mirror of
https://github.com/pgvector/pgvector.git
synced 2026-07-23 20:40:55 +08:00
Compare commits
3 Commits
tuple-vers
...
time-budge
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
dad5dffe8e | ||
|
|
06b641407f | ||
|
|
6d2af6d3f9 |
@@ -18,6 +18,7 @@
|
|||||||
#endif
|
#endif
|
||||||
|
|
||||||
int hnsw_ef_search;
|
int hnsw_ef_search;
|
||||||
|
int hnsw_time_budget;
|
||||||
int hnsw_lock_tranche_id;
|
int hnsw_lock_tranche_id;
|
||||||
static relopt_kind hnsw_relopt_kind;
|
static relopt_kind hnsw_relopt_kind;
|
||||||
|
|
||||||
@@ -68,6 +69,10 @@ HnswInit(void)
|
|||||||
"Valid range is 1..1000.", &hnsw_ef_search,
|
"Valid range is 1..1000.", &hnsw_ef_search,
|
||||||
HNSW_DEFAULT_EF_SEARCH, HNSW_MIN_EF_SEARCH, HNSW_MAX_EF_SEARCH, PGC_USERSET, 0, NULL, NULL, NULL);
|
HNSW_DEFAULT_EF_SEARCH, HNSW_MIN_EF_SEARCH, HNSW_MAX_EF_SEARCH, PGC_USERSET, 0, NULL, NULL, NULL);
|
||||||
|
|
||||||
|
DefineCustomIntVariable("hnsw.time_budget", "Sets the time budget for search",
|
||||||
|
NULL, &hnsw_time_budget,
|
||||||
|
-1, -1, INT_MAX, PGC_USERSET, GUC_UNIT_MS, NULL, NULL, NULL);
|
||||||
|
|
||||||
MarkGUCPrefixReserved("hnsw");
|
MarkGUCPrefixReserved("hnsw");
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|||||||
11
src/hnsw.h
11
src/hnsw.h
@@ -106,6 +106,7 @@
|
|||||||
|
|
||||||
/* Variables */
|
/* Variables */
|
||||||
extern int hnsw_ef_search;
|
extern int hnsw_ef_search;
|
||||||
|
extern int hnsw_time_budget;
|
||||||
extern int hnsw_lock_tranche_id;
|
extern int hnsw_lock_tranche_id;
|
||||||
|
|
||||||
typedef struct HnswElementData HnswElementData;
|
typedef struct HnswElementData HnswElementData;
|
||||||
@@ -129,7 +130,6 @@ struct HnswElementData
|
|||||||
uint8 heaptidsLength;
|
uint8 heaptidsLength;
|
||||||
uint8 level;
|
uint8 level;
|
||||||
uint8 deleted;
|
uint8 deleted;
|
||||||
uint8 version;
|
|
||||||
uint32 hash;
|
uint32 hash;
|
||||||
HnswNeighborsPtr neighbors;
|
HnswNeighborsPtr neighbors;
|
||||||
BlockNumber blkno;
|
BlockNumber blkno;
|
||||||
@@ -306,10 +306,10 @@ typedef struct HnswElementTupleData
|
|||||||
uint8 type;
|
uint8 type;
|
||||||
uint8 level;
|
uint8 level;
|
||||||
uint8 deleted;
|
uint8 deleted;
|
||||||
uint8 version;
|
uint8 unused;
|
||||||
ItemPointerData heaptids[HNSW_HEAPTIDS];
|
ItemPointerData heaptids[HNSW_HEAPTIDS];
|
||||||
ItemPointerData neighbortid;
|
ItemPointerData neighbortid;
|
||||||
uint16 unused;
|
uint16 unused2;
|
||||||
Vector data;
|
Vector data;
|
||||||
} HnswElementTupleData;
|
} HnswElementTupleData;
|
||||||
|
|
||||||
@@ -318,7 +318,7 @@ typedef HnswElementTupleData * HnswElementTuple;
|
|||||||
typedef struct HnswNeighborTupleData
|
typedef struct HnswNeighborTupleData
|
||||||
{
|
{
|
||||||
uint8 type;
|
uint8 type;
|
||||||
uint8 version;
|
uint8 unused;
|
||||||
uint16 count;
|
uint16 count;
|
||||||
ItemPointerData indextids[FLEXIBLE_ARRAY_MEMBER];
|
ItemPointerData indextids[FLEXIBLE_ARRAY_MEMBER];
|
||||||
} HnswNeighborTupleData;
|
} HnswNeighborTupleData;
|
||||||
@@ -331,6 +331,7 @@ typedef struct HnswScanOpaqueData
|
|||||||
bool first;
|
bool first;
|
||||||
List *w;
|
List *w;
|
||||||
MemoryContext tmpCtx;
|
MemoryContext tmpCtx;
|
||||||
|
instr_time start;
|
||||||
|
|
||||||
/* Support functions */
|
/* Support functions */
|
||||||
FmgrInfo *procinfo;
|
FmgrInfo *procinfo;
|
||||||
@@ -375,7 +376,7 @@ bool HnswCheckNorm(FmgrInfo *procinfo, Oid collation, Datum value);
|
|||||||
Buffer HnswNewBuffer(Relation index, ForkNumber forkNum);
|
Buffer HnswNewBuffer(Relation index, ForkNumber forkNum);
|
||||||
void HnswInitPage(Buffer buf, Page page);
|
void HnswInitPage(Buffer buf, Page page);
|
||||||
void HnswInit(void);
|
void HnswInit(void);
|
||||||
List *HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool inserting, HnswElement skipElement);
|
List *HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool inserting, HnswElement skipElement, instr_time *start);
|
||||||
HnswElement HnswGetEntryPoint(Relation index);
|
HnswElement HnswGetEntryPoint(Relation index);
|
||||||
void HnswGetMetaPageInfo(Relation index, int *m, HnswElement * entryPoint);
|
void HnswGetMetaPageInfo(Relation index, int *m, HnswElement * entryPoint);
|
||||||
void *HnswAlloc(HnswAllocator * allocator, Size size);
|
void *HnswAlloc(HnswAllocator * allocator, Size size);
|
||||||
|
|||||||
@@ -36,7 +36,7 @@ GetInsertPage(Relation index)
|
|||||||
* Check for a free offset
|
* Check for a free offset
|
||||||
*/
|
*/
|
||||||
static bool
|
static bool
|
||||||
HnswFreeOffset(Relation index, Buffer buf, Page page, HnswElement element, Size etupSize, Size ntupSize, Buffer *nbuf, Page *npage, OffsetNumber *freeOffno, OffsetNumber *freeNeighborOffno, BlockNumber *newInsertPage, uint8 *tupleVersion)
|
HnswFreeOffset(Relation index, Buffer buf, Page page, HnswElement element, Size etupSize, Size ntupSize, Buffer *nbuf, Page *npage, OffsetNumber *freeOffno, OffsetNumber *freeNeighborOffno, BlockNumber *newInsertPage)
|
||||||
{
|
{
|
||||||
OffsetNumber offno;
|
OffsetNumber offno;
|
||||||
OffsetNumber maxoffno = PageGetMaxOffsetNumber(page);
|
OffsetNumber maxoffno = PageGetMaxOffsetNumber(page);
|
||||||
@@ -98,7 +98,6 @@ HnswFreeOffset(Relation index, Buffer buf, Page page, HnswElement element, Size
|
|||||||
{
|
{
|
||||||
*freeOffno = offno;
|
*freeOffno = offno;
|
||||||
*freeNeighborOffno = neighborOffno;
|
*freeNeighborOffno = neighborOffno;
|
||||||
*tupleVersion = etup->version;
|
|
||||||
return true;
|
return true;
|
||||||
}
|
}
|
||||||
else if (*nbuf != buf)
|
else if (*nbuf != buf)
|
||||||
@@ -154,7 +153,6 @@ AddElementOnDisk(Relation index, HnswElement e, int m, BlockNumber insertPage, B
|
|||||||
OffsetNumber freeOffno = InvalidOffsetNumber;
|
OffsetNumber freeOffno = InvalidOffsetNumber;
|
||||||
OffsetNumber freeNeighborOffno = InvalidOffsetNumber;
|
OffsetNumber freeNeighborOffno = InvalidOffsetNumber;
|
||||||
BlockNumber newInsertPage = InvalidBlockNumber;
|
BlockNumber newInsertPage = InvalidBlockNumber;
|
||||||
uint8 tupleVersion;
|
|
||||||
char *base = NULL;
|
char *base = NULL;
|
||||||
|
|
||||||
/* Calculate sizes */
|
/* Calculate sizes */
|
||||||
@@ -204,7 +202,7 @@ AddElementOnDisk(Relation index, HnswElement e, int m, BlockNumber insertPage, B
|
|||||||
}
|
}
|
||||||
|
|
||||||
/* Next, try space from a deleted element */
|
/* Next, try space from a deleted element */
|
||||||
if (HnswFreeOffset(index, buf, page, e, etupSize, ntupSize, &nbuf, &npage, &freeOffno, &freeNeighborOffno, &newInsertPage, &tupleVersion))
|
if (HnswFreeOffset(index, buf, page, e, etupSize, ntupSize, &nbuf, &npage, &freeOffno, &freeNeighborOffno, &newInsertPage))
|
||||||
{
|
{
|
||||||
if (nbuf != buf)
|
if (nbuf != buf)
|
||||||
{
|
{
|
||||||
@@ -214,10 +212,6 @@ AddElementOnDisk(Relation index, HnswElement e, int m, BlockNumber insertPage, B
|
|||||||
npage = GenericXLogRegisterBuffer(state, nbuf, 0);
|
npage = GenericXLogRegisterBuffer(state, nbuf, 0);
|
||||||
}
|
}
|
||||||
|
|
||||||
/* Set tuple version */
|
|
||||||
etup->version = tupleVersion;
|
|
||||||
ntup->version = tupleVersion;
|
|
||||||
|
|
||||||
break;
|
break;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|||||||
@@ -3,6 +3,7 @@
|
|||||||
#include "access/relscan.h"
|
#include "access/relscan.h"
|
||||||
#include "hnsw.h"
|
#include "hnsw.h"
|
||||||
#include "pgstat.h"
|
#include "pgstat.h"
|
||||||
|
#include "portability/instr_time.h"
|
||||||
#include "storage/bufmgr.h"
|
#include "storage/bufmgr.h"
|
||||||
#include "storage/lmgr.h"
|
#include "storage/lmgr.h"
|
||||||
#include "utils/memutils.h"
|
#include "utils/memutils.h"
|
||||||
@@ -22,6 +23,7 @@ GetScanItems(IndexScanDesc scan, Datum q)
|
|||||||
int m;
|
int m;
|
||||||
HnswElement entryPoint;
|
HnswElement entryPoint;
|
||||||
char *base = NULL;
|
char *base = NULL;
|
||||||
|
instr_time *start = hnsw_time_budget == -1 ? NULL : &so->start;
|
||||||
|
|
||||||
/* Get m and entry point */
|
/* Get m and entry point */
|
||||||
HnswGetMetaPageInfo(index, &m, &entryPoint);
|
HnswGetMetaPageInfo(index, &m, &entryPoint);
|
||||||
@@ -33,11 +35,11 @@ GetScanItems(IndexScanDesc scan, Datum q)
|
|||||||
|
|
||||||
for (int lc = entryPoint->level; lc >= 1; lc--)
|
for (int lc = entryPoint->level; lc >= 1; lc--)
|
||||||
{
|
{
|
||||||
w = HnswSearchLayer(base, q, ep, 1, lc, index, procinfo, collation, m, false, NULL);
|
w = HnswSearchLayer(base, q, ep, 1, lc, index, procinfo, collation, m, false, NULL, start);
|
||||||
ep = w;
|
ep = w;
|
||||||
}
|
}
|
||||||
|
|
||||||
return HnswSearchLayer(base, q, ep, hnsw_ef_search, 0, index, procinfo, collation, m, false, NULL);
|
return HnswSearchLayer(base, q, ep, hnsw_ef_search, 0, index, procinfo, collation, m, false, NULL, start);
|
||||||
}
|
}
|
||||||
|
|
||||||
/*
|
/*
|
||||||
@@ -90,6 +92,9 @@ hnswbeginscan(Relation index, int nkeys, int norderbys)
|
|||||||
so->normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
|
so->normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
|
||||||
so->collation = index->rd_indcollation[0];
|
so->collation = index->rd_indcollation[0];
|
||||||
|
|
||||||
|
if (hnsw_time_budget != -1)
|
||||||
|
INSTR_TIME_SET_CURRENT(so->start);
|
||||||
|
|
||||||
scan->opaque = so;
|
scan->opaque = so;
|
||||||
|
|
||||||
return scan;
|
return scan;
|
||||||
|
|||||||
@@ -9,6 +9,7 @@
|
|||||||
#include "fmgr.h"
|
#include "fmgr.h"
|
||||||
#include "hnsw.h"
|
#include "hnsw.h"
|
||||||
#include "lib/pairingheap.h"
|
#include "lib/pairingheap.h"
|
||||||
|
#include "portability/instr_time.h"
|
||||||
#include "sparsevec.h"
|
#include "sparsevec.h"
|
||||||
#include "storage/bufmgr.h"
|
#include "storage/bufmgr.h"
|
||||||
#include "utils/datum.h"
|
#include "utils/datum.h"
|
||||||
@@ -253,8 +254,6 @@ HnswInitElement(char *base, ItemPointer heaptid, int m, double ml, int maxLevel,
|
|||||||
|
|
||||||
element->level = level;
|
element->level = level;
|
||||||
element->deleted = 0;
|
element->deleted = 0;
|
||||||
/* Start at one to make it easier to find issues */
|
|
||||||
element->version = 1;
|
|
||||||
|
|
||||||
HnswInitNeighbors(base, element, m, allocator);
|
HnswInitNeighbors(base, element, m, allocator);
|
||||||
|
|
||||||
@@ -407,7 +406,6 @@ HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element)
|
|||||||
etup->type = HNSW_ELEMENT_TUPLE_TYPE;
|
etup->type = HNSW_ELEMENT_TUPLE_TYPE;
|
||||||
etup->level = element->level;
|
etup->level = element->level;
|
||||||
etup->deleted = 0;
|
etup->deleted = 0;
|
||||||
etup->version = element->version;
|
|
||||||
for (int i = 0; i < HNSW_HEAPTIDS; i++)
|
for (int i = 0; i < HNSW_HEAPTIDS; i++)
|
||||||
{
|
{
|
||||||
if (i < element->heaptidsLength)
|
if (i < element->heaptidsLength)
|
||||||
@@ -450,7 +448,6 @@ HnswSetNeighborTuple(char *base, HnswNeighborTuple ntup, HnswElement e, int m)
|
|||||||
}
|
}
|
||||||
|
|
||||||
ntup->count = idx;
|
ntup->count = idx;
|
||||||
ntup->version = e->version;
|
|
||||||
}
|
}
|
||||||
|
|
||||||
/*
|
/*
|
||||||
@@ -524,7 +521,6 @@ HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHe
|
|||||||
{
|
{
|
||||||
element->level = etup->level;
|
element->level = etup->level;
|
||||||
element->deleted = etup->deleted;
|
element->deleted = etup->deleted;
|
||||||
element->version = etup->version;
|
|
||||||
element->neighborPage = ItemPointerGetBlockNumber(&etup->neighbortid);
|
element->neighborPage = ItemPointerGetBlockNumber(&etup->neighbortid);
|
||||||
element->neighborOffno = ItemPointerGetOffsetNumber(&etup->neighbortid);
|
element->neighborOffno = ItemPointerGetOffsetNumber(&etup->neighbortid);
|
||||||
element->heaptidsLength = 0;
|
element->heaptidsLength = 0;
|
||||||
@@ -771,30 +767,20 @@ HnswLoadUnvisitedFromDisk(HnswElement element, HnswUnvisited * unvisited, int *u
|
|||||||
int start;
|
int start;
|
||||||
ItemPointerData indextids[HNSW_MAX_M * 2];
|
ItemPointerData indextids[HNSW_MAX_M * 2];
|
||||||
|
|
||||||
*unvisitedLength = 0;
|
|
||||||
|
|
||||||
buf = ReadBuffer(index, element->neighborPage);
|
buf = ReadBuffer(index, element->neighborPage);
|
||||||
LockBuffer(buf, BUFFER_LOCK_SHARE);
|
LockBuffer(buf, BUFFER_LOCK_SHARE);
|
||||||
page = BufferGetPage(buf);
|
page = BufferGetPage(buf);
|
||||||
|
|
||||||
ntup = (HnswNeighborTuple) PageGetItem(page, PageGetItemId(page, element->neighborOffno));
|
ntup = (HnswNeighborTuple) PageGetItem(page, PageGetItemId(page, element->neighborOffno));
|
||||||
|
start = (element->level - lc) * m;
|
||||||
/*
|
|
||||||
* Ensure the neighbor tuple has not been deleted or replaced between
|
|
||||||
* index scan iterations
|
|
||||||
*/
|
|
||||||
if (ntup->version != element->version)
|
|
||||||
{
|
|
||||||
UnlockReleaseBuffer(buf);
|
|
||||||
return;
|
|
||||||
}
|
|
||||||
|
|
||||||
/* Copy to minimize lock time */
|
/* Copy to minimize lock time */
|
||||||
start = (element->level - lc) * m;
|
|
||||||
memcpy(&indextids, ntup->indextids + start, lm * sizeof(ItemPointerData));
|
memcpy(&indextids, ntup->indextids + start, lm * sizeof(ItemPointerData));
|
||||||
|
|
||||||
UnlockReleaseBuffer(buf);
|
UnlockReleaseBuffer(buf);
|
||||||
|
|
||||||
|
*unvisitedLength = 0;
|
||||||
|
|
||||||
for (int i = 0; i < lm; i++)
|
for (int i = 0; i < lm; i++)
|
||||||
{
|
{
|
||||||
ItemPointer indextid = &indextids[i];
|
ItemPointer indextid = &indextids[i];
|
||||||
@@ -814,7 +800,7 @@ HnswLoadUnvisitedFromDisk(HnswElement element, HnswUnvisited * unvisited, int *u
|
|||||||
* Algorithm 2 from paper
|
* Algorithm 2 from paper
|
||||||
*/
|
*/
|
||||||
List *
|
List *
|
||||||
HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool inserting, HnswElement skipElement)
|
HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool inserting, HnswElement skipElement, instr_time *start)
|
||||||
{
|
{
|
||||||
List *w = NIL;
|
List *w = NIL;
|
||||||
pairingheap *C = pairingheap_allocate(CompareNearestCandidates, NULL);
|
pairingheap *C = pairingheap_allocate(CompareNearestCandidates, NULL);
|
||||||
@@ -865,6 +851,17 @@ HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, F
|
|||||||
HnswCandidate *f = HnswGetPairingHeapCandidate(w_node, pairingheap_first(W));
|
HnswCandidate *f = HnswGetPairingHeapCandidate(w_node, pairingheap_first(W));
|
||||||
HnswElement cElement;
|
HnswElement cElement;
|
||||||
|
|
||||||
|
/* Check time budget */
|
||||||
|
if (start != NULL)
|
||||||
|
{
|
||||||
|
instr_time duration;
|
||||||
|
|
||||||
|
INSTR_TIME_SET_CURRENT(duration);
|
||||||
|
INSTR_TIME_SUBTRACT(duration, *start);
|
||||||
|
if (INSTR_TIME_GET_MILLISEC(duration) >= hnsw_time_budget)
|
||||||
|
break;
|
||||||
|
}
|
||||||
|
|
||||||
if (c->distance > f->distance)
|
if (c->distance > f->distance)
|
||||||
break;
|
break;
|
||||||
|
|
||||||
@@ -889,9 +886,6 @@ HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, F
|
|||||||
{
|
{
|
||||||
eElement = unvisited[i].element;
|
eElement = unvisited[i].element;
|
||||||
eDistance = GetElementDistance(base, eElement, q, procinfo, collation);
|
eDistance = GetElementDistance(base, eElement, q, procinfo, collation);
|
||||||
|
|
||||||
if (!(eDistance < f->distance || alwaysAdd))
|
|
||||||
continue;
|
|
||||||
}
|
}
|
||||||
else
|
else
|
||||||
{
|
{
|
||||||
@@ -907,6 +901,9 @@ HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, F
|
|||||||
continue;
|
continue;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
if (!(eDistance < f->distance || alwaysAdd))
|
||||||
|
continue;
|
||||||
|
|
||||||
Assert(!eElement->deleted);
|
Assert(!eElement->deleted);
|
||||||
|
|
||||||
/* Make robust to issues */
|
/* Make robust to issues */
|
||||||
@@ -1306,7 +1303,7 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
|
|||||||
/* 1st phase: greedy search to insert level */
|
/* 1st phase: greedy search to insert level */
|
||||||
for (int lc = entryLevel; lc >= level + 1; lc--)
|
for (int lc = entryLevel; lc >= level + 1; lc--)
|
||||||
{
|
{
|
||||||
w = HnswSearchLayer(base, q, ep, 1, lc, index, procinfo, collation, m, true, skipElement);
|
w = HnswSearchLayer(base, q, ep, 1, lc, index, procinfo, collation, m, true, skipElement, NULL);
|
||||||
ep = w;
|
ep = w;
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -1324,7 +1321,7 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
|
|||||||
List *neighbors;
|
List *neighbors;
|
||||||
List *lw;
|
List *lw;
|
||||||
|
|
||||||
w = HnswSearchLayer(base, q, ep, efConstruction, lc, index, procinfo, collation, m, true, skipElement);
|
w = HnswSearchLayer(base, q, ep, efConstruction, lc, index, procinfo, collation, m, true, skipElement, NULL);
|
||||||
|
|
||||||
/* Elements being deleted or skipped can help with search */
|
/* Elements being deleted or skipped can help with search */
|
||||||
/* but should be removed before selecting neighbors */
|
/* but should be removed before selecting neighbors */
|
||||||
|
|||||||
@@ -527,11 +527,6 @@ MarkDeleted(HnswVacuumState * vacuumstate)
|
|||||||
for (int i = 0; i < ntup->count; i++)
|
for (int i = 0; i < ntup->count; i++)
|
||||||
ItemPointerSetInvalid(&ntup->indextids[i]);
|
ItemPointerSetInvalid(&ntup->indextids[i]);
|
||||||
|
|
||||||
/* Increment version */
|
|
||||||
/* This is used to avoid incorrect reads for iterative scans */
|
|
||||||
etup->version++;
|
|
||||||
ntup->version = etup->version;
|
|
||||||
|
|
||||||
/*
|
/*
|
||||||
* We modified the tuples in place, no need to call
|
* We modified the tuples in place, no need to call
|
||||||
* PageIndexTupleOverwrite
|
* PageIndexTupleOverwrite
|
||||||
|
|||||||
Reference in New Issue
Block a user