mirror of
https://github.com/pgvector/pgvector.git
synced 2026-07-23 12:30:56 +08:00
Compare commits
10 Commits
v0.8.5
...
amgetbatch
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
89dc41ce2b | ||
|
|
06ab41c094 | ||
|
|
8a8bc90d6d | ||
|
|
91717c81b3 | ||
|
|
98a7f94608 | ||
|
|
7db3d67b2d | ||
|
|
1dd39f66de | ||
|
|
cd431c51ca | ||
|
|
73890f2f70 | ||
|
|
18980387ec |
15
src/hnsw.c
15
src/hnsw.c
@@ -258,6 +258,11 @@ hnswvalidate(Oid opclassoid)
|
|||||||
return true;
|
return true;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
static void
|
||||||
|
hnswunguardbatch(IndexScanDesc scan, IndexScanBatch batch)
|
||||||
|
{
|
||||||
|
}
|
||||||
|
|
||||||
/*
|
/*
|
||||||
* Define index handler
|
* Define index handler
|
||||||
*
|
*
|
||||||
@@ -279,6 +284,7 @@ hnswhandler(PG_FUNCTION_ARGS)
|
|||||||
.amconsistentequality = false,
|
.amconsistentequality = false,
|
||||||
.amconsistentordering = false,
|
.amconsistentordering = false,
|
||||||
.amcanbackward = false,
|
.amcanbackward = false,
|
||||||
|
.amcanmarkpos = false,
|
||||||
.amcanunique = false,
|
.amcanunique = false,
|
||||||
.amcanmulticol = false,
|
.amcanmulticol = false,
|
||||||
.amoptionalkey = true,
|
.amoptionalkey = true,
|
||||||
@@ -311,11 +317,14 @@ hnswhandler(PG_FUNCTION_ARGS)
|
|||||||
.amadjustmembers = NULL,
|
.amadjustmembers = NULL,
|
||||||
.ambeginscan = hnswbeginscan,
|
.ambeginscan = hnswbeginscan,
|
||||||
.amrescan = hnswrescan,
|
.amrescan = hnswrescan,
|
||||||
.amgettuple = hnswgettuple,
|
.amgettuple = NULL,
|
||||||
|
.amgetbatch = hnswgetbatch,
|
||||||
|
.amunguardbatch = hnswunguardbatch,
|
||||||
|
.amkillitemsbatch = NULL,
|
||||||
|
.amgettransform = NULL,
|
||||||
.amgetbitmap = NULL,
|
.amgetbitmap = NULL,
|
||||||
.amendscan = hnswendscan,
|
.amendscan = hnswendscan,
|
||||||
.ammarkpos = NULL,
|
.amposreset = NULL,
|
||||||
.amrestrpos = NULL,
|
|
||||||
.amestimateparallelscan = NULL,
|
.amestimateparallelscan = NULL,
|
||||||
.aminitparallelscan = NULL,
|
.aminitparallelscan = NULL,
|
||||||
.amparallelrescan = NULL,
|
.amparallelrescan = NULL,
|
||||||
|
|||||||
@@ -465,7 +465,7 @@ IndexBulkDeleteResult *hnswbulkdelete(IndexVacuumInfo *info, IndexBulkDeleteResu
|
|||||||
IndexBulkDeleteResult *hnswvacuumcleanup(IndexVacuumInfo *info, IndexBulkDeleteResult *stats);
|
IndexBulkDeleteResult *hnswvacuumcleanup(IndexVacuumInfo *info, IndexBulkDeleteResult *stats);
|
||||||
IndexScanDesc hnswbeginscan(Relation index, int nkeys, int norderbys);
|
IndexScanDesc hnswbeginscan(Relation index, int nkeys, int norderbys);
|
||||||
void hnswrescan(IndexScanDesc scan, ScanKey keys, int nkeys, ScanKey orderbys, 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);
|
void hnswendscan(IndexScanDesc scan);
|
||||||
|
|
||||||
static inline HnswNeighborArray *
|
static inline HnswNeighborArray *
|
||||||
|
|||||||
@@ -3,6 +3,7 @@
|
|||||||
#include <limits.h>
|
#include <limits.h>
|
||||||
|
|
||||||
#include "access/genam.h"
|
#include "access/genam.h"
|
||||||
|
#include "access/indexbatch.h"
|
||||||
#include "access/relscan.h"
|
#include "access/relscan.h"
|
||||||
#include "hnsw.h"
|
#include "hnsw.h"
|
||||||
#include "lib/pairingheap.h"
|
#include "lib/pairingheap.h"
|
||||||
@@ -135,6 +136,11 @@ hnswbeginscan(Relation index, int nkeys, int norderbys)
|
|||||||
double maxMemory;
|
double maxMemory;
|
||||||
|
|
||||||
scan = RelationGetIndexScan(index, nkeys, norderbys);
|
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 = (HnswScanOpaque) palloc(sizeof(HnswScanOpaqueData));
|
||||||
so->typeInfo = HnswGetTypeInfo(index);
|
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
|
IndexScanBatch
|
||||||
hnswgettuple(IndexScanDesc scan, ScanDirection dir)
|
hnswgetbatch(IndexScanDesc scan, IndexScanBatch priorbatch, ScanDirection dir)
|
||||||
{
|
{
|
||||||
HnswScanOpaque so = (HnswScanOpaque) scan->opaque;
|
HnswScanOpaque so = (HnswScanOpaque) scan->opaque;
|
||||||
|
IndexScanBatch batch = indexam_util_alloc_batch(scan);
|
||||||
MemoryContext oldCtx = MemoryContextSwitchTo(so->tmpCtx);
|
MemoryContext oldCtx = MemoryContextSwitchTo(so->tmpCtx);
|
||||||
|
|
||||||
/*
|
/*
|
||||||
@@ -245,6 +252,7 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
|
|||||||
HnswSearchCandidate *sc;
|
HnswSearchCandidate *sc;
|
||||||
HnswElement element;
|
HnswElement element;
|
||||||
ItemPointer heaptid;
|
ItemPointer heaptid;
|
||||||
|
int nitems = 0;
|
||||||
|
|
||||||
if (list_length(so->w) == 0)
|
if (list_length(so->w) == 0)
|
||||||
{
|
{
|
||||||
@@ -290,44 +298,64 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
|
|||||||
break;
|
break;
|
||||||
}
|
}
|
||||||
|
|
||||||
sc = llast(so->w);
|
while (list_length(so->w) != 0)
|
||||||
element = HnswPtrAccess(base, sc->element);
|
|
||||||
|
|
||||||
/* Move to next element if no valid heap TIDs */
|
|
||||||
if (element->heaptidsLength == 0)
|
|
||||||
{
|
{
|
||||||
so->w = list_delete_last(so->w);
|
sc = llast(so->w);
|
||||||
|
element = HnswPtrAccess(base, sc->element);
|
||||||
|
|
||||||
/* Mark memory as free for next iteration */
|
/* Move to next element if no valid heap TIDs */
|
||||||
if (hnsw_iterative_scan != HNSW_ITERATIVE_SCAN_OFF)
|
if (element->heaptidsLength == 0)
|
||||||
{
|
{
|
||||||
pfree(element);
|
so->w = list_delete_last(so->w);
|
||||||
pfree(sc);
|
|
||||||
|
/* 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;
|
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);
|
MemoryContextSwitchTo(oldCtx);
|
||||||
|
|
||||||
scan->xs_heaptid = *heaptid;
|
|
||||||
scan->xs_recheck = false;
|
scan->xs_recheck = false;
|
||||||
scan->xs_recheckorderby = false;
|
scan->xs_recheckorderby = false;
|
||||||
return true;
|
|
||||||
|
batch->firstItem = 0;
|
||||||
|
batch->lastItem = nitems - 1;
|
||||||
|
batch->dir = ForwardScanDirection;
|
||||||
|
return batch;
|
||||||
}
|
}
|
||||||
|
|
||||||
MemoryContextSwitchTo(oldCtx);
|
MemoryContextSwitchTo(oldCtx);
|
||||||
return false;
|
indexam_util_release_batch(scan, batch);
|
||||||
|
return NULL;
|
||||||
}
|
}
|
||||||
|
|
||||||
/*
|
/*
|
||||||
|
|||||||
@@ -175,6 +175,11 @@ ivfflatvalidate(Oid opclassoid)
|
|||||||
return true;
|
return true;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
static void
|
||||||
|
ivfflatunguardbatch(IndexScanDesc scan, IndexScanBatch batch)
|
||||||
|
{
|
||||||
|
}
|
||||||
|
|
||||||
/*
|
/*
|
||||||
* Define index handler
|
* Define index handler
|
||||||
*
|
*
|
||||||
@@ -196,6 +201,7 @@ ivfflathandler(PG_FUNCTION_ARGS)
|
|||||||
.amconsistentequality = false,
|
.amconsistentequality = false,
|
||||||
.amconsistentordering = false,
|
.amconsistentordering = false,
|
||||||
.amcanbackward = false,
|
.amcanbackward = false,
|
||||||
|
.amcanmarkpos = false,
|
||||||
.amcanunique = false,
|
.amcanunique = false,
|
||||||
.amcanmulticol = false,
|
.amcanmulticol = false,
|
||||||
.amoptionalkey = true,
|
.amoptionalkey = true,
|
||||||
@@ -228,11 +234,14 @@ ivfflathandler(PG_FUNCTION_ARGS)
|
|||||||
.amadjustmembers = NULL,
|
.amadjustmembers = NULL,
|
||||||
.ambeginscan = ivfflatbeginscan,
|
.ambeginscan = ivfflatbeginscan,
|
||||||
.amrescan = ivfflatrescan,
|
.amrescan = ivfflatrescan,
|
||||||
.amgettuple = ivfflatgettuple,
|
.amgettuple = NULL,
|
||||||
|
.amgetbatch = ivfflatgetbatch,
|
||||||
|
.amunguardbatch = ivfflatunguardbatch,
|
||||||
|
.amkillitemsbatch = NULL,
|
||||||
|
.amgettransform = NULL,
|
||||||
.amgetbitmap = NULL,
|
.amgetbitmap = NULL,
|
||||||
.amendscan = ivfflatendscan,
|
.amendscan = ivfflatendscan,
|
||||||
.ammarkpos = NULL,
|
.amposreset = NULL,
|
||||||
.amrestrpos = NULL,
|
|
||||||
.amestimateparallelscan = NULL,
|
.amestimateparallelscan = NULL,
|
||||||
.aminitparallelscan = NULL,
|
.aminitparallelscan = NULL,
|
||||||
.amparallelrescan = NULL,
|
.amparallelrescan = NULL,
|
||||||
|
|||||||
@@ -344,7 +344,7 @@ IndexBulkDeleteResult *ivfflatbulkdelete(IndexVacuumInfo *info, IndexBulkDeleteR
|
|||||||
IndexBulkDeleteResult *ivfflatvacuumcleanup(IndexVacuumInfo *info, IndexBulkDeleteResult *stats);
|
IndexBulkDeleteResult *ivfflatvacuumcleanup(IndexVacuumInfo *info, IndexBulkDeleteResult *stats);
|
||||||
IndexScanDesc ivfflatbeginscan(Relation index, int nkeys, int norderbys);
|
IndexScanDesc ivfflatbeginscan(Relation index, int nkeys, int norderbys);
|
||||||
void ivfflatrescan(IndexScanDesc scan, ScanKey keys, int nkeys, ScanKey orderbys, 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);
|
void ivfflatendscan(IndexScanDesc scan);
|
||||||
|
|
||||||
#endif
|
#endif
|
||||||
|
|||||||
@@ -3,6 +3,7 @@
|
|||||||
#include <float.h>
|
#include <float.h>
|
||||||
|
|
||||||
#include "access/genam.h"
|
#include "access/genam.h"
|
||||||
|
#include "access/indexbatch.h"
|
||||||
#include "access/itup.h"
|
#include "access/itup.h"
|
||||||
#include "access/relscan.h"
|
#include "access/relscan.h"
|
||||||
#include "access/tupdesc.h"
|
#include "access/tupdesc.h"
|
||||||
@@ -261,6 +262,11 @@ ivfflatbeginscan(Relation index, int nkeys, int norderbys)
|
|||||||
MemoryContext oldCtx;
|
MemoryContext oldCtx;
|
||||||
|
|
||||||
scan = RelationGetIndexScan(index, nkeys, norderbys);
|
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 */
|
/* Get lists and dimensions from metapage */
|
||||||
IvfflatGetMetaPageInfo(index, &lists, &dimensions);
|
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
|
IndexScanBatch
|
||||||
ivfflatgettuple(IndexScanDesc scan, ScanDirection dir)
|
ivfflatgetbatch(IndexScanDesc scan, IndexScanBatch priorbatch, ScanDirection dir)
|
||||||
{
|
{
|
||||||
IvfflatScanOpaque so = (IvfflatScanOpaque) scan->opaque;
|
IvfflatScanOpaque so = (IvfflatScanOpaque) scan->opaque;
|
||||||
|
IndexScanBatch batch = indexam_util_alloc_batch(scan);
|
||||||
ItemPointer heaptid;
|
ItemPointer heaptid;
|
||||||
bool isnull;
|
bool isnull;
|
||||||
|
int nitems = 0;
|
||||||
|
|
||||||
/*
|
/*
|
||||||
* Index can be used to scan backward, but Postgres doesn't support
|
* 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))
|
while (!tuplesort_gettupleslot(so->sortstate, true, false, so->mslot, NULL))
|
||||||
{
|
{
|
||||||
if (so->listIndex == so->maxProbes)
|
if (so->listIndex == so->maxProbes)
|
||||||
return false;
|
{
|
||||||
|
indexam_util_release_batch(scan, batch);
|
||||||
|
return NULL;
|
||||||
|
}
|
||||||
|
|
||||||
IvfflatBench("GetScanItems", GetScanItems(scan, so->value));
|
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_recheck = false;
|
||||||
scan->xs_recheckorderby = 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