liuyu/pgvector
1
0
Fork 0
mirror of https://github.com/pgvector/pgvector.git synced 2026-07-03 11:10:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into hqann2

Browse Source
This commit is contained in:
Andrew Kane
2024-10-09 23:26:57 -07:00
parent d650d23da8 32ab27d72a
commit 46209740ce
6 changed files with 104 additions and 110 deletions
Download Patch File Download Diff File Expand all files Collapse all files

38
src/hnsw.h
View File

@@ -243,6 +243,13 @@ typedef struct HnswTypeInfo
void (*checkValue) (Pointer v);
} HnswTypeInfo;
typedef struct HnswSupport
{
FmgrInfo *procinfo[2];
FmgrInfo *normprocinfo;
Oid *collation;
} HnswSupport;
typedef struct HnswBuildState
{
/* Info */
@@ -262,9 +269,7 @@ typedef struct HnswBuildState
double reltuples;
/* Support functions */
FmgrInfo *procinfo[2];
FmgrInfo *normprocinfo;
Oid *collation;
HnswSupport support;
/* Variables */
HnswGraph graphData;
@@ -341,9 +346,7 @@ typedef struct HnswScanOpaqueData
MemoryContext tmpCtx;
/* Support functions */
FmgrInfo *procinfo[2];
FmgrInfo *normprocinfo;
Oid *collation;
HnswSupport support;
} HnswScanOpaqueData;
typedef HnswScanOpaqueData * HnswScanOpaque;
@@ -361,8 +364,7 @@ typedef struct HnswVacuumState
int efConstruction;
/* Support functions */
FmgrInfo *procinfo[2];
Oid *collation;
HnswSupport support;
/* Variables */
struct tidhash_hash *deleted;
@@ -378,32 +380,32 @@ typedef struct HnswVacuumState
int HnswGetM(Relation index);
int HnswGetEfConstruction(Relation index);
FmgrInfo *HnswOptionalProcInfo(Relation index, uint16 procnum);
void HnswSetProcinfo(Relation index, FmgrInfo **procinfo, FmgrInfo **normprocinfo, Oid **collation);
void HnswInitSupport(HnswSupport * support, Relation index);
Datum HnswNormValue(const HnswTypeInfo * typeInfo, Oid collation, Datum value);
bool HnswCheckNorm(FmgrInfo *procinfo, Oid collation, Datum value);
bool HnswCheckNorm(HnswSupport * support, Datum value);
Buffer HnswNewBuffer(Relation index, ForkNumber forkNum);
void HnswInitPage(Buffer buf, Page page);
void HnswInit(void);
List *HnswSearchLayer(char *base, Datum q, IndexTuple qtup, ScanKeyData *keyData, List *ep, int ef, int lc, Relation index, FmgrInfo **procinfo, Oid *collation, int m, bool inserting, HnswElement skipElement, bool inMemory);
List *HnswSearchLayer(char *base, Datum q, IndexTuple qtup, ScanKeyData *keyData, List *ep, int ef, int lc, Relation index, HnswSupport * support, int m, bool inserting, HnswElement skipElement, bool inMemory);
HnswElement HnswGetEntryPoint(Relation index);
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 HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, FmgrInfo **procinfo, Oid *collation, int m, int efConstruction, bool existing, bool inMemory);
HnswSearchCandidate *HnswEntryCandidate(char *base, HnswElement em, Datum q, IndexTuple qtup, ScanKeyData *keyData, Relation rel, FmgrInfo **procinfo, Oid *collation, bool loadVec, bool inMemory);
void HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, HnswSupport * support, int m, int efConstruction, bool existing, bool inMemory);
HnswSearchCandidate *HnswEntryCandidate(char *base, HnswElement em, Datum q, IndexTuple qtup, ScanKeyData *keyData, Relation rel, HnswSupport * support, bool loadVec, bool inMemory);
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);
HnswNeighborArray *HnswInitNeighborArray(int lm, HnswAllocator * allocator);
void HnswInitNeighbors(char *base, HnswElement element, int m, HnswAllocator * alloc);
bool HnswInsertTupleOnDisk(Relation index, FmgrInfo **procinfo, Oid *collation, IndexTuple itup, ItemPointer heaptid, bool building);
void HnswUpdateNeighborsOnDisk(Relation index, FmgrInfo **procinfo, Oid *collation, HnswElement e, int m, bool checkExisting, bool building);
bool HnswInsertTupleOnDisk(Relation index, HnswSupport * support, IndexTuple itup, ItemPointer heaptid, bool building);
void HnswUpdateNeighborsOnDisk(Relation index, HnswSupport * support, HnswElement e, int m, bool checkExisting, bool building);
void HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHeaptids, bool loadVec, Relation index);
void HnswLoadElement(HnswElement element, double *distance, bool *matches, Datum *q, IndexTuple qtup, ScanKeyData *keyData, Relation index, FmgrInfo **procinfo, Oid *collation, bool loadVec, double *maxDistance);
void HnswLoadElement(HnswElement element, double *distance, bool *matches, Datum *q, IndexTuple qtup, ScanKeyData *keyData, Relation index, HnswSupport * support, bool loadVec, double *maxDistance);
void HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element, bool useIndexTuple);
void HnswUpdateConnection(char *base, HnswNeighborArray * neighbors, HnswElement newElement, float distance, int lm, int *updateIdx, Relation index, FmgrInfo **procinfo, Oid *collation);
bool HnswFormIndexTuple(IndexTuple *out, Datum *values, bool *isnull, const HnswTypeInfo * typeInfo, FmgrInfo *normprocinfo, Oid collation, TupleDesc tupdesc);
void HnswUpdateConnection(char *base, HnswNeighborArray * neighbors, HnswElement newElement, float distance, int lm, int *updateIdx, Relation index, HnswSupport * support);
bool HnswFormIndexTuple(IndexTuple *out, Datum *values, bool *isnull, const HnswTypeInfo * typeInfo, HnswSupport * support, TupleDesc tupdesc);
bool HnswLoadNeighborTids(HnswElement element, ItemPointerData *indextids, Relation index, int m, int lm, int lc);
void HnswInitLockTranche(void);
const HnswTypeInfo *HnswGetTypeInfo(Relation index);

26
src/hnswbuild.c
View File

@@ -365,7 +365,7 @@ AddElementInMemory(char *base, HnswGraph * graph, HnswElement element)
* Update neighbors
*/
static void
UpdateNeighborsInMemory(char *base, Relation index, FmgrInfo **procinfo, Oid *collation, HnswElement e, int m)
UpdateNeighborsInMemory(char *base, Relation index, HnswSupport * support, HnswElement e, int m)
{
for (int lc = e->level; lc >= 0; lc--)
{
@@ -387,7 +387,7 @@ UpdateNeighborsInMemory(char *base, Relation index, FmgrInfo **procinfo, Oid *co
Assert(neighborElement);
LWLockAcquire(&neighborElement->lock, LW_EXCLUSIVE);
HnswUpdateConnection(base, HnswGetNeighbors(base, neighborElement, lc), e, hc->distance, lm, NULL, index, procinfo, collation);
HnswUpdateConnection(base, HnswGetNeighbors(base, neighborElement, lc), e, hc->distance, lm, NULL, index, support);
LWLockRelease(&neighborElement->lock);
}
}
@@ -397,7 +397,7 @@ UpdateNeighborsInMemory(char *base, Relation index, FmgrInfo **procinfo, Oid *co
* Update graph in memory
*/
static void
UpdateGraphInMemory(FmgrInfo **procinfo, Oid *collation, HnswElement element, int m, int efConstruction, HnswElement entryPoint, HnswBuildState * buildstate)
UpdateGraphInMemory(HnswSupport * support, HnswElement element, int m, int efConstruction, HnswElement entryPoint, HnswBuildState * buildstate)
{
HnswGraph *graph = buildstate->graph;
char *base = buildstate->hnswarea;
@@ -410,7 +410,7 @@ UpdateGraphInMemory(FmgrInfo **procinfo, Oid *collation, HnswElement element, in
AddElementInMemory(base, graph, element);
/* Update neighbors */
UpdateNeighborsInMemory(base, buildstate->index, procinfo, collation, element, m);
UpdateNeighborsInMemory(base, buildstate->index, support, element, m);
/* Update entry point if needed (already have lock) */
if (entryPoint == NULL || element->level > entryPoint->level)
@@ -424,9 +424,8 @@ static void
InsertTupleInMemory(HnswBuildState * buildstate, HnswElement element)
{
Relation index = buildstate->index;
FmgrInfo **procinfo = buildstate->procinfo;
Oid *collation = buildstate->collation;
HnswGraph *graph = buildstate->graph;
HnswSupport *support = &buildstate->support;
HnswElement entryPoint;
LWLock *entryLock = &graph->entryLock;
LWLock *entryWaitLock = &graph->entryWaitLock;
@@ -458,10 +457,10 @@ InsertTupleInMemory(HnswBuildState * buildstate, HnswElement element)
}
/* Find neighbors for element */
HnswFindElementNeighbors(base, element, entryPoint, index, procinfo, collation, m, efConstruction, false, true);
HnswFindElementNeighbors(base, element, entryPoint, index, support, m, efConstruction, false, true);
/* Update graph in memory */
UpdateGraphInMemory(procinfo, collation, element, m, efConstruction, entryPoint, buildstate);
UpdateGraphInMemory(support, element, m, efConstruction, entryPoint, buildstate);
/* Release entry lock */
LWLockRelease(entryLock);
@@ -476,8 +475,7 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
HnswGraph *graph = buildstate->graph;
HnswElement element;
HnswAllocator *allocator = &buildstate->allocator;
FmgrInfo **procinfo = buildstate->procinfo;
Oid *collation = buildstate->collation;
HnswSupport *support = &buildstate->support;
LWLock *flushLock = &graph->flushLock;
char *base = buildstate->hnswarea;
TupleDesc tupdesc = buildstate->tupdesc;
@@ -487,7 +485,7 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
bool unused;
/* Form index tuple */
if (!HnswFormIndexTuple(&itup, values, isnull, buildstate->typeInfo, buildstate->normprocinfo, collation[0], tupdesc))
if (!HnswFormIndexTuple(&itup, values, isnull, buildstate->typeInfo, support, tupdesc))
return false;
/* Get tuple size */
@@ -501,7 +499,7 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
{
LWLockRelease(flushLock);
return HnswInsertTupleOnDisk(index, procinfo, collation, itup, heaptid, true);
return HnswInsertTupleOnDisk(index, support, itup, heaptid, true);
}
/*
@@ -533,7 +531,7 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
LWLockRelease(flushLock);
return HnswInsertTupleOnDisk(index, procinfo, collation, itup, heaptid, true);
return HnswInsertTupleOnDisk(index, support, itup, heaptid, true);
}
/* Ok, we can proceed to allocate the element */
@@ -710,7 +708,7 @@ InitBuildState(HnswBuildState * buildstate, Relation heap, Relation index, Index
buildstate->indtuples = 0;
/* Get support functions */
HnswSetProcinfo(index, buildstate->procinfo, &buildstate->normprocinfo, &buildstate->collation);
HnswInitSupport(&buildstate->support, index);
InitGraph(&buildstate->graphData, NULL, (Size) maintenance_work_mem * 1024L);
buildstate->graph = &buildstate->graphData;

34
src/hnswinsert.c
View File

@@ -369,7 +369,7 @@ HnswLoadNeighbors(HnswElement element, Relation index, int m, int lm, int lc)
* Load elements for insert
*/
static void
LoadElementsForInsert(HnswNeighborArray * neighbors, Datum q, IndexTuple qtup, int *idx, Relation index, FmgrInfo **procinfo, Oid *collation)
LoadElementsForInsert(HnswNeighborArray * neighbors, Datum q, IndexTuple qtup, int *idx, Relation index, HnswSupport * support)
{
char *base = NULL;
@@ -380,7 +380,7 @@ LoadElementsForInsert(HnswNeighborArray * neighbors, Datum q, IndexTuple qtup, i
double distance;
bool matches;
HnswLoadElement(element, &distance, &matches, &q, qtup, NULL, index, procinfo, collation, true, NULL);
HnswLoadElement(element, &distance, &matches, &q, qtup, NULL, index, support, true, NULL);
hc->distance = distance;
/* Prune element if being deleted */
@@ -396,7 +396,7 @@ LoadElementsForInsert(HnswNeighborArray * neighbors, Datum q, IndexTuple qtup, i
* Get update index
*/
static int
GetUpdateIndex(HnswElement element, HnswElement newElement, float distance, int m, int lm, int lc, Relation index, FmgrInfo **procinfo, Oid *collation, MemoryContext updateCtx)
GetUpdateIndex(HnswElement element, HnswElement newElement, float distance, int m, int lm, int lc, Relation index, HnswSupport * support, MemoryContext updateCtx)
{
char *base = NULL;
int idx = -1;
@@ -424,10 +424,10 @@ GetUpdateIndex(HnswElement element, HnswElement newElement, float distance, int
Datum q = HnswGetValue(base, element);
IndexTuple qtup = HnswPtrAccess(base, element->itup);;
LoadElementsForInsert(neighbors, q, qtup, &idx, index, procinfo, collation);
LoadElementsForInsert(neighbors, q, qtup, &idx, index, support);
if (idx == -1)
HnswUpdateConnection(base, neighbors, newElement, distance, lm, &idx, index, procinfo, collation);
HnswUpdateConnection(base, neighbors, newElement, distance, lm, &idx, index, support);
}
MemoryContextSwitchTo(oldCtx);
@@ -532,7 +532,7 @@ UpdateNeighborOnDisk(HnswElement element, HnswElement newElement, int idx, int m
* Update neighbors
*/
void
HnswUpdateNeighborsOnDisk(Relation index, FmgrInfo **procinfo, Oid *collation, HnswElement e, int m, bool checkExisting, bool building)
HnswUpdateNeighborsOnDisk(Relation index, HnswSupport * support, HnswElement e, int m, bool checkExisting, bool building)
{
char *base = NULL;
@@ -555,7 +555,7 @@ HnswUpdateNeighborsOnDisk(Relation index, FmgrInfo **procinfo, Oid *collation, H
HnswElement neighborElement = HnswPtrAccess(base, hc->element);
int idx;
idx = GetUpdateIndex(neighborElement, e, hc->distance, m, lm, lc, index, procinfo, collation, updateCtx);
idx = GetUpdateIndex(neighborElement, e, hc->distance, m, lm, lc, index, support, updateCtx);
/* New element was not selected as a neighbor */
if (idx == -1)
@@ -665,7 +665,7 @@ FindDuplicateOnDisk(Relation index, HnswElement element, bool building)
* Update graph on disk
*/
static void
UpdateGraphOnDisk(Relation index, FmgrInfo **procinfo, Oid *collation, HnswElement element, int m, int efConstruction, HnswElement entryPoint, bool building)
UpdateGraphOnDisk(Relation index, HnswSupport * support, HnswElement element, int m, int efConstruction, HnswElement entryPoint, bool building)
{
BlockNumber newInsertPage = InvalidBlockNumber;
@@ -681,7 +681,7 @@ UpdateGraphOnDisk(Relation index, FmgrInfo **procinfo, Oid *collation, HnswEleme
HnswUpdateMetaPage(index, 0, NULL, newInsertPage, MAIN_FORKNUM, building);
/* Update neighbors */
HnswUpdateNeighborsOnDisk(index, procinfo, collation, element, m, false, building);
HnswUpdateNeighborsOnDisk(index, support, element, m, false, building);
/* Update entry point if needed */
if (entryPoint == NULL || element->level > entryPoint->level)
@@ -692,7 +692,7 @@ UpdateGraphOnDisk(Relation index, FmgrInfo **procinfo, Oid *collation, HnswEleme
* Insert a tuple into the index
*/
bool
HnswInsertTupleOnDisk(Relation index, FmgrInfo **procinfo, Oid *collation, IndexTuple itup, ItemPointer heaptid, bool building)
HnswInsertTupleOnDisk(Relation index, HnswSupport * support, IndexTuple itup, ItemPointer heaptid, bool building)
{
HnswElement entryPoint;
HnswElement element;
@@ -733,10 +733,10 @@ HnswInsertTupleOnDisk(Relation index, FmgrInfo **procinfo, Oid *collation, Index
}
/* Find neighbors for element */
HnswFindElementNeighbors(base, element, entryPoint, index, procinfo, collation, m, efConstruction, false, false);
HnswFindElementNeighbors(base, element, entryPoint, index, support, m, efConstruction, false, false);
/* Update graph on disk */
UpdateGraphOnDisk(index, procinfo, collation, element, m, efConstruction, entryPoint, building);
UpdateGraphOnDisk(index, support, element, m, efConstruction, entryPoint, building);
/* Release lock */
UnlockPage(index, HNSW_UPDATE_LOCK, lockmode);
@@ -753,17 +753,15 @@ HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid
IndexTuple itup;
const HnswTypeInfo *typeInfo = HnswGetTypeInfo(index);
TupleDesc tupdesc = RelationGetDescr(index);
FmgrInfo *procinfo[2];
FmgrInfo *normprocinfo;
Oid *collation;
HnswSupport support;
HnswSetProcinfo(index, procinfo, &normprocinfo, &collation);
HnswInitSupport(&support, index);
/* Form index tuple */
if (!HnswFormIndexTuple(&itup, values, isnull, typeInfo, normprocinfo, collation[0], tupdesc))
if (!HnswFormIndexTuple(&itup, values, isnull, typeInfo, &support, tupdesc))
return;
HnswInsertTupleOnDisk(index, procinfo, collation, itup, heaptid, false);
HnswInsertTupleOnDisk(index, &support, itup, heaptid, false);
}
/*

15
src/hnswscan.c
View File

@@ -15,8 +15,7 @@ GetScanItems(IndexScanDesc scan, Datum q)
{
HnswScanOpaque so = (HnswScanOpaque) scan->opaque;
Relation index = scan->indexRelation;
FmgrInfo **procinfo = so->procinfo;
Oid *collation = so->collation;
HnswSupport *support = &so->support;
List *ep;
List *w;
int m;
@@ -31,15 +30,15 @@ GetScanItems(IndexScanDesc scan, Datum q)
if (entryPoint == NULL)
return NIL;
ep = list_make1(HnswEntryCandidate(base, entryPoint, q, NULL, keyData, index, procinfo, collation, false, inMemory));
ep = list_make1(HnswEntryCandidate(base, entryPoint, q, NULL, keyData, index, support, false, inMemory));
for (int lc = entryPoint->level; lc >= 1; lc--)
{
w = HnswSearchLayer(base, q, NULL, keyData, ep, 1, lc, index, procinfo, collation, m, false, NULL, inMemory);
w = HnswSearchLayer(base, q, NULL, keyData, ep, 1, lc, index, support, m, false, NULL, inMemory);
ep = w;
}
return HnswSearchLayer(base, q, NULL, keyData, ep, hnsw_ef_search, 0, index, procinfo, collation, m, false, NULL, inMemory);
return HnswSearchLayer(base, q, NULL, keyData, ep, hnsw_ef_search, 0, index, support, m, false, NULL, inMemory);
}
/*
@@ -62,8 +61,8 @@ GetScanValue(IndexScanDesc scan)
Assert(!VARATT_IS_EXTENDED(DatumGetPointer(value)));
/* Normalize if needed */
if (so->normprocinfo != NULL)
value = HnswNormValue(so->typeInfo, so->collation[0], value);
if (so->support.normprocinfo != NULL)
value = HnswNormValue(so->typeInfo, so->support.collation[0], value);
}
return value;
@@ -88,7 +87,7 @@ hnswbeginscan(Relation index, int nkeys, int norderbys)
ALLOCSET_DEFAULT_SIZES);
/* Set support functions */
HnswSetProcinfo(index, so->procinfo, &so->normprocinfo, &so->collation);
HnswInitSupport(&so->support, index);
scan->opaque = so;

87
src/hnswutils.c
View File

@@ -154,20 +154,18 @@ HnswOptionalProcInfo(Relation index, uint16 procnum)
}
/*
* Set procinfo
* Init support functions
*/
void
HnswSetProcinfo(Relation index, FmgrInfo **procinfo, FmgrInfo **normprocinfo, Oid **collation)
HnswInitSupport(HnswSupport * support, Relation index)
{
procinfo[0] = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
support->procinfo[0] = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
if (IndexRelationGetNumberOfKeyAttributes(index) > 1)
procinfo[1] = index_getprocinfo(index, 2, HNSW_ATTRIBUTE_DISTANCE_PROC);
support->procinfo[1] = index_getprocinfo(index, 2, HNSW_ATTRIBUTE_DISTANCE_PROC);
*collation = index->rd_indcollation;
if (normprocinfo != NULL)
*normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
support->collation = index->rd_indcollation;
support->normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
}
/*
@@ -207,9 +205,9 @@ HnswNormValue(const HnswTypeInfo * typeInfo, Oid collation, Datum value)
* Check if non-zero norm
*/
bool
HnswCheckNorm(FmgrInfo *procinfo, Oid collation, Datum value)
HnswCheckNorm(HnswSupport * support, Datum value)
{
return DatumGetFloat8(FunctionCall1Coll(procinfo, collation, value)) > 0;
return DatumGetFloat8(FunctionCall1Coll(support->normprocinfo, support->collation[0], value)) > 0;
}
/*
@@ -472,7 +470,7 @@ HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, Bloc
* Form index tuple
*/
bool
HnswFormIndexTuple(IndexTuple *out, Datum *values, bool *isnull, const HnswTypeInfo * typeInfo, FmgrInfo *normprocinfo, Oid collation, TupleDesc tupdesc)
HnswFormIndexTuple(IndexTuple *out, Datum *values, bool *isnull, const HnswTypeInfo * typeInfo, HnswSupport * support, TupleDesc tupdesc)
{
Datum newValues[2];
@@ -484,12 +482,12 @@ HnswFormIndexTuple(IndexTuple *out, Datum *values, bool *isnull, const HnswTypeI
typeInfo->checkValue(DatumGetPointer(value));
/* Normalize if needed */
if (normprocinfo != NULL)
if (support->normprocinfo != NULL)
{
if (!HnswCheckNorm(normprocinfo, collation, value))
if (!HnswCheckNorm(support, value))
return false;
value = HnswNormValue(typeInfo, collation, value);
value = HnswNormValue(typeInfo, support->collation[0], value);
}
newValues[0] = value;
@@ -629,14 +627,14 @@ AttributeDistance(double e)
* Calculate the distance between values
*/
static double
HnswGetDistance(IndexTuple itup, Datum vec, Datum q, IndexTuple qtup, ScanKeyData *keyData, Relation index, FmgrInfo **procinfo, Oid *collation, bool *matches)
HnswGetDistance(IndexTuple itup, Datum vec, Datum q, IndexTuple qtup, ScanKeyData *keyData, Relation index, HnswSupport * support, bool *matches)
{
double g;
if (DatumGetPointer(q) == NULL)
g = 0;
else
g = DatumGetFloat8(FunctionCall2Coll(procinfo[0], collation[0], q, vec));
g = DatumGetFloat8(FunctionCall2Coll(support->procinfo[0], support->collation[0], q, vec));
Assert(PointerIsValid(matches));
*matches = true;
@@ -669,7 +667,7 @@ HnswGetDistance(IndexTuple itup, Datum vec, Datum q, IndexTuple qtup, ScanKeyDat
}
else if (!DatumGetBool(FunctionCall2Coll(&key->sk_func, key->sk_collation, value, key->sk_argument)))
{
double ei = fabs(DatumGetFloat8(FunctionCall2Coll(procinfo[key->sk_attno - 1], collation[key->sk_attno - 1], value, key->sk_argument)));
double ei = fabs(DatumGetFloat8(FunctionCall2Coll(support->procinfo[key->sk_attno - 1], support->collation[key->sk_attno - 1], value, key->sk_argument)));
if (ei > 0)
e += ei;
@@ -700,7 +698,7 @@ HnswGetDistance(IndexTuple itup, Datum vec, Datum q, IndexTuple qtup, ScanKeyDat
e += 1000;
}
else
e += fabs(DatumGetFloat8(FunctionCall2Coll(procinfo[i + 1], collation[i + 1], value, value2)));
e += fabs(DatumGetFloat8(FunctionCall2Coll(support->procinfo[i + 1], support->collation[i + 1], value, value2)));
}
return w * g + AttributeDistance(e);
@@ -714,7 +712,7 @@ HnswGetDistance(IndexTuple itup, Datum vec, Datum q, IndexTuple qtup, ScanKeyDat
* Load an element and optionally get its distance from q
*/
static void
HnswLoadElementImpl(BlockNumber blkno, OffsetNumber offno, double *distance, bool *matches, Datum *q, IndexTuple qtup, ScanKeyData *keyData, Relation index, FmgrInfo **procinfo, Oid *collation, bool loadVec, double *maxDistance, HnswElement * element)
HnswLoadElementImpl(BlockNumber blkno, OffsetNumber offno, double *distance, bool *matches, Datum *q, IndexTuple qtup, ScanKeyData *keyData, Relation index, HnswSupport * support, bool loadVec, double *maxDistance, HnswElement * element)
{
Buffer buf;
Page page;
@@ -748,7 +746,7 @@ HnswLoadElementImpl(BlockNumber blkno, OffsetNumber offno, double *distance, boo
value = PointerGetDatum(&etup->data);
}
*distance = HnswGetDistance(itup, value, *q, qtup, keyData, index, procinfo, collation, matches);
*distance = HnswGetDistance(itup, value, *q, qtup, keyData, index, support, matches);
}
/* Load element */
@@ -767,36 +765,36 @@ HnswLoadElementImpl(BlockNumber blkno, OffsetNumber offno, double *distance, boo
* Load an element and optionally get its distance from q
*/
void
HnswLoadElement(HnswElement element, double *distance, bool *matches, Datum *q, IndexTuple qtup, ScanKeyData *keyData, Relation index, FmgrInfo **procinfo, Oid *collation, bool loadVec, double *maxDistance)
HnswLoadElement(HnswElement element, double *distance, bool *matches, Datum *q, IndexTuple qtup, ScanKeyData *keyData, Relation index, HnswSupport * support, bool loadVec, double *maxDistance)
{
HnswLoadElementImpl(element->blkno, element->offno, distance, matches, q, qtup, keyData, index, procinfo, collation, loadVec, maxDistance, &element);
HnswLoadElementImpl(element->blkno, element->offno, distance, matches, q, qtup, keyData, index, support, loadVec, maxDistance, &element);
}
/*
* Get the distance for an element
*/
static double
GetElementDistance(char *base, HnswElement element, bool *matches, Datum q, IndexTuple qtup, ScanKeyData *keyData, Relation index, FmgrInfo **procinfo, Oid *collation)
GetElementDistance(char *base, HnswElement element, bool *matches, Datum q, IndexTuple qtup, ScanKeyData *keyData, Relation index, HnswSupport * support)
{
Datum value = HnswGetValue(base, element);
IndexTuple itup = HnswPtrAccess(base, element->itup);
return HnswGetDistance(itup, value, q, qtup, keyData, index, procinfo, collation, matches);
return HnswGetDistance(itup, value, q, qtup, keyData, index, support, matches);
}
/*
* Create a candidate for the entry point
*/
HnswSearchCandidate *
HnswEntryCandidate(char *base, HnswElement entryPoint, Datum q, IndexTuple qtup, ScanKeyData *keyData, Relation index, FmgrInfo **procinfo, Oid *collation, bool loadVec, bool inMemory)
HnswEntryCandidate(char *base, HnswElement entryPoint, Datum q, IndexTuple qtup, ScanKeyData *keyData, Relation index, HnswSupport * support, bool loadVec, bool inMemory)
{
HnswSearchCandidate *sc = palloc(sizeof(HnswSearchCandidate));
HnswPtrStore(base, sc->element, entryPoint);
if (inMemory)
sc->distance = GetElementDistance(base, entryPoint, &sc->matches, q, qtup, keyData, index, procinfo, collation);
sc->distance = GetElementDistance(base, entryPoint, &sc->matches, q, qtup, keyData, index, support);
else
HnswLoadElement(entryPoint, &sc->distance, &sc->matches, &q, qtup, keyData, index, procinfo, collation, loadVec, NULL);
HnswLoadElement(entryPoint, &sc->distance, &sc->matches, &q, qtup, keyData, index, support, loadVec, NULL);
return sc;
}
@@ -985,7 +983,7 @@ HnswLoadUnvisitedFromDisk(HnswElement element, HnswUnvisited * unvisited, int *u
* Algorithm 2 from paper
*/
List *
HnswSearchLayer(char *base, Datum q, IndexTuple qtup, ScanKeyData *keyData, List *ep, int ef, int lc, Relation index, FmgrInfo **procinfo, Oid *collation, int m, bool inserting, HnswElement skipElement, bool inMemory)
HnswSearchLayer(char *base, Datum q, IndexTuple qtup, ScanKeyData *keyData, List *ep, int ef, int lc, Relation index, HnswSupport * support, int m, bool inserting, HnswElement skipElement, bool inMemory)
{
List *w = NIL;
pairingheap *C = pairingheap_allocate(CompareNearestCandidates, NULL);
@@ -1063,7 +1061,7 @@ HnswSearchLayer(char *base, Datum q, IndexTuple qtup, ScanKeyData *keyData, List
if (inMemory)
{
eElement = unvisited[i].element;
eDistance = GetElementDistance(base, eElement, &eMatches, q, qtup, keyData, index, procinfo, collation);
eDistance = GetElementDistance(base, eElement, &eMatches, q, qtup, keyData, index, support);
}
else
{
@@ -1073,7 +1071,7 @@ HnswSearchLayer(char *base, Datum q, IndexTuple qtup, ScanKeyData *keyData, List
/* Avoid any allocations if not adding */
eElement = NULL;
HnswLoadElementImpl(blkno, offno, &eDistance, &eMatches, &q, qtup, keyData, index, procinfo, collation, inserting, alwaysAdd ? NULL : &f->distance, &eElement);
HnswLoadElementImpl(blkno, offno, &eDistance, &eMatches, &q, qtup, keyData, index, support, inserting, alwaysAdd ? NULL : &f->distance, &eElement);
if (eElement == NULL)
continue;
@@ -1179,7 +1177,7 @@ CompareCandidateDistancesOffset(const ListCell *a, const ListCell *b)
* Check if an element is closer to q than any element from R
*/
static bool
CheckElementCloser(char *base, HnswCandidate * e, List *r, Relation index, FmgrInfo **procinfo, Oid *collation)
CheckElementCloser(char *base, HnswCandidate * e, List *r, Relation index, HnswSupport * support)
{
HnswElement eElement = HnswPtrAccess(base, e->element);
Datum eValue = HnswGetValue(base, eElement);
@@ -1193,7 +1191,7 @@ CheckElementCloser(char *base, HnswCandidate * e, List *r, Relation index, FmgrI
Datum riValue = HnswGetValue(base, riElement);
IndexTuple ritup = HnswPtrAccess(base, riElement->itup);
bool matches;
float distance = HnswGetDistance(etup, eValue, riValue, ritup, NULL, index, procinfo, collation, &matches);
float distance = HnswGetDistance(etup, eValue, riValue, ritup, NULL, index, support, &matches);
if (distance <= e->distance)
return false;
@@ -1206,7 +1204,7 @@ CheckElementCloser(char *base, HnswCandidate * e, List *r, Relation index, FmgrI
* Algorithm 4 from paper
*/
static List *
SelectNeighbors(char *base, List *c, int lm, Relation index, FmgrInfo **procinfo, Oid *collation, bool *closerSet, HnswCandidate * newCandidate, HnswCandidate * *pruned, bool sortCandidates)
SelectNeighbors(char *base, List *c, int lm, Relation index, HnswSupport * support, bool *closerSet, HnswCandidate * newCandidate, HnswCandidate * *pruned, bool sortCandidates)
{
List *r = NIL;
List *w = list_copy(c);
@@ -1240,7 +1238,7 @@ SelectNeighbors(char *base, List *c, int lm, Relation index, FmgrInfo **procinfo
/* Use previous state of r and wd to skip work when possible */
if (mustCalculate)
e->closer = CheckElementCloser(base, e, r, index, procinfo, collation);
e->closer = CheckElementCloser(base, e, r, index, support);
else if (list_length(added) > 0)
{
/* Keep Valgrind happy for in-memory, parallel builds */
@@ -1253,8 +1251,7 @@ SelectNeighbors(char *base, List *c, int lm, Relation index, FmgrInfo **procinfo
*/
if (e->closer)
{
e->closer = CheckElementCloser(base, e, added, index, procinfo, collation);
e->closer = CheckElementCloser(base, e, added, index, support);
if (!e->closer)
removedAny = true;
}
@@ -1266,7 +1263,7 @@ SelectNeighbors(char *base, List *c, int lm, Relation index, FmgrInfo **procinfo
*/
if (removedAny)
{
e->closer = CheckElementCloser(base, e, r, index, procinfo, collation);
e->closer = CheckElementCloser(base, e, r, index, support);
if (e->closer)
added = lappend(added, e);
}
@@ -1274,7 +1271,7 @@ SelectNeighbors(char *base, List *c, int lm, Relation index, FmgrInfo **procinfo
}
else if (e == newCandidate)
{
e->closer = CheckElementCloser(base, e, r, index, procinfo, collation);
e->closer = CheckElementCloser(base, e, r, index, support);
if (e->closer)
added = lappend(added, e);
}
@@ -1325,7 +1322,7 @@ AddConnections(char *base, HnswElement element, List *neighbors, int lc)
* Update connections
*/
void
HnswUpdateConnection(char *base, HnswNeighborArray * neighbors, HnswElement newElement, float distance, int lm, int *updateIdx, Relation index, FmgrInfo **procinfo, Oid *collation)
HnswUpdateConnection(char *base, HnswNeighborArray * neighbors, HnswElement newElement, float distance, int lm, int *updateIdx, Relation index, HnswSupport * support)
{
HnswCandidate newHc;
@@ -1351,7 +1348,7 @@ HnswUpdateConnection(char *base, HnswNeighborArray * neighbors, HnswElement newE
c = lappend(c, &neighbors->items[i]);
c = lappend(c, &newHc);
SelectNeighbors(base, c, lm, index, procinfo, collation, &neighbors->closerSet, &newHc, &pruned, true);
SelectNeighbors(base, c, lm, index, support, &neighbors->closerSet, &newHc, &pruned, true);
/* Should not happen */
if (pruned == NULL)
@@ -1422,7 +1419,7 @@ PrecomputeHash(char *base, HnswElement element)
* Algorithm 1 from paper
*/
void
HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, FmgrInfo **procinfo, Oid *collation, int m, int efConstruction, bool existing, bool inMemory)
HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, HnswSupport * support, int m, int efConstruction, bool existing, bool inMemory)
{
List *ep;
List *w;
@@ -1442,13 +1439,13 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
return;
/* Get entry point and level */
ep = list_make1(HnswEntryCandidate(base, entryPoint, q, qtup, keyData, index, procinfo, collation, true, inMemory));
ep = list_make1(HnswEntryCandidate(base, entryPoint, q, qtup, keyData, index, support, true, inMemory));
entryLevel = entryPoint->level;
/* 1st phase: greedy search to insert level */
for (int lc = entryLevel; lc >= level + 1; lc--)
{
w = HnswSearchLayer(base, q, qtup, keyData, ep, 1, lc, index, procinfo, collation, m, true, skipElement, inMemory);
w = HnswSearchLayer(base, q, qtup, keyData, ep, 1, lc, index, support, m, true, skipElement, inMemory);
ep = w;
}
@@ -1467,7 +1464,7 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
List *lw = NIL;
ListCell *lc2;
w = HnswSearchLayer(base, q, qtup, keyData, ep, efConstruction, lc, index, procinfo, collation, m, true, skipElement, inMemory);
w = HnswSearchLayer(base, q, qtup, keyData, ep, efConstruction, lc, index, support, m, true, skipElement, inMemory);
/* Convert search candidates to candidates */
foreach(lc2, w)
@@ -1491,7 +1488,7 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
* sortCandidates to true for in-memory builds to enable closer
* caching, but there does not seem to be a difference in performance.
*/
neighbors = SelectNeighbors(base, lw, lm, index, procinfo, collation, &HnswGetNeighbors(base, element, lc)->closerSet, NULL, NULL, false);
neighbors = SelectNeighbors(base, lw, lm, index, support, &HnswGetNeighbors(base, element, lc)->closerSet, NULL, NULL, false);
AddConnections(base, element, neighbors, lc);

14
src/hnswvacuum.c
View File

@@ -184,13 +184,12 @@ static void
RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswElement entryPoint)
{
Relation index = vacuumstate->index;
HnswSupport *support = &vacuumstate->support;
Buffer buf;
Page page;
GenericXLogState *state;
int m = vacuumstate->m;
int efConstruction = vacuumstate->efConstruction;
FmgrInfo **procinfo = vacuumstate->procinfo;
Oid *collation = vacuumstate->collation;
BufferAccessStrategy bas = vacuumstate->bas;
HnswNeighborTuple ntup = vacuumstate->ntup;
Size ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(element->level, m);
@@ -205,7 +204,7 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
element->heaptidsLength = 0;
/* Find neighbors for element, skipping itself */
HnswFindElementNeighbors(base, element, entryPoint, index, procinfo, collation, m, efConstruction, true, false);
HnswFindElementNeighbors(base, element, entryPoint, index, support, m, efConstruction, true, false);
/* Zero memory for each element */
MemSet(ntup, 0, HNSW_TUPLE_ALLOC_SIZE);
@@ -229,7 +228,7 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
UnlockReleaseBuffer(buf);
/* Update neighbors */
HnswUpdateNeighborsOnDisk(index, procinfo, collation, element, m, true, false);
HnswUpdateNeighborsOnDisk(index, support, element, m, true, false);
}
/*
@@ -239,6 +238,7 @@ static void
RepairGraphEntryPoint(HnswVacuumState * vacuumstate)
{
Relation index = vacuumstate->index;
HnswSupport *support = &vacuumstate->support;
HnswElement highestPoint = &vacuumstate->highestPoint;
HnswElement entryPoint;
MemoryContext oldCtx = MemoryContextSwitchTo(vacuumstate->tmpCtx);
@@ -256,7 +256,7 @@ RepairGraphEntryPoint(HnswVacuumState * vacuumstate)
LockPage(index, HNSW_UPDATE_LOCK, ShareLock);
/* Load element */
HnswLoadElement(highestPoint, NULL, NULL, NULL, NULL, NULL, index, vacuumstate->procinfo, vacuumstate->collation, true, NULL);
HnswLoadElement(highestPoint, NULL, NULL, NULL, NULL, NULL, index, support, true, NULL);
/* Repair if needed */
if (NeedsUpdated(vacuumstate, highestPoint))
@@ -294,7 +294,7 @@ RepairGraphEntryPoint(HnswVacuumState * vacuumstate)
* is outdated, this can remove connections at higher levels in
* the graph until they are repaired, but this should be fine.
*/
HnswLoadElement(entryPoint, NULL, NULL, NULL, NULL, NULL, index, vacuumstate->procinfo, vacuumstate->collation, true, NULL);
HnswLoadElement(entryPoint, NULL, NULL, NULL, NULL, NULL, index, support, true, NULL);
if (NeedsUpdated(vacuumstate, entryPoint))
{
@@ -586,7 +586,7 @@ InitVacuumState(HnswVacuumState * vacuumstate, IndexVacuumInfo *info, IndexBulkD
"Hnsw vacuum temporary context",
ALLOCSET_DEFAULT_SIZES);
HnswSetProcinfo(index, vacuumstate->procinfo, NULL, &vacuumstate->collation);
HnswInitSupport(&vacuumstate->support, index);
/* Get m from metapage */
HnswGetMetaPageInfo(index, &vacuumstate->m, NULL);