Replace dynahash hash table in HNSW with simplehash for speed - #378

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

CHANGELOG.md

@@ -1,5 +1,6 @@
 ## 0.5.2 (unreleased)
 
+- Improved performance of HNSW
 - Added support for on-disk parallel index builds for HNSW
 - Fixed `invalid memory alloc request size` error with HNSW index build
 

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;
@@ -360,4 +361,31 @@ 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/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
  */
@@ -553,16 +636,22 @@ 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);
 	}
 }
 
@@ -578,30 +667,21 @@ 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));
@@ -1021,6 +1101,12 @@ 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))
 			{
@@ -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);