Removed unused functions

Co-authored-by: Heikki Linnakangas <heikki.linnakangas@iki.fi>

CHANGELOG.md

@@ -1,6 +1,9 @@
 ## 0.5.2 (unreleased)
 
+- Improved performance of HNSW
 - Added support for on-disk parallel index builds for HNSW
+- Reduced WAL generation for HNSW index builds
+- Fixed `invalid memory alloc request size` error with HNSW index build
 
 ## 0.5.1 (2023-10-10)
 

README.md

@@ -10,7 +10,7 @@ Store your vectors with the rest of your data. Supports:
 
 Plus [ACID](https://en.wikipedia.org/wiki/ACID) compliance, point-in-time recovery, JOINs, and all of the other [great features](https://www.postgresql.org/about/) of Postgres
 
-[![Build Status](https://github.com/pgvector/pgvector/workflows/build/badge.svg?branch=master)](https://github.com/pgvector/pgvector/actions)
+[![Build Status](https://github.com/pgvector/pgvector/actions/workflows/build.yml/badge.svg)](https://github.com/pgvector/pgvector/actions)
 
 ## Installation
 
@@ -269,6 +269,8 @@ Specify HNSW parameters
 CREATE INDEX ON items USING hnsw (embedding vector_l2_ops) WITH (m = 16, ef_construction = 64);
 ```
 
+A higher value of `ef_construction` provides better recall at the cost of index build time / insert speed.
+
 ### Query Options
 
 Specify the size of the dynamic candidate list for search (40 by default)
@@ -377,7 +379,7 @@ Language | Libraries / Examples
 --- | ---
 C | [pgvector-c](https://github.com/pgvector/pgvector-c)
 C++ | [pgvector-cpp](https://github.com/pgvector/pgvector-cpp)
-C# | [pgvector-dotnet](https://github.com/pgvector/pgvector-dotnet)
+C#, F#, Visual Basic | [pgvector-dotnet](https://github.com/pgvector/pgvector-dotnet)
 Crystal | [pgvector-crystal](https://github.com/pgvector/pgvector-crystal)
 Dart | [pgvector-dart](https://github.com/pgvector/pgvector-dart)
 Elixir | [pgvector-elixir](https://github.com/pgvector/pgvector-elixir)
@@ -386,8 +388,10 @@ Haskell | [pgvector-haskell](https://github.com/pgvector/pgvector-haskell)
 Java, Kotlin, Groovy, Scala | [pgvector-java](https://github.com/pgvector/pgvector-java)
 JavaScript, TypeScript | [pgvector-node](https://github.com/pgvector/pgvector-node)
 Julia | [pgvector-julia](https://github.com/pgvector/pgvector-julia)
+Lisp | [pgvector-lisp](https://github.com/pgvector/pgvector-lisp)
 Lua | [pgvector-lua](https://github.com/pgvector/pgvector-lua)
 Nim | [pgvector-nim](https://github.com/pgvector/pgvector-nim)
+OCaml | [pgvector-ocaml](https://github.com/pgvector/pgvector-ocaml)
 Perl | [pgvector-perl](https://github.com/pgvector/pgvector-perl)
 PHP | [pgvector-php](https://github.com/pgvector/pgvector-php)
 Python | [pgvector-python](https://github.com/pgvector/pgvector-python)
@@ -460,6 +464,14 @@ and query with:
 SELECT * FROM items ORDER BY embedding::vector(3) <-> '[3,1,2]' LIMIT 5;
 ```
 
+#### Do indexes need to fit into memory?
+
+No, but like other index types, you’ll likely see better performance if they do. You can get the size of an index with:
+
+```sql
+SELECT pg_size_pretty(pg_relation_size('index_name'));
+```
+
 ## Troubleshooting
 
 #### Why isn’t a query using an index?
@@ -678,16 +690,6 @@ SELECT extversion FROM pg_extension WHERE extname = 'vector';
 
 ## Upgrade Notes
 
-### 0.6.0
-
-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

@@ -1,5 +0,0 @@
--- 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);

sql/vector.sql

@@ -26,7 +26,7 @@ CREATE TYPE vector (
 	TYPMOD_IN = vector_typmod_in,
 	RECEIVE   = vector_recv,
 	SEND      = vector_send,
-	STORAGE   = external
+	STORAGE   = extended
 );
 
 -- functions

src/hnsw.h

@@ -104,6 +104,7 @@ typedef struct HnswElementData
 	List	   *heaptids;
 	uint8		level;
 	uint8		deleted;
+	uint32		hash;
 	HnswNeighborArray *neighbors;
 	BlockNumber blkno;
 	OffsetNumber offno;
@@ -303,7 +304,7 @@ typedef struct HnswVacuumState
 	Oid			collation;
 
 	/* Variables */
-	HTAB	   *deleted;
+	struct tidhash_hash *deleted;
 	BufferAccessStrategy bas;
 	HnswNeighborTuple ntup;
 	HnswElementData highestPoint;
@@ -317,10 +318,8 @@ int			HnswGetM(Relation index);
 int			HnswGetEfConstruction(Relation index);
 FmgrInfo   *HnswOptionalProcInfo(Relation index, uint16 procnum);
 bool		HnswNormValue(FmgrInfo *procinfo, Oid collation, Datum *value, Vector * result);
-void		HnswCommitBuffer(Buffer buf, GenericXLogState *state);
 Buffer		HnswNewBuffer(Relation index, ForkNumber forkNum);
 void		HnswInitPage(Buffer buf, Page page);
-void		HnswInitRegisterPage(Relation index, Buffer *buf, Page *page, GenericXLogState **state);
 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);
 HnswElement HnswGetEntryPoint(Relation index);
@@ -331,12 +330,12 @@ HnswElement HnswInitElementFromBlock(BlockNumber blkno, OffsetNumber offno);
 void		HnswInsertElement(HnswElement element, HnswElement entryPoint, Relation index, FmgrInfo *procinfo, Oid collation, int m, int efConstruction, bool existing);
 HnswElement HnswFindDuplicate(HnswElement e);
 HnswCandidate *HnswEntryCandidate(HnswElement em, Datum q, Relation rel, FmgrInfo *procinfo, Oid collation, bool loadVec);
-void		HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, BlockNumber insertPage, ForkNumber forkNum);
+void		HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, BlockNumber insertPage, ForkNumber forkNum, bool building);
 void		HnswSetNeighborTuple(HnswNeighborTuple ntup, HnswElement e, int m);
 void		HnswAddHeapTid(HnswElement element, ItemPointer heaptid);
 void		HnswInitNeighbors(HnswElement element, int m);
-bool		HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid, Relation heapRel);
+bool		HnswInsertTuple(Relation index, 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);
+void		HnswUpdateNeighborPages(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);
@@ -360,4 +359,31 @@ void		hnswrescan(IndexScanDesc scan, ScanKey keys, int nkeys, ScanKey orderbys,
 bool		hnswgettuple(IndexScanDesc scan, ScanDirection dir);
 void		hnswendscan(IndexScanDesc scan);
 
+/* Hash tables */
+typedef struct TidHashEntry
+{
+	ItemPointerData tid;
+	char		status;
+}			TidHashEntry;
+
+#define SH_PREFIX tidhash
+#define SH_ELEMENT_TYPE TidHashEntry
+#define SH_KEY_TYPE ItemPointerData
+#define SH_SCOPE extern
+#define SH_DECLARE
+#include "lib/simplehash.h"
+
+typedef struct PointerHashEntry
+{
+	uintptr_t	ptr;
+	char		status;
+}			PointerHashEntry;
+
+#define SH_PREFIX pointerhash
+#define SH_ELEMENT_TYPE PointerHashEntry
+#define SH_KEY_TYPE uintptr_t
+#define SH_SCOPE extern
+#define SH_DECLARE
+#include "lib/simplehash.h"
+
 #endif

src/hnswbuild.c

@@ -56,6 +56,8 @@
 #define PARALLEL_KEY_HNSW_SHARED		UINT64CONST(0xA000000000000001)
 #define PARALLEL_KEY_QUERY_TEXT			UINT64CONST(0xA000000000000002)
 
+#define LIST_MAX_LENGTH ((1 << 26) - 1)
+
 /*
  * Create the metapage
  */
@@ -66,11 +68,11 @@ CreateMetaPage(HnswBuildState * buildstate)
 	ForkNumber	forkNum = buildstate->forkNum;
 	Buffer		buf;
 	Page		page;
-	GenericXLogState *state;
 	HnswMetaPage metap;
 
 	buf = HnswNewBuffer(index, forkNum);
-	HnswInitRegisterPage(index, &buf, &page, &state);
+	page = BufferGetPage(buf);
+	HnswInitPage(buf, page);
 
 	/* Set metapage data */
 	metap = HnswPageGetMeta(page);
@@ -86,14 +88,14 @@ CreateMetaPage(HnswBuildState * buildstate)
 	((PageHeader) page)->pd_lower =
 		((char *) metap + sizeof(HnswMetaPageData)) - (char *) page;
 
-	HnswCommitBuffer(buf, state);
+	UnlockReleaseBuffer(buf);
 }
 
 /*
  * Add a new page
  */
 static void
-HnswBuildAppendPage(Relation index, Buffer *buf, Page *page, GenericXLogState **state, ForkNumber forkNum)
+HnswBuildAppendPage(Relation index, Buffer *buf, Page *page, ForkNumber forkNum)
 {
 	/* Add a new page */
 	Buffer		newbuf = HnswNewBuffer(index, forkNum);
@@ -102,7 +104,6 @@ HnswBuildAppendPage(Relation index, Buffer *buf, Page *page, GenericXLogState **
 	HnswPageGetOpaque(*page)->nextblkno = BufferGetBlockNumber(newbuf);
 
 	/* Commit */
-	GenericXLogFinish(*state);
 	UnlockReleaseBuffer(*buf);
 
 	/* Can take a while, so ensure we can interrupt */
@@ -113,8 +114,7 @@ HnswBuildAppendPage(Relation index, Buffer *buf, Page *page, GenericXLogState **
 
 	/* Prepare new page */
 	*buf = newbuf;
-	*state = GenericXLogStart(index);
+	*page = BufferGetPage(*buf);
-	*page = GenericXLogRegisterBuffer(*state, *buf, GENERIC_XLOG_FULL_IMAGE);
 	HnswInitPage(*buf, *page);
 }
 
@@ -133,7 +133,6 @@ CreateElementPages(HnswBuildState * buildstate)
 	BlockNumber insertPage;
 	Buffer		buf;
 	Page		page;
-	GenericXLogState *state;
 	ListCell   *lc;
 
 	/* Calculate sizes */
@@ -146,8 +145,7 @@ CreateElementPages(HnswBuildState * buildstate)
 
 	/* Prepare first page */
 	buf = HnswNewBuffer(index, forkNum);
-	state = GenericXLogStart(index);
+	page = BufferGetPage(buf);
-	page = GenericXLogRegisterBuffer(state, buf, GENERIC_XLOG_FULL_IMAGE);
 	HnswInitPage(buf, page);
 
 	foreach(lc, buildstate->elements)
@@ -173,7 +171,7 @@ CreateElementPages(HnswBuildState * buildstate)
 
 		/* Keep element and neighbors on the same page if possible */
 		if (PageGetFreeSpace(page) < etupSize || (combinedSize <= maxSize && PageGetFreeSpace(page) < combinedSize))
-			HnswBuildAppendPage(index, &buf, &page, &state, forkNum);
+			HnswBuildAppendPage(index, &buf, &page, forkNum);
 
 		/* Calculate offsets */
 		element->blkno = BufferGetBlockNumber(buf);
@@ -197,7 +195,7 @@ CreateElementPages(HnswBuildState * buildstate)
 
 		/* Add new page if needed */
 		if (PageGetFreeSpace(page) < ntupSize)
-			HnswBuildAppendPage(index, &buf, &page, &state, forkNum);
+			HnswBuildAppendPage(index, &buf, &page, forkNum);
 
 		/* Add placeholder for neighbors */
 		if (PageAddItem(page, (Item) ntup, ntupSize, InvalidOffsetNumber, false, false) != element->neighborOffno)
@@ -207,10 +205,9 @@ CreateElementPages(HnswBuildState * buildstate)
 	insertPage = BufferGetBlockNumber(buf);
 
 	/* Commit */
-	GenericXLogFinish(state);
 	UnlockReleaseBuffer(buf);
 
-	HnswUpdateMetaPage(index, HNSW_UPDATE_ENTRY_ALWAYS, buildstate->entryPoint, insertPage, forkNum);
+	HnswUpdateMetaPage(index, HNSW_UPDATE_ENTRY_ALWAYS, buildstate->entryPoint, insertPage, forkNum, true);
 
 	pfree(etup);
 	pfree(ntup);
@@ -236,7 +233,6 @@ CreateNeighborPages(HnswBuildState * buildstate)
 		HnswElement e = lfirst(lc);
 		Buffer		buf;
 		Page		page;
-		GenericXLogState *state;
 		Size		ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(e->level, m);
 
 		/* Can take a while, so ensure we can interrupt */
@@ -245,8 +241,7 @@ CreateNeighborPages(HnswBuildState * buildstate)
 
 		buf = ReadBufferExtended(index, forkNum, e->neighborPage, RBM_NORMAL, NULL);
 		LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
-		state = GenericXLogStart(index);
+		page = BufferGetPage(buf);
-		page = GenericXLogRegisterBuffer(state, buf, 0);
 
 		HnswSetNeighborTuple(ntup, e, m);
 
@@ -254,7 +249,6 @@ CreateNeighborPages(HnswBuildState * buildstate)
 			elog(ERROR, "failed to add index item to \"%s\"", RelationGetRelationName(index));
 
 		/* Commit */
-		GenericXLogFinish(state);
 		UnlockReleaseBuffer(buf);
 	}
 
@@ -381,21 +375,22 @@ BuildCallback(Relation index, CALLBACK_ITEM_POINTER, Datum *values,
 	if (isnull[0])
 		return;
 
-	if (buildstate->memoryLeft <= 0)
+	if (buildstate->flushed || buildstate->memoryLeft <= 0 || list_length(buildstate->elements) == LIST_MAX_LENGTH)
 	{
 		if (!buildstate->flushed)
 		{
-			ereport(NOTICE,
+			if (buildstate->memoryLeft <= 0)
-					(errmsg("hnsw graph no longer fits into maintenance_work_mem after " INT64_FORMAT " tuples", (int64) buildstate->indtuples),
+				ereport(NOTICE,
-					 errdetail("Building will take significantly more time."),
+						(errmsg("hnsw graph no longer fits into maintenance_work_mem after " INT64_FORMAT " tuples", (int64) buildstate->indtuples),
-					 errhint("Increase maintenance_work_mem to speed up builds.")));
+						 errdetail("Building will take significantly more time."),
+						 errhint("Increase maintenance_work_mem to speed up builds.")));
 
 			FlushPages(buildstate);
 		}
 
 		oldCtx = MemoryContextSwitchTo(buildstate->tmpCtx);
 
-		if (HnswInsertTuple(buildstate->index, values, isnull, tid, buildstate->heap))
+		if (HnswInsertTuple(buildstate->index, values, isnull, tid, buildstate->heap, true))
 		{
 			if (buildstate->hnswshared)
 			{
@@ -877,6 +872,22 @@ 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
  */
@@ -892,6 +903,9 @@ BuildIndex(Relation heap, Relation index, IndexInfo *indexInfo,
 	if (!buildstate->flushed)
 		FlushPages(buildstate);
 
+	if (RelationNeedsWAL(index))
+		log_newpage_range(index, forkNum, 0, RelationGetNumberOfBlocks(index), true);
+
 	FreeBuildState(buildstate);
 }
 

src/hnswinsert.c

@@ -92,7 +92,7 @@ HnswFreeOffset(Relation index, Buffer buf, Page page, HnswElement element, Size
  * Add a new page
  */
 static void
-HnswInsertAppendPage(Relation index, Buffer *nbuf, Page *npage, GenericXLogState *state, Page page)
+HnswInsertAppendPage(Relation index, Buffer *nbuf, Page *npage, GenericXLogState *state, Page page, bool building)
 {
 	/* Add a new page */
 	LockRelationForExtension(index, ExclusiveLock);
@@ -100,7 +100,11 @@ HnswInsertAppendPage(Relation index, Buffer *nbuf, Page *npage, GenericXLogState
 	UnlockRelationForExtension(index, ExclusiveLock);
 
 	/* Init new page */
-	*npage = GenericXLogRegisterBuffer(state, *nbuf, GENERIC_XLOG_FULL_IMAGE);
+	if (building)
+		*npage = BufferGetPage(*nbuf);
+	else
+		*npage = GenericXLogRegisterBuffer(state, *nbuf, GENERIC_XLOG_FULL_IMAGE);
+
 	HnswInitPage(*nbuf, *npage);
 
 	/* Update previous buffer */
@@ -111,7 +115,7 @@ 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)
+WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPage, BlockNumber *updatedInsertPage, bool building)
 {
 	Buffer		buf;
 	Page		page;
@@ -151,8 +155,16 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
 		buf = ReadBuffer(index, currentPage);
 		LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
 
-		state = GenericXLogStart(index);
+		if (building)
-		page = GenericXLogRegisterBuffer(state, buf, 0);
+		{
+			state = NULL;
+			page = BufferGetPage(buf);
+		}
+		else
+		{
+			state = GenericXLogStart(index);
+			page = GenericXLogRegisterBuffer(state, buf, 0);
+		}
 
 		/* Keep track of first page where element at level 0 can fit */
 		if (!BlockNumberIsValid(newInsertPage) && PageGetFreeSpace(page) >= minCombinedSize)
@@ -172,7 +184,12 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
 		if (HnswFreeOffset(index, buf, page, e, ntupSize, &nbuf, &npage, &freeOffno, &freeNeighborOffno, &newInsertPage))
 		{
 			if (nbuf != buf)
-				npage = GenericXLogRegisterBuffer(state, nbuf, 0);
+			{
+				if (building)
+					npage = BufferGetPage(nbuf);
+				else
+					npage = GenericXLogRegisterBuffer(state, nbuf, 0);
+			}
 
 			break;
 		}
@@ -181,7 +198,7 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
 		/* Skip if both tuples can fit on the same page */
 		if (combinedSize > maxSize && PageGetFreeSpace(page) >= etupSize && !BlockNumberIsValid(HnswPageGetOpaque(page)->nextblkno))
 		{
-			HnswInsertAppendPage(index, &nbuf, &npage, state, page);
+			HnswInsertAppendPage(index, &nbuf, &npage, state, page, building);
 			break;
 		}
 
@@ -190,7 +207,8 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
 		if (BlockNumberIsValid(currentPage))
 		{
 			/* Move to next page */
-			GenericXLogAbort(state);
+			if (!building)
+				GenericXLogAbort(state);
 			UnlockReleaseBuffer(buf);
 		}
 		else
@@ -198,22 +216,31 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
 			Buffer		newbuf;
 			Page		newpage;
 
-			HnswInsertAppendPage(index, &newbuf, &newpage, state, page);
+			HnswInsertAppendPage(index, &newbuf, &newpage, state, page, building);
 
 			/* Commit */
-			GenericXLogFinish(state);
+			if (!building)
+				GenericXLogFinish(state);
 
 			/* Unlock previous buffer */
 			UnlockReleaseBuffer(buf);
 
 			/* Prepare new buffer */
-			state = GenericXLogStart(index);
 			buf = newbuf;
-			page = GenericXLogRegisterBuffer(state, buf, 0);
+			if (building)
+			{
+				state = NULL;
+				page = BufferGetPage(buf);
+			}
+			else
+			{
+				state = GenericXLogStart(index);
+				page = GenericXLogRegisterBuffer(state, buf, 0);
+			}
 
 			/* Create new page for neighbors if needed */
 			if (PageGetFreeSpace(page) < combinedSize)
-				HnswInsertAppendPage(index, &nbuf, &npage, state, page);
+				HnswInsertAppendPage(index, &nbuf, &npage, state, page, building);
 			else
 			{
 				nbuf = buf;
@@ -267,7 +294,8 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
 	}
 
 	/* Commit */
-	GenericXLogFinish(state);
+	if (!building)
+		GenericXLogFinish(state);
 	UnlockReleaseBuffer(buf);
 	if (nbuf != buf)
 		UnlockReleaseBuffer(nbuf);
@@ -301,7 +329,7 @@ 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)
+HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement e, int m, bool checkExisting, bool building)
 {
 	for (int lc = e->level; lc >= 0; lc--)
 	{
@@ -342,8 +370,16 @@ HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswE
 			/* Register page */
 			buf = ReadBuffer(index, hc->element->neighborPage);
 			LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
-			state = GenericXLogStart(index);
+			if (building)
-			page = GenericXLogRegisterBuffer(state, buf, 0);
+			{
+				state = NULL;
+				page = BufferGetPage(buf);
+			}
+			else
+			{
+				state = GenericXLogStart(index);
+				page = GenericXLogRegisterBuffer(state, buf, 0);
+			}
 
 			/* Get tuple */
 			itemid = PageGetItemId(page, offno);
@@ -385,9 +421,10 @@ HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswE
 					elog(ERROR, "failed to add index item to \"%s\"", RelationGetRelationName(index));
 
 				/* Commit */
-				GenericXLogFinish(state);
+				if (!building)
+					GenericXLogFinish(state);
 			}
-			else
+			else if (!building)
 				GenericXLogAbort(state);
 
 			UnlockReleaseBuffer(buf);
@@ -399,7 +436,7 @@ 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)
+HnswAddDuplicate(Relation index, HnswElement element, HnswElement dup, bool building)
 {
 	Buffer		buf;
 	Page		page;
@@ -412,8 +449,16 @@ HnswAddDuplicate(Relation index, HnswElement element, HnswElement dup)
 	/* Read page */
 	buf = ReadBuffer(index, dup->blkno);
 	LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
-	state = GenericXLogStart(index);
+	if (building)
-	page = GenericXLogRegisterBuffer(state, buf, 0);
+	{
+		state = NULL;
+		page = BufferGetPage(buf);
+	}
+	else
+	{
+		state = GenericXLogStart(index);
+		page = GenericXLogRegisterBuffer(state, buf, 0);
+	}
 
 	/* Find space */
 	itemid = PageGetItemId(page, dup->offno);
@@ -428,7 +473,8 @@ HnswAddDuplicate(Relation index, HnswElement element, HnswElement dup)
 	/* Either being deleted or we lost our chance to another backend */
 	if (i == 0 || i == HNSW_HEAPTIDS)
 	{
-		GenericXLogAbort(state);
+		if (!building)
+			GenericXLogAbort(state);
 		UnlockReleaseBuffer(buf);
 		return false;
 	}
@@ -441,7 +487,8 @@ HnswAddDuplicate(Relation index, HnswElement element, HnswElement dup)
 		elog(ERROR, "failed to add index item to \"%s\"", RelationGetRelationName(index));
 
 	/* Commit */
-	GenericXLogFinish(state);
+	if (!building)
+		GenericXLogFinish(state);
 	UnlockReleaseBuffer(buf);
 
 	return true;
@@ -451,37 +498,37 @@ HnswAddDuplicate(Relation index, HnswElement element, HnswElement dup)
  * Write changes to disk
  */
 static void
-WriteElement(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement element, int m, int efConstruction, HnswElement dup, HnswElement entryPoint)
+WriteElement(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement element, int m, int efConstruction, HnswElement dup, HnswElement entryPoint, bool building)
 {
 	BlockNumber newInsertPage = InvalidBlockNumber;
 
 	/* Try to add to existing page */
 	if (dup != NULL)
 	{
-		if (HnswAddDuplicate(index, element, dup))
+		if (HnswAddDuplicate(index, element, dup, building))
 			return;
 	}
 
 	/* Write element and neighbor tuples */
-	WriteNewElementPages(index, element, m, GetInsertPage(index), &newInsertPage);
+	WriteNewElementPages(index, element, m, GetInsertPage(index), &newInsertPage, building);
 
 	/* Update insert page if needed */
 	if (BlockNumberIsValid(newInsertPage))
-		HnswUpdateMetaPage(index, 0, NULL, newInsertPage, MAIN_FORKNUM);
+		HnswUpdateMetaPage(index, 0, NULL, newInsertPage, MAIN_FORKNUM, building);
 
 	/* Update neighbors */
-	HnswUpdateNeighborPages(index, procinfo, collation, element, m, false);
+	HnswUpdateNeighborPages(index, procinfo, collation, element, m, false, building);
 
 	/* Update metapage if needed */
 	if (entryPoint == NULL || element->level > entryPoint->level)
-		HnswUpdateMetaPage(index, HNSW_UPDATE_ENTRY_GREATER, element, InvalidBlockNumber, MAIN_FORKNUM);
+		HnswUpdateMetaPage(index, HNSW_UPDATE_ENTRY_GREATER, element, InvalidBlockNumber, MAIN_FORKNUM, building);
 }
 
 /*
  * Insert a tuple into the index
  */
 bool
-HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid, Relation heapRel)
+HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid, Relation heapRel, bool building)
 {
 	Datum		value;
 	FmgrInfo   *normprocinfo;
@@ -540,7 +587,7 @@ HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_ti
 	dup = HnswFindDuplicate(element);
 
 	/* Write to disk */
-	WriteElement(index, procinfo, collation, element, m, efConstruction, dup, entryPoint);
+	WriteElement(index, procinfo, collation, element, m, efConstruction, dup, entryPoint, building);
 
 	/* Release lock */
 	UnlockPage(index, HNSW_UPDATE_LOCK, lockmode);
@@ -574,7 +621,7 @@ hnswinsert(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid,
 	oldCtx = MemoryContextSwitchTo(insertCtx);
 
 	/* Insert tuple */
-	HnswInsertTuple(index, values, isnull, heap_tid, heap);
+	HnswInsertTuple(index, values, isnull, heap_tid, heap, false);
 
 	/* Delete memory context */
 	MemoryContextSwitchTo(oldCtx);

src/hnswutils.c

@@ -7,6 +7,89 @@
 #include "utils/datum.h"
 #include "vector.h"
 
+#if PG_VERSION_NUM >= 130000
+#include "common/hashfn.h"
+#else
+#include "utils/hashutils.h"
+#endif
+
+#if PG_VERSION_NUM < 170000
+static inline uint64
+murmurhash64(uint64 data)
+{
+	uint64		h = data;
+
+	h ^= h >> 33;
+	h *= 0xff51afd7ed558ccd;
+	h ^= h >> 33;
+	h *= 0xc4ceb9fe1a85ec53;
+	h ^= h >> 33;
+
+	return h;
+}
+#endif
+
+/* TID hash table */
+static uint32
+hash_tid(ItemPointerData tid)
+{
+	union
+	{
+		uint64		i;
+		ItemPointerData tid;
+	}			x;
+
+	/* Initialize unused bytes */
+	x.i = 0;
+	x.tid = tid;
+
+	return murmurhash64(x.i);
+}
+
+#define SH_PREFIX		tidhash
+#define SH_ELEMENT_TYPE	TidHashEntry
+#define SH_KEY_TYPE		ItemPointerData
+#define	SH_KEY			tid
+#define SH_HASH_KEY(tb, key)	hash_tid(key)
+#define SH_EQUAL(tb, a, b)		ItemPointerEquals(&a, &b)
+#define	SH_SCOPE		extern
+#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)
+{
+#if SIZEOF_VOID_P == 8
+	return murmurhash64((uint64) ptr);
+#else
+	return murmurhash32((uint32) ptr);
+#endif
+}
+
+#define SH_PREFIX		pointerhash
+#define SH_ELEMENT_TYPE	PointerHashEntry
+#define SH_KEY_TYPE		uintptr_t
+#define	SH_KEY			ptr
+#define SH_HASH_KEY(tb, key)	hash_pointer(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;
+	tidhash_hash *tids;
+}			visited_hash;
+
 /*
  * Get the max number of connections in an upper layer for each element in the index
  */
@@ -101,27 +184,6 @@ HnswInitPage(Buffer buf, Page page)
 	HnswPageGetOpaque(page)->page_id = HNSW_PAGE_ID;
 }
 
-/*
- * Init and register page
- */
-void
-HnswInitRegisterPage(Relation index, Buffer *buf, Page *page, GenericXLogState **state)
-{
-	*state = GenericXLogStart(index);
-	*page = GenericXLogRegisterBuffer(*state, *buf, GENERIC_XLOG_FULL_IMAGE);
-	HnswInitPage(*buf, *page);
-}
-
-/*
- * Commit buffer
- */
-void
-HnswCommitBuffer(Buffer buf, GenericXLogState *state)
-{
-	GenericXLogFinish(state);
-	UnlockReleaseBuffer(buf);
-}
-
 /*
  * Allocate neighbors
  */
@@ -177,6 +239,8 @@ HnswInitElement(ItemPointer heaptid, int m, double ml, int maxLevel)
 
 	HnswInitNeighbors(element, m);
 
+	element->value = PointerGetDatum(NULL);
+
 	return element;
 }
 
@@ -294,7 +358,7 @@ HnswUpdateMetaPageInfo(Page page, int updateEntry, HnswElement entryPoint, Block
  * Update the metapage
  */
 void
-HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, BlockNumber insertPage, ForkNumber forkNum)
+HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, BlockNumber insertPage, ForkNumber forkNum, bool building)
 {
 	Buffer		buf;
 	Page		page;
@@ -302,12 +366,22 @@ HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, Bloc
 
 	buf = ReadBufferExtended(index, forkNum, HNSW_METAPAGE_BLKNO, RBM_NORMAL, NULL);
 	LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
-	state = GenericXLogStart(index);
+	if (building)
-	page = GenericXLogRegisterBuffer(state, buf, 0);
+	{
+		state = NULL;
+		page = BufferGetPage(buf);
+	}
+	else
+	{
+		state = GenericXLogStart(index);
+		page = GenericXLogRegisterBuffer(state, buf, 0);
+	}
 
 	HnswUpdateMetaPageInfo(page, updateEntry, entryPoint, insertPage);
 
-	HnswCommitBuffer(buf, state);
+	if (!building)
+		GenericXLogFinish(state);
+	UnlockReleaseBuffer(buf);
 }
 
 /*
@@ -551,16 +625,22 @@ CreatePairingHeapNode(HnswCandidate * c)
  * Add to visited
  */
 static inline void
-AddToVisited(HTAB *v, HnswCandidate * hc, Relation index, bool *found)
+AddToVisited(visited_hash v, HnswCandidate * hc, Relation index, bool *found)
 {
 	if (index == NULL)
-		hash_search(v, &hc->element, HASH_ENTER, found);
+	{
+#if PG_VERSION_NUM >= 130000
+		pointerhash_insert_hash(v.pointers, (uintptr_t) hc->element, hc->element->hash, found);
+#else
+		pointerhash_insert(v.pointers, (uintptr_t) hc->element, found);
+#endif
+	}
 	else
 	{
 		ItemPointerData indextid;
 
 		ItemPointerSet(&indextid, hc->element->blkno, hc->element->offno);
-		hash_search(v, &indextid, HASH_ENTER, found);
+		tidhash_insert(v.tids, indextid, found);
 	}
 }
 
@@ -576,30 +656,21 @@ HnswSearchLayer(Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *pro
 	pairingheap *C = pairingheap_allocate(CompareNearestCandidates, NULL);
 	pairingheap *W = pairingheap_allocate(CompareFurthestCandidates, NULL);
 	int			wlen = 0;
-	HASHCTL		hash_ctl;
+	visited_hash v;
-	HTAB	   *v;
 
 	/* Create hash table */
 	if (index == NULL)
-	{
+		v.pointers = pointerhash_create(CurrentMemoryContext, ef * m * 2, NULL);
-		hash_ctl.keysize = sizeof(HnswElement *);
-		hash_ctl.entrysize = sizeof(HnswElement *);
-	}
 	else
-	{
+		v.tids = tidhash_create(CurrentMemoryContext, ef * m * 2, NULL);
-		hash_ctl.keysize = sizeof(ItemPointerData);
-		hash_ctl.entrysize = sizeof(ItemPointerData);
-	}
-
-	hash_ctl.hcxt = CurrentMemoryContext;
-	v = hash_create("hnsw visited", 256, &hash_ctl, HASH_ELEM | HASH_BLOBS | HASH_CONTEXT);
 
 	/* Add entry points to v, C, and W */
 	foreach(lc2, ep)
 	{
 		HnswCandidate *hc = (HnswCandidate *) lfirst(lc2);
+		bool		found;
 
-		AddToVisited(v, hc, index, NULL);
+		AddToVisited(v, hc, index, &found);
 
 		pairingheap_add(C, &(CreatePairingHeapNode(hc)->ph_node));
 		pairingheap_add(W, &(CreatePairingHeapNode(hc)->ph_node));
@@ -1019,6 +1090,12 @@ HnswInsertElement(HnswElement element, HnswElement entryPoint, Relation index, F
 	Datum		q = element->value;
 	HnswElement skipElement = existing ? element : NULL;
 
+#if PG_VERSION_NUM >= 130000
+	/* Precompute hash */
+	if (index == NULL)
+		element->hash = hash_pointer((uintptr_t) element);
+#endif
+
 	/* No neighbors if no entry point */
 	if (entryPoint == NULL)
 		return;

src/hnswvacuum.c

@@ -12,12 +12,9 @@
  * Check if deleted list contains an index TID
  */
 static bool
-DeletedContains(HTAB *deleted, ItemPointer indextid)
+DeletedContains(tidhash_hash * deleted, ItemPointer indextid)
 {
-	bool		found;
+	return tidhash_lookup(deleted, *indextid) != NULL;
-
-	hash_search(deleted, indextid, HASH_FIND, &found);
-	return found;
 }
 
 /*
@@ -110,11 +107,13 @@ RemoveHeapTids(HnswVacuumState * vacuumstate)
 			if (!ItemPointerIsValid(&etup->heaptids[0]))
 			{
 				ItemPointerData ip;
+				bool		found;
 
 				/* Add to deleted list */
 				ItemPointerSet(&ip, blkno, offno);
 
-				(void) hash_search(vacuumstate->deleted, &ip, HASH_ENTER, NULL);
+				tidhash_insert(vacuumstate->deleted, ip, &found);
+				Assert(!found);
 			}
 			else if (etup->level > highestLevel && !(entryPoint != NULL && blkno == entryPoint->blkno && offno == entryPoint->offno))
 			{
@@ -231,7 +230,7 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
 	UnlockReleaseBuffer(buf);
 
 	/* Update neighbors */
-	HnswUpdateNeighborPages(index, procinfo, collation, element, m, true);
+	HnswUpdateNeighborPages(index, procinfo, collation, element, m, true, false);
 }
 
 /*
@@ -287,7 +286,7 @@ RepairGraphEntryPoint(HnswVacuumState * vacuumstate)
 			 * point is outdated and empty, the entry point will be empty
 			 * until an element is repaired.
 			 */
-			HnswUpdateMetaPage(index, HNSW_UPDATE_ENTRY_ALWAYS, highestPoint, InvalidBlockNumber, MAIN_FORKNUM);
+			HnswUpdateMetaPage(index, HNSW_UPDATE_ENTRY_ALWAYS, highestPoint, InvalidBlockNumber, MAIN_FORKNUM, false);
 		}
 		else
 		{
@@ -420,7 +419,7 @@ RepairGraph(HnswVacuumState * vacuumstate)
 			 * was replaced and highest point was outdated.
 			 */
 			if (entryPoint == NULL || element->level > entryPoint->level)
-				HnswUpdateMetaPage(index, HNSW_UPDATE_ENTRY_GREATER, element, InvalidBlockNumber, MAIN_FORKNUM);
+				HnswUpdateMetaPage(index, HNSW_UPDATE_ENTRY_GREATER, element, InvalidBlockNumber, MAIN_FORKNUM, false);
 
 			/* Release lock */
 			UnlockPage(index, HNSW_UPDATE_LOCK, lockmode);
@@ -565,7 +564,7 @@ MarkDeleted(HnswVacuumState * vacuumstate)
 	}
 
 	/* Update insert page last, after everything has been marked as deleted */
-	HnswUpdateMetaPage(index, 0, NULL, insertPage, MAIN_FORKNUM);
+	HnswUpdateMetaPage(index, 0, NULL, insertPage, MAIN_FORKNUM, false);
 }
 
 /*
@@ -575,7 +574,6 @@ static void
 InitVacuumState(HnswVacuumState * vacuumstate, IndexVacuumInfo *info, IndexBulkDeleteResult *stats, IndexBulkDeleteCallback callback, void *callback_state)
 {
 	Relation	index = info->index;
-	HASHCTL		hash_ctl;
 
 	if (stats == NULL)
 		stats = (IndexBulkDeleteResult *) palloc0(sizeof(IndexBulkDeleteResult));
@@ -597,10 +595,7 @@ InitVacuumState(HnswVacuumState * vacuumstate, IndexVacuumInfo *info, IndexBulkD
 	HnswGetMetaPageInfo(index, &vacuumstate->m, NULL);
 
 	/* Create hash table */
-	hash_ctl.keysize = sizeof(ItemPointerData);
+	vacuumstate->deleted = tidhash_create(CurrentMemoryContext, 256, NULL);
-	hash_ctl.entrysize = sizeof(ItemPointerData);
-	hash_ctl.hcxt = CurrentMemoryContext;
-	vacuumstate->deleted = hash_create("hnswbulkdelete indextids", 256, &hash_ctl, HASH_ELEM | HASH_BLOBS | HASH_CONTEXT);
 }
 
 /*
@@ -609,7 +604,7 @@ InitVacuumState(HnswVacuumState * vacuumstate, IndexVacuumInfo *info, IndexBulkD
 static void
 FreeVacuumState(HnswVacuumState * vacuumstate)
 {
-	hash_destroy(vacuumstate->deleted);
+	tidhash_destroy(vacuumstate->deleted);
 	FreeAccessStrategy(vacuumstate->bas);
 	pfree(vacuumstate->ntup);
 	MemoryContextDelete(vacuumstate->tmpCtx);

src/vector.c

@@ -724,7 +724,7 @@ vector_spherical_distance(PG_FUNCTION_ARGS)
 }
 
 /*
- * Get the L1 distance between vectors
+ * Get the L1 distance between two vectors
  */
 PGDLLEXPORT PG_FUNCTION_INFO_V1(l1_distance);
 Datum
@@ -903,8 +903,8 @@ PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_lt);
 Datum
 vector_lt(PG_FUNCTION_ARGS)
 {
-	Vector	   *a = (Vector *) PG_GETARG_VECTOR_P(0);
+	Vector	   *a = PG_GETARG_VECTOR_P(0);
-	Vector	   *b = (Vector *) PG_GETARG_VECTOR_P(1);
+	Vector	   *b = PG_GETARG_VECTOR_P(1);
 
 	PG_RETURN_BOOL(vector_cmp_internal(a, b) < 0);
 }
@@ -916,8 +916,8 @@ PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_le);
 Datum
 vector_le(PG_FUNCTION_ARGS)
 {
-	Vector	   *a = (Vector *) PG_GETARG_VECTOR_P(0);
+	Vector	   *a = PG_GETARG_VECTOR_P(0);
-	Vector	   *b = (Vector *) PG_GETARG_VECTOR_P(1);
+	Vector	   *b = PG_GETARG_VECTOR_P(1);
 
 	PG_RETURN_BOOL(vector_cmp_internal(a, b) <= 0);
 }
@@ -929,8 +929,8 @@ PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_eq);
 Datum
 vector_eq(PG_FUNCTION_ARGS)
 {
-	Vector	   *a = (Vector *) PG_GETARG_VECTOR_P(0);
+	Vector	   *a = PG_GETARG_VECTOR_P(0);
-	Vector	   *b = (Vector *) PG_GETARG_VECTOR_P(1);
+	Vector	   *b = PG_GETARG_VECTOR_P(1);
 
 	PG_RETURN_BOOL(vector_cmp_internal(a, b) == 0);
 }
@@ -942,8 +942,8 @@ PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_ne);
 Datum
 vector_ne(PG_FUNCTION_ARGS)
 {
-	Vector	   *a = (Vector *) PG_GETARG_VECTOR_P(0);
+	Vector	   *a = PG_GETARG_VECTOR_P(0);
-	Vector	   *b = (Vector *) PG_GETARG_VECTOR_P(1);
+	Vector	   *b = PG_GETARG_VECTOR_P(1);
 
 	PG_RETURN_BOOL(vector_cmp_internal(a, b) != 0);
 }
@@ -955,8 +955,8 @@ PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_ge);
 Datum
 vector_ge(PG_FUNCTION_ARGS)
 {
-	Vector	   *a = (Vector *) PG_GETARG_VECTOR_P(0);
+	Vector	   *a = PG_GETARG_VECTOR_P(0);
-	Vector	   *b = (Vector *) PG_GETARG_VECTOR_P(1);
+	Vector	   *b = PG_GETARG_VECTOR_P(1);
 
 	PG_RETURN_BOOL(vector_cmp_internal(a, b) >= 0);
 }
@@ -968,8 +968,8 @@ PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_gt);
 Datum
 vector_gt(PG_FUNCTION_ARGS)
 {
-	Vector	   *a = (Vector *) PG_GETARG_VECTOR_P(0);
+	Vector	   *a = PG_GETARG_VECTOR_P(0);
-	Vector	   *b = (Vector *) PG_GETARG_VECTOR_P(1);
+	Vector	   *b = PG_GETARG_VECTOR_P(1);
 
 	PG_RETURN_BOOL(vector_cmp_internal(a, b) > 0);
 }
@@ -981,8 +981,8 @@ PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_cmp);
 Datum
 vector_cmp(PG_FUNCTION_ARGS)
 {
-	Vector	   *a = (Vector *) PG_GETARG_VECTOR_P(0);
+	Vector	   *a = PG_GETARG_VECTOR_P(0);
-	Vector	   *b = (Vector *) PG_GETARG_VECTOR_P(1);
+	Vector	   *b = PG_GETARG_VECTOR_P(1);
 
 	PG_RETURN_INT32(vector_cmp_internal(a, b));
 }