From 32ab27d72a36f4aced101a5d8f42e1fc78d42024 Mon Sep 17 00:00:00 2001 From: Andrew Kane Date: Wed, 9 Oct 2024 23:10:26 -0700 Subject: [PATCH] Added HnswSupport struct for support functions --- src/hnsw.h | 38 ++++++++++++----------- src/hnswbuild.c | 26 ++++++++-------- src/hnswinsert.c | 34 ++++++++++---------- src/hnswscan.c | 15 +++++---- src/hnswutils.c | 80 +++++++++++++++++++++++------------------------- src/hnswvacuum.c | 14 ++++----- 6 files changed, 101 insertions(+), 106 deletions(-) diff --git a/src/hnsw.h b/src/hnsw.h index 364e03e..bfc12f6 100644 --- a/src/hnsw.h +++ b/src/hnsw.h @@ -237,6 +237,13 @@ typedef struct HnswTypeInfo void (*checkValue) (Pointer v); } HnswTypeInfo; +typedef struct HnswSupport +{ + FmgrInfo *procinfo; + FmgrInfo *normprocinfo; + Oid collation; +} HnswSupport; + typedef struct HnswBuildState { /* Info */ @@ -256,9 +263,7 @@ typedef struct HnswBuildState double reltuples; /* Support functions */ - FmgrInfo *procinfo; - FmgrInfo *normprocinfo; - Oid collation; + HnswSupport support; /* Variables */ HnswGraph graphData; @@ -333,9 +338,7 @@ typedef struct HnswScanOpaqueData MemoryContext tmpCtx; /* Support functions */ - FmgrInfo *procinfo; - FmgrInfo *normprocinfo; - Oid collation; + HnswSupport support; } HnswScanOpaqueData; typedef HnswScanOpaqueData * HnswScanOpaque; @@ -353,8 +356,7 @@ typedef struct HnswVacuumState int efConstruction; /* Support functions */ - FmgrInfo *procinfo; - Oid collation; + HnswSupport support; /* Variables */ struct tidhash_hash *deleted; @@ -370,32 +372,32 @@ 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, 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, HnswSupport * support, int m, bool inserting, HnswElement skipElement); 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); -HnswSearchCandidate *HnswEntryCandidate(char *base, HnswElement em, Datum q, Relation rel, FmgrInfo *procinfo, Oid collation, bool loadVec); +void HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, HnswSupport * support, int m, int efConstruction, bool existing); +HnswSearchCandidate *HnswEntryCandidate(char *base, HnswElement em, Datum q, Relation rel, HnswSupport * support, bool loadVec); 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, Datum value, 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, Datum value, 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); -void HnswLoadElement(HnswElement element, double *distance, Datum *q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec, double *maxDistance); -bool HnswFormIndexValue(Datum *out, Datum *values, bool *isnull, const HnswTypeInfo * typeInfo, FmgrInfo *normprocinfo, Oid collation); +void HnswLoadElement(HnswElement element, double *distance, Datum *q, Relation index, HnswSupport * support, bool loadVec, double *maxDistance); +bool HnswFormIndexValue(Datum *out, Datum *values, bool *isnull, const HnswTypeInfo * typeInfo, HnswSupport * support); void HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element); -void HnswUpdateConnection(char *base, HnswNeighborArray * neighbors, HnswElement newElement, float distance, int lm, int *updateIdx, Relation index, FmgrInfo *procinfo, Oid collation); +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); void HnswInitLockTranche(void); const HnswTypeInfo *HnswGetTypeInfo(Relation index); diff --git a/src/hnswbuild.c b/src/hnswbuild.c index 6fab132..b667478 100644 --- a/src/hnswbuild.c +++ b/src/hnswbuild.c @@ -366,7 +366,7 @@ AddElementInMemory(char *base, HnswGraph * graph, HnswElement element) * Update neighbors */ static void -UpdateNeighborsInMemory(char *base, FmgrInfo *procinfo, Oid collation, HnswElement e, int m) +UpdateNeighborsInMemory(char *base, HnswSupport * support, HnswElement e, int m) { for (int lc = e->level; lc >= 0; lc--) { @@ -388,7 +388,7 @@ UpdateNeighborsInMemory(char *base, FmgrInfo *procinfo, Oid collation, HnswEleme Assert(neighborElement); LWLockAcquire(&neighborElement->lock, LW_EXCLUSIVE); - HnswUpdateConnection(base, HnswGetNeighbors(base, neighborElement, lc), e, hc->distance, lm, NULL, NULL, procinfo, collation); + HnswUpdateConnection(base, HnswGetNeighbors(base, neighborElement, lc), e, hc->distance, lm, NULL, NULL, support); LWLockRelease(&neighborElement->lock); } } @@ -398,7 +398,7 @@ UpdateNeighborsInMemory(char *base, FmgrInfo *procinfo, Oid collation, HnswEleme * 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; @@ -411,7 +411,7 @@ UpdateGraphInMemory(FmgrInfo *procinfo, Oid collation, HnswElement element, int AddElementInMemory(base, graph, element); /* Update neighbors */ - UpdateNeighborsInMemory(base, procinfo, collation, element, m); + UpdateNeighborsInMemory(base, support, element, m); /* Update entry point if needed (already have lock) */ if (entryPoint == NULL || element->level > entryPoint->level) @@ -424,9 +424,8 @@ UpdateGraphInMemory(FmgrInfo *procinfo, Oid collation, HnswElement element, int static void InsertTupleInMemory(HnswBuildState * buildstate, HnswElement element) { - 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, NULL, procinfo, collation, m, efConstruction, false); + HnswFindElementNeighbors(base, element, entryPoint, NULL, support, m, efConstruction, false); /* 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; Size valueSize; Pointer valuePtr; LWLock *flushLock = &graph->flushLock; @@ -485,7 +483,7 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn Datum value; /* Form index value */ - if (!HnswFormIndexValue(&value, values, isnull, buildstate->typeInfo, buildstate->normprocinfo, collation)) + if (!HnswFormIndexValue(&value, values, isnull, buildstate->typeInfo, support)) return false; /* Get datum size */ @@ -499,7 +497,7 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn { LWLockRelease(flushLock); - return HnswInsertTupleOnDisk(index, procinfo, collation, value, heaptid, true); + return HnswInsertTupleOnDisk(index, support, value, heaptid, true); } /* @@ -531,7 +529,7 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn LWLockRelease(flushLock); - return HnswInsertTupleOnDisk(index, procinfo, collation, value, heaptid, true); + return HnswInsertTupleOnDisk(index, support, value, heaptid, true); } /* Ok, we can proceed to allocate the element */ @@ -694,7 +692,7 @@ 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; diff --git a/src/hnswinsert.c b/src/hnswinsert.c index 45530b9..87204ca 100644 --- a/src/hnswinsert.c +++ b/src/hnswinsert.c @@ -368,7 +368,7 @@ HnswLoadNeighbors(HnswElement element, Relation index, int m, int lm, int lc) * Load elements for insert */ static void -LoadElementsForInsert(HnswNeighborArray * neighbors, Datum q, int *idx, Relation index, FmgrInfo *procinfo, Oid collation) +LoadElementsForInsert(HnswNeighborArray * neighbors, Datum q, int *idx, Relation index, HnswSupport * support) { char *base = NULL; @@ -378,7 +378,7 @@ LoadElementsForInsert(HnswNeighborArray * neighbors, Datum q, int *idx, Relation HnswElement element = HnswPtrAccess(base, hc->element); double distance; - HnswLoadElement(element, &distance, &q, index, procinfo, collation, true, NULL); + HnswLoadElement(element, &distance, &q, index, support, true, NULL); hc->distance = distance; /* Prune element if being deleted */ @@ -394,7 +394,7 @@ LoadElementsForInsert(HnswNeighborArray * neighbors, Datum q, int *idx, Relation * 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; @@ -421,10 +421,10 @@ GetUpdateIndex(HnswElement element, HnswElement newElement, float distance, int { Datum q = HnswGetValue(base, element); - LoadElementsForInsert(neighbors, q, &idx, index, procinfo, collation); + LoadElementsForInsert(neighbors, q, &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); @@ -529,7 +529,7 @@ 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; @@ -552,7 +552,7 @@ HnswUpdateNeighborsOnDisk(Relation index, FmgrInfo *procinfo, Oid collation, Hns 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) @@ -652,7 +652,7 @@ 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; @@ -668,7 +668,7 @@ UpdateGraphOnDisk(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement 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) @@ -679,7 +679,7 @@ UpdateGraphOnDisk(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement * Insert a tuple into the index */ bool -HnswInsertTupleOnDisk(Relation index, FmgrInfo *procinfo, Oid collation, Datum value, ItemPointer heaptid, bool building) +HnswInsertTupleOnDisk(Relation index, HnswSupport * support, Datum value, ItemPointer heaptid, bool building) { HnswElement entryPoint; HnswElement element; @@ -717,10 +717,10 @@ HnswInsertTupleOnDisk(Relation index, FmgrInfo *procinfo, Oid collation, Datum v } /* Find neighbors for element */ - HnswFindElementNeighbors(base, element, entryPoint, index, procinfo, collation, m, efConstruction, false); + HnswFindElementNeighbors(base, element, entryPoint, index, support, m, efConstruction, 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); @@ -736,17 +736,15 @@ HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid { Datum value; const HnswTypeInfo *typeInfo = HnswGetTypeInfo(index); - FmgrInfo *procinfo; - FmgrInfo *normprocinfo; - Oid collation; + HnswSupport support; - HnswSetProcinfo(index, &procinfo, &normprocinfo, &collation); + HnswInitSupport(&support, index); /* Form index value */ - if (!HnswFormIndexValue(&value, values, isnull, typeInfo, normprocinfo, collation)) + if (!HnswFormIndexValue(&value, values, isnull, typeInfo, &support)) return; - HnswInsertTupleOnDisk(index, procinfo, collation, value, heaptid, false); + HnswInsertTupleOnDisk(index, &support, value, heaptid, false); } /* diff --git a/src/hnswscan.c b/src/hnswscan.c index c8af889..e3aaced 100644 --- a/src/hnswscan.c +++ b/src/hnswscan.c @@ -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; @@ -29,15 +28,15 @@ GetScanItems(IndexScanDesc scan, Datum q) if (entryPoint == NULL) return NIL; - ep = list_make1(HnswEntryCandidate(base, entryPoint, q, index, procinfo, collation, false)); + ep = list_make1(HnswEntryCandidate(base, entryPoint, q, index, support, false)); 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, support, m, false, NULL); 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, support, m, false, NULL); } /* @@ -60,8 +59,8 @@ GetScanValue(IndexScanDesc scan) Assert(!VARATT_IS_EXTENDED(DatumGetPointer(value))); /* Normalize if needed */ - if (so->normprocinfo != NULL) - value = HnswNormValue(so->typeInfo, so->collation, value); + if (so->support.normprocinfo != NULL) + value = HnswNormValue(so->typeInfo, so->support.collation, value); } return value; @@ -86,7 +85,7 @@ 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; diff --git a/src/hnswutils.c b/src/hnswutils.c index 03c033e..7fa0720 100644 --- a/src/hnswutils.c +++ b/src/hnswutils.c @@ -154,16 +154,14 @@ 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 = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC); - *collation = index->rd_indcollation[0]; - - if (normprocinfo != NULL) - *normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC); + support->procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC); + support->collation = index->rd_indcollation[0]; + support->normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC); } /* @@ -179,9 +177,9 @@ 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, value)) > 0; } /* @@ -411,7 +409,7 @@ HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, Bloc * Form index value */ bool -HnswFormIndexValue(Datum *out, Datum *values, bool *isnull, const HnswTypeInfo * typeInfo, FmgrInfo *normprocinfo, Oid collation) +HnswFormIndexValue(Datum *out, Datum *values, bool *isnull, const HnswTypeInfo * typeInfo, HnswSupport * support) { /* Detoast once for all calls */ Datum value = PointerGetDatum(PG_DETOAST_DATUM(values[0])); @@ -421,12 +419,12 @@ HnswFormIndexValue(Datum *out, Datum *values, bool *isnull, const HnswTypeInfo * 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, value); } *out = value; @@ -526,16 +524,16 @@ HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHe * Calculate the distance between values */ static inline double -HnswGetDistance(Datum a, Datum b, FmgrInfo *procinfo, Oid collation) +HnswGetDistance(Datum a, Datum b, HnswSupport * support) { - return DatumGetFloat8(FunctionCall2Coll(procinfo, collation, a, b)); + return DatumGetFloat8(FunctionCall2Coll(support->procinfo, support->collation, a, b)); } /* * Load an element and optionally get its distance from q */ static void -HnswLoadElementImpl(BlockNumber blkno, OffsetNumber offno, double *distance, Datum *q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec, double *maxDistance, HnswElement * element) +HnswLoadElementImpl(BlockNumber blkno, OffsetNumber offno, double *distance, Datum *q, Relation index, HnswSupport * support, bool loadVec, double *maxDistance, HnswElement * element) { Buffer buf; Page page; @@ -556,7 +554,7 @@ HnswLoadElementImpl(BlockNumber blkno, OffsetNumber offno, double *distance, Dat if (DatumGetPointer(*q) == NULL) *distance = 0; else - *distance = HnswGetDistance(*q, PointerGetDatum(&etup->data), procinfo, collation); + *distance = HnswGetDistance(*q, PointerGetDatum(&etup->data), support); } /* Load element */ @@ -575,36 +573,36 @@ HnswLoadElementImpl(BlockNumber blkno, OffsetNumber offno, double *distance, Dat * Load an element and optionally get its distance from q */ void -HnswLoadElement(HnswElement element, double *distance, Datum *q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec, double *maxDistance) +HnswLoadElement(HnswElement element, double *distance, Datum *q, Relation index, HnswSupport * support, bool loadVec, double *maxDistance) { - HnswLoadElementImpl(element->blkno, element->offno, distance, q, index, procinfo, collation, loadVec, maxDistance, &element); + HnswLoadElementImpl(element->blkno, element->offno, distance, q, index, support, loadVec, maxDistance, &element); } /* * Get the distance for an element */ static double -GetElementDistance(char *base, HnswElement element, Datum q, FmgrInfo *procinfo, Oid collation) +GetElementDistance(char *base, HnswElement element, Datum q, HnswSupport * support) { Datum value = HnswGetValue(base, element); - return HnswGetDistance(q, value, procinfo, collation); + return HnswGetDistance(q, value, support); } /* * Create a candidate for the entry point */ HnswSearchCandidate * -HnswEntryCandidate(char *base, HnswElement entryPoint, Datum q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec) +HnswEntryCandidate(char *base, HnswElement entryPoint, Datum q, Relation index, HnswSupport * support, bool loadVec) { HnswSearchCandidate *sc = palloc(sizeof(HnswSearchCandidate)); bool inMemory = index == NULL; HnswPtrStore(base, sc->element, entryPoint); if (inMemory) - sc->distance = GetElementDistance(base, entryPoint, q, procinfo, collation); + sc->distance = GetElementDistance(base, entryPoint, q, support); else - HnswLoadElement(entryPoint, &sc->distance, &q, index, procinfo, collation, loadVec, NULL); + HnswLoadElement(entryPoint, &sc->distance, &q, index, support, loadVec, NULL); return sc; } @@ -793,7 +791,7 @@ HnswLoadUnvisitedFromDisk(HnswElement element, HnswUnvisited * unvisited, int *u * Algorithm 2 from paper */ 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, HnswSupport * support, int m, bool inserting, HnswElement skipElement) { List *w = NIL; pairingheap *C = pairingheap_allocate(CompareNearestCandidates, NULL); @@ -865,7 +863,7 @@ HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, F if (inMemory) { eElement = unvisited[i].element; - eDistance = GetElementDistance(base, eElement, q, procinfo, collation); + eDistance = GetElementDistance(base, eElement, q, support); } else { @@ -875,7 +873,7 @@ HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, F /* Avoid any allocations if not adding */ eElement = NULL; - HnswLoadElementImpl(blkno, offno, &eDistance, &q, index, procinfo, collation, inserting, alwaysAdd ? NULL : &f->distance, &eElement); + HnswLoadElementImpl(blkno, offno, &eDistance, &q, index, support, inserting, alwaysAdd ? NULL : &f->distance, &eElement); if (eElement == NULL) continue; @@ -976,7 +974,7 @@ 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, FmgrInfo *procinfo, Oid collation) +CheckElementCloser(char *base, HnswCandidate * e, List *r, HnswSupport * support) { HnswElement eElement = HnswPtrAccess(base, e->element); Datum eValue = HnswGetValue(base, eElement); @@ -987,7 +985,7 @@ CheckElementCloser(char *base, HnswCandidate * e, List *r, FmgrInfo *procinfo, O HnswCandidate *ri = lfirst(lc2); HnswElement riElement = HnswPtrAccess(base, ri->element); Datum riValue = HnswGetValue(base, riElement); - float distance = HnswGetDistance(eValue, riValue, procinfo, collation); + float distance = HnswGetDistance(eValue, riValue, support); if (distance <= e->distance) return false; @@ -1000,7 +998,7 @@ CheckElementCloser(char *base, HnswCandidate * e, List *r, FmgrInfo *procinfo, O * Algorithm 4 from paper */ static List * -SelectNeighbors(char *base, List *c, int lm, FmgrInfo *procinfo, Oid collation, bool *closerSet, HnswCandidate * newCandidate, HnswCandidate * *pruned, bool sortCandidates) +SelectNeighbors(char *base, List *c, int lm, HnswSupport * support, bool *closerSet, HnswCandidate * newCandidate, HnswCandidate * *pruned, bool sortCandidates) { List *r = NIL; List *w = list_copy(c); @@ -1034,7 +1032,7 @@ SelectNeighbors(char *base, List *c, int lm, FmgrInfo *procinfo, Oid collation, /* Use previous state of r and wd to skip work when possible */ if (mustCalculate) - e->closer = CheckElementCloser(base, e, r, procinfo, collation); + e->closer = CheckElementCloser(base, e, r, support); else if (list_length(added) > 0) { /* Keep Valgrind happy for in-memory, parallel builds */ @@ -1047,7 +1045,7 @@ SelectNeighbors(char *base, List *c, int lm, FmgrInfo *procinfo, Oid collation, */ if (e->closer) { - e->closer = CheckElementCloser(base, e, added, procinfo, collation); + e->closer = CheckElementCloser(base, e, added, support); if (!e->closer) removedAny = true; @@ -1060,7 +1058,7 @@ SelectNeighbors(char *base, List *c, int lm, FmgrInfo *procinfo, Oid collation, */ if (removedAny) { - e->closer = CheckElementCloser(base, e, r, procinfo, collation); + e->closer = CheckElementCloser(base, e, r, support); if (e->closer) added = lappend(added, e); } @@ -1068,7 +1066,7 @@ SelectNeighbors(char *base, List *c, int lm, FmgrInfo *procinfo, Oid collation, } else if (e == newCandidate) { - e->closer = CheckElementCloser(base, e, r, procinfo, collation); + e->closer = CheckElementCloser(base, e, r, support); if (e->closer) added = lappend(added, e); } @@ -1119,7 +1117,7 @@ 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; @@ -1145,7 +1143,7 @@ HnswUpdateConnection(char *base, HnswNeighborArray * neighbors, HnswElement newE c = lappend(c, &neighbors->items[i]); c = lappend(c, &newHc); - SelectNeighbors(base, c, lm, procinfo, collation, &neighbors->closerSet, &newHc, &pruned, true); + SelectNeighbors(base, c, lm, support, &neighbors->closerSet, &newHc, &pruned, true); /* Should not happen */ if (pruned == NULL) @@ -1216,7 +1214,7 @@ 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) +HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, HnswSupport * support, int m, int efConstruction, bool existing) { List *ep; List *w; @@ -1235,13 +1233,13 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint return; /* Get entry point and level */ - ep = list_make1(HnswEntryCandidate(base, entryPoint, q, index, procinfo, collation, true)); + ep = list_make1(HnswEntryCandidate(base, entryPoint, q, index, support, true)); entryLevel = entryPoint->level; /* 1st phase: greedy search to insert level */ 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, support, m, true, skipElement); ep = w; } @@ -1260,7 +1258,7 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint List *lw = NIL; ListCell *lc2; - w = HnswSearchLayer(base, q, ep, efConstruction, lc, index, procinfo, collation, m, true, skipElement); + w = HnswSearchLayer(base, q, ep, efConstruction, lc, index, support, m, true, skipElement); /* Convert search candidates to candidates */ foreach(lc2, w) @@ -1284,7 +1282,7 @@ 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, procinfo, collation, &HnswGetNeighbors(base, element, lc)->closerSet, NULL, NULL, false); + neighbors = SelectNeighbors(base, lw, lm, support, &HnswGetNeighbors(base, element, lc)->closerSet, NULL, NULL, false); AddConnections(base, element, neighbors, lc); diff --git a/src/hnswvacuum.c b/src/hnswvacuum.c index 7931f85..d3cdf68 100644 --- a/src/hnswvacuum.c +++ b/src/hnswvacuum.c @@ -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); + HnswFindElementNeighbors(base, element, entryPoint, index, support, m, efConstruction, true); /* 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, index, vacuumstate->procinfo, vacuumstate->collation, true, NULL); + HnswLoadElement(highestPoint, 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, index, vacuumstate->procinfo, vacuumstate->collation, true, NULL); + HnswLoadElement(entryPoint, NULL, NULL, index, support, true, NULL); if (NeedsUpdated(vacuumstate, entryPoint)) { @@ -578,7 +578,7 @@ 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);