mirror of
https://github.com/pgvector/pgvector.git
synced 2026-07-22 20:15:46 +08:00
Compare commits
10 Commits
hnsw-bench
...
amgetbatch
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
89dc41ce2b | ||
|
|
06ab41c094 | ||
|
|
8a8bc90d6d | ||
|
|
91717c81b3 | ||
|
|
98a7f94608 | ||
|
|
7db3d67b2d | ||
|
|
1dd39f66de | ||
|
|
cd431c51ca | ||
|
|
73890f2f70 | ||
|
|
18980387ec |
2
.github/workflows/build.yml
vendored
2
.github/workflows/build.yml
vendored
@@ -97,7 +97,7 @@ jobs:
|
||||
with:
|
||||
postgres-version: ${{ matrix.postgres }}
|
||||
- run: |
|
||||
call "C:\Program Files\Microsoft Visual Studio\${{ matrix.os == 'windows-2025' && 18 || 2022 }}\Enterprise\VC\Auxiliary\Build\vcvars64.bat" && ^
|
||||
call "C:\Program Files\Microsoft Visual Studio\2022\Enterprise\VC\Auxiliary\Build\vcvars64.bat" && ^
|
||||
nmake /NOLOGO /F Makefile.win && ^
|
||||
nmake /NOLOGO /F Makefile.win install && ^
|
||||
nmake /NOLOGO /F Makefile.win installcheck ${{ matrix.postgres != 17 && 'PG_REGRESS=$(PGROOT)\bin\pg_regress' || '' }} && ^
|
||||
|
||||
@@ -1,7 +1,3 @@
|
||||
## 0.8.3 (unreleased)
|
||||
|
||||
- Fixed performance regression with Hamming distance and Jaccard distance with Postgres 18
|
||||
|
||||
## 0.8.2 (2026-02-25)
|
||||
|
||||
- Fixed buffer overflow with parallel HNSW index build - [more info](https://github.com/pgvector/pgvector/issues/959)
|
||||
|
||||
@@ -1329,7 +1329,7 @@ make clean && PG_CFLAGS="-DUSE_ASSERT_CHECKING" make && make install
|
||||
To enable benchmarking:
|
||||
|
||||
```sh
|
||||
make clean && PG_CFLAGS="-DHNSW_BENCH -DIVFFLAT_BENCH" make && make install
|
||||
make clean && PG_CFLAGS="-DIVFFLAT_BENCH" make && make install
|
||||
```
|
||||
|
||||
To show memory usage:
|
||||
|
||||
@@ -31,12 +31,10 @@
|
||||
#define BIT_TARGET_CLONES
|
||||
#endif
|
||||
|
||||
/* Use built-ins when possible for Postgres < 19 for inlining */
|
||||
#if PG_VERSION_NUM >= 190000
|
||||
#define popcount64(x) pg_popcount64(x)
|
||||
#elif defined(HAVE__BUILTIN_POPCOUNT) && (defined(HAVE_LONG_INT_64) || SIZEOF_LONG == 8)
|
||||
/* Use built-ins when possible for inlining */
|
||||
#if defined(HAVE__BUILTIN_POPCOUNT) && defined(HAVE_LONG_INT_64)
|
||||
#define popcount64(x) __builtin_popcountl(x)
|
||||
#elif defined(HAVE__BUILTIN_POPCOUNT) && (defined(HAVE_LONG_LONG_INT_64) || SIZEOF_LONG_LONG == 8)
|
||||
#elif defined(HAVE__BUILTIN_POPCOUNT) && defined(HAVE_LONG_LONG_INT_64)
|
||||
#define popcount64(x) __builtin_popcountll(x)
|
||||
#elif !defined(_MSC_VER)
|
||||
/* Fails to resolve with MSVC */
|
||||
|
||||
15
src/hnsw.c
15
src/hnsw.c
@@ -258,6 +258,11 @@ hnswvalidate(Oid opclassoid)
|
||||
return true;
|
||||
}
|
||||
|
||||
static void
|
||||
hnswunguardbatch(IndexScanDesc scan, IndexScanBatch batch)
|
||||
{
|
||||
}
|
||||
|
||||
/*
|
||||
* Define index handler
|
||||
*
|
||||
@@ -279,6 +284,7 @@ hnswhandler(PG_FUNCTION_ARGS)
|
||||
.amconsistentequality = false,
|
||||
.amconsistentordering = false,
|
||||
.amcanbackward = false,
|
||||
.amcanmarkpos = false,
|
||||
.amcanunique = false,
|
||||
.amcanmulticol = false,
|
||||
.amoptionalkey = true,
|
||||
@@ -311,11 +317,14 @@ hnswhandler(PG_FUNCTION_ARGS)
|
||||
.amadjustmembers = NULL,
|
||||
.ambeginscan = hnswbeginscan,
|
||||
.amrescan = hnswrescan,
|
||||
.amgettuple = hnswgettuple,
|
||||
.amgettuple = NULL,
|
||||
.amgetbatch = hnswgetbatch,
|
||||
.amunguardbatch = hnswunguardbatch,
|
||||
.amkillitemsbatch = NULL,
|
||||
.amgettransform = NULL,
|
||||
.amgetbitmap = NULL,
|
||||
.amendscan = hnswendscan,
|
||||
.ammarkpos = NULL,
|
||||
.amrestrpos = NULL,
|
||||
.amposreset = NULL,
|
||||
.amestimateparallelscan = NULL,
|
||||
.aminitparallelscan = NULL,
|
||||
.amparallelrescan = NULL,
|
||||
|
||||
21
src/hnsw.h
21
src/hnsw.h
@@ -18,10 +18,6 @@
|
||||
#include "utils/sampling.h"
|
||||
#include "vector.h"
|
||||
|
||||
#ifdef HNSW_BENCH
|
||||
#include "portability/instr_time.h"
|
||||
#endif
|
||||
|
||||
#if PG_VERSION_NUM >= 190000
|
||||
typedef Pointer Item;
|
||||
#endif
|
||||
@@ -82,21 +78,6 @@ typedef Pointer Item;
|
||||
#define HnswPageGetOpaque(page) ((HnswPageOpaque) PageGetSpecialPointer(page))
|
||||
#define HnswPageGetMeta(page) ((HnswMetaPageData *) PageGetContents(page))
|
||||
|
||||
#ifdef HNSW_BENCH
|
||||
#define HnswBench(name, code) \
|
||||
do { \
|
||||
instr_time start; \
|
||||
instr_time duration; \
|
||||
INSTR_TIME_SET_CURRENT(start); \
|
||||
(code); \
|
||||
INSTR_TIME_SET_CURRENT(duration); \
|
||||
INSTR_TIME_SUBTRACT(duration, start); \
|
||||
elog(INFO, "%s: %.3f ms", name, INSTR_TIME_GET_MILLISEC(duration)); \
|
||||
} while (0)
|
||||
#else
|
||||
#define HnswBench(name, code) (code)
|
||||
#endif
|
||||
|
||||
#if PG_VERSION_NUM >= 150000
|
||||
#define RandomDouble() pg_prng_double(&pg_global_prng_state)
|
||||
#define SeedRandom(seed) pg_prng_seed(&pg_global_prng_state, seed)
|
||||
@@ -484,7 +465,7 @@ IndexBulkDeleteResult *hnswbulkdelete(IndexVacuumInfo *info, IndexBulkDeleteResu
|
||||
IndexBulkDeleteResult *hnswvacuumcleanup(IndexVacuumInfo *info, IndexBulkDeleteResult *stats);
|
||||
IndexScanDesc hnswbeginscan(Relation index, int nkeys, int norderbys);
|
||||
void hnswrescan(IndexScanDesc scan, ScanKey keys, int nkeys, ScanKey orderbys, int norderbys);
|
||||
bool hnswgettuple(IndexScanDesc scan, ScanDirection dir);
|
||||
IndexScanBatch hnswgetbatch(IndexScanDesc scan, IndexScanBatch priorbatch, ScanDirection dir);
|
||||
void hnswendscan(IndexScanDesc scan);
|
||||
|
||||
static inline HnswNeighborArray *
|
||||
|
||||
@@ -3,6 +3,7 @@
|
||||
#include <limits.h>
|
||||
|
||||
#include "access/genam.h"
|
||||
#include "access/indexbatch.h"
|
||||
#include "access/relscan.h"
|
||||
#include "hnsw.h"
|
||||
#include "lib/pairingheap.h"
|
||||
@@ -135,6 +136,11 @@ hnswbeginscan(Relation index, int nkeys, int norderbys)
|
||||
double maxMemory;
|
||||
|
||||
scan = RelationGetIndexScan(index, nkeys, norderbys);
|
||||
scan->maxitemsbatch = hnsw_ef_search * HNSW_HEAPTIDS;
|
||||
/* unused but must be > 0 */
|
||||
scan->batch_index_opaque_static = MAXALIGN(1);
|
||||
scan->batch_index_opaque_dyn = 0;
|
||||
scan->batch_tuples_workspace = 0;
|
||||
|
||||
so = (HnswScanOpaque) palloc(sizeof(HnswScanOpaqueData));
|
||||
so->typeInfo = HnswGetTypeInfo(index);
|
||||
@@ -184,12 +190,13 @@ hnswrescan(IndexScanDesc scan, ScanKey keys, int nkeys, ScanKey orderbys, int no
|
||||
}
|
||||
|
||||
/*
|
||||
* Fetch the next tuple in the given scan
|
||||
* Fetch the next batch in the given scan
|
||||
*/
|
||||
bool
|
||||
hnswgettuple(IndexScanDesc scan, ScanDirection dir)
|
||||
IndexScanBatch
|
||||
hnswgetbatch(IndexScanDesc scan, IndexScanBatch priorbatch, ScanDirection dir)
|
||||
{
|
||||
HnswScanOpaque so = (HnswScanOpaque) scan->opaque;
|
||||
IndexScanBatch batch = indexam_util_alloc_batch(scan);
|
||||
MemoryContext oldCtx = MemoryContextSwitchTo(so->tmpCtx);
|
||||
|
||||
/*
|
||||
@@ -245,6 +252,7 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
|
||||
HnswSearchCandidate *sc;
|
||||
HnswElement element;
|
||||
ItemPointer heaptid;
|
||||
int nitems = 0;
|
||||
|
||||
if (list_length(so->w) == 0)
|
||||
{
|
||||
@@ -290,44 +298,64 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
|
||||
break;
|
||||
}
|
||||
|
||||
sc = llast(so->w);
|
||||
element = HnswPtrAccess(base, sc->element);
|
||||
|
||||
/* Move to next element if no valid heap TIDs */
|
||||
if (element->heaptidsLength == 0)
|
||||
while (list_length(so->w) != 0)
|
||||
{
|
||||
so->w = list_delete_last(so->w);
|
||||
sc = llast(so->w);
|
||||
element = HnswPtrAccess(base, sc->element);
|
||||
|
||||
/* Mark memory as free for next iteration */
|
||||
if (hnsw_iterative_scan != HNSW_ITERATIVE_SCAN_OFF)
|
||||
/* Move to next element if no valid heap TIDs */
|
||||
if (element->heaptidsLength == 0)
|
||||
{
|
||||
pfree(element);
|
||||
pfree(sc);
|
||||
so->w = list_delete_last(so->w);
|
||||
|
||||
/* Mark memory as free for next iteration */
|
||||
if (hnsw_iterative_scan != HNSW_ITERATIVE_SCAN_OFF)
|
||||
{
|
||||
pfree(element);
|
||||
pfree(sc);
|
||||
}
|
||||
|
||||
continue;
|
||||
}
|
||||
|
||||
heaptid = &element->heaptids[--element->heaptidsLength];
|
||||
|
||||
if (hnsw_iterative_scan == HNSW_ITERATIVE_SCAN_STRICT)
|
||||
{
|
||||
if (sc->distance < so->previousDistance)
|
||||
continue;
|
||||
|
||||
so->previousDistance = sc->distance;
|
||||
}
|
||||
|
||||
batch->items[nitems].tableTid = *heaptid;
|
||||
batch->items[nitems].indexOffset = -1;
|
||||
batch->items[nitems].tupleOffset = 0;
|
||||
nitems++;
|
||||
|
||||
/* Keep batch size flexible */
|
||||
if (nitems == scan->maxitemsbatch)
|
||||
break;
|
||||
}
|
||||
|
||||
/* Needed for strict iterative scans */
|
||||
if (nitems == 0)
|
||||
continue;
|
||||
}
|
||||
|
||||
heaptid = &element->heaptids[--element->heaptidsLength];
|
||||
|
||||
if (hnsw_iterative_scan == HNSW_ITERATIVE_SCAN_STRICT)
|
||||
{
|
||||
if (sc->distance < so->previousDistance)
|
||||
continue;
|
||||
|
||||
so->previousDistance = sc->distance;
|
||||
}
|
||||
|
||||
MemoryContextSwitchTo(oldCtx);
|
||||
|
||||
scan->xs_heaptid = *heaptid;
|
||||
scan->xs_recheck = false;
|
||||
scan->xs_recheckorderby = false;
|
||||
return true;
|
||||
|
||||
batch->firstItem = 0;
|
||||
batch->lastItem = nitems - 1;
|
||||
batch->dir = ForwardScanDirection;
|
||||
return batch;
|
||||
}
|
||||
|
||||
MemoryContextSwitchTo(oldCtx);
|
||||
return false;
|
||||
indexam_util_release_batch(scan, batch);
|
||||
return NULL;
|
||||
}
|
||||
|
||||
/*
|
||||
|
||||
@@ -634,13 +634,13 @@ hnswbulkdelete(IndexVacuumInfo *info, IndexBulkDeleteResult *stats,
|
||||
InitVacuumState(&vacuumstate, info, stats, callback, callback_state);
|
||||
|
||||
/* Pass 1: Remove heap TIDs */
|
||||
HnswBench("RemoveHeapTids", RemoveHeapTids(&vacuumstate));
|
||||
RemoveHeapTids(&vacuumstate);
|
||||
|
||||
/* Pass 2: Repair graph */
|
||||
HnswBench("RepairGraph", RepairGraph(&vacuumstate));
|
||||
RepairGraph(&vacuumstate);
|
||||
|
||||
/* Pass 3: Mark as deleted */
|
||||
HnswBench("MarkDeleted", MarkDeleted(&vacuumstate));
|
||||
MarkDeleted(&vacuumstate);
|
||||
|
||||
FreeVacuumState(&vacuumstate);
|
||||
|
||||
|
||||
@@ -175,6 +175,11 @@ ivfflatvalidate(Oid opclassoid)
|
||||
return true;
|
||||
}
|
||||
|
||||
static void
|
||||
ivfflatunguardbatch(IndexScanDesc scan, IndexScanBatch batch)
|
||||
{
|
||||
}
|
||||
|
||||
/*
|
||||
* Define index handler
|
||||
*
|
||||
@@ -196,6 +201,7 @@ ivfflathandler(PG_FUNCTION_ARGS)
|
||||
.amconsistentequality = false,
|
||||
.amconsistentordering = false,
|
||||
.amcanbackward = false,
|
||||
.amcanmarkpos = false,
|
||||
.amcanunique = false,
|
||||
.amcanmulticol = false,
|
||||
.amoptionalkey = true,
|
||||
@@ -228,11 +234,14 @@ ivfflathandler(PG_FUNCTION_ARGS)
|
||||
.amadjustmembers = NULL,
|
||||
.ambeginscan = ivfflatbeginscan,
|
||||
.amrescan = ivfflatrescan,
|
||||
.amgettuple = ivfflatgettuple,
|
||||
.amgettuple = NULL,
|
||||
.amgetbatch = ivfflatgetbatch,
|
||||
.amunguardbatch = ivfflatunguardbatch,
|
||||
.amkillitemsbatch = NULL,
|
||||
.amgettransform = NULL,
|
||||
.amgetbitmap = NULL,
|
||||
.amendscan = ivfflatendscan,
|
||||
.ammarkpos = NULL,
|
||||
.amrestrpos = NULL,
|
||||
.amposreset = NULL,
|
||||
.amestimateparallelscan = NULL,
|
||||
.aminitparallelscan = NULL,
|
||||
.amparallelrescan = NULL,
|
||||
|
||||
@@ -344,7 +344,7 @@ IndexBulkDeleteResult *ivfflatbulkdelete(IndexVacuumInfo *info, IndexBulkDeleteR
|
||||
IndexBulkDeleteResult *ivfflatvacuumcleanup(IndexVacuumInfo *info, IndexBulkDeleteResult *stats);
|
||||
IndexScanDesc ivfflatbeginscan(Relation index, int nkeys, int norderbys);
|
||||
void ivfflatrescan(IndexScanDesc scan, ScanKey keys, int nkeys, ScanKey orderbys, int norderbys);
|
||||
bool ivfflatgettuple(IndexScanDesc scan, ScanDirection dir);
|
||||
IndexScanBatch ivfflatgetbatch(IndexScanDesc scan, IndexScanBatch priorbatch, ScanDirection dir);
|
||||
void ivfflatendscan(IndexScanDesc scan);
|
||||
|
||||
#endif
|
||||
|
||||
@@ -3,6 +3,7 @@
|
||||
#include <float.h>
|
||||
|
||||
#include "access/genam.h"
|
||||
#include "access/indexbatch.h"
|
||||
#include "access/itup.h"
|
||||
#include "access/relscan.h"
|
||||
#include "access/tupdesc.h"
|
||||
@@ -261,6 +262,11 @@ ivfflatbeginscan(Relation index, int nkeys, int norderbys)
|
||||
MemoryContext oldCtx;
|
||||
|
||||
scan = RelationGetIndexScan(index, nkeys, norderbys);
|
||||
scan->maxitemsbatch = 1000;
|
||||
/* unused but must be > 0 */
|
||||
scan->batch_index_opaque_static = MAXALIGN(1);
|
||||
scan->batch_index_opaque_dyn = 0;
|
||||
scan->batch_tuples_workspace = 0;
|
||||
|
||||
/* Get lists and dimensions from metapage */
|
||||
IvfflatGetMetaPageInfo(index, &lists, &dimensions);
|
||||
@@ -348,14 +354,16 @@ ivfflatrescan(IndexScanDesc scan, ScanKey keys, int nkeys, ScanKey orderbys, int
|
||||
}
|
||||
|
||||
/*
|
||||
* Fetch the next tuple in the given scan
|
||||
* Fetch the next batch in the given scan
|
||||
*/
|
||||
bool
|
||||
ivfflatgettuple(IndexScanDesc scan, ScanDirection dir)
|
||||
IndexScanBatch
|
||||
ivfflatgetbatch(IndexScanDesc scan, IndexScanBatch priorbatch, ScanDirection dir)
|
||||
{
|
||||
IvfflatScanOpaque so = (IvfflatScanOpaque) scan->opaque;
|
||||
IndexScanBatch batch = indexam_util_alloc_batch(scan);
|
||||
ItemPointer heaptid;
|
||||
bool isnull;
|
||||
int nitems = 0;
|
||||
|
||||
/*
|
||||
* Index can be used to scan backward, but Postgres doesn't support
|
||||
@@ -393,17 +401,37 @@ ivfflatgettuple(IndexScanDesc scan, ScanDirection dir)
|
||||
while (!tuplesort_gettupleslot(so->sortstate, true, false, so->mslot, NULL))
|
||||
{
|
||||
if (so->listIndex == so->maxProbes)
|
||||
return false;
|
||||
{
|
||||
indexam_util_release_batch(scan, batch);
|
||||
return NULL;
|
||||
}
|
||||
|
||||
IvfflatBench("GetScanItems", GetScanItems(scan, so->value));
|
||||
}
|
||||
|
||||
heaptid = (ItemPointer) DatumGetPointer(slot_getattr(so->mslot, 2, &isnull));
|
||||
for (;;)
|
||||
{
|
||||
heaptid = (ItemPointer) DatumGetPointer(slot_getattr(so->mslot, 2, &isnull));
|
||||
|
||||
batch->items[nitems].tableTid = *heaptid;
|
||||
batch->items[nitems].indexOffset = -1;
|
||||
batch->items[nitems].tupleOffset = 0;
|
||||
nitems++;
|
||||
|
||||
if (nitems == scan->maxitemsbatch)
|
||||
break;
|
||||
|
||||
if (!tuplesort_gettupleslot(so->sortstate, true, false, so->mslot, NULL))
|
||||
break;
|
||||
}
|
||||
|
||||
scan->xs_heaptid = *heaptid;
|
||||
scan->xs_recheck = false;
|
||||
scan->xs_recheckorderby = false;
|
||||
return true;
|
||||
|
||||
batch->firstItem = 0;
|
||||
batch->lastItem = nitems - 1;
|
||||
batch->dir = ForwardScanDirection;
|
||||
return batch;
|
||||
}
|
||||
|
||||
/*
|
||||
|
||||
Reference in New Issue
Block a user