Less space [skip ci]

And rewrite some of the comments in InsertTuple(), to also give more
of a high-level overview of the flow.

src/hnsw.h

@@ -114,8 +114,6 @@
 
 /* Variables */
 extern int	hnsw_ef_search;
-
-/* This is initialized when the module is loaded */
 extern int	hnsw_lock_tranche_id;
 
 typedef struct HnswElementData HnswElementData;
@@ -200,20 +198,12 @@ typedef struct HnswGraph
 	bool		flushed;
 }			HnswGraph;
 
-typedef struct HnswSpool
-{
-	Relation	heap;
-	Relation	index;
-}			HnswSpool;
-
 typedef struct HnswShared
 {
 	/* Immutable state */
 	Oid			heaprelid;
 	Oid			indexrelid;
 	bool		isconcurrent;
-	int			scantuplesortstates;
-	dsa_pointer dsaptr;
 
 	/* Worker progress */
 	ConditionVariable workersdonecv;
@@ -393,14 +383,14 @@ void		HnswGetMetaPageInfo(Relation index, int *m, HnswElement * entryPoint);
 void	   *HnswAlloc(HnswAllocator * allocator, Size size);
 HnswElement HnswInitElement(char *base, ItemPointer tid, int m, double ml, int maxLevel, HnswAllocator * alloc);
 HnswElement HnswInitElementFromBlock(BlockNumber blkno, OffsetNumber offno);
-void		HnswInsertElement(char *base, 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(char *base, HnswElement em, Datum q, Relation rel, FmgrInfo *procinfo, Oid collation, bool loadVec);
 void		HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, BlockNumber insertPage, ForkNumber forkNum, bool building);
 void		HnswSetNeighborTuple(char *base, HnswNeighborTuple ntup, HnswElement e, int m);
 void		HnswAddHeapTid(HnswElement element, ItemPointer heaptid);
 void		HnswInitNeighbors(char *base, HnswElement element, int m, HnswAllocator * alloc);
 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(char *base, HnswElementTuple etup, HnswElement element);

src/hnswbuild.c

@@ -1,3 +1,39 @@
+/*
+ * 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>
@@ -295,7 +331,7 @@ FlushPages(HnswBuildState * buildstate)
  * Add a heap TID to an existing element
  */
 static bool
-HnswAddDuplicateInMemory(HnswElement element, HnswElement dup)
+AddDuplicateInMemory(HnswElement element, HnswElement dup)
 {
 	LWLockAcquire(&dup->lock, LW_EXCLUSIVE);
 
@@ -316,15 +352,15 @@ HnswAddDuplicateInMemory(HnswElement element, HnswElement dup)
  * Find duplicate element
  */
 static bool
-HnswFindDuplicateInMemory(char *base, HnswElement element)
+FindDuplicateInMemory(char *base, HnswElement element)
 {
 	HnswNeighborArray *neighbors = HnswGetNeighbors(base, element, 0);
+	Datum		value = HnswGetValue(base, element);
 
 	for (int i = 0; i < neighbors->length; i++)
 	{
 		HnswCandidate *neighbor = &neighbors->items[i];
 		HnswElement neighborElement = HnswPtrAccess(base, neighbor->element);
-		Datum		value = HnswGetValue(base, element);
 		Datum		neighborValue = HnswGetValue(base, neighborElement);
 
 		/* Exit early since ordered by distance */
@@ -332,7 +368,7 @@ HnswFindDuplicateInMemory(char *base, HnswElement element)
 			return false;
 
 		/* Check for space */
-		if (HnswAddDuplicateInMemory(element, neighborElement))
+		if (AddDuplicateInMemory(element, neighborElement))
 			return true;
 	}
 
@@ -340,10 +376,10 @@ HnswFindDuplicateInMemory(char *base, HnswElement element)
 }
 
 /*
- * Add to element and neighbor pages
+ * Add to element list
  */
 static void
-WriteNewElementPagesInMemory(char *base, HnswGraph * graph, HnswElement element)
+AddElementInMemory(char *base, HnswGraph * graph, HnswElement element)
 {
 	SpinLockAcquire(&graph->lock);
 	element->next = graph->head;
@@ -355,7 +391,7 @@ WriteNewElementPagesInMemory(char *base, HnswGraph * graph, HnswElement element)
  * Update neighbors
  */
 static void
-HnswUpdateNeighborPagesInMemory(char *base, FmgrInfo *procinfo, Oid collation, HnswElement e, int m)
+UpdateNeighborsInMemory(char *base, FmgrInfo *procinfo, Oid collation, HnswElement e, int m)
 {
 	for (int lc = e->level; lc >= 0; lc--)
 	{
@@ -379,45 +415,82 @@ HnswUpdateNeighborPagesInMemory(char *base, FmgrInfo *procinfo, Oid collation, H
 }
 
 /*
- * Write changes in memory
+ * Update graph in memory
  */
 static void
-WriteElementInMemory(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement element, int m, int efConstruction, HnswElement entryPoint, HnswBuildState * buildstate, HnswGraph * graph, bool updateEntryPoint)
+UpdateGraphInMemory(FmgrInfo *procinfo, Oid collation, HnswElement element, int m, int efConstruction, HnswElement entryPoint, HnswBuildState * buildstate)
 {
+	HnswGraph  *graph = buildstate->graph;
 	char	   *base = buildstate->hnswarea;
 
-	/* Try to add to existing page */
-	if (HnswFindDuplicateInMemory(base, element))
+	/* Look for duplicate */
+	if (FindDuplicateInMemory(base, element))
 		return;
 
-	/* Write element and neighbor tuples */
-	WriteNewElementPagesInMemory(base, graph, element);
+	/* Add element */
+	AddElementInMemory(base, graph, element);
 
 	/* Update neighbors */
-	HnswUpdateNeighborPagesInMemory(base, procinfo, collation, element, m);
+	UpdateNeighborsInMemory(base, procinfo, collation, element, m);
 
 	/* Update entry point if needed (already have lock) */
-	if (updateEntryPoint)
+	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;
+	LWLock	   *entryLock = &graph->entryLock;
+	int			efConstruction = buildstate->efConstruction;
+	int			m = buildstate->m;
+	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)
 {
-	FmgrInfo   *procinfo = buildstate->procinfo;
-	Oid			collation = buildstate->collation;
 	HnswGraph  *graph = buildstate->graph;
-	HnswElement entryPoint;
-	int			efConstruction = buildstate->efConstruction;
-	int			m = buildstate->m;
 	HnswElement element;
 	HnswAllocator *allocator = &buildstate->allocator;
 	Size		valueSize;
 	Pointer		valuePtr;
-	bool		updateEntryPoint;
 	LWLock	   *flushLock = &graph->flushLock;
 	char	   *base = buildstate->hnswarea;
 
@@ -427,7 +500,7 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
 	/* 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;
 	}
 
@@ -437,6 +510,7 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
 	/* Ensure graph not flushed when inserting */
 	LWLockAcquire(flushLock, LW_SHARED);
 
+	/* Are we in the on-disk phase? */
 	if (graph->flushed)
 	{
 		LWLockRelease(flushLock);
@@ -444,10 +518,16 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
 		return HnswInsertTupleOnDisk(index, value, values, isnull, heaptid, buildstate->heap, true);
 	}
 
-	/* Get lock for allocator */
+	/*
+	 * 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);
 
-	/* Flush pages if needed */
+	/*
+	 * 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)
 	{
 		LWLockRelease(&graph->allocatorLock);
@@ -470,38 +550,26 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
 		return HnswInsertTupleOnDisk(index, value, values, isnull, heaptid, buildstate->heap, true);
 	}
 
-	/* Create an element */
+	/* Ok, we can proceed to allocate the element */
 	element = HnswInitElement(base, heaptid, buildstate->m, buildstate->ml, buildstate->maxLevel, allocator);
 	valuePtr = HnswAlloc(allocator, valueSize);
 
-	/* Release allocator lock */
+	/*
+	 * 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 datum */
+	/* Copy the datum */
 	memcpy(valuePtr, DatumGetPointer(value), valueSize);
 	HnswPtrStore(base, element->value, valuePtr);
 
-	/* Create element lock */
+	/* Create a lock for the element */
 	LWLockInitialize(&element->lock, hnsw_lock_tranche_id);
 
-	/* Get entry point */
-	LWLockAcquire(&graph->entryLock, LW_EXCLUSIVE);
-	entryPoint = HnswPtrAccess(base, graph->entryPoint);
-	updateEntryPoint = entryPoint == NULL || element->level > entryPoint->level;
-
-	/* Release lock if not updating entry point */
-	if (!updateEntryPoint)
-		LWLockRelease(&graph->entryLock);
-
-	/* Insert element in graph */
-	HnswInsertElement(base, element, entryPoint, NULL, procinfo, collation, m, efConstruction, false);
-
-	/* Write to memory */
-	WriteElementInMemory(index, procinfo, collation, element, m, efConstruction, entryPoint, buildstate, graph, updateEntryPoint);
-
-	/* Release lock if needed */
-	if (updateEntryPoint)
-		LWLockRelease(&graph->entryLock);
+	/* Insert tuple */
+	InsertTupleInMemory(buildstate, element);
 
 	/* Release flush lock */
 	LWLockRelease(flushLock);
@@ -710,7 +778,7 @@ ParallelHeapScan(HnswBuildState * buildstate)
  * Perform a worker's portion of a parallel insert
  */
 static void
-HnswParallelScanAndInsert(HnswSpool * hnswspool, HnswShared * hnswshared, char *hnswarea, bool progress)
+HnswParallelScanAndInsert(Relation heapRel, Relation indexRel, HnswShared * hnswshared, char *hnswarea, bool progress)
 {
 	HnswBuildState buildstate;
 #if PG_VERSION_NUM >= 120000
@@ -722,21 +790,21 @@ HnswParallelScanAndInsert(HnswSpool * hnswspool, HnswShared * hnswshared, char *
 	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.hnswarea = hnswarea;
 	InitAllocator(&buildstate.allocator, &HnswSharedMemoryAlloc, &buildstate);
 #if PG_VERSION_NUM >= 120000
-	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,
+	scan = heap_beginscan_parallel(heapRel, &hnswshared->heapdesc);
+	reltuples = IndexBuildHeapScan(heapRel, indexRel, indexInfo,
 								   true, BuildCallback,
 								   (void *) &buildstate, scan);
 #endif
@@ -766,10 +834,7 @@ void
 HnswParallelBuildMain(dsm_segment *seg, shm_toc *toc)
 {
 	char	   *sharedquery;
-	HnswSpool  *hnswspool;
 	HnswShared *hnswshared;
-	dsa_area   *dsa;
-	void	   *dsaspace;
 	char	   *hnswarea;
 	Relation	heapRel;
 	Relation	indexRel;
@@ -806,17 +871,10 @@ HnswParallelBuildMain(dsm_segment *seg, shm_toc *toc)
 #endif
 	indexRel = index_open(hnswshared->indexrelid, indexLockmode);
 
-	/* Initialize worker's own spool */
-	hnswspool = (HnswSpool *) palloc0(sizeof(HnswSpool));
-	hnswspool->heap = heapRel;
-	hnswspool->index = indexRel;
-
-	dsaspace = shm_toc_lookup(toc, PARALLEL_KEY_HNSW_AREA, false);
-	dsa = dsa_attach_in_place(dsaspace, seg);
-	hnswarea = dsa_get_address(dsa, hnswshared->dsaptr);
+	hnswarea = shm_toc_lookup(toc, PARALLEL_KEY_HNSW_AREA, false);
 
 	/* Perform inserts */
-	HnswParallelScanAndInsert(hnswspool, hnswshared, hnswarea, false);
+	HnswParallelScanAndInsert(heapRel, indexRel, hnswshared, hnswarea, false);
 
 	/* Close relations within worker */
 	index_close(indexRel, indexLockmode);
@@ -871,15 +929,9 @@ 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, hnswleader->hnswarea, true);
+	HnswParallelScanAndInsert(buildstate->heap, buildstate->index, hnswleader->hnswshared, hnswleader->hnswarea, true);
 }
 
 /*
@@ -889,14 +941,11 @@ static void
 HnswBeginParallel(HnswBuildState * buildstate, bool isconcurrent, int request)
 {
 	ParallelContext *pcxt;
-	int			scantuplesortstates;
 	Snapshot	snapshot;
 	Size		esthnswshared;
 	Size		esthnswarea;
-	Size		estdsaspace;
+	Size		estother;
 	HnswShared *hnswshared;
-	void	   *dsaspace;
-	dsa_area   *dsa;
 	char	   *hnswarea;
 	HnswLeader *hnswleader = (HnswLeader *) palloc0(sizeof(HnswLeader));
 	bool		leaderparticipates = true;
@@ -915,8 +964,6 @@ HnswBeginParallel(HnswBuildState * buildstate, bool isconcurrent, int request)
 	pcxt = CreateParallelContext("vector", "HnswParallelBuildMain", request, true);
 #endif
 
-	scantuplesortstates = leaderparticipates ? request + 1 : request;
-
 	/* Get snapshot for table scan */
 	if (!isconcurrent)
 		snapshot = SnapshotAny;
@@ -927,9 +974,15 @@ HnswBeginParallel(HnswBuildState * buildstate, bool isconcurrent, int request)
 	esthnswshared = ParallelEstimateShared(buildstate->heap, snapshot);
 	shm_toc_estimate_chunk(&pcxt->estimator, esthnswshared);
 
-	/* Start with a minimal DSA so InitializeParallelDSM does not fail */
-	estdsaspace = dsa_minimum_size();
-	shm_toc_estimate_chunk(&pcxt->estimator, estdsaspace);
+	/* 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 = 2 * 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 */
@@ -961,7 +1014,6 @@ 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 */
@@ -975,28 +1027,12 @@ HnswBeginParallel(HnswBuildState * buildstate, bool isconcurrent, int request)
 	heap_parallelscan_initialize(&hnswshared->heapdesc, buildstate->heap, snapshot);
 #endif
 
-	dsaspace = shm_toc_allocate(pcxt->toc, estdsaspace);
-	dsa = dsa_create_in_place(dsaspace, estdsaspace, hnsw_lock_tranche_id, pcxt->seg);
-
-	esthnswarea = maintenance_work_mem * 1024L;
-	hnswshared->dsaptr = dsa_allocate_extended(dsa, esthnswarea, DSA_ALLOC_HUGE | DSA_ALLOC_NO_OOM);
-
-	/* If not enough shared memory, back out (do serial build) */
-	if (!DsaPointerIsValid(hnswshared->dsaptr))
-	{
-		if (IsMVCCSnapshot(snapshot))
-			UnregisterSnapshot(snapshot);
-		DestroyParallelContext(pcxt);
-		ExitParallelMode();
-		return;
-	}
-
-	hnswarea = dsa_get_address(dsa, hnswshared->dsaptr);
+	hnswarea = (char *) shm_toc_allocate(pcxt->toc, esthnswarea);
 	/* 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, dsaspace);
+	shm_toc_insert(pcxt->toc, PARALLEL_KEY_HNSW_AREA, hnswarea);
 
 	/* Store query string for workers */
 	if (debug_query_string)

src/hnswinsert.c

@@ -116,7 +116,7 @@ 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;
@@ -339,7 +339,7 @@ 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, bool building)
+HnswUpdateNeighborsOnDisk(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement e, int m, bool checkExisting, bool building)
 {
 	char	   *base = NULL;
 
@@ -451,7 +451,7 @@ 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;
@@ -515,23 +515,23 @@ 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)
 {
 	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		value = HnswGetValue(base, element);
 		Datum		neighborValue = HnswGetValue(base, neighborElement);
 
 		/* Exit early since ordered by distance */
 		if (!datumIsEqual(value, neighborValue, false, -1))
 			return false;
 
-		if (HnswAddDuplicate(index, element, neighborElement, building))
+		if (AddDuplicateOnDisk(index, element, neighborElement, building))
 			return true;
 	}
 
@@ -539,26 +539,26 @@ 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 */
-	WriteNewElementPages(index, element, m, GetInsertPage(index), &newInsertPage, building);
+	/* Add element */
+	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)
@@ -608,11 +608,11 @@ HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull,
 		entryPoint = HnswGetEntryPoint(index);
 	}
 
-	/* Insert element in graph */
-	HnswInsertElement(base, element, entryPoint, index, procinfo, collation, m, efConstruction, false);
+	/* Find neighbors for element */
+	HnswFindElementNeighbors(base, element, entryPoint, index, procinfo, collation, m, efConstruction, false);
 
-	/* Write to disk */
-	WriteElement(index, procinfo, collation, element, m, efConstruction, entryPoint, building);
+	/* Update graph on disk */
+	UpdateGraphOnDisk(index, procinfo, collation, element, m, efConstruction, entryPoint, building);
 
 	/* Release lock */
 	UnlockPage(index, HNSW_UPDATE_LOCK, lockmode);

src/hnswutils.c

@@ -656,11 +656,25 @@ 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(char *base, visited_hash v, HnswCandidate * hc, Relation index, bool *found)
+AddToVisited(char *base, visited_hash * v, HnswCandidate * hc, Relation index, bool *found)
 {
 	if (index != NULL)
 	{
@@ -668,16 +682,16 @@ AddToVisited(char *base, visited_hash v, HnswCandidate * hc, Relation index, boo
 		ItemPointerData indextid;
 
 		ItemPointerSet(&indextid, element->blkno, element->offno);
-		tidhash_insert(v.tids, indextid, found);
+		tidhash_insert(v->tids, indextid, found);
 	}
 	else if (base != NULL)
 	{
 #if PG_VERSION_NUM >= 130000
 		HnswElement element = HnswPtrAccess(base, hc->element);
 
-		offsethash_insert_hash(v.offsets, HnswPtrOffset(hc->element), element->hash, found);
+		offsethash_insert_hash(v->offsets, HnswPtrOffset(hc->element), element->hash, found);
 #else
-		offsethash_insert(v.offsets, HnswPtrOffset(hc->element), found);
+		offsethash_insert(v->offsets, HnswPtrOffset(hc->element), found);
 #endif
 	}
 	else
@@ -685,9 +699,9 @@ AddToVisited(char *base, visited_hash v, HnswCandidate * hc, Relation index, boo
 #if PG_VERSION_NUM >= 130000
 		HnswElement element = HnswPtrAccess(base, hc->element);
 
-		pointerhash_insert_hash(v.pointers, (uintptr_t) HnswPtrPointer(hc->element), element->hash, found);
+		pointerhash_insert_hash(v->pointers, (uintptr_t) HnswPtrPointer(hc->element), element->hash, found);
 #else
-		pointerhash_insert(v.pointers, (uintptr_t) HnswPtrPointer(hc->element), found);
+		pointerhash_insert(v->pointers, (uintptr_t) HnswPtrPointer(hc->element), found);
 #endif
 	}
 }
@@ -725,13 +739,7 @@ HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, F
 	HnswNeighborArray *neighborhoodData = NULL;
 	Size		neighborhoodSize;
 
-	/* Create hash table */
-	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);
+	InitVisited(base, &v, index, ef, m);
 
 	/* Create local memory for neighborhood if needed */
 	if (index == NULL)
@@ -746,7 +754,7 @@ HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, F
 		HnswCandidate *hc = (HnswCandidate *) lfirst(lc2);
 		bool		found;
 
-		AddToVisited(base, v, hc, index, &found);
+		AddToVisited(base, &v, hc, index, &found);
 
 		pairingheap_add(C, &(CreatePairingHeapNode(hc)->ph_node));
 		pairingheap_add(W, &(CreatePairingHeapNode(hc)->ph_node));
@@ -781,7 +789,7 @@ HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, F
 		/* Copy neighborhood to local memory if needed */
 		if (index == NULL)
 		{
-			LWLockAcquire(&cElement->lock, LW_EXCLUSIVE);
+			LWLockAcquire(&cElement->lock, LW_SHARED);
 			memcpy(neighborhoodData, neighborhood, neighborhoodSize);
 			LWLockRelease(&cElement->lock);
 			neighborhood = neighborhoodData;
@@ -792,7 +800,7 @@ HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, F
 			HnswCandidate *e = &neighborhood->items[i];
 			bool		visited;
 
-			AddToVisited(base, v, e, index, &visited);
+			AddToVisited(base, &v, e, index, &visited);
 
 			if (!visited)
 			{
@@ -963,7 +971,6 @@ CheckElementCloser(char *base, HnswCandidate * e, List *r, int lc, FmgrInfo *pro
 	{
 		HnswCandidate *ri = lfirst(lc2);
 		HnswElement riElement = HnswPtrAccess(base, ri->element);
-
 		float		distance = HnswGetDistance(base, eElement, riElement, lc, procinfo, collation);
 
 		if (distance <= e->distance)
@@ -1216,7 +1223,7 @@ PrecomputeHash(char *base, HnswElement element)
  * Algorithm 1 from paper
  */
 void
-HnswInsertElement(char *base, 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;

src/hnswvacuum.c

@@ -199,21 +199,22 @@ 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(NULL, element, m, NULL);
+	HnswInitNeighbors(base, element, m, NULL);
 	element->heaptidsLength = 0;
 
-	/* Add element to graph, skipping itself */
-	HnswInsertElement(NULL, element, entryPoint, index, procinfo, collation, m, efConstruction, true);
+	/* Find neighbors for element, skipping itself */
+	HnswFindElementNeighbors(base, element, entryPoint, index, procinfo, collation, m, efConstruction, true);
 
 	/* Update neighbor tuple */
 	/* Do this before getting page to minimize locking */
-	HnswSetNeighborTuple(NULL, ntup, element, m);
+	HnswSetNeighborTuple(base, ntup, element, m);
 
 	/* Get neighbor page */
 	buf = ReadBufferExtended(index, MAIN_FORKNUM, element->neighborPage, RBM_NORMAL, bas);
@@ -230,7 +231,7 @@ 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);
 }
 
 /*