #if PG_VERSION_NUM >= 140000
 #include "utils/backend_progress.h"
-#elif PG_VERSION_NUM >= 120000
-#include "pgstat.h"
-#endif
-
-#if PG_VERSION_NUM >= 120000
-#include "access/tableam.h"
-#include "commands/progress.h"
 #else
-#define PROGRESS_CREATEIDX_TUPLES_DONE 0
+#include "pgstat.h"
 #endif
 
 #if PG_VERSION_NUM >= 130000
@@ -33,28 +65,16 @@
 #define CALLBACK_ITEM_POINTER HeapTuple hup
 #endif
 
-#if PG_VERSION_NUM >= 120000
 #define UpdateProgress(index, val) pgstat_progress_update_param(index, val)
-#else
-#define UpdateProgress(index, val) ((void)val)
-#endif
 
 #if PG_VERSION_NUM >= 140000
 #include "utils/backend_status.h"
 #include "utils/wait_event.h"
 #endif
 
-#if PG_VERSION_NUM >= 120000
-#include "access/table.h"
-#include "optimizer/optimizer.h"
-#else
-#include "access/heapam.h"
-#include "optimizer/planner.h"
-#include "pgstat.h"
-#endif
-
 #define PARALLEL_KEY_HNSW_SHARED		UINT64CONST(0xA000000000000001)
-#define PARALLEL_KEY_QUERY_TEXT			UINT64CONST(0xA000000000000002)
+#define PARALLEL_KEY_HNSW_AREA			UINT64CONST(0xA000000000000002)
+#define PARALLEL_KEY_QUERY_TEXT			UINT64CONST(0xA000000000000003)
 
 #if PG_VERSION_NUM < 130000
 #define GENERATIONCHUNK_RAWSIZE (SIZEOF_SIZE_T + SIZEOF_VOID_P * 2)
@@ -135,9 +155,11 @@ CreateElementPages(HnswBuildState * buildstate)
 	HnswElementTuple etup;
 	HnswNeighborTuple ntup;
 	BlockNumber insertPage;
+	HnswElement entryPoint;
 	Buffer		buf;
 	Page		page;
-	slist_iter	iter;
+	HnswElementPtr iter = buildstate->graph->head;
+	char	   *base = buildstate->hnswarea;
 
 	/* Calculate sizes */
 	etupAllocSize = BLCKSZ;
@@ -152,18 +174,22 @@ CreateElementPages(HnswBuildState * buildstate)
 	page = BufferGetPage(buf);
 	HnswInitPage(buf, page);
 
-	slist_foreach(iter, &buildstate->graph->elements)
+	while (!HnswPtrIsNull(base, iter))
 	{
-		HnswElement element = slist_container(HnswElementData, next, iter.cur);
+		HnswElement element = HnswPtrAccess(base, iter);
 		Size		etupSize;
 		Size		ntupSize;
 		Size		combinedSize;
+		void	   *valuePtr = HnswPtrAccess(base, element->value);
+
+		/* Update iterator */
+		iter = element->next;
 
 		/* Zero memory for each element */
 		MemSet(etup, 0, etupAllocSize);
 
 		/* Calculate sizes */
-		etupSize = HNSW_ELEMENT_TUPLE_SIZE(VARSIZE_ANY(DatumGetPointer(element->value)));
+		etupSize = HNSW_ELEMENT_TUPLE_SIZE(VARSIZE_ANY(valuePtr));
 		ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(element->level, buildstate->m);
 		combinedSize = etupSize + ntupSize + sizeof(ItemIdData);
 
@@ -171,7 +197,7 @@ CreateElementPages(HnswBuildState * buildstate)
 		if (etupSize > etupAllocSize)
 			elog(ERROR, "index tuple too large");
 
-		HnswSetElementTuple(etup, element);
+		HnswSetElementTuple(base, etup, element);
 
 		/* Keep element and neighbors on the same page if possible */
 		if (PageGetFreeSpace(page) < etupSize || (combinedSize <= maxSize && PageGetFreeSpace(page) < combinedSize))
@@ -212,7 +238,8 @@ CreateElementPages(HnswBuildState * buildstate)
 	MarkBufferDirty(buf);
 	UnlockReleaseBuffer(buf);
 
-	HnswUpdateMetaPage(index, HNSW_UPDATE_ENTRY_ALWAYS, buildstate->graph->entryPoint, insertPage, forkNum, true);
+	entryPoint = HnswPtrAccess(base, buildstate->graph->entryPoint);
+	HnswUpdateMetaPage(index, HNSW_UPDATE_ENTRY_ALWAYS, entryPoint, insertPage, forkNum, true);
 
 	pfree(etup);
 	pfree(ntup);
@@ -227,19 +254,23 @@ CreateNeighborPages(HnswBuildState * buildstate)
 	Relation	index = buildstate->index;
 	ForkNumber	forkNum = buildstate->forkNum;
 	int			m = buildstate->m;
-	slist_iter	iter;
+	HnswElementPtr iter = buildstate->graph->head;
+	char	   *base = buildstate->hnswarea;
 	HnswNeighborTuple ntup;
 
 	/* Allocate once */
 	ntup = palloc0(BLCKSZ);
 
-	slist_foreach(iter, &buildstate->graph->elements)
+	while (!HnswPtrIsNull(base, iter))
 	{
-		HnswElement e = slist_container(HnswElementData, next, iter.cur);
+		HnswElement e = HnswPtrAccess(base, iter);
 		Buffer		buf;
 		Page		page;
 		Size		ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(e->level, m);
 
+		/* Update iterator */
+		iter = e->next;
+
 		/* Can take a while, so ensure we can interrupt */
 		/* Needs to be called when no buffer locks are held */
 		CHECK_FOR_INTERRUPTS();
@@ -248,7 +279,7 @@ CreateNeighborPages(HnswBuildState * buildstate)
 		LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
 		page = BufferGetPage(buf);
 
-		HnswSetNeighborTuple(ntup, e, m);
+		HnswSetNeighborTuple(base, ntup, e, m);
 
 		if (!PageIndexTupleOverwrite(page, e->neighborOffno, (Item) ntup, ntupSize))
 			elog(ERROR, "failed to add index item to \"%s\"", RelationGetRelationName(index));
@@ -261,24 +292,6 @@ CreateNeighborPages(HnswBuildState * buildstate)
 	pfree(ntup);
 }
 
-#ifdef HNSW_MEMORY
-/*
- * Show memory usage
- */
-static void
-ShowMemoryUsage(HnswBuildState * buildstate)
-{
-#if PG_VERSION_NUM >= 130000
-	elog(INFO, "graph memory: %zu MB, total memory: %zu MB",
-		 MemoryContextMemAllocated(buildstate->graphCtx, false) / (1024 * 1024),
-		 MemoryContextMemAllocated(CurrentMemoryContext, true) / (1024 * 1024));
-#else
-	MemoryContextStats(CurrentMemoryContext);
-	elog(INFO, "estimated memory: %zu MB", buildstate->memoryUsed / (1024 * 1024));
-#endif
-}
-#endif
-
 /*
  * Flush pages
  */
@@ -286,7 +299,7 @@ static void
 FlushPages(HnswBuildState * buildstate)
 {
 #ifdef HNSW_MEMORY
-	ShowMemoryUsage(buildstate);
+	elog(INFO, "memory: %zu MB", buildstate->graph->memoryUsed / (1024 * 1024));
 #endif
 
 	CreateMetaPage(buildstate);
@@ -297,66 +310,172 @@ FlushPages(HnswBuildState * buildstate)
 	MemoryContextReset(buildstate->graphCtx);
 }
 
-#if PG_VERSION_NUM < 130000
 /*
- * Get the memory used by an element
+ * Add a heap TID to an existing element
  */
-static long
+static bool
-HnswElementMemory(HnswElement e, int m)
+AddDuplicateInMemory(HnswElement element, HnswElement dup)
 {
-	long		elementSize = sizeof(HnswElementData);
+	LWLockAcquire(&dup->lock, LW_EXCLUSIVE);
 
-	elementSize += sizeof(HnswNeighborArray) * (e->level + 1);
+	if (dup->heaptidsLength == HNSW_HEAPTIDS)
-	elementSize += sizeof(HnswCandidate) * (m * (e->level + 2));
+	{
-	elementSize += VARSIZE_ANY(DatumGetPointer(e->value));
+		LWLockRelease(&dup->lock);
-	/* Each allocation has a chunk header */
+		return false;
-	elementSize += (e->level + 4) * GENERATIONCHUNK_RAWSIZE;
+	}
-	/* Add an extra 5% for alignment and other overhead */
+
-	return elementSize * 1.05;
+	HnswAddHeapTid(dup, &element->heaptids[0]);
+
+	LWLockRelease(&dup->lock);
+
+	return true;
 }
-#endif
 
 /*
  * Find duplicate element
  */
 static bool
-HnswFindDuplicateInMemory(HnswElement element)
+FindDuplicateInMemory(char *base, HnswElement element)
 {
-	HnswNeighborArray *neighbors = HnswGetNeighbors(element, 0);
+	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 (!datumIsEqual(element->value, neighbor->element->value, false, -1))
+		if (!datumIsEqual(value, neighborValue, false, -1))
 			return false;
 
 		/* Check for space */
-		if (neighbor->element->heaptidsLength < HNSW_HEAPTIDS)
+		if (AddDuplicateInMemory(element, neighborElement))
-		{
-			HnswAddHeapTid(neighbor->element, &element->heaptids[0]);
 			return true;
-		}
 	}
 
 	return false;
 }
 
 /*
- * Insert tuple into in-memory graph
+ * Add to element list
  */
-static bool
+static void
-InsertTupleInMemory(Relation index, Datum *values, ItemPointer heaptid, HnswBuildState * buildstate)
+AddElementInMemory(char *base, HnswGraph * graph, HnswElement element)
+{
+	SpinLockAcquire(&graph->lock);
+	element->next = graph->head;
+	HnswPtrStore(base, graph->head, element);
+	SpinLockRelease(&graph->lock);
+}
+
+/*
+ * Update neighbors
+ */
+static void
+UpdateNeighborsInMemory(char *base, FmgrInfo *procinfo, Oid collation, HnswElement e, int m)
+{
+	for (int lc = e->level; lc >= 0; lc--)
+	{
+		int			lm = HnswGetLayerM(m, lc);
+		HnswNeighborArray *neighbors = HnswGetNeighbors(base, e, lc);
+
+		for (int i = 0; i < neighbors->length; i++)
+		{
+			HnswCandidate *hc = &neighbors->items[i];
+			HnswElement neighborElement = HnswPtrAccess(base, hc->element);
+
+			/* Keep scan-build happy on Mac x86-64 */
+			Assert(neighborElement);
+
+			/* Use element for lock instead of hc since hc can be replaced */
+			LWLockAcquire(&neighborElement->lock, LW_EXCLUSIVE);
+			HnswUpdateConnection(base, e, hc, lm, lc, NULL, NULL, procinfo, collation);
+			LWLockRelease(&neighborElement->lock);
+		}
+	}
+}
+
+/*
+ * Update graph in memory
+ */
+static void
+UpdateGraphInMemory(FmgrInfo *procinfo, Oid collation, HnswElement element, int m, int efConstruction, HnswElement entryPoint, HnswBuildState * buildstate)
+{
+	HnswGraph  *graph = buildstate->graph;
+	char	   *base = buildstate->hnswarea;
+
+	/* Look for duplicate */
+	if (FindDuplicateInMemory(base, element))
+		return;
+
+	/* Add element */
+	AddElementInMemory(base, graph, element);
+
+	/* Update neighbors */
+	UpdateNeighborsInMemory(base, procinfo, collation, element, m);
+
+	/* Update entry point if needed (already have lock) */
+	if (entryPoint == NULL || element->level > entryPoint->level)
+		HnswPtrStore(base, graph->entryPoint, element);
+}
+
+/*
+ * Insert tuple in memory
+ */
+static void
+InsertTupleInMemory(HnswBuildState * buildstate, HnswElement element)
 {
 	FmgrInfo   *procinfo = buildstate->procinfo;
 	Oid			collation = buildstate->collation;
 	HnswGraph  *graph = buildstate->graph;
-	HnswElement entryPoint = graph->entryPoint;
+	HnswElement entryPoint;
+	LWLock	   *entryLock = &graph->entryLock;
 	int			efConstruction = buildstate->efConstruction;
 	int			m = buildstate->m;
-	MemoryContext oldCtx;
+	char	   *base = buildstate->hnswarea;
+
+	/* Get entry point */
+	LWLockAcquire(entryLock, LW_SHARED);
+	entryPoint = HnswPtrAccess(base, graph->entryPoint);
+
+	/* Prevent concurrent inserts when likely updating entry point */
+	if (entryPoint == NULL || element->level > entryPoint->level)
+	{
+		/* Release shared lock */
+		LWLockRelease(entryLock);
+
+		/* Get exclusive lock */
+		LWLockAcquire(entryLock, LW_EXCLUSIVE);
+
+		/* Get latest entry point after lock is acquired */
+		entryPoint = HnswPtrAccess(base, graph->entryPoint);
+	}
+
+	/* Find neighbors for element */
+	HnswFindElementNeighbors(base, element, entryPoint, NULL, procinfo, collation, m, efConstruction, false);
+
+	/* Update graph in memory */
+	UpdateGraphInMemory(procinfo, collation, element, m, efConstruction, entryPoint, buildstate);
+
+	/* Release entry lock */
+	LWLockRelease(entryLock);
+}
+
+/*
+ * Insert tuple
+ */
+static bool
+InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, HnswBuildState * buildstate)
+{
+	HnswGraph  *graph = buildstate->graph;
 	HnswElement element;
+	HnswAllocator *allocator = &buildstate->allocator;
+	Size		valueSize;
+	Pointer		valuePtr;
+	LWLock	   *flushLock = &graph->flushLock;
+	char	   *base = buildstate->hnswarea;
 
 	/* Detoast once for all calls */
 	Datum		value = PointerGetDatum(PG_DETOAST_DATUM(values[0]));
@@ -364,73 +483,83 @@ InsertTupleInMemory(Relation index, Datum *values, ItemPointer heaptid, HnswBuil
 	/* Normalize if needed */
 	if (buildstate->normprocinfo != NULL)
 	{
-		if (!HnswNormValue(buildstate->normprocinfo, collation, &value, buildstate->normvec))
+		if (!HnswNormValue(buildstate->normprocinfo, buildstate->collation, &value, buildstate->normvec))
 			return false;
 	}
 
-	/* Allocate element in graph memory context */
+	/* Get datum size */
-	oldCtx = MemoryContextSwitchTo(buildstate->graphCtx);
+	valueSize = VARSIZE_ANY(DatumGetPointer(value));
-	element = HnswInitElement(heaptid, buildstate->m, buildstate->ml, buildstate->maxLevel);
-	element->value = datumCopy(value, false, -1);
-	MemoryContextSwitchTo(oldCtx);
 
-	/* Update memory usage */
+	/* Ensure graph not flushed when inserting */
-#if PG_VERSION_NUM >= 130000
+	LWLockAcquire(flushLock, LW_SHARED);
-	graph->memoryUsed = MemoryContextMemAllocated(buildstate->graphCtx, false);
-#else
-	graph->memoryUsed += HnswElementMemory(element, buildstate->m);
-#endif
 
-	/* Insert element in graph */
+	/* Are we in the on-disk phase? */
-	HnswInsertElement(element, entryPoint, NULL, procinfo, collation, m, efConstruction, false);
+	if (graph->flushed)
-
-	/* Look for duplicate */
-	if (HnswFindDuplicateInMemory(element))
 	{
-		/* No need to free element since memory unlikely to be reallocated */
+		LWLockRelease(flushLock);
-		return true;
+
+		return HnswInsertTupleOnDisk(index, value, values, isnull, heaptid, buildstate->heap, true);
 	}
 
-	/* Add element */
+	/*
-	slist_push_head(&graph->elements, &element->next);
+	 * In a parallel build, the HnswElement is allocated from the shared
+	 * memory area, so we need to coordinate with other processes.
+	 */
+	LWLockAcquire(&graph->allocatorLock, LW_EXCLUSIVE);
 
-	/* Update neighbors */
+	/*
-	for (int lc = element->level; lc >= 0; lc--)
+	 * Check that we have enough memory available for the new element now that
+	 * we have the allocator lock, and flush pages if needed.
+	 */
+	if (graph->memoryUsed >= graph->memoryTotal)
 	{
-		int			lm = HnswGetLayerM(m, lc);
+		LWLockRelease(&graph->allocatorLock);
-		HnswNeighborArray *neighbors = HnswGetNeighbors(element, lc);
 
-		for (int i = 0; i < neighbors->length; i++)
+		LWLockRelease(flushLock);
-			HnswUpdateConnection(element, &neighbors->items[i], lm, lc, NULL, NULL, procinfo, collation);
+		LWLockAcquire(flushLock, LW_EXCLUSIVE);
+
+		if (!graph->flushed)
+		{
+			ereport(NOTICE,
+					(errmsg("hnsw graph no longer fits into maintenance_work_mem after " INT64_FORMAT " tuples", (int64) graph->indtuples),
+					 errdetail("Building will take significantly more time."),
+					 errhint("Increase maintenance_work_mem to speed up builds.")));
+
+			FlushPages(buildstate);
+		}
+
+		LWLockRelease(flushLock);
+
+		return HnswInsertTupleOnDisk(index, value, values, isnull, heaptid, buildstate->heap, true);
 	}
 
-	/* Update entry point if needed */
+	/* Ok, we can proceed to allocate the element */
-	if (entryPoint == NULL || element->level > entryPoint->level)
+	element = HnswInitElement(base, heaptid, buildstate->m, buildstate->ml, buildstate->maxLevel, allocator);
-		graph->entryPoint = element;
+	valuePtr = HnswAlloc(allocator, valueSize);
+
+	/*
+	 * We have now allocated the space needed for the element, so we don't
+	 * need the allocator lock anymore. Release it and initialize the rest of
+	 * the element.
+	 */
+	LWLockRelease(&graph->allocatorLock);
+
+	/* Copy the datum */
+	memcpy(valuePtr, DatumGetPointer(value), valueSize);
+	HnswPtrStore(base, element->value, valuePtr);
+
+	/* Create a lock for the element */
+	LWLockInitialize(&element->lock, hnsw_lock_tranche_id);
+
+	/* Insert tuple */
+	InsertTupleInMemory(buildstate, element);
+
+	/* Release flush lock */
+	LWLockRelease(flushLock);
 
 	return true;
 }
 
-/*
- * Acquire a lock if needed
- */
-static inline void
-HnswLockAcquire(HnswShared * hnswshared)
-{
-	if (hnswshared)
-		SpinLockAcquire(&hnswshared->mutex);
-}
-
-/*
- * Release a lock if needed
- */
-static inline void
-HnswLockRelease(HnswShared * hnswshared)
-{
-	if (hnswshared)
-		SpinLockRelease(&hnswshared->mutex);
-}
-
 /*
  * Callback for table_index_build_scan
  */
@@ -440,9 +569,7 @@ BuildCallback(Relation index, CALLBACK_ITEM_POINTER, Datum *values,
 {
 	HnswBuildState *buildstate = (HnswBuildState *) state;
 	HnswGraph  *graph = buildstate->graph;
-	HnswShared *hnswshared = buildstate->hnswshared;
 	MemoryContext oldCtx;
-	bool		inserted;
 
 #if PG_VERSION_NUM < 130000
 	ItemPointer tid = &hup->t_self;
@@ -452,31 +579,16 @@ BuildCallback(Relation index, CALLBACK_ITEM_POINTER, Datum *values,
 	if (isnull[0])
 		return;
 
-	/* Flush pages if needed */
+	/* Use memory context */
-	if (!graph->flushed && graph->memoryUsed >= graph->memoryTotal)
-	{
-		ereport(NOTICE,
-				(errmsg("hnsw graph no longer fits into maintenance_work_mem after " INT64_FORMAT " tuples", (int64) graph->indtuples),
-				 errdetail("Building will take significantly more time."),
-				 errhint("Increase maintenance_work_mem to speed up builds.")));
-
-		FlushPages(buildstate);
-	}
-
 	oldCtx = MemoryContextSwitchTo(buildstate->tmpCtx);
 
 	/* Insert tuple */
-	if (graph->flushed)
+	if (InsertTuple(index, values, isnull, tid, buildstate))
-		inserted = HnswInsertTuple(index, values, isnull, tid, buildstate->heap, true);
-	else
-		inserted = InsertTupleInMemory(index, values, tid, buildstate);
-
-	/* Update progress */
-	if (inserted)
 	{
-		HnswLockAcquire(hnswshared);
+		/* Update progress */
+		SpinLockAcquire(&graph->lock);
 		UpdateProgress(PROGRESS_CREATEIDX_TUPLES_DONE, ++graph->indtuples);
-		HnswLockRelease(hnswshared);
+		SpinLockRelease(&graph->lock);
 	}
 
 	/* Reset memory context */
@@ -488,14 +600,59 @@ BuildCallback(Relation index, CALLBACK_ITEM_POINTER, Datum *values,
  * Initialize the graph
  */
 static void
-InitGraph(HnswGraph * graph)
+InitGraph(HnswGraph * graph, char *base, long memoryTotal)
 {
-	slist_init(&graph->elements);
+	HnswPtrStore(base, graph->head, (HnswElement) NULL);
-	graph->entryPoint = NULL;
+	HnswPtrStore(base, graph->entryPoint, (HnswElement) NULL);
 	graph->memoryUsed = 0;
-	graph->memoryTotal = maintenance_work_mem * 1024L;
+	graph->memoryTotal = memoryTotal;
 	graph->flushed = false;
 	graph->indtuples = 0;
+	SpinLockInit(&graph->lock);
+	LWLockInitialize(&graph->entryLock, hnsw_lock_tranche_id);
+	LWLockInitialize(&graph->allocatorLock, hnsw_lock_tranche_id);
+	LWLockInitialize(&graph->flushLock, hnsw_lock_tranche_id);
+}
+
+/*
+ * Initialize an allocator
+ */
+static void
+InitAllocator(HnswAllocator * allocator, void *(*alloc) (Size size, void *state), void *state)
+{
+	allocator->alloc = alloc;
+	allocator->state = state;
+}
+
+/*
+ * Memory context allocator
+ */
+static void *
+HnswMemoryContextAlloc(Size size, void *state)
+{
+	HnswBuildState *buildstate = (HnswBuildState *) state;
+	void	   *chunk = MemoryContextAlloc(buildstate->graphCtx, size);
+
+#if PG_VERSION_NUM >= 130000
+	buildstate->graphData.memoryUsed = MemoryContextMemAllocated(buildstate->graphCtx, false);
+#else
+	buildstate->graphData.memoryUsed += MAXALIGN(size);
+#endif
+
+	return chunk;
+}
+
+/*
+ * Shared memory allocator
+ */
+static void *
+HnswSharedMemoryAlloc(Size size, void *state)
+{
+	HnswBuildState *buildstate = (HnswBuildState *) state;
+	void	   *chunk = buildstate->hnswarea + buildstate->graph->memoryUsed;
+
+	buildstate->graph->memoryUsed += MAXALIGN(size);
+	return chunk;
 }
 
 /*
@@ -531,7 +688,7 @@ InitBuildState(HnswBuildState * buildstate, Relation heap, Relation index, Index
 	buildstate->normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
 	buildstate->collation = index->rd_indcollation[0];
 
-	InitGraph(&buildstate->graphData);
+	InitGraph(&buildstate->graphData, NULL, maintenance_work_mem * 1024L);
 	buildstate->graph = &buildstate->graphData;
 	buildstate->ml = HnswGetMl(buildstate->m);
 	buildstate->maxLevel = HnswGetMaxLevel(buildstate->m);
@@ -549,8 +706,11 @@ InitBuildState(HnswBuildState * buildstate, Relation heap, Relation index, Index
 											   "Hnsw build temporary context",
 											   ALLOCSET_DEFAULT_SIZES);
 
+	InitAllocator(&buildstate->allocator, &HnswMemoryContextAlloc, buildstate);
+
 	buildstate->hnswleader = NULL;
 	buildstate->hnswshared = NULL;
+	buildstate->hnswarea = NULL;
 }
 
 /*
@@ -581,6 +741,7 @@ ParallelHeapScan(HnswBuildState * buildstate)
 		if (hnswshared->nparticipantsdone == nparticipanttuplesorts)
 		{
 			buildstate->graph = &hnswshared->graphData;
+			buildstate->hnswarea = buildstate->hnswleader->hnswarea;
 			reltuples = hnswshared->reltuples;
 			SpinLockRelease(&hnswshared->mutex);
 			break;
@@ -600,35 +761,25 @@ ParallelHeapScan(HnswBuildState * buildstate)
  * Perform a worker's portion of a parallel insert
  */
 static void
-HnswParallelScanAndInsert(HnswSpool * hnswspool, HnswShared * hnswshared, bool progress)
+HnswParallelScanAndInsert(Relation heapRel, Relation indexRel, HnswShared * hnswshared, char *hnswarea, bool progress)
 {
 	HnswBuildState buildstate;
-#if PG_VERSION_NUM >= 120000
 	TableScanDesc scan;
-#else
-	HeapScanDesc scan;
-#endif
 	double		reltuples;
 	IndexInfo  *indexInfo;
 
 	/* Join parallel scan */
-	indexInfo = BuildIndexInfo(hnswspool->index);
+	indexInfo = BuildIndexInfo(indexRel);
 	indexInfo->ii_Concurrent = hnswshared->isconcurrent;
-	InitBuildState(&buildstate, hnswspool->heap, hnswspool->index, indexInfo, MAIN_FORKNUM);
+	InitBuildState(&buildstate, heapRel, indexRel, indexInfo, MAIN_FORKNUM);
 	buildstate.graph = &hnswshared->graphData;
-	buildstate.hnswshared = hnswshared;
+	buildstate.hnswarea = hnswarea;
-#if PG_VERSION_NUM >= 120000
+	InitAllocator(&buildstate.allocator, &HnswSharedMemoryAlloc, &buildstate);
-	scan = table_beginscan_parallel(hnswspool->heap,
+	scan = table_beginscan_parallel(heapRel,
 									ParallelTableScanFromHnswShared(hnswshared));
-	reltuples = table_index_build_scan(hnswspool->heap, hnswspool->index, indexInfo,
+	reltuples = table_index_build_scan(heapRel, indexRel, indexInfo,
 									   true, progress, BuildCallback,
 									   (void *) &buildstate, scan);
-#else
-	scan = heap_beginscan_parallel(hnswspool->heap, &hnswshared->heapdesc);
-	reltuples = IndexBuildHeapScan(hnswspool->heap, hnswspool->index, indexInfo,
-								   true, BuildCallback,
-								   (void *) &buildstate, scan);
-#endif
 
 	/* Record statistics */
 	SpinLockAcquire(&hnswshared->mutex);
@@ -655,8 +806,8 @@ void
 HnswParallelBuildMain(dsm_segment *seg, shm_toc *toc)
 {
 	char	   *sharedquery;
-	HnswSpool  *hnswspool;
 	HnswShared *hnswshared;
+	char	   *hnswarea;
 	Relation	heapRel;
 	Relation	indexRel;
 	LOCKMODE	heapLockmode;
@@ -685,28 +836,17 @@ HnswParallelBuildMain(dsm_segment *seg, shm_toc *toc)
 	}
 
 	/* Open relations within worker */
-#if PG_VERSION_NUM >= 120000
 	heapRel = table_open(hnswshared->heaprelid, heapLockmode);
-#else
-	heapRel = heap_open(hnswshared->heaprelid, heapLockmode);
-#endif
 	indexRel = index_open(hnswshared->indexrelid, indexLockmode);
 
-	/* Initialize worker's own spool */
+	hnswarea = shm_toc_lookup(toc, PARALLEL_KEY_HNSW_AREA, false);
-	hnswspool = (HnswSpool *) palloc0(sizeof(HnswSpool));
-	hnswspool->heap = heapRel;
-	hnswspool->index = indexRel;
 
 	/* Perform inserts */
-	HnswParallelScanAndInsert(hnswspool, hnswshared, false);
+	HnswParallelScanAndInsert(heapRel, indexRel, hnswshared, hnswarea, false);
 
 	/* Close relations within worker */
 	index_close(indexRel, indexLockmode);
-#if PG_VERSION_NUM >= 120000
 	table_close(heapRel, heapLockmode);
-#else
-	heap_close(heapRel, heapLockmode);
-#endif
 }
 
 /*
@@ -731,19 +871,7 @@ HnswEndParallel(HnswLeader * hnswleader)
 static Size
 ParallelEstimateShared(Relation heap, Snapshot snapshot)
 {
-#if PG_VERSION_NUM >= 120000
 	return add_size(BUFFERALIGN(sizeof(HnswShared)), table_parallelscan_estimate(heap, snapshot));
-#else
-	if (!IsMVCCSnapshot(snapshot))
-	{
-		Assert(snapshot == SnapshotAny);
-		return sizeof(HnswShared);
-	}
-
-	return add_size(offsetof(HnswShared, heapdesc) +
-					offsetof(ParallelHeapScanDescData, phs_snapshot_data),
-					EstimateSnapshotSpace(snapshot));
-#endif
 }
 
 /*
@@ -753,15 +881,9 @@ static void
 HnswLeaderParticipateAsWorker(HnswBuildState * buildstate)
 {
 	HnswLeader *hnswleader = buildstate->hnswleader;
-	HnswSpool  *leaderworker;
-
-	/* Allocate memory and initialize private spool */
-	leaderworker = (HnswSpool *) palloc0(sizeof(HnswSpool));
-	leaderworker->heap = buildstate->heap;
-	leaderworker->index = buildstate->index;
 
 	/* Perform work common to all participants */
-	HnswParallelScanAndInsert(leaderworker, hnswleader->hnswshared, true);
+	HnswParallelScanAndInsert(buildstate->heap, buildstate->index, hnswleader->hnswshared, hnswleader->hnswarea, true);
 }
 
 /*
@@ -771,10 +893,12 @@ static void
 HnswBeginParallel(HnswBuildState * buildstate, bool isconcurrent, int request)
 {
 	ParallelContext *pcxt;
-	int			scantuplesortstates;
 	Snapshot	snapshot;
 	Size		esthnswshared;
+	Size		esthnswarea;
+	Size		estother;
 	HnswShared *hnswshared;
+	char	   *hnswarea;
 	HnswLeader *hnswleader = (HnswLeader *) palloc0(sizeof(HnswLeader));
 	bool		leaderparticipates = true;
 	int			querylen;
@@ -786,13 +910,7 @@ HnswBeginParallel(HnswBuildState * buildstate, bool isconcurrent, int request)
 	/* Enter parallel mode and create context */
 	EnterParallelMode();
 	Assert(request > 0);
-#if PG_VERSION_NUM >= 120000
 	pcxt = CreateParallelContext("vector", "HnswParallelBuildMain", request);
-#else
-	pcxt = CreateParallelContext("vector", "HnswParallelBuildMain", request, true);
-#endif
-
-	scantuplesortstates = leaderparticipates ? request + 1 : request;
 
 	/* Get snapshot for table scan */
 	if (!isconcurrent)
@@ -803,7 +921,17 @@ HnswBeginParallel(HnswBuildState * buildstate, bool isconcurrent, int request)
 	/* Estimate size of workspaces */
 	esthnswshared = ParallelEstimateShared(buildstate->heap, snapshot);
 	shm_toc_estimate_chunk(&pcxt->estimator, esthnswshared);
-	shm_toc_estimate_keys(&pcxt->estimator, 1);
+
+	/* Leave space for other objects in shared memory */
+	/* Docker has a default limit of 64 MB for shm_size */
+	/* which happens to be the default value of maintenance_work_mem */
+	esthnswarea = maintenance_work_mem * 1024L;
+	estother = 3 * 1024 * 1024;
+	if (esthnswarea > estother)
+		esthnswarea -= estother;
+
+	shm_toc_estimate_chunk(&pcxt->estimator, esthnswarea);
+	shm_toc_estimate_keys(&pcxt->estimator, 2);
 
 	/* Finally, estimate PARALLEL_KEY_QUERY_TEXT space */
 	if (debug_query_string)
@@ -834,25 +962,21 @@ HnswBeginParallel(HnswBuildState * buildstate, bool isconcurrent, int request)
 	hnswshared->heaprelid = RelationGetRelid(buildstate->heap);
 	hnswshared->indexrelid = RelationGetRelid(buildstate->index);
 	hnswshared->isconcurrent = isconcurrent;
-	hnswshared->scantuplesortstates = scantuplesortstates;
 	ConditionVariableInit(&hnswshared->workersdonecv);
 	SpinLockInit(&hnswshared->mutex);
 	/* Initialize mutable state */
 	hnswshared->nparticipantsdone = 0;
 	hnswshared->reltuples = 0;
-	InitGraph(&hnswshared->graphData);
-	/* TODO Support in-memory builds */
-	hnswshared->graphData.memoryTotal = 0;
-	hnswshared->graphData.flushed = true;
-#if PG_VERSION_NUM >= 120000
 	table_parallelscan_initialize(buildstate->heap,
 								  ParallelTableScanFromHnswShared(hnswshared),
 								  snapshot);
-#else
+
-	heap_parallelscan_initialize(&hnswshared->heapdesc, buildstate->heap, snapshot);
+	hnswarea = (char *) shm_toc_allocate(pcxt->toc, esthnswarea);
-#endif
+	/* Report less than allocated so never fails */
+	InitGraph(&hnswshared->graphData, hnswarea, esthnswarea - 1024 * 1024);
 
 	shm_toc_insert(pcxt->toc, PARALLEL_KEY_HNSW_SHARED, hnswshared);
+	shm_toc_insert(pcxt->toc, PARALLEL_KEY_HNSW_AREA, hnswarea);
 
 	/* Store query string for workers */
 	if (debug_query_string)
@@ -872,6 +996,7 @@ HnswBeginParallel(HnswBuildState * buildstate, bool isconcurrent, int request)
 		hnswleader->nparticipanttuplesorts++;
 	hnswleader->hnswshared = hnswshared;
 	hnswleader->snapshot = snapshot;
+	hnswleader->hnswarea = hnswarea;
 
 	/* If no workers were successfully launched, back out (do serial build) */
 	if (pcxt->nworkers_launched == 0)
@@ -926,16 +1051,12 @@ BuildGraph(HnswBuildState * buildstate, ForkNumber forkNum)
 	UpdateProgress(PROGRESS_CREATEIDX_SUBPHASE, PROGRESS_HNSW_PHASE_LOAD);
 
 	/* Calculate parallel workers */
-	if (buildstate->heap != NULL && hnsw_enable_parallel_build)
+	if (buildstate->heap != NULL)
 		parallel_workers = ComputeParallelWorkers(buildstate->heap, buildstate->index);
 
 	/* Attempt to launch parallel worker scan when required */
 	if (parallel_workers > 0)
-	{
-		/* TODO Support in-memory builds */
-		FlushPages(buildstate);
 		HnswBeginParallel(buildstate, buildstate->indexInfo->ii_Concurrent, parallel_workers);
-	}
 
 	/* Add tuples to graph */
 	if (buildstate->heap != NULL)
@@ -943,15 +1064,8 @@ BuildGraph(HnswBuildState * buildstate, ForkNumber forkNum)
 		if (buildstate->hnswleader)
 			buildstate->reltuples = ParallelHeapScan(buildstate);
 		else
-		{
-#if PG_VERSION_NUM >= 120000
 			buildstate->reltuples = table_index_build_scan(buildstate->heap, buildstate->index, buildstate->indexInfo,
 														   true, true, BuildCallback, (void *) buildstate, NULL);
-#else
-			buildstate->reltuples = IndexBuildHeapScan(buildstate->heap, buildstate->index, buildstate->indexInfo,
-													   true, BuildCallback, (void *) buildstate, NULL);
-#endif
-		}
 
 		buildstate->indtuples = buildstate->graph->indtuples;
 	}
@@ -965,22 +1079,6 @@ BuildGraph(HnswBuildState * buildstate, ForkNumber forkNum)
 		HnswEndParallel(buildstate->hnswleader);
 }
 
-#if PG_VERSION_NUM < 110008
-void
-log_newpage_range(Relation rel, ForkNumber forkNum, BlockNumber startblk, BlockNumber endblk, bool page_std)
-{
-	for (BlockNumber blkno = startblk; blkno < endblk; blkno++)
-	{
-		Buffer		buf = ReadBufferExtended(rel, forkNum, blkno, RBM_NORMAL, NULL);
-
-		LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
-		MarkBufferDirty(buf);
-		log_newpage_buffer(buf, page_std);
-		UnlockReleaseBuffer(buf);
-	}
-}
-#endif
-
 /*
  * Build the index
  */

src/hnswinsert.c

@@ -2,6 +2,7 @@
 
 #include <math.h>
 
+#include "access/generic_xlog.h"
 #include "hnsw.h"
 #include "storage/bufmgr.h"
 #include "storage/lmgr.h"
@@ -116,7 +117,7 @@ HnswInsertAppendPage(Relation index, Buffer *nbuf, Page *npage, GenericXLogState
  * Add to element and neighbor pages
  */
 static void
-WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPage, BlockNumber *updatedInsertPage, bool building)
+AddElementOnDisk(Relation index, HnswElement e, int m, BlockNumber insertPage, BlockNumber *updatedInsertPage, bool building)
 {
 	Buffer		buf;
 	Page		page;
@@ -134,9 +135,10 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
 	OffsetNumber freeOffno = InvalidOffsetNumber;
 	OffsetNumber freeNeighborOffno = InvalidOffsetNumber;
 	BlockNumber newInsertPage = InvalidBlockNumber;
+	char	   *base = NULL;
 
 	/* Calculate sizes */
-	etupSize = HNSW_ELEMENT_TUPLE_SIZE(VARSIZE_ANY(DatumGetPointer(e->value)));
+	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;
@@ -144,11 +146,11 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
 
 	/* Prepare element tuple */
 	etup = palloc0(etupSize);
-	HnswSetElementTuple(etup, e);
+	HnswSetElementTuple(base, etup, e);
 
 	/* Prepare neighbor tuple */
 	ntup = palloc0(ntupSize);
-	HnswSetNeighborTuple(ntup, e, m);
+	HnswSetNeighborTuple(base, ntup, e, m);
 
 	/* Find a page (or two if needed) to insert the tuples */
 	for (;;)
@@ -338,12 +340,14 @@ ConnectionExists(HnswElement e, HnswNeighborTuple ntup, int startIdx, int lm)
  * Update neighbors
  */
 void
-HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, 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;
+
 	for (int lc = e->level; lc >= 0; lc--)
 	{
 		int			lm = HnswGetLayerM(m, lc);
-		HnswNeighborArray *neighbors = HnswGetNeighbors(e, lc);
+		HnswNeighborArray *neighbors = HnswGetNeighbors(base, e, lc);
 
 		for (int i = 0; i < neighbors->length; i++)
 		{
@@ -356,11 +360,12 @@ HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswE
 			Size		ntupSize;
 			int			idx = -1;
 			int			startIdx;
-			OffsetNumber offno = hc->element->neighborOffno;
+			HnswElement neighborElement = HnswPtrAccess(base, hc->element);
+			OffsetNumber offno = neighborElement->neighborOffno;
 
 			/* Get latest neighbors since they may have changed */
 			/* Do not lock yet since selecting neighbors can take time */
-			HnswLoadNeighbors(hc->element, index, m);
+			HnswLoadNeighbors(neighborElement, index, m);
 
 			/*
 			 * Could improve performance for vacuuming by checking neighbors
@@ -370,14 +375,14 @@ HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswE
 			 */
 
 			/* Select neighbors */
-			HnswUpdateConnection(e, hc, lm, lc, &idx, index, procinfo, collation);
+			HnswUpdateConnection(NULL, e, hc, lm, lc, &idx, index, procinfo, collation);
 
 			/* New element was not selected as a neighbor */
 			if (idx == -1)
 				continue;
 
 			/* Register page */
-			buf = ReadBuffer(index, hc->element->neighborPage);
+			buf = ReadBuffer(index, neighborElement->neighborPage);
 			LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
 			if (building)
 			{
@@ -396,7 +401,7 @@ HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswE
 			ntupSize = ItemIdGetLength(itemid);
 
 			/* Calculate index for update */
-			startIdx = (hc->element->level - lc) * m;
+			startIdx = (neighborElement->level - lc) * m;
 
 			/* Check for existing connection */
 			if (checkExisting && ConnectionExists(e, ntup, startIdx, lm))
@@ -447,7 +452,7 @@ HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswE
  * Add a heap TID to an existing element
  */
 static bool
-HnswAddDuplicate(Relation index, HnswElement element, HnswElement dup, bool building)
+AddDuplicateOnDisk(Relation index, HnswElement element, HnswElement dup, bool building)
 {
 	Buffer		buf;
 	Page		page;
@@ -511,19 +516,23 @@ HnswAddDuplicate(Relation index, HnswElement element, HnswElement dup, bool buil
  * Find duplicate element
  */
 static bool
-HnswFindDuplicate(Relation index, HnswElement element, bool building)
+FindDuplicateOnDisk(Relation index, HnswElement element, bool building)
 {
-	HnswNeighborArray *neighbors = HnswGetNeighbors(element, 0);
+	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 (!datumIsEqual(element->value, neighbor->element->value, false, -1))
+		if (!datumIsEqual(value, neighborValue, false, -1))
 			return false;
 
-		if (HnswAddDuplicate(index, element, neighbor->element, building))
+		if (AddDuplicateOnDisk(index, element, neighborElement, building))
 			return true;
 	}
 
@@ -531,26 +540,26 @@ HnswFindDuplicate(Relation index, HnswElement element, bool building)
 }
 
 /*
- * Write changes to disk
+ * Update graph on disk
  */
 static void
-WriteElement(Relation index, FmgrInfo *procinfo, Oid collation, 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;
 
 	/* Look for duplicate */
-	if (HnswFindDuplicate(index, element, building))
+	if (FindDuplicateOnDisk(index, element, building))
 		return;
 
-	/* Write element and neighbor tuples */
+	/* Add element */
-	WriteNewElementPages(index, element, m, GetInsertPage(index), &newInsertPage, building);
+	AddElementOnDisk(index, element, m, GetInsertPage(index), &newInsertPage, building);
 
 	/* Update insert page if needed */
 	if (BlockNumberIsValid(newInsertPage))
 		HnswUpdateMetaPage(index, 0, NULL, newInsertPage, MAIN_FORKNUM, building);
 
 	/* Update neighbors */
-	HnswUpdateNeighborPages(index, procinfo, collation, element, m, false, building);
+	HnswUpdateNeighborsOnDisk(index, procinfo, collation, element, m, false, building);
 
 	/* Update entry point if needed */
 	if (entryPoint == NULL || element->level > entryPoint->level)
@@ -561,10 +570,8 @@ WriteElement(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement elem
  * Insert a tuple into the index
  */
 bool
-HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid, Relation heapRel, bool building)
+HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull, ItemPointer heap_tid, Relation heapRel, bool building)
 {
-	Datum		value;
-	FmgrInfo   *normprocinfo;
 	HnswElement entryPoint;
 	HnswElement element;
 	int			m;
@@ -572,17 +579,7 @@ HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_ti
 	FmgrInfo   *procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
 	Oid			collation = index->rd_indcollation[0];
 	LOCKMODE	lockmode = ShareLock;
-
+	char	   *base = NULL;
-	/* Detoast once for all calls */
-	value = PointerGetDatum(PG_DETOAST_DATUM(values[0]));
-
-	/* Normalize if needed */
-	normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
-	if (normprocinfo != NULL)
-	{
-		if (!HnswNormValue(normprocinfo, collation, &value, NULL))
-			return false;
-	}
 
 	/*
 	 * Get a shared lock. This allows vacuum to ensure no in-flight inserts
@@ -595,8 +592,8 @@ HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_ti
 	HnswGetMetaPageInfo(index, &m, &entryPoint);
 
 	/* Create an element */
-	element = HnswInitElement(heap_tid, m, HnswGetMl(m), HnswGetMaxLevel(m));
+	element = HnswInitElement(base, heap_tid, m, HnswGetMl(m), HnswGetMaxLevel(m), NULL);
-	element->value = value;
+	HnswPtrStore(base, element->value, DatumGetPointer(value));
 
 	/* Prevent concurrent inserts when likely updating entry point */
 	if (entryPoint == NULL || element->level > entryPoint->level)
@@ -612,11 +609,11 @@ HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_ti
 		entryPoint = HnswGetEntryPoint(index);
 	}
 
-	/* Insert element in graph */
+	/* Find neighbors for element */
-	HnswInsertElement(element, entryPoint, index, procinfo, collation, m, efConstruction, false);
+	HnswFindElementNeighbors(base, element, entryPoint, index, procinfo, collation, m, efConstruction, false);
 
-	/* Write to disk */
+	/* Update graph on disk */
-	WriteElement(index, procinfo, collation, element, m, efConstruction, entryPoint, building);
+	UpdateGraphOnDisk(index, procinfo, collation, element, m, efConstruction, entryPoint, building);
 
 	/* Release lock */
 	UnlockPage(index, HNSW_UPDATE_LOCK, lockmode);
@@ -624,6 +621,30 @@ HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_ti
 	return true;
 }
 
+/*
+ * Insert a tuple into the index
+ */
+static void
+HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid, Relation heapRel)
+{
+	Datum		value;
+	FmgrInfo   *normprocinfo;
+	Oid			collation = index->rd_indcollation[0];
+
+	/* Detoast once for all calls */
+	value = PointerGetDatum(PG_DETOAST_DATUM(values[0]));
+
+	/* Normalize if needed */
+	normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
+	if (normprocinfo != NULL)
+	{
+		if (!HnswNormValue(normprocinfo, collation, &value, NULL))
+			return;
+	}
+
+	HnswInsertTupleOnDisk(index, value, values, isnull, heap_tid, heapRel, false);
+}
+
 /*
  * Insert a tuple into the index
  */
@@ -650,7 +671,7 @@ hnswinsert(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid,
 	oldCtx = MemoryContextSwitchTo(insertCtx);
 
 	/* Insert tuple */
-	HnswInsertTuple(index, values, isnull, heap_tid, heap, false);
+	HnswInsertTuple(index, values, isnull, heap_tid, heap);
 
 	/* Delete memory context */
 	MemoryContextSwitchTo(oldCtx);

src/hnswscan.c

@@ -21,6 +21,7 @@ GetScanItems(IndexScanDesc scan, Datum q)
 	List	   *w;
 	int			m;
 	HnswElement entryPoint;
+	char	   *base = NULL;
 
 	/* Get m and entry point */
 	HnswGetMetaPageInfo(index, &m, &entryPoint);
@@ -28,15 +29,15 @@ GetScanItems(IndexScanDesc scan, Datum q)
 	if (entryPoint == NULL)
 		return NIL;
 
-	ep = list_make1(HnswEntryCandidate(entryPoint, q, index, procinfo, collation, false));
+	ep = list_make1(HnswEntryCandidate(base, entryPoint, q, index, procinfo, collation, false));
 
 	for (int lc = entryPoint->level; lc >= 1; lc--)
 	{
-		w = HnswSearchLayer(q, ep, 1, lc, index, procinfo, collation, m, false, NULL);
+		w = HnswSearchLayer(base, q, ep, 1, lc, index, procinfo, collation, m, false, NULL);
 		ep = w;
 	}
 
-	return HnswSearchLayer(q, 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);
 }
 
 /*
@@ -184,26 +185,23 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
 
 	while (list_length(so->w) > 0)
 	{
+		char	   *base = NULL;
 		HnswCandidate *hc = llast(so->w);
+		HnswElement element = HnswPtrAccess(base, hc->element);
 		ItemPointer heaptid;
 
 		/* Move to next element if no valid heap TIDs */
-		if (hc->element->heaptidsLength == 0)
+		if (element->heaptidsLength == 0)
 		{
 			so->w = list_delete_last(so->w);
 			continue;
 		}
 
-		heaptid = &hc->element->heaptids[--hc->element->heaptidsLength];
+		heaptid = &element->heaptids[--element->heaptidsLength];
 
 		MemoryContextSwitchTo(oldCtx);
 
-#if PG_VERSION_NUM >= 120000
 		scan->xs_heaptid = *heaptid;
-#else
-		scan->xs_ctup.t_self = *heaptid;
-#endif
-
 		scan->xs_recheckorderby = false;
 		return true;
 	}

src/hnswutils.c

@@ -2,9 +2,12 @@
 
 #include <math.h>
 
+#include "access/generic_xlog.h"
 #include "hnsw.h"
+#include "lib/pairingheap.h"
 #include "storage/bufmgr.h"
 #include "utils/datum.h"
+#include "utils/rel.h"
 #include "vector.h"
 
 #if PG_VERSION_NUM >= 130000
@@ -56,13 +59,6 @@ hash_tid(ItemPointerData tid)
 #define SH_DEFINE
 #include "lib/simplehash.h"
 
-/* Needed to include simplehash.h twice */
-#if PG_VERSION_NUM < 120000
-#undef SH_EQUAL
-#define sh_log2 pointerhash_sh_log2
-#define sh_pow2 pointerhash_sh_pow2
-#endif
-
 /* Pointer hash table */
 static uint32
 hash_pointer(uintptr_t ptr)
@@ -84,9 +80,31 @@ hash_pointer(uintptr_t ptr)
 #define SH_DEFINE
 #include "lib/simplehash.h"
 
+/* Offset hash table */
+static uint32
+hash_offset(Size offset)
+{
+#if SIZEOF_SIZE_T == 8
+	return murmurhash64((uint64) offset);
+#else
+	return murmurhash32((uint32) offset);
+#endif
+}
+
+#define SH_PREFIX		offsethash
+#define SH_ELEMENT_TYPE	OffsetHashEntry
+#define SH_KEY_TYPE		Size
+#define	SH_KEY			offset
+#define SH_HASH_KEY(tb, key)	hash_offset(key)
+#define SH_EQUAL(tb, a, b)		(a == b)
+#define	SH_SCOPE		extern
+#define SH_DEFINE
+#include "lib/simplehash.h"
+
 typedef union
 {
 	pointerhash_hash *pointers;
+	offsethash_hash *offsets;
 	tidhash_hash *tids;
 }			visited_hash;
 
@@ -188,31 +206,46 @@ HnswInitPage(Buffer buf, Page page)
  * Allocate neighbors
  */
 void
-HnswInitNeighbors(HnswElement element, int m)
+HnswInitNeighbors(char *base, HnswElement element, int m, HnswAllocator * allocator)
 {
 	int			level = element->level;
 
-	element->neighbors = palloc(sizeof(HnswNeighborArray) * (level + 1));
+	HnswNeighborArrayPtr *neighborList = (HnswNeighborArrayPtr *) HnswAlloc(allocator, sizeof(HnswNeighborArrayPtr) * (level + 1));
+
+	HnswPtrStore(base, element->neighbors, neighborList);
 
 	for (int lc = 0; lc <= level; lc++)
 	{
 		HnswNeighborArray *a;
 		int			lm = HnswGetLayerM(m, lc);
 
-		a = &element->neighbors[lc];
+		HnswPtrStore(base, neighborList[lc], (HnswNeighborArray *) HnswAlloc(allocator, offsetof(HnswNeighborArray, items) + sizeof(HnswCandidate) * lm));
+
+		a = HnswGetNeighbors(base, element, lc);
 		a->length = 0;
-		a->items = palloc(sizeof(HnswCandidate) * lm);
 		a->closerSet = false;
 	}
 }
 
+/*
+ * Allocate memory from the allocator
+ */
+void *
+HnswAlloc(HnswAllocator * allocator, Size size)
+{
+	if (allocator)
+		return (*(allocator)->alloc) (size, (allocator)->state);
+
+	return palloc(size);
+}
+
 /*
  * Allocate an element
  */
 HnswElement
-HnswInitElement(ItemPointer heaptid, int m, double ml, int maxLevel)
+HnswInitElement(char *base, ItemPointer heaptid, int m, double ml, int maxLevel, HnswAllocator * allocator)
 {
-	HnswElement element = palloc(sizeof(HnswElementData));
+	HnswElement element = HnswAlloc(allocator, sizeof(HnswElementData));
 
 	int			level = (int) (-log(RandomDouble()) * ml);
 
@@ -226,9 +259,9 @@ HnswInitElement(ItemPointer heaptid, int m, double ml, int maxLevel)
 	element->level = level;
 	element->deleted = 0;
 
-	HnswInitNeighbors(element, m);
+	HnswInitNeighbors(base, element, m, allocator);
 
-	element->value = PointerGetDatum(NULL);
+	HnswPtrStore(base, element->value, (Pointer) NULL);
 
 	return element;
 }
@@ -249,11 +282,12 @@ HnswElement
 HnswInitElementFromBlock(BlockNumber blkno, OffsetNumber offno)
 {
 	HnswElement element = palloc(sizeof(HnswElementData));
+	char	   *base = NULL;
 
 	element->blkno = blkno;
 	element->offno = offno;
-	element->neighbors = NULL;
+	HnswPtrStore(base, element->neighbors, (HnswNeighborArrayPtr *) NULL);
-	element->value = PointerGetDatum(NULL);
+	HnswPtrStore(base, element->value, (Pointer) NULL);
 	return element;
 }
 
@@ -363,8 +397,10 @@ HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, Bloc
  * Set element tuple, except for neighbor info
  */
 void
-HnswSetElementTuple(HnswElementTuple etup, HnswElement element)
+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;
@@ -375,14 +411,14 @@ HnswSetElementTuple(HnswElementTuple etup, HnswElement element)
 		else
 			ItemPointerSetInvalid(&etup->heaptids[i]);
 	}
-	memcpy(&etup->data, DatumGetPointer(element->value), VARSIZE_ANY(DatumGetPointer(element->value)));
+	memcpy(&etup->data, valuePtr, VARSIZE_ANY(valuePtr));
 }
 
 /*
  * Set neighbor tuple
  */
 void
-HnswSetNeighborTuple(HnswNeighborTuple ntup, HnswElement e, int m)
+HnswSetNeighborTuple(char *base, HnswNeighborTuple ntup, HnswElement e, int m)
 {
 	int			idx = 0;
 
@@ -390,7 +426,7 @@ HnswSetNeighborTuple(HnswNeighborTuple ntup, HnswElement e, int m)
 
 	for (int lc = e->level; lc >= 0; lc--)
 	{
-		HnswNeighborArray *neighbors = HnswGetNeighbors(e, lc);
+		HnswNeighborArray *neighbors = HnswGetNeighbors(base, e, lc);
 		int			lm = HnswGetLayerM(m, lc);
 
 		for (int i = 0; i < lm; i++)
@@ -400,8 +436,9 @@ HnswSetNeighborTuple(HnswNeighborTuple ntup, HnswElement e, int m)
 			if (i < neighbors->length)
 			{
 				HnswCandidate *hc = &neighbors->items[i];
+				HnswElement hce = HnswPtrAccess(base, hc->element);
 
-				ItemPointerSet(indextid, hc->element->blkno, hc->element->offno);
+				ItemPointerSet(indextid, hce->blkno, hce->offno);
 			}
 			else
 				ItemPointerSetInvalid(indextid);
@@ -417,12 +454,14 @@ HnswSetNeighborTuple(HnswNeighborTuple ntup, HnswElement e, int m)
 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(element, m);
+	HnswInitNeighbors(base, element, m, NULL);
 
 	/* Ensure expected neighbors */
 	if (ntup->count != neighborCount)
@@ -448,9 +487,9 @@ LoadNeighborsFromPage(HnswElement element, Relation index, Page page, int m)
 		if (level < 0)
 			level = 0;
 
-		neighbors = HnswGetNeighbors(element, level);
+		neighbors = HnswGetNeighbors(base, element, level);
 		hc = &neighbors->items[neighbors->length++];
-		hc->element = e;
+		HnswPtrStore(base, hc->element, e);
 	}
 }
 
@@ -497,7 +536,12 @@ HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHe
 	}
 
 	if (loadVec)
-		element->value = datumCopy(PointerGetDatum(&etup->data), false, -1);
+	{
+		char	   *base = NULL;
+		Datum		value = datumCopy(PointerGetDatum(&etup->data), false, -1);
+
+		HnswPtrStore(base, element->value, DatumGetPointer(value));
+	}
 }
 
 /*
@@ -533,24 +577,27 @@ HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation index,
  * Get the distance for a candidate
  */
 static float
-GetCandidateDistance(HnswCandidate * hc, Datum q, FmgrInfo *procinfo, Oid collation)
+GetCandidateDistance(char *base, HnswCandidate * hc, Datum q, FmgrInfo *procinfo, Oid collation)
 {
-	return DatumGetFloat8(FunctionCall2Coll(procinfo, collation, q, hc->element->value));
+	HnswElement hce = HnswPtrAccess(base, hc->element);
+	Datum		value = HnswGetValue(base, hce);
+
+	return DatumGetFloat8(FunctionCall2Coll(procinfo, collation, q, value));
 }
 
 /*
  * Create a candidate for the entry point
  */
 HnswCandidate *
-HnswEntryCandidate(HnswElement entryPoint, Datum q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec)
+HnswEntryCandidate(char *base, HnswElement entryPoint, Datum q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec)
 {
 	HnswCandidate *hc = palloc(sizeof(HnswCandidate));
 
-	hc->element = entryPoint;
+	HnswPtrStore(base, hc->element, entryPoint);
 	if (index == NULL)
-		hc->distance = GetCandidateDistance(hc, q, procinfo, collation);
+		hc->distance = GetCandidateDistance(base, hc, q, procinfo, collation);
 	else
-		HnswLoadElement(hc->element, &hc->distance, &q, index, procinfo, collation, loadVec);
+		HnswLoadElement(entryPoint, &hc->distance, &q, index, procinfo, collation, loadVec);
 	return hc;
 }
 
@@ -596,34 +643,79 @@ CreatePairingHeapNode(HnswCandidate * c)
 	return node;
 }
 
+/*
+ * Init visited
+ */
+static inline void
+InitVisited(char *base, visited_hash * v, Relation index, int ef, int m)
+{
+	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);
+	else
+		v->pointers = pointerhash_create(CurrentMemoryContext, ef * m * 2, NULL);
+}
+
 /*
  * Add to visited
  */
 static inline void
-AddToVisited(visited_hash v, HnswCandidate * hc, Relation index, bool *found)
+AddToVisited(char *base, visited_hash * v, HnswCandidate * hc, Relation index, bool *found)
 {
-	if (index == NULL)
+	if (index != NULL)
+	{
+		HnswElement element = HnswPtrAccess(base, hc->element);
+		ItemPointerData indextid;
+
+		ItemPointerSet(&indextid, element->blkno, element->offno);
+		tidhash_insert(v->tids, indextid, found);
+	}
+	else if (base != NULL)
 	{
 #if PG_VERSION_NUM >= 130000
-		pointerhash_insert_hash(v.pointers, (uintptr_t) hc->element, hc->element->hash, found);
+		HnswElement element = HnswPtrAccess(base, hc->element);
+
+		offsethash_insert_hash(v->offsets, HnswPtrOffset(hc->element), element->hash, found);
 #else
-		pointerhash_insert(v.pointers, (uintptr_t) hc->element, found);
+		offsethash_insert(v->offsets, HnswPtrOffset(hc->element), found);
 #endif
 	}
 	else
 	{
-		ItemPointerData indextid;
+#if PG_VERSION_NUM >= 130000
+		HnswElement element = HnswPtrAccess(base, hc->element);
 
-		ItemPointerSet(&indextid, hc->element->blkno, hc->element->offno);
+		pointerhash_insert_hash(v->pointers, (uintptr_t) HnswPtrPointer(hc->element), element->hash, found);
-		tidhash_insert(v.tids, indextid, found);
+#else
+		pointerhash_insert(v->pointers, (uintptr_t) HnswPtrPointer(hc->element), found);
+#endif
 	}
 }
 
+/*
+ * Count element towards ef
+ */
+static inline bool
+CountElement(char *base, HnswElement skipElement, HnswCandidate * hc)
+{
+	HnswElement e;
+
+	if (skipElement == NULL)
+		return true;
+
+	/* Ensure does not access heaptidsLength during in-memory build */
+	pg_memory_barrier();
+
+	e = HnswPtrAccess(base, hc->element);
+	return e->heaptidsLength != 0;
+}
+
 /*
  * Algorithm 2 from paper
  */
 List *
-HnswSearchLayer(Datum q, 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);
@@ -631,12 +723,17 @@ HnswSearchLayer(Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *pro
 	int			wlen = 0;
 	visited_hash v;
 	ListCell   *lc2;
+	HnswNeighborArray *neighborhoodData = NULL;
+	Size		neighborhoodSize;
 
-	/* Create hash table */
+	InitVisited(base, &v, index, ef, m);
+
+	/* Create local memory for neighborhood if needed */
 	if (index == NULL)
-		v.pointers = pointerhash_create(CurrentMemoryContext, ef * m * 2, NULL);
+	{
-	else
+		neighborhoodSize = offsetof(HnswNeighborArray, items) + sizeof(HnswCandidate) * HnswGetLayerM(m, lc);
-		v.tids = tidhash_create(CurrentMemoryContext, ef * m * 2, NULL);
+		neighborhoodData = palloc(neighborhoodSize);
+	}
 
 	/* Add entry points to v, C, and W */
 	foreach(lc2, ep)
@@ -644,7 +741,7 @@ HnswSearchLayer(Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *pro
 		HnswCandidate *hc = (HnswCandidate *) lfirst(lc2);
 		bool		found;
 
-		AddToVisited(v, hc, index, &found);
+		AddToVisited(base, &v, hc, index, &found);
 
 		pairingheap_add(C, &(CreatePairingHeapNode(hc)->ph_node));
 		pairingheap_add(W, &(CreatePairingHeapNode(hc)->ph_node));
@@ -654,7 +751,7 @@ HnswSearchLayer(Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *pro
 		 * would be ideal to do this for inserts as well, but this could
 		 * affect insert performance.
 		 */
-		if (skipElement == NULL || hc->element->heaptidsLength != 0)
+		if (CountElement(base, skipElement, hc))
 			wlen++;
 	}
 
@@ -663,38 +760,51 @@ HnswSearchLayer(Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *pro
 		HnswNeighborArray *neighborhood;
 		HnswCandidate *c = ((HnswPairingHeapNode *) pairingheap_remove_first(C))->inner;
 		HnswCandidate *f = ((HnswPairingHeapNode *) pairingheap_first(W))->inner;
+		HnswElement cElement;
 
 		if (c->distance > f->distance)
 			break;
 
-		if (c->element->neighbors == NULL)
+		cElement = HnswPtrAccess(base, c->element);
-			HnswLoadNeighbors(c->element, index, m);
+
+		if (HnswPtrIsNull(base, cElement->neighbors))
+			HnswLoadNeighbors(cElement, index, m);
 
 		/* Get the neighborhood at layer lc */
-		neighborhood = HnswGetNeighbors(c->element, lc);
+		neighborhood = HnswGetNeighbors(base, cElement, lc);
+
+		/* Copy neighborhood to local memory if needed */
+		if (index == NULL)
+		{
+			LWLockAcquire(&cElement->lock, LW_SHARED);
+			memcpy(neighborhoodData, neighborhood, neighborhoodSize);
+			LWLockRelease(&cElement->lock);
+			neighborhood = neighborhoodData;
+		}
 
 		for (int i = 0; i < neighborhood->length; i++)
 		{
 			HnswCandidate *e = &neighborhood->items[i];
 			bool		visited;
 
-			AddToVisited(v, e, index, &visited);
+			AddToVisited(base, &v, e, index, &visited);
 
 			if (!visited)
 			{
 				float		eDistance;
+				HnswElement eElement = HnswPtrAccess(base, e->element);
 
 				f = ((HnswPairingHeapNode *) pairingheap_first(W))->inner;
 
 				if (index == NULL)
-					eDistance = GetCandidateDistance(e, q, procinfo, collation);
+					eDistance = GetCandidateDistance(base, e, q, procinfo, collation);
 				else
-					HnswLoadElement(e->element, &eDistance, &q, index, procinfo, collation, inserting);
+					HnswLoadElement(eElement, &eDistance, &q, index, procinfo, collation, inserting);
 
-				Assert(!e->element->deleted);
+				Assert(!eElement->deleted);
 
 				/* Make robust to issues */
-				if (e->element->level < lc)
+				if (eElement->level < lc)
 					continue;
 
 				if (eDistance < f->distance || wlen < ef)
@@ -702,7 +812,7 @@ HnswSearchLayer(Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *pro
 					/* Copy e */
 					HnswCandidate *ec = palloc(sizeof(HnswCandidate));
 
-					ec->element = e->element;
+					HnswPtrStore(base, ec->element, eElement);
 					ec->distance = eDistance;
 
 					pairingheap_add(C, &(CreatePairingHeapNode(ec)->ph_node));
@@ -713,7 +823,7 @@ HnswSearchLayer(Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *pro
 					 * vacuuming. It would be ideal to do this for inserts as
 					 * well, but this could affect insert performance.
 					 */
-					if (skipElement == NULL || e->element->heaptidsLength != 0)
+					if (CountElement(base, skipElement, e))
 					{
 						wlen++;
 
@@ -738,7 +848,7 @@ HnswSearchLayer(Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *pro
 }
 
 /*
- * Compare candidate distances
+ * Compare candidate distances with pointer tie-breaker
  */
 static int
 #if PG_VERSION_NUM >= 130000
@@ -756,10 +866,38 @@ CompareCandidateDistances(const void *a, const void *b)
 	if (hca->distance > hcb->distance)
 		return -1;
 
-	if (hca->element < hcb->element)
+	if (HnswPtrPointer(hca->element) < HnswPtrPointer(hcb->element))
 		return 1;
 
-	if (hca->element > hcb->element)
+	if (HnswPtrPointer(hca->element) > HnswPtrPointer(hcb->element))
+		return -1;
+
+	return 0;
+}
+
+/*
+ * Compare candidate distances with offset tie-breaker
+ */
+static int
+#if PG_VERSION_NUM >= 130000
+CompareCandidateDistancesOffset(const ListCell *a, const ListCell *b)
+#else
+CompareCandidateDistancesOffset(const void *a, const void *b)
+#endif
+{
+	HnswCandidate *hca = lfirst((ListCell *) a);
+	HnswCandidate *hcb = lfirst((ListCell *) b);
+
+	if (hca->distance < hcb->distance)
+		return 1;
+
+	if (hca->distance > hcb->distance)
+		return -1;
+
+	if (HnswPtrOffset(hca->element) < HnswPtrOffset(hcb->element))
+		return 1;
+
+	if (HnswPtrOffset(hca->element) > HnswPtrOffset(hcb->element))
 		return -1;
 
 	return 0;
@@ -769,46 +907,58 @@ CompareCandidateDistances(const void *a, const void *b)
  * Calculate the distance between elements
  */
 static float
-HnswGetDistance(HnswElement a, HnswElement b, int lc, FmgrInfo *procinfo, Oid collation)
+HnswGetDistance(char *base, HnswElement a, HnswElement b, int lc, FmgrInfo *procinfo, Oid collation)
 {
+	Datum		aValue;
+	Datum		bValue;
+
 	/* Look for cached distance */
-	if (a->neighbors != NULL)
+	if (!HnswPtrIsNull(base, a->neighbors))
 	{
-		HnswNeighborArray *neighbors = HnswGetNeighbors(a, lc);
+		HnswNeighborArray *neighbors = HnswGetNeighbors(base, a, lc);
 
 		for (int i = 0; i < neighbors->length; i++)
 		{
-			if (neighbors->items[i].element == b)
+			HnswElement element = HnswPtrAccess(base, neighbors->items[i].element);
+
+			if (element == b)
 				return neighbors->items[i].distance;
 		}
 	}
 
-	if (b->neighbors != NULL)
+	if (!HnswPtrIsNull(base, b->neighbors))
 	{
-		HnswNeighborArray *neighbors = HnswGetNeighbors(b, lc);
+		HnswNeighborArray *neighbors = HnswGetNeighbors(base, b, lc);
 
 		for (int i = 0; i < neighbors->length; i++)
 		{
-			if (neighbors->items[i].element == a)
+			HnswElement element = HnswPtrAccess(base, neighbors->items[i].element);
+
+			if (element == a)
 				return neighbors->items[i].distance;
 		}
 	}
 
-	return DatumGetFloat8(FunctionCall2Coll(procinfo, collation, a->value, b->value));
+	aValue = HnswGetValue(base, a);
+	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(HnswCandidate * e, List *r, int lc, FmgrInfo *procinfo, Oid collation)
+CheckElementCloser(char *base, HnswCandidate * e, List *r, int lc, FmgrInfo *procinfo, Oid collation)
 {
+	HnswElement eElement = HnswPtrAccess(base, e->element);
 	ListCell   *lc2;
 
 	foreach(lc2, r)
 	{
 		HnswCandidate *ri = lfirst(lc2);
-		float		distance = HnswGetDistance(e->element, ri->element, lc, procinfo, collation);
+		HnswElement riElement = HnswPtrAccess(base, ri->element);
+		float		distance = HnswGetDistance(base, eElement, riElement, lc, procinfo, collation);
 
 		if (distance <= e->distance)
 			return false;
@@ -821,26 +971,31 @@ CheckElementCloser(HnswCandidate * e, List *r, int lc, FmgrInfo *procinfo, Oid c
  * Algorithm 4 from paper
  */
 static List *
-SelectNeighbors(List *c, int m, int lc, FmgrInfo *procinfo, Oid collation, HnswElement e2, 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);
 	pairingheap *wd;
-	HnswNeighborArray *neighbors = HnswGetNeighbors(e2, lc);
+	HnswNeighborArray *neighbors = HnswGetNeighbors(base, e2, lc);
 	bool		mustCalculate = !neighbors->closerSet;
 	List	   *added = NIL;
 	bool		removedAny = false;
 
-	if (list_length(w) <= m)
+	if (list_length(w) <= lm)
 		return w;
 
 	wd = pairingheap_allocate(CompareNearestCandidates, NULL);
 
 	/* Ensure order of candidates is deterministic for closer caching */
 	if (sortCandidates)
-		list_sort(w, CompareCandidateDistances);
+	{
+		if (base == NULL)
+			list_sort(w, CompareCandidateDistances);
+		else
+			list_sort(w, CompareCandidateDistancesOffset);
+	}
 
-	while (list_length(w) > 0 && list_length(r) < m)
+	while (list_length(w) > 0 && list_length(r) < lm)
 	{
 		/* Assumes w is already ordered desc */
 		HnswCandidate *e = llast(w);
@@ -849,7 +1004,7 @@ SelectNeighbors(List *c, int m, int lc, FmgrInfo *procinfo, Oid collation, HnswE
 
 		/* Use previous state of r and wd to skip work when possible */
 		if (mustCalculate)
-			e->closer = CheckElementCloser(e, r, lc, procinfo, collation);
+			e->closer = CheckElementCloser(base, e, r, lc, procinfo, collation);
 		else if (list_length(added) > 0)
 		{
 			/*
@@ -858,7 +1013,7 @@ SelectNeighbors(List *c, int m, int lc, FmgrInfo *procinfo, Oid collation, HnswE
 			 */
 			if (e->closer)
 			{
-				e->closer = CheckElementCloser(e, added, lc, procinfo, collation);
+				e->closer = CheckElementCloser(base, e, added, lc, procinfo, collation);
 
 				if (!e->closer)
 					removedAny = true;
@@ -871,7 +1026,7 @@ SelectNeighbors(List *c, int m, int lc, FmgrInfo *procinfo, Oid collation, HnswE
 				 */
 				if (removedAny)
 				{
-					e->closer = CheckElementCloser(e, r, lc, procinfo, collation);
+					e->closer = CheckElementCloser(base, e, r, lc, procinfo, collation);
 					if (e->closer)
 						added = lappend(added, e);
 				}
@@ -879,7 +1034,7 @@ SelectNeighbors(List *c, int m, int lc, FmgrInfo *procinfo, Oid collation, HnswE
 		}
 		else if (e == newCandidate)
 		{
-			e->closer = CheckElementCloser(e, r, lc, procinfo, collation);
+			e->closer = CheckElementCloser(base, e, r, lc, procinfo, collation);
 			if (e->closer)
 				added = lappend(added, e);
 		}
@@ -894,7 +1049,7 @@ SelectNeighbors(List *c, int m, int lc, FmgrInfo *procinfo, Oid collation, HnswE
 	neighbors->closerSet = sortCandidates;
 
 	/* Keep pruned connections */
-	while (!pairingheap_is_empty(wd) && list_length(r) < m)
+	while (!pairingheap_is_empty(wd) && list_length(r) < lm)
 		r = lappend(r, ((HnswPairingHeapNode *) pairingheap_remove_first(wd))->inner);
 
 	/* Return pruned for update connections */
@@ -913,10 +1068,10 @@ SelectNeighbors(List *c, int m, int lc, FmgrInfo *procinfo, Oid collation, HnswE
  * Add connections
  */
 static void
-AddConnections(HnswElement element, List *neighbors, int m, int lc)
+AddConnections(char *base, HnswElement element, List *neighbors, int lc)
 {
 	ListCell   *lc2;
-	HnswNeighborArray *a = HnswGetNeighbors(element, lc);
+	HnswNeighborArray *a = HnswGetNeighbors(base, element, lc);
 
 	foreach(lc2, neighbors)
 		a->items[a->length++] = *((HnswCandidate *) lfirst(lc2));
@@ -926,16 +1081,16 @@ AddConnections(HnswElement element, List *neighbors, int m, int lc)
  * Update connections
  */
 void
-HnswUpdateConnection(HnswElement element, HnswCandidate * hc, int m, int lc, int *updateIdx, Relation index, FmgrInfo *procinfo, Oid collation)
+HnswUpdateConnection(char *base, HnswElement element, HnswCandidate * hc, int lm, int lc, int *updateIdx, Relation index, FmgrInfo *procinfo, Oid collation)
 {
-	HnswNeighborArray *currentNeighbors = HnswGetNeighbors(hc->element, lc);
+	HnswElement hce = HnswPtrAccess(base, hc->element);
-
+	HnswNeighborArray *currentNeighbors = HnswGetNeighbors(base, hce, lc);
 	HnswCandidate hc2;
 
-	hc2.element = element;
+	HnswPtrStore(base, hc2.element, element);
 	hc2.distance = hc->distance;
 
-	if (currentNeighbors->length < m)
+	if (currentNeighbors->length < lm)
 	{
 		currentNeighbors->items[currentNeighbors->length++] = hc2;
 
@@ -951,19 +1106,20 @@ HnswUpdateConnection(HnswElement element, HnswCandidate * hc, int m, int lc, int
 		/* Load elements on insert */
 		if (index != NULL)
 		{
-			Datum		q = hc->element->value;
+			Datum		q = HnswGetValue(base, hce);
 
 			for (int i = 0; i < currentNeighbors->length; i++)
 			{
 				HnswCandidate *hc3 = &currentNeighbors->items[i];
+				HnswElement hc3Element = HnswPtrAccess(base, hc3->element);
 
-				if (DatumGetPointer(hc3->element->value) == NULL)
+				if (HnswPtrIsNull(base, hc3Element->value))
-					HnswLoadElement(hc3->element, &hc3->distance, &q, index, procinfo, collation, true);
+					HnswLoadElement(hc3Element, &hc3->distance, &q, index, procinfo, collation, true);
 				else
-					hc3->distance = GetCandidateDistance(hc3, q, procinfo, collation);
+					hc3->distance = GetCandidateDistance(base, hc3, q, procinfo, collation);
 
 				/* Prune element if being deleted */
-				if (hc3->element->heaptidsLength == 0)
+				if (hc3Element->heaptidsLength == 0)
 				{
 					pruned = &currentNeighbors->items[i];
 					break;
@@ -980,7 +1136,7 @@ HnswUpdateConnection(HnswElement element, HnswCandidate * hc, int m, int lc, int
 				c = lappend(c, &currentNeighbors->items[i]);
 			c = lappend(c, &hc2);
 
-			SelectNeighbors(c, m, lc, procinfo, collation, hc->element, &hc2, &pruned, true);
+			SelectNeighbors(base, c, lm, lc, procinfo, collation, hce, &hc2, &pruned, true);
 
 			/* Should not happen */
 			if (pruned == NULL)
@@ -990,7 +1146,7 @@ HnswUpdateConnection(HnswElement element, HnswCandidate * hc, int m, int lc, int
 		/* Find and replace the pruned element */
 		for (int i = 0; i < currentNeighbors->length; i++)
 		{
-			if (currentNeighbors->items[i].element == pruned->element)
+			if (HnswPtrEqual(base, currentNeighbors->items[i].element, pruned->element))
 			{
 				currentNeighbors->items[i] = hc2;
 
@@ -1008,43 +1164,65 @@ HnswUpdateConnection(HnswElement element, HnswCandidate * hc, int m, int lc, int
  * Remove elements being deleted or skipped
  */
 static List *
-RemoveElements(List *w, HnswElement skipElement)
+RemoveElements(char *base, List *w, HnswElement skipElement)
 {
 	ListCell   *lc2;
 	List	   *w2 = NIL;
 
+	/* Ensure does not access heaptidsLength during in-memory build */
+	pg_memory_barrier();
+
 	foreach(lc2, w)
 	{
 		HnswCandidate *hc = (HnswCandidate *) lfirst(lc2);
+		HnswElement hce = HnswPtrAccess(base, hc->element);
 
 		/* Skip self for vacuuming update */
-		if (skipElement != NULL && hc->element->blkno == skipElement->blkno && hc->element->offno == skipElement->offno)
+		if (skipElement != NULL && hce->blkno == skipElement->blkno && hce->offno == skipElement->offno)
 			continue;
 
-		if (hc->element->heaptidsLength != 0)
+		if (hce->heaptidsLength != 0)
 			w2 = lappend(w2, hc);
 	}
 
 	return w2;
 }
 
+#if PG_VERSION_NUM >= 130000
+/*
+ * Precompute hash
+ */
+static void
+PrecomputeHash(char *base, HnswElement element)
+{
+	HnswElementPtr ptr;
+
+	HnswPtrStore(base, ptr, element);
+
+	if (base == NULL)
+		element->hash = hash_pointer((uintptr_t) HnswPtrPointer(ptr));
+	else
+		element->hash = hash_offset(HnswPtrOffset(ptr));
+}
+#endif
+
 /*
  * Algorithm 1 from paper
  */
 void
-HnswInsertElement(HnswElement element, HnswElement entryPoint, Relation index, FmgrInfo *procinfo, Oid collation, 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;
-	Datum		q = element->value;
+	Datum		q = HnswGetValue(base, element);
 	HnswElement skipElement = existing ? element : NULL;
 
 #if PG_VERSION_NUM >= 130000
 	/* Precompute hash */
 	if (index == NULL)
-		element->hash = hash_pointer((uintptr_t) element);
+		PrecomputeHash(base, element);
 #endif
 
 	/* No neighbors if no entry point */
@@ -1052,13 +1230,13 @@ HnswInsertElement(HnswElement element, HnswElement entryPoint, Relation index, F
 		return;
 
 	/* Get entry point and level */
-	ep = list_make1(HnswEntryCandidate(entryPoint, q, index, procinfo, collation, 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(q, ep, 1, lc, index, procinfo, collation, m, true, skipElement);
+		w = HnswSearchLayer(base, q, ep, 1, lc, index, procinfo, collation, m, true, skipElement);
 		ep = w;
 	}
 
@@ -1076,12 +1254,12 @@ HnswInsertElement(HnswElement element, HnswElement entryPoint, Relation index, F
 		List	   *neighbors;
 		List	   *lw;
 
-		w = HnswSearchLayer(q, 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 */
 		if (index != NULL)
-			lw = RemoveElements(w, skipElement);
+			lw = RemoveElements(base, w, skipElement);
 		else
 			lw = w;
 
@@ -1090,9 +1268,9 @@ HnswInsertElement(HnswElement element, HnswElement entryPoint, Relation index, F
 		 * sortCandidates to true for in-memory builds to enable closer
 		 * caching, but there does not seem to be a difference in performance.
 		 */
-		neighbors = SelectNeighbors(lw, lm, lc, procinfo, collation, element, NULL, NULL, false);
+		neighbors = SelectNeighbors(base, lw, lm, lc, procinfo, collation, element, NULL, NULL, false);
 
-		AddConnections(element, neighbors, lm, lc);
+		AddConnections(base, element, neighbors, lc);
 
 		ep = w;
 	}

src/hnswvacuum.c

@@ -2,6 +2,7 @@
 
 #include <math.h>
 
+#include "access/generic_xlog.h"
 #include "commands/vacuum.h"
 #include "hnsw.h"
 #include "storage/bufmgr.h"
@@ -199,21 +200,22 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
 	BufferAccessStrategy bas = vacuumstate->bas;
 	HnswNeighborTuple ntup = vacuumstate->ntup;
 	Size		ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(element->level, m);
+	char	   *base = NULL;
 
 	/* Skip if element is entry point */
 	if (entryPoint != NULL && element->blkno == entryPoint->blkno && element->offno == entryPoint->offno)
 		return;
 
 	/* Init fields */
-	HnswInitNeighbors(element, m);
+	HnswInitNeighbors(base, element, m, NULL);
 	element->heaptidsLength = 0;
 
-	/* Add element to graph, skipping itself */
+	/* Find neighbors for element, skipping itself */
-	HnswInsertElement(element, entryPoint, index, procinfo, collation, m, efConstruction, true);
+	HnswFindElementNeighbors(base, element, entryPoint, index, procinfo, collation, m, efConstruction, true);
 
 	/* Update neighbor tuple */
 	/* Do this before getting page to minimize locking */
-	HnswSetNeighborTuple(ntup, element, m);
+	HnswSetNeighborTuple(base, ntup, element, m);
 
 	/* Get neighbor page */
 	buf = ReadBufferExtended(index, MAIN_FORKNUM, element->neighborPage, RBM_NORMAL, bas);
@@ -230,7 +232,7 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
 	UnlockReleaseBuffer(buf);
 
 	/* Update neighbors */
-	HnswUpdateNeighborPages(index, procinfo, collation, element, m, true, false);
+	HnswUpdateNeighborsOnDisk(index, procinfo, collation, element, m, true, false);
 }
 
 /*
@@ -301,7 +303,7 @@ RepairGraphEntryPoint(HnswVacuumState * vacuumstate)
 			{
 				/* Reset neighbors from previous update */
 				if (highestPoint != NULL)
-					highestPoint->neighbors = NULL;
+					HnswPtrStore((char *) NULL, highestPoint->neighbors, (HnswNeighborArrayPtr *) NULL);
 
 				RepairGraphElement(vacuumstate, entryPoint, highestPoint);
 			}

src/ivfbuild.c

@@ -2,30 +2,25 @@
 
 #include <float.h>
 
+#include "access/table.h"
+#include "access/tableam.h"
 #include "access/parallel.h"
 #include "access/xact.h"
 #include "catalog/index.h"
 #include "catalog/pg_operator_d.h"
 #include "catalog/pg_type_d.h"
+#include "commands/progress.h"
 #include "ivfflat.h"
 #include "miscadmin.h"
+#include "optimizer/optimizer.h"
 #include "storage/bufmgr.h"
 #include "tcop/tcopprot.h"
 #include "utils/memutils.h"
 
 #if PG_VERSION_NUM >= 140000
 #include "utils/backend_progress.h"
-#elif PG_VERSION_NUM >= 120000
-#include "pgstat.h"
-#endif
-
-#if PG_VERSION_NUM >= 120000
-#include "access/tableam.h"
-#include "commands/progress.h"
 #else
-#define PROGRESS_CREATEIDX_SUBPHASE 0
+#include "pgstat.h"
-#define PROGRESS_CREATEIDX_TUPLES_TOTAL 0
-#define PROGRESS_CREATEIDX_TUPLES_DONE 0
 #endif
 
 #if PG_VERSION_NUM >= 130000
@@ -34,26 +29,13 @@
 #define CALLBACK_ITEM_POINTER HeapTuple hup
 #endif
 
-#if PG_VERSION_NUM >= 120000
 #define UpdateProgress(index, val) pgstat_progress_update_param(index, val)
-#else
-#define UpdateProgress(index, val) ((void)val)
-#endif
 
 #if PG_VERSION_NUM >= 140000
 #include "utils/backend_status.h"
 #include "utils/wait_event.h"
 #endif
 
-#if PG_VERSION_NUM >= 120000
-#include "access/table.h"
-#include "optimizer/optimizer.h"
-#else
-#include "access/heapam.h"
-#include "optimizer/planner.h"
-#include "pgstat.h"
-#endif
-
 #define PARALLEL_KEY_IVFFLAT_SHARED		UINT64CONST(0xA000000000000001)
 #define PARALLEL_KEY_TUPLESORT			UINT64CONST(0xA000000000000002)
 #define PARALLEL_KEY_IVFFLAT_CENTERS	UINT64CONST(0xA000000000000003)
@@ -150,13 +132,8 @@ SampleRows(IvfflatBuildState * buildstate)
 	{
 		BlockNumber targblock = BlockSampler_Next(&buildstate->bs);
 
-#if PG_VERSION_NUM >= 120000
 		table_index_build_range_scan(buildstate->heap, buildstate->index, buildstate->indexInfo,
 									 false, true, false, targblock, 1, SampleCallback, (void *) buildstate, NULL);
-#else
-		IndexBuildHeapRangeScan(buildstate->heap, buildstate->index, buildstate->indexInfo,
-								false, true, targblock, 1, SampleCallback, (void *) buildstate, NULL);
-#endif
 	}
 }
 
@@ -282,11 +259,7 @@ InsertTuples(Relation index, IvfflatBuildState * buildstate, ForkNumber forkNum)
 	IndexTuple	itup = NULL;	/* silence compiler warning */
 	int64		inserted = 0;
 
-#if PG_VERSION_NUM >= 120000
 	TupleTableSlot *slot = MakeSingleTupleTableSlot(buildstate->tupdesc, &TTSOpsMinimalTuple);
-#else
-	TupleTableSlot *slot = MakeSingleTupleTableSlot(buildstate->tupdesc);
-#endif
 	TupleDesc	tupdesc = RelationGetDescr(index);
 
 	UpdateProgress(PROGRESS_CREATEIDX_SUBPHASE, PROGRESS_IVFFLAT_PHASE_LOAD);
@@ -375,20 +348,12 @@ InitBuildState(IvfflatBuildState * buildstate, Relation heap, Relation index, In
 		elog(ERROR, "dimensions must be greater than one for this opclass");
 
 	/* Create tuple description for sorting */
-#if PG_VERSION_NUM >= 120000
 	buildstate->tupdesc = CreateTemplateTupleDesc(3);
-#else
-	buildstate->tupdesc = CreateTemplateTupleDesc(3, false);
-#endif
 	TupleDescInitEntry(buildstate->tupdesc, (AttrNumber) 1, "list", INT4OID, -1, 0);
 	TupleDescInitEntry(buildstate->tupdesc, (AttrNumber) 2, "tid", TIDOID, -1, 0);
 	TupleDescInitEntry(buildstate->tupdesc, (AttrNumber) 3, "vector", RelationGetDescr(index)->attrs[0].atttypid, -1, 0);
 
-#if PG_VERSION_NUM >= 120000
 	buildstate->slot = MakeSingleTupleTableSlot(buildstate->tupdesc, &TTSOpsVirtual);
-#else
-	buildstate->slot = MakeSingleTupleTableSlot(buildstate->tupdesc);
-#endif
 
 	buildstate->centers = VectorArrayInit(buildstate->lists, buildstate->dimensions);
 	buildstate->listInfo = palloc(sizeof(ListInfo) * buildstate->lists);
@@ -631,11 +596,7 @@ IvfflatParallelScanAndSort(IvfflatSpool * ivfspool, IvfflatShared * ivfshared, S
 {
 	SortCoordinate coordinate;
 	IvfflatBuildState buildstate;
-#if PG_VERSION_NUM >= 120000
 	TableScanDesc scan;
-#else
-	HeapScanDesc scan;
-#endif
 	double		reltuples;
 	IndexInfo  *indexInfo;
 
@@ -659,18 +620,11 @@ IvfflatParallelScanAndSort(IvfflatSpool * ivfspool, IvfflatShared * ivfshared, S
 	buildstate.centers->length = buildstate.centers->maxlen;
 	ivfspool->sortstate = tuplesort_begin_heap(buildstate.tupdesc, 1, attNums, sortOperators, sortCollations, nullsFirstFlags, sortmem, coordinate, false);
 	buildstate.sortstate = ivfspool->sortstate;
-#if PG_VERSION_NUM >= 120000
 	scan = table_beginscan_parallel(ivfspool->heap,
 									ParallelTableScanFromIvfflatShared(ivfshared));
 	reltuples = table_index_build_scan(ivfspool->heap, ivfspool->index, indexInfo,
 									   true, progress, BuildCallback,
 									   (void *) &buildstate, scan);
-#else
-	scan = heap_beginscan_parallel(ivfspool->heap, &ivfshared->heapdesc);
-	reltuples = IndexBuildHeapScan(ivfspool->heap, ivfspool->index, indexInfo,
-								   true, BuildCallback,
-								   (void *) &buildstate, scan);
-#endif
 
 	/* Execute this worker's part of the sort */
 	tuplesort_performsort(ivfspool->sortstate);
@@ -740,11 +694,7 @@ IvfflatParallelBuildMain(dsm_segment *seg, shm_toc *toc)
 	}
 
 	/* Open relations within worker */
-#if PG_VERSION_NUM >= 120000
 	heapRel = table_open(ivfshared->heaprelid, heapLockmode);
-#else
-	heapRel = heap_open(ivfshared->heaprelid, heapLockmode);
-#endif
 	indexRel = index_open(ivfshared->indexrelid, indexLockmode);
 
 	/* Initialize worker's own spool */
@@ -764,11 +714,7 @@ IvfflatParallelBuildMain(dsm_segment *seg, shm_toc *toc)
 
 	/* Close relations within worker */
 	index_close(indexRel, indexLockmode);
-#if PG_VERSION_NUM >= 120000
 	table_close(heapRel, heapLockmode);
-#else
-	heap_close(heapRel, heapLockmode);
-#endif
 }
 
 /*
@@ -793,19 +739,7 @@ IvfflatEndParallel(IvfflatLeader * ivfleader)
 static Size
 ParallelEstimateShared(Relation heap, Snapshot snapshot)
 {
-#if PG_VERSION_NUM >= 120000
 	return add_size(BUFFERALIGN(sizeof(IvfflatShared)), table_parallelscan_estimate(heap, snapshot));
-#else
-	if (!IsMVCCSnapshot(snapshot))
-	{
-		Assert(snapshot == SnapshotAny);
-		return sizeof(IvfflatShared);
-	}
-
-	return add_size(offsetof(IvfflatShared, heapdesc) +
-					offsetof(ParallelHeapScanDescData, phs_snapshot_data),
-					EstimateSnapshotSpace(snapshot));
-#endif
 }
 
 /*
@@ -856,11 +790,7 @@ IvfflatBeginParallel(IvfflatBuildState * buildstate, bool isconcurrent, int requ
 	/* Enter parallel mode and create context */
 	EnterParallelMode();
 	Assert(request > 0);
-#if PG_VERSION_NUM >= 120000
 	pcxt = CreateParallelContext("vector", "IvfflatParallelBuildMain", request);
-#else
-	pcxt = CreateParallelContext("vector", "IvfflatParallelBuildMain", request, true);
-#endif
 
 	scantuplesortstates = leaderparticipates ? request + 1 : request;
 
@@ -918,13 +848,9 @@ IvfflatBeginParallel(IvfflatBuildState * buildstate, bool isconcurrent, int requ
 #ifdef IVFFLAT_KMEANS_DEBUG
 	ivfshared->inertia = 0;
 #endif
-#if PG_VERSION_NUM >= 120000
 	table_parallelscan_initialize(buildstate->heap,
 								  ParallelTableScanFromIvfflatShared(ivfshared),
 								  snapshot);
-#else
-	heap_parallelscan_initialize(&ivfshared->heapdesc, buildstate->heap, snapshot);
-#endif
 
 	/* Store shared tuplesort-private state, for which we reserved space */
 	sharedsort = (Sharedsort *) shm_toc_allocate(pcxt->toc, estsort);
@@ -1023,15 +949,8 @@ AssignTuples(IvfflatBuildState * buildstate)
 		if (buildstate->ivfleader)
 			buildstate->reltuples = ParallelHeapScan(buildstate);
 		else
-		{
-#if PG_VERSION_NUM >= 120000
 			buildstate->reltuples = table_index_build_scan(buildstate->heap, buildstate->index, buildstate->indexInfo,
 														   true, true, BuildCallback, (void *) buildstate, NULL);
-#else
-			buildstate->reltuples = IndexBuildHeapScan(buildstate->heap, buildstate->index, buildstate->indexInfo,
-													   true, BuildCallback, (void *) buildstate, NULL);
-#endif
-		}
 
 #ifdef IVFFLAT_KMEANS_DEBUG
 		PrintKmeansMetrics(buildstate);

src/ivfflat.c

@@ -3,14 +3,16 @@
 #include <float.h>
 
 #include "access/amapi.h"
+#include "access/reloptions.h"
+#include "commands/progress.h"
 #include "commands/vacuum.h"
 #include "ivfflat.h"
 #include "utils/guc.h"
 #include "utils/selfuncs.h"
 #include "utils/spccache.h"
 
-#if PG_VERSION_NUM >= 120000
+#if PG_VERSION_NUM < 150000
-#include "commands/progress.h"
+#define MarkGUCPrefixReserved(x) EmitWarningsOnPlaceholders(x)
 #endif
 
 int			ivfflat_probes;
@@ -33,12 +35,13 @@ IvfflatInit(void)
 	DefineCustomIntVariable("ivfflat.probes", "Sets the number of probes",
 							"Valid range is 1..lists.", &ivfflat_probes,
 							IVFFLAT_DEFAULT_PROBES, IVFFLAT_MIN_LISTS, IVFFLAT_MAX_LISTS, PGC_USERSET, 0, NULL, NULL, NULL);
+
+	MarkGUCPrefixReserved("ivfflat");
 }
 
 /*
  * Get the name of index build phase
  */
-#if PG_VERSION_NUM >= 120000
 static char *
 ivfflatbuildphasename(int64 phasenum)
 {
@@ -56,7 +59,6 @@ ivfflatbuildphasename(int64 phasenum)
 			return NULL;
 	}
 }
-#endif
 
 /*
  * Estimate the cost of an index scan
@@ -72,9 +74,6 @@ ivfflatcostestimate(PlannerInfo *root, IndexPath *path, double loop_count,
 	double		ratio;
 	double		spc_seq_page_cost;
 	Relation	index;
-#if PG_VERSION_NUM < 120000
-	List	   *qinfos;
-#endif
 
 	/* Never use index without order */
 	if (path->indexorderbys == NULL)
@@ -105,26 +104,7 @@ ivfflatcostestimate(PlannerInfo *root, IndexPath *path, double loop_count,
 	 */
 	costs.numIndexTuples = path->indexinfo->tuples * ratio;
 
-	/*
-	 * Do not use index if no limit or limit + offset > expected tuples unless
-	 * enable_seqscan = off
-	 */
-	if (root->limit_tuples < 0 || root->limit_tuples > costs.numIndexTuples)
-	{
-		*indexStartupCost = 1.0e10 - 1;
-		*indexTotalCost = 1.0e10 - 1;
-		*indexSelectivity = 0;
-		*indexCorrelation = 0;
-		*indexPages = 0;
-		return;
-	}
-
-#if PG_VERSION_NUM >= 120000
 	genericcostestimate(root, path, loop_count, &costs);
-#else
-	qinfos = deconstruct_indexquals(path);
-	genericcostestimate(root, path, loop_count, qinfos, &costs);
-#endif
 
 	get_tablespace_page_costs(path->indexinfo->reltablespace, NULL, &spc_seq_page_cost);
 
@@ -241,9 +221,7 @@ ivfflathandler(PG_FUNCTION_ARGS)
 	amroutine->amcostestimate = ivfflatcostestimate;
 	amroutine->amoptions = ivfflatoptions;
 	amroutine->amproperty = NULL;	/* TODO AMPROP_DISTANCE_ORDERABLE */
-#if PG_VERSION_NUM >= 120000
 	amroutine->ambuildphasename = ivfflatbuildphasename;
-#endif
 	amroutine->amvalidate = ivfflatvalidate;
 #if PG_VERSION_NUM >= 140000
 	amroutine->amadjustmembers = NULL;

src/ivfflat.h

@@ -3,9 +3,10 @@
 
 #include "postgres.h"
 
+#include "access/genam.h"
 #include "access/generic_xlog.h"
 #include "access/parallel.h"
-#include "access/reloptions.h"
+#include "lib/pairingheap.h"
 #include "nodes/execnodes.h"
 #include "port.h"				/* for random() */
 #include "utils/sampling.h"
@@ -16,10 +17,6 @@
 #include "common/pg_prng.h"
 #endif
 
-#if PG_VERSION_NUM < 120000
-#include "access/relscan.h"
-#endif
-
 #ifdef IVFFLAT_BENCH
 #include "portability/instr_time.h"
 #endif
@@ -135,16 +132,10 @@ typedef struct IvfflatShared
 #ifdef IVFFLAT_KMEANS_DEBUG
 	double		inertia;
 #endif
-
-#if PG_VERSION_NUM < 120000
-	ParallelHeapScanDescData heapdesc;	/* must come last */
-#endif
 }			IvfflatShared;
 
-#if PG_VERSION_NUM >= 120000
 #define ParallelTableScanFromIvfflatShared(shared) \
 	(ParallelTableScanDesc) ((char *) (shared) + BUFFERALIGN(sizeof(IvfflatShared)))
-#endif
 
 typedef struct IvfflatLeader
 {

src/ivfinsert.c

@@ -2,6 +2,7 @@
 
 #include <float.h>
 
+#include "access/generic_xlog.h"
 #include "ivfflat.h"
 #include "storage/bufmgr.h"
 #include "storage/lmgr.h"

src/ivfscan.c

@@ -5,6 +5,7 @@
 #include "access/relscan.h"
 #include "catalog/pg_operator_d.h"
 #include "catalog/pg_type_d.h"
+#include "lib/pairingheap.h"
 #include "ivfflat.h"
 #include "miscadmin.h"
 #include "pgstat.h"
@@ -105,12 +106,7 @@ GetScanItems(IndexScanDesc scan, Datum value)
 	IvfflatScanOpaque so = (IvfflatScanOpaque) scan->opaque;
 	TupleDesc	tupdesc = RelationGetDescr(scan->indexRelation);
 	double		tuples = 0;
-
-#if PG_VERSION_NUM >= 120000
 	TupleTableSlot *slot = MakeSingleTupleTableSlot(so->tupdesc, &TTSOpsVirtual);
-#else
-	TupleTableSlot *slot = MakeSingleTupleTableSlot(so->tupdesc);
-#endif
 
 	/*
 	 * Reuse same set of shared buffers for scan
@@ -216,22 +212,14 @@ ivfflatbeginscan(Relation index, int nkeys, int norderbys)
 	so->collation = index->rd_indcollation[0];
 
 	/* Create tuple description for sorting */
-#if PG_VERSION_NUM >= 120000
 	so->tupdesc = CreateTemplateTupleDesc(2);
-#else
-	so->tupdesc = CreateTemplateTupleDesc(2, false);
-#endif
 	TupleDescInitEntry(so->tupdesc, (AttrNumber) 1, "distance", FLOAT8OID, -1, 0);
 	TupleDescInitEntry(so->tupdesc, (AttrNumber) 2, "heaptid", TIDOID, -1, 0);
 
 	/* Prep sort */
 	so->sortstate = tuplesort_begin_heap(so->tupdesc, 1, attNums, sortOperators, sortCollations, nullsFirstFlags, work_mem, NULL, false);
 
-#if PG_VERSION_NUM >= 120000
 	so->slot = MakeSingleTupleTableSlot(so->tupdesc, &TTSOpsMinimalTuple);
-#else
-	so->slot = MakeSingleTupleTableSlot(so->tupdesc);
-#endif
 
 	so->listQueue = pairingheap_allocate(CompareLists, scan);
 
@@ -321,12 +309,7 @@ ivfflatgettuple(IndexScanDesc scan, ScanDirection dir)
 	{
 		ItemPointer heaptid = (ItemPointer) DatumGetPointer(slot_getattr(so->slot, 2, &so->isnull));
 
-#if PG_VERSION_NUM >= 120000
 		scan->xs_heaptid = *heaptid;
-#else
-		scan->xs_ctup.t_self = *heaptid;
-#endif
-
 		scan->xs_recheckorderby = false;
 		return true;
 	}

src/ivfutils.c

@@ -1,5 +1,6 @@
 #include "postgres.h"
 
+#include "access/generic_xlog.h"
 #include "ivfflat.h"
 #include "storage/bufmgr.h"
 #include "vector.h"

src/ivfvacuum.c

@@ -1,5 +1,6 @@
 #include "postgres.h"
 
+#include "access/generic_xlog.h"
 #include "commands/vacuum.h"
 #include "ivfflat.h"
 #include "storage/bufmgr.h"

src/vector.c

@@ -3,14 +3,17 @@
 #include <math.h>
 
 #include "catalog/pg_type.h"
+#include "common/shortest_dec.h"
 #include "fmgr.h"
 #include "hnsw.h"
 #include "ivfflat.h"
 #include "lib/stringinfo.h"
 #include "libpq/pqformat.h"
 #include "port.h"				/* for strtof() */
+#include "port/pg_bitutils.h"
 #include "utils/array.h"
 #include "utils/builtins.h"
+#include "utils/float.h"
 #include "utils/lsyscache.h"
 #include "utils/numeric.h"
 #include "vector.h"
@@ -19,13 +22,6 @@
 #include "varatt.h"
 #endif
 
-#if PG_VERSION_NUM >= 120000
-#include "common/shortest_dec.h"
-#include "utils/float.h"
-#else
-#include <float.h>
-#endif
-
 #if PG_VERSION_NUM < 130000
 #define TYPALIGN_DOUBLE 'd'
 #define TYPALIGN_INT 'i'
@@ -293,15 +289,6 @@ vector_out(PG_FUNCTION_ARGS)
 	char	   *ptr;
 	int			n;
 
-#if PG_VERSION_NUM < 120000
-	int			ndig = FLT_DIG + extra_float_digits;
-
-	if (ndig < 1)
-		ndig = 1;
-
-#define FLOAT_SHORTEST_DECIMAL_LEN (ndig + 10)
-#endif
-
 	/*
 	 * Need:
 	 *
@@ -325,11 +312,7 @@ vector_out(PG_FUNCTION_ARGS)
 			ptr++;
 		}
 
-#if PG_VERSION_NUM >= 120000
 		n = float_to_shortest_decimal_bufn(vector->x[i], ptr);
-#else
-		n = sprintf(ptr, "%.*g", ndig, vector->x[i]);
-#endif
 		ptr += n;
 	}
 	*ptr = ']';
@@ -1152,3 +1135,43 @@ vector_avg(PG_FUNCTION_ARGS)
 
 	PG_RETURN_POINTER(result);
 }
+
+/*
+ * Ensure same number of bytes
+ */
+static inline void
+CheckByteLengths(uint32 aLen, uint32 bLen)
+{
+	if (aLen != bLen)
+		ereport(ERROR,
+				(errcode(ERRCODE_DATA_EXCEPTION),
+				 errmsg("different byte lengths %u and %u", aLen, bLen)));
+}
+
+/*
+ * Get the Hamming distance between two binary strings
+ */
+PGDLLEXPORT PG_FUNCTION_INFO_V1(hamming_distance);
+Datum
+hamming_distance(PG_FUNCTION_ARGS)
+{
+	bytea	   *a = PG_GETARG_BYTEA_PP(0);
+	bytea	   *b = PG_GETARG_BYTEA_PP(1);
+	char	   *ax = VARDATA_ANY(a);
+	char	   *bx = VARDATA_ANY(b);
+	uint32		aLen = VARSIZE_ANY_EXHDR(a);
+	uint32		bLen = VARSIZE_ANY_EXHDR(b);
+	uint64		distance = 0;
+
+	CheckByteLengths(aLen, bLen);
+
+	for (uint32 i = 0; i < aLen; i++)
+	{
+		unsigned char diff = (unsigned char) (ax[i] ^ bx[i]);
+
+		distance += pg_number_of_ones[diff];
+	}
+
+	/* TODO Decide on return type */
+	PG_RETURN_FLOAT8((double) distance);
+}

test/expected/functions.out

@@ -158,6 +158,32 @@ SELECT l1_distance('[3e38]', '[-3e38]');
     Infinity
 (1 row)
 
+SELECT hamming_distance('\xFFFF', '\xFFFF');
+ hamming_distance 
+------------------
+                0
+(1 row)
+
+SELECT hamming_distance('\xFFFF', '\xFFFE');
+ hamming_distance 
+------------------
+                1
+(1 row)
+
+SELECT hamming_distance('\xFFFF', '\xFFFC');
+ hamming_distance 
+------------------
+                2
+(1 row)
+
+SELECT hamming_distance('\xFFFF', '\x0000');
+ hamming_distance 
+------------------
+               16
+(1 row)
+
+SELECT hamming_distance('\xFFFF', '\x00');
+ERROR:  different byte lengths 2 and 1
 SELECT avg(v) FROM unnest(ARRAY['[1,2,3]'::vector, '[3,5,7]']) v;
     avg    
 -----------

test/sql/functions.sql

@@ -37,6 +37,12 @@ SELECT l1_distance('[0,0]', '[0,1]');
 SELECT l1_distance('[1,2]', '[3]');
 SELECT l1_distance('[3e38]', '[-3e38]');
 
+SELECT hamming_distance('\xFFFF', '\xFFFF');
+SELECT hamming_distance('\xFFFF', '\xFFFE');
+SELECT hamming_distance('\xFFFF', '\xFFFC');
+SELECT hamming_distance('\xFFFF', '\x0000');
+SELECT hamming_distance('\xFFFF', '\x00');
+
 SELECT avg(v) FROM unnest(ARRAY['[1,2,3]'::vector, '[3,5,7]']) v;
 SELECT avg(v) FROM unnest(ARRAY['[1,2,3]'::vector, '[3,5,7]', NULL]) v;
 SELECT avg(v) FROM unnest(ARRAY[]::vector[]) v;

test/t/012_hnsw_build_recall.pl

@@ -95,11 +95,10 @@ for my $i (0 .. $#operators)
 
 	$node->safe_psql("postgres", "DROP INDEX idx;");
 
-	# Build index in parallel
+	# Build index in parallel in memory
 	my ($ret, $stdout, $stderr) = $node->psql("postgres", qq(
 		SET client_min_messages = DEBUG;
 		SET min_parallel_table_scan_size = 1;
-		SET hnsw.enable_parallel_build = on;
 		CREATE INDEX idx ON tst USING hnsw (v $opclass);
 	));
 	is($ret, 0, $stderr);
@@ -109,6 +108,21 @@ for my $i (0 .. $#operators)
 	test_recall($min, $operator);
 
 	$node->safe_psql("postgres", "DROP INDEX idx;");
+
+	# Build index in parallel on disk
+	# Set parallel_workers on table to use workers with low maintenance_work_mem
+	($ret, $stdout, $stderr) = $node->psql("postgres", qq(
+		ALTER TABLE tst SET (parallel_workers = 2);
+		SET client_min_messages = DEBUG;
+		SET maintenance_work_mem = '4MB';
+		CREATE INDEX idx ON tst USING hnsw (v $opclass);
+		ALTER TABLE tst RESET (parallel_workers);
+	));
+	is($ret, 0, $stderr);
+	like($stderr, qr/using \d+ parallel workers/);
+	like($stderr, qr/hnsw graph no longer fits into maintenance_work_mem/);
+
+	$node->safe_psql("postgres", "DROP INDEX idx;");
 }
 
 done_testing();

test/t/018_hnsw_filtering.pl

@@ -0,0 +1,114 @@
+use strict;
+use warnings;
+use PostgresNode;
+use TestLib;
+use Test::More;
+
+my $dim = 3;
+my $nc = 50;
+my $limit = 20;
+
+my $array_sql = join(",", ('random()') x $dim);
+
+# Initialize node
+my $node = get_new_node('node');
+$node->init;
+$node->start;
+
+# Create table and index
+$node->safe_psql("postgres", "CREATE EXTENSION vector;");
+$node->safe_psql("postgres", "CREATE TABLE tst (i int4, v vector($dim), c int4, t text);");
+$node->safe_psql("postgres",
+	"INSERT INTO tst SELECT i, ARRAY[$array_sql], i % $nc, 'test ' || i FROM generate_series(1, 10000) i;"
+);
+$node->safe_psql("postgres", "CREATE INDEX idx ON tst USING hnsw (v vector_l2_ops);");
+$node->safe_psql("postgres", "ANALYZE tst;");
+
+# Generate query
+my @r = ();
+for (1 .. $dim)
+{
+	push(@r, rand());
+}
+my $query = "[" . join(",", @r) . "]";
+my $c = int(rand() * $nc);
+
+# Test attribute filtering
+my $explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE c = $c ORDER BY v <-> '$query' LIMIT $limit;
+));
+# TODO Do not use index
+like($explain, qr/Index Scan using idx/);
+
+# Test attribute filtering with few rows removed
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE c != $c ORDER BY v <-> '$query' LIMIT $limit;
+));
+like($explain, qr/Index Scan using idx/);
+
+# Test attribute filtering with few rows removed comparison
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE c >= 1 ORDER BY v <-> '$query' LIMIT $limit;
+));
+like($explain, qr/Index Scan using idx/);
+
+# Test attribute filtering with many rows removed comparison
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE c < 1 ORDER BY v <-> '$query' LIMIT $limit;
+));
+# TODO Do not use index
+like($explain, qr/Index Scan using idx/);
+
+# Test attribute filtering with few rows removed like
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE t LIKE '%%test%%' ORDER BY v <-> '$query' LIMIT $limit;
+));
+like($explain, qr/Index Scan using idx/);
+
+# Test attribute filtering with many rows removed like
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE t LIKE '%%other%%' ORDER BY v <-> '$query' LIMIT $limit;
+));
+like($explain, qr/Seq Scan/);
+
+# Test distance filtering
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE v <-> '$query' < 1 ORDER BY v <-> '$query' LIMIT $limit;
+));
+like($explain, qr/Index Scan using idx/);
+
+# Test distance filtering greater than distance
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE v <-> '$query' > 1 ORDER BY v <-> '$query' LIMIT $limit;
+));
+# TODO Do not use index
+like($explain, qr/Index Scan using idx/);
+
+# Test distance filtering without order
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE v <-> '$query' < 1;
+));
+like($explain, qr/Seq Scan/);
+
+# Test distance filtering without limit
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE v <-> '$query' < 1 ORDER BY v <-> '$query';
+));
+like($explain, qr/Seq Scan/);
+
+# Test attribute index
+$node->safe_psql("postgres", "CREATE INDEX attribute_idx ON tst (c);");
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE c = $c ORDER BY v <-> '$query' LIMIT $limit;
+));
+# TODO Use attribute index
+like($explain, qr/Index Scan using idx/);
+
+# Test partial index
+$node->safe_psql("postgres", "CREATE INDEX partial_idx ON tst USING hnsw (v vector_l2_ops) WHERE (c = $c);");
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE c = $c ORDER BY v <-> '$query' LIMIT $limit;
+));
+like($explain, qr/Index Scan using partial_idx/);
+
+done_testing();

test/t/019_ivfflat_filtering.pl

@@ -0,0 +1,116 @@
+use strict;
+use warnings;
+use PostgresNode;
+use TestLib;
+use Test::More;
+
+my $dim = 3;
+my $nc = 50;
+my $limit = 20;
+
+my $array_sql = join(",", ('random()') x $dim);
+
+# Initialize node
+my $node = get_new_node('node');
+$node->init;
+$node->start;
+
+# Create table and index
+$node->safe_psql("postgres", "CREATE EXTENSION vector;");
+$node->safe_psql("postgres", "CREATE TABLE tst (i int4, v vector($dim), c int4, t text);");
+$node->safe_psql("postgres",
+	"INSERT INTO tst SELECT i, ARRAY[$array_sql], i % $nc, 'test ' || i FROM generate_series(1, 10000) i;"
+);
+$node->safe_psql("postgres", "CREATE INDEX idx ON tst USING ivfflat (v vector_l2_ops) WITH (lists = 100);");
+$node->safe_psql("postgres", "ANALYZE tst;");
+
+# Generate query
+my @r = ();
+for (1 .. $dim)
+{
+	push(@r, rand());
+}
+my $query = "[" . join(",", @r) . "]";
+my $c = int(rand() * $nc);
+
+# Test attribute filtering
+my $explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE c = $c ORDER BY v <-> '$query' LIMIT $limit;
+));
+# TODO Do not use index
+like($explain, qr/Index Scan using idx/);
+
+# Test attribute filtering with few rows removed
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE c != $c ORDER BY v <-> '$query' LIMIT $limit;
+));
+like($explain, qr/Index Scan using idx/);
+
+# Test attribute filtering with few rows removed comparison
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE c >= 1 ORDER BY v <-> '$query' LIMIT $limit;
+));
+like($explain, qr/Index Scan using idx/);
+
+# Test attribute filtering with many rows removed comparison
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE c < 1 ORDER BY v <-> '$query' LIMIT $limit;
+));
+# TODO Do not use index
+like($explain, qr/Index Scan using idx/);
+
+# Test attribute filtering with few rows removed like
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE t LIKE '%%test%%' ORDER BY v <-> '$query' LIMIT $limit;
+));
+like($explain, qr/Index Scan using idx/);
+
+# Test attribute filtering with many rows removed like
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE t LIKE '%%other%%' ORDER BY v <-> '$query' LIMIT $limit;
+));
+like($explain, qr/Seq Scan/);
+
+# Test distance filtering
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE v <-> '$query' < 1 ORDER BY v <-> '$query' LIMIT $limit;
+));
+like($explain, qr/Index Scan using idx/);
+
+# Test distance filtering greater than distance
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE v <-> '$query' > 1 ORDER BY v <-> '$query' LIMIT $limit;
+));
+# TODO Do not use index
+like($explain, qr/Index Scan using idx/);
+
+# Test distance filtering without order
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE v <-> '$query' < 1;
+));
+like($explain, qr/Seq Scan/);
+
+# Test distance filtering without limit
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE v <-> '$query' < 1 ORDER BY v <-> '$query';
+));
+# TODO Do not use index
+like($explain, qr/Index Scan using idx/);
+
+# Test attribute index
+$node->safe_psql("postgres", "CREATE INDEX attribute_idx ON tst (c);");
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE c = $c ORDER BY v <-> '$query' LIMIT $limit;
+));
+# TODO Use attribute index
+like($explain, qr/Index Scan using idx/);
+
+# Test partial index
+$node->safe_psql("postgres", "CREATE INDEX partial_idx ON tst USING ivfflat (v vector_l2_ops) WITH (lists = 5) WHERE (c = $c);");
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE c = $c ORDER BY v <-> '$query' LIMIT $limit;
+));
+# TODO Use partial index
+like($explain, qr/Index Scan using idx/);
+
+done_testing();

test/t/019_ivfflat_limit.pl

@@ -1,64 +0,0 @@
-use strict;
-use warnings;
-use PostgresNode;
-use TestLib;
-use Test::More;
-
-# Initialize node
-my $node = get_new_node('node');
-$node->init;
-$node->start;
-
-# Create table and index
-$node->safe_psql("postgres", "CREATE EXTENSION vector;");
-$node->safe_psql("postgres", "CREATE TABLE tst (v vector(3));");
-$node->safe_psql("postgres",
-	"INSERT INTO tst SELECT ARRAY[random(), random(), random()] FROM generate_series(1, 1000) i;"
-);
-$node->safe_psql("postgres", "CREATE INDEX ON tst USING ivfflat (v vector_l2_ops) WITH (lists = 10);");
-
-# Test limit
-my $explain = $node->safe_psql("postgres", qq(
-	EXPLAIN ANALYZE SELECT * FROM tst ORDER BY v <-> '[1,2,3]' LIMIT 100;
-));
-like($explain, qr/Index Scan/);
-
-# Test limit with probes
-$explain = $node->safe_psql("postgres", qq(
-	SET ivfflat.probes = 2;
-	EXPLAIN ANALYZE SELECT * FROM tst ORDER BY v <-> '[1,2,3]' LIMIT 200;
-));
-like($explain, qr/Index Scan/);
-
-# Test limit + offset
-$explain = $node->safe_psql("postgres", qq(
-	EXPLAIN ANALYZE SELECT * FROM tst ORDER BY v <-> '[1,2,3]' LIMIT 90 OFFSET 10;
-));
-like($explain, qr/Index Scan/);
-
-# Test limit > expected tuples
-$explain = $node->safe_psql("postgres", qq(
-	EXPLAIN ANALYZE SELECT * FROM tst ORDER BY v <-> '[1,2,3]' LIMIT 101;
-));
-like($explain, qr/Seq Scan/);
-
-# Test limit > expected tuples with probes
-$explain = $node->safe_psql("postgres", qq(
-	SET ivfflat.probes = 2;
-	EXPLAIN ANALYZE SELECT * FROM tst ORDER BY v <-> '[1,2,3]' LIMIT 201;
-));
-like($explain, qr/Seq Scan/);
-
-# Test limit + offset > expected tuples
-$explain = $node->safe_psql("postgres", qq(
-	EXPLAIN ANALYZE SELECT * FROM tst ORDER BY v <-> '[1,2,3]' LIMIT 91 OFFSET 10;
-));
-like($explain, qr/Seq Scan/);
-
-# Test no limit
-$explain = $node->safe_psql("postgres", qq(
-	EXPLAIN ANALYZE SELECT * FROM tst ORDER BY v <-> '[1,2,3]';
-));
-like($explain, qr/Seq Scan/);
-
-done_testing();

test/t/020_hnsw_limit.pl

@@ -1,62 +0,0 @@
-use strict;
-use warnings;
-use PostgresNode;
-use TestLib;
-use Test::More;
-
-# Initialize node
-my $node = get_new_node('node');
-$node->init;
-$node->start;
-
-# Create table and index
-$node->safe_psql("postgres", "CREATE EXTENSION vector;");
-$node->safe_psql("postgres", "CREATE TABLE tst (v vector(3));");
-$node->safe_psql("postgres",
-	"INSERT INTO tst SELECT ARRAY[random(), random(), random()] FROM generate_series(1, 1000) i;"
-);
-$node->safe_psql("postgres", "CREATE INDEX ON tst USING hnsw (v vector_l2_ops);");
-
-# Test limit
-my $explain = $node->safe_psql("postgres", qq(
-	EXPLAIN ANALYZE SELECT * FROM tst ORDER BY v <-> '[1,2,3]' LIMIT 40;
-));
-like($explain, qr/Index Scan/);
-
-# Test limit with CTE
-$explain = $node->safe_psql("postgres", qq(
-	EXPLAIN ANALYZE WITH cte AS (SELECT * FROM tst ORDER BY v <-> '[1,2,3]' LIMIT 40) SELECT * FROM cte;
-));
-like($explain, qr/Index Scan/);
-
-# Test limit + offset
-$explain = $node->safe_psql("postgres", qq(
-	EXPLAIN ANALYZE SELECT * FROM tst ORDER BY v <-> '[1,2,3]' LIMIT 30 OFFSET 10;
-));
-like($explain, qr/Index Scan/);
-
-# Test limit > ef_search
-$explain = $node->safe_psql("postgres", qq(
-	EXPLAIN ANALYZE SELECT * FROM tst ORDER BY v <-> '[1,2,3]' LIMIT 41;
-));
-like($explain, qr/Seq Scan/);
-
-# Test limit > ef_search with CTE
-$explain = $node->safe_psql("postgres", qq(
-	EXPLAIN ANALYZE WITH cte AS (SELECT * FROM tst ORDER BY v <-> '[1,2,3]' LIMIT 41) SELECT * FROM cte;
-));
-like($explain, qr/Seq Scan/);
-
-# Test limit + offset > ef_search
-$explain = $node->safe_psql("postgres", qq(
-	EXPLAIN ANALYZE SELECT * FROM tst ORDER BY v <-> '[1,2,3]' LIMIT 31 OFFSET 10;
-));
-like($explain, qr/Seq Scan/);
-
-# Test no limit
-$explain = $node->safe_psql("postgres", qq(
-	EXPLAIN ANALYZE SELECT * FROM tst ORDER BY v <-> '[1,2,3]';
-));
-like($explain, qr/Seq Scan/);
-
-done_testing();