liuyu/pgvector
1
0
Fork 0
mirror of https://github.com/pgvector/pgvector.git synced 2026-07-12 23:56:55 +08:00
Code Issues Packages Projects Releases Wiki Activity

Added IndexTuple to HNSW elements (first step to support multiple attributes)

Browse Source
This commit is contained in:
Andrew Kane
2024-10-11 14:12:01 -07:00
parent 7484625227
commit 53a8734bac
4 changed files with 51 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
src/hnsw.h
View File

@@ -133,6 +133,7 @@ HnswPtrDeclare(HnswElementData, HnswElementRelptr, HnswElementPtr);
HnswPtrDeclare(HnswNeighborArray, HnswNeighborArrayRelptr, HnswNeighborArrayPtr); HnswPtrDeclare(HnswNeighborArray, HnswNeighborArrayRelptr, HnswNeighborArrayPtr);
HnswPtrDeclare(HnswNeighborArrayPtr, HnswNeighborsRelptr, HnswNeighborsPtr); HnswPtrDeclare(HnswNeighborArrayPtr, HnswNeighborsRelptr, HnswNeighborsPtr);
HnswPtrDeclare(char, DatumRelptr, DatumPtr); HnswPtrDeclare(char, DatumRelptr, DatumPtr);
HnswPtrDeclare(IndexTupleData, IndexTupleRelptr, IndexTuplePtr);
struct HnswElementData struct HnswElementData
{ {
@@ -149,6 +150,7 @@ struct HnswElementData
OffsetNumber neighborOffno; OffsetNumber neighborOffno;
BlockNumber neighborPage; BlockNumber neighborPage;
DatumPtr value; DatumPtr value;
IndexTuplePtr itup;
LWLock lock; LWLock lock;
}; };
@@ -288,6 +290,7 @@ typedef struct HnswBuildState
HnswGraph *graph; HnswGraph *graph;
double ml; double ml;
int maxLevel; int maxLevel;
TupleDesc tupdesc;
/* Memory */ /* Memory */
MemoryContext graphCtx; MemoryContext graphCtx;
@@ -428,11 +431,12 @@ void HnswSetNeighborTuple(char *base, HnswNeighborTuple ntup, HnswElement e, in
void HnswAddHeapTid(HnswElement element, ItemPointer heaptid); void HnswAddHeapTid(HnswElement element, ItemPointer heaptid);
HnswNeighborArray *HnswInitNeighborArray(int lm, HnswAllocator * allocator); HnswNeighborArray *HnswInitNeighborArray(int lm, HnswAllocator * allocator);
void HnswInitNeighbors(char *base, HnswElement element, int m, HnswAllocator * alloc); void HnswInitNeighbors(char *base, HnswElement element, int m, HnswAllocator * alloc);
bool HnswInsertTupleOnDisk(Relation index, HnswSupport * support, Datum value, ItemPointer heaptid, bool building); bool HnswInsertTupleOnDisk(Relation index, HnswSupport * support, TupleDesc tupdesc, IndexTuple itup, ItemPointer heaptid, bool building);
void HnswUpdateNeighborsOnDisk(Relation index, HnswSupport * support, HnswElement e, int m, bool checkExisting, 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); void HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHeaptids, bool loadVec);
void HnswLoadElement(HnswElement element, double *distance, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec, double *maxDistance); void HnswLoadElement(HnswElement element, double *distance, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec, double *maxDistance);
bool HnswFormIndexValue(Datum *out, Datum *values, bool *isnull, const HnswTypeInfo * typeInfo, HnswSupport * support); TupleDesc HnswTupleDesc(Relation index);
bool HnswFormIndexTuple(IndexTuple *out, Datum *values, bool *isnull, const HnswTypeInfo * typeInfo, HnswSupport * support, TupleDesc tupdesc);
void HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element); void HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element);
void HnswUpdateConnection(char *base, HnswNeighborArray * neighbors, HnswElement newElement, float distance, int lm, int *updateIdx, Relation index, HnswSupport * support); void HnswUpdateConnection(char *base, HnswNeighborArray * neighbors, HnswElement newElement, float distance, int lm, int *updateIdx, Relation index, HnswSupport * support);
bool HnswLoadNeighborTids(HnswElement element, ItemPointerData *indextids, Relation index, int m, int lm, int lc); bool HnswLoadNeighborTids(HnswElement element, ItemPointerData *indextids, Relation index, int m, int lm, int lc);

29
src/hnswbuild.c
View File

@@ -476,18 +476,20 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
HnswElement element; HnswElement element;
HnswAllocator *allocator = &buildstate->allocator; HnswAllocator *allocator = &buildstate->allocator;
HnswSupport *support = &buildstate->support; HnswSupport *support = &buildstate->support;
Size valueSize;
Pointer valuePtr;
LWLock *flushLock = &graph->flushLock; LWLock *flushLock = &graph->flushLock;
char *base = buildstate->hnswarea; char *base = buildstate->hnswarea;
Datum value; TupleDesc tupdesc = buildstate->tupdesc;
IndexTuple itup;
Size itupSize;
IndexTuple itupShared;
bool unused;
/* Form index value */ /* Form index value */
if (!HnswFormIndexValue(&value, values, isnull, buildstate->typeInfo, support)) if (!HnswFormIndexTuple(&itup, values, isnull, buildstate->typeInfo, support, tupdesc))
return false; return false;
/* Get datum size */ /* Get tuple size */
valueSize = VARSIZE_ANY(DatumGetPointer(value)); itupSize = IndexTupleSize(itup);
/* Ensure graph not flushed when inserting */ /* Ensure graph not flushed when inserting */
LWLockAcquire(flushLock, LW_SHARED); LWLockAcquire(flushLock, LW_SHARED);
@@ -497,7 +499,7 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
{ {
LWLockRelease(flushLock); LWLockRelease(flushLock);
return HnswInsertTupleOnDisk(index, support, value, heaptid, true); return HnswInsertTupleOnDisk(index, support, tupdesc, itup, heaptid, true);
} }
/* /*
@@ -529,12 +531,12 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
LWLockRelease(flushLock); LWLockRelease(flushLock);
return HnswInsertTupleOnDisk(index, support, value, heaptid, true); return HnswInsertTupleOnDisk(index, support, tupdesc, itup, heaptid, true);
} }
/* Ok, we can proceed to allocate the element */ /* Ok, we can proceed to allocate the element */
element = HnswInitElement(base, heaptid, buildstate->m, buildstate->ml, buildstate->maxLevel, allocator); element = HnswInitElement(base, heaptid, buildstate->m, buildstate->ml, buildstate->maxLevel, allocator);
valuePtr = HnswAlloc(allocator, valueSize); itupShared = HnswAlloc(allocator, itupSize);
/* /*
* We have now allocated the space needed for the element, so we don't * We have now allocated the space needed for the element, so we don't
@@ -543,9 +545,10 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
*/ */
LWLockRelease(&graph->allocatorLock); LWLockRelease(&graph->allocatorLock);
/* Copy the datum */ /* Copy the tuple */
memcpy(valuePtr, DatumGetPointer(value), valueSize); memcpy(itupShared, itup, itupSize);
HnswPtrStore(base, element->value, valuePtr); HnswPtrStore(base, element->itup, itupShared);
HnswPtrStore(base, element->value, DatumGetPointer(index_getattr(itupShared, 1, tupdesc, &unused)));
/* Create a lock for the element */ /* Create a lock for the element */
LWLockInitialize(&element->lock, hnsw_lock_tranche_id); LWLockInitialize(&element->lock, hnsw_lock_tranche_id);
@@ -698,6 +701,7 @@ InitBuildState(HnswBuildState * buildstate, Relation heap, Relation index, Index
buildstate->graph = &buildstate->graphData; buildstate->graph = &buildstate->graphData;
buildstate->ml = HnswGetMl(buildstate->m); buildstate->ml = HnswGetMl(buildstate->m);
buildstate->maxLevel = HnswGetMaxLevel(buildstate->m); buildstate->maxLevel = HnswGetMaxLevel(buildstate->m);
buildstate->tupdesc = HnswTupleDesc(index);
buildstate->graphCtx = GenerationContextCreate(CurrentMemoryContext, buildstate->graphCtx = GenerationContextCreate(CurrentMemoryContext,
"Hnsw build graph context", "Hnsw build graph context",
@@ -722,6 +726,7 @@ InitBuildState(HnswBuildState * buildstate, Relation heap, Relation index, Index
static void static void
FreeBuildState(HnswBuildState * buildstate) FreeBuildState(HnswBuildState * buildstate)
{ {
pfree(buildstate->tupdesc);
MemoryContextDelete(buildstate->graphCtx); MemoryContextDelete(buildstate->graphCtx);
MemoryContextDelete(buildstate->tmpCtx); MemoryContextDelete(buildstate->tmpCtx);
} }

15
src/hnswinsert.c
View File

@@ -687,7 +687,7 @@ UpdateGraphOnDisk(Relation index, HnswSupport * support, HnswElement element, in
* Insert a tuple into the index * Insert a tuple into the index
*/ */
bool bool
HnswInsertTupleOnDisk(Relation index, HnswSupport * support, Datum value, ItemPointer heaptid, bool building) HnswInsertTupleOnDisk(Relation index, HnswSupport * support, TupleDesc tupdesc, IndexTuple itup, ItemPointer heaptid, bool building)
{ {
HnswElement entryPoint; HnswElement entryPoint;
HnswElement element; HnswElement element;
@@ -695,6 +695,7 @@ HnswInsertTupleOnDisk(Relation index, HnswSupport * support, Datum value, ItemPo
int efConstruction = HnswGetEfConstruction(index); int efConstruction = HnswGetEfConstruction(index);
LOCKMODE lockmode = ShareLock; LOCKMODE lockmode = ShareLock;
char *base = NULL; char *base = NULL;
bool unused;
/* /*
* Get a shared lock. This allows vacuum to ensure no in-flight inserts * Get a shared lock. This allows vacuum to ensure no in-flight inserts
@@ -708,7 +709,8 @@ HnswInsertTupleOnDisk(Relation index, HnswSupport * support, Datum value, ItemPo
/* Create an element */ /* Create an element */
element = HnswInitElement(base, heaptid, m, HnswGetMl(m), HnswGetMaxLevel(m), NULL); element = HnswInitElement(base, heaptid, m, HnswGetMl(m), HnswGetMaxLevel(m), NULL);
HnswPtrStore(base, element->value, DatumGetPointer(value)); HnswPtrStore(base, element->itup, itup);
HnswPtrStore(base, element->value, DatumGetPointer(index_getattr(itup, 1, tupdesc, &unused)));
/* Prevent concurrent inserts when likely updating entry point */ /* Prevent concurrent inserts when likely updating entry point */
if (entryPoint == NULL || element->level > entryPoint->level) if (entryPoint == NULL || element->level > entryPoint->level)
@@ -742,17 +744,18 @@ HnswInsertTupleOnDisk(Relation index, HnswSupport * support, Datum value, ItemPo
static void static void
HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid) HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid)
{ {
Datum value; IndexTuple itup;
const HnswTypeInfo *typeInfo = HnswGetTypeInfo(index); const HnswTypeInfo *typeInfo = HnswGetTypeInfo(index);
HnswSupport support; HnswSupport support;
TupleDesc tupdesc = HnswTupleDesc(index);
HnswInitSupport(&support, index); HnswInitSupport(&support, index);
/* Form index value */ /* Form index tuple */
if (!HnswFormIndexValue(&value, values, isnull, typeInfo, &support)) if (!HnswFormIndexTuple(&itup, values, isnull, typeInfo, &support, tupdesc))
return; return;
HnswInsertTupleOnDisk(index, &support, value, heaptid, false); HnswInsertTupleOnDisk(index, &support, tupdesc, itup, heaptid, false);
} }
/* /*

22
src/hnswutils.c
View File

@@ -395,10 +395,24 @@ HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, Bloc
} }
/* /*
* Form index value * Get the tuple descriptor
*/
TupleDesc
HnswTupleDesc(Relation index)
{
TupleDesc tupdesc = CreateTupleDescCopyConstr(RelationGetDescr(index));
/* Prevent compression */
TupleDescAttr(tupdesc, 0)->attstorage = TYPSTORAGE_PLAIN;
return tupdesc;
}
/*
* Form index tuple
*/ */
bool bool
HnswFormIndexValue(Datum *out, Datum *values, bool *isnull, const HnswTypeInfo * typeInfo, HnswSupport * support) HnswFormIndexTuple(IndexTuple *out, Datum *values, bool *isnull, const HnswTypeInfo * typeInfo, HnswSupport * support, TupleDesc tupdesc)
{ {
/* Detoast once for all calls */ /* Detoast once for all calls */
Datum value = PointerGetDatum(PG_DETOAST_DATUM(values[0])); Datum value = PointerGetDatum(PG_DETOAST_DATUM(values[0]));
@@ -416,7 +430,9 @@ HnswFormIndexValue(Datum *out, Datum *values, bool *isnull, const HnswTypeInfo *
value = HnswNormValue(typeInfo, support->collation, value); value = HnswNormValue(typeInfo, support->collation, value);
} }
*out = value; /* TODO Combine value with values to support multiple attributes */
Assert(tupdesc->natts == 1);
*out = index_form_tuple(tupdesc, &value, isnull);
return true; return true;
} }