Compare commits

..

1 Commits

Author SHA1 Message Date
Andrew Kane
eb9fa5cf8c Added HnswSupport struct [skip ci] 2024-02-04 23:28:32 -08:00
12 changed files with 92 additions and 141 deletions

View File

@@ -28,7 +28,7 @@ jobs:
dev-files: true
- run: make
env:
PG_CFLAGS: -DUSE_ASSERT_CHECKING -Wall -Wextra -Werror -Wno-unused-parameter -Wno-sign-compare
PG_CFLAGS: -Wall -Wextra -Werror -Wno-unused-parameter -Wno-sign-compare
- run: |
export PG_CONFIG=`which pg_config`
sudo --preserve-env=PG_CONFIG make install
@@ -49,7 +49,7 @@ jobs:
postgres-version: 14
- run: make
env:
PG_CFLAGS: -DUSE_ASSERT_CHECKING -Wall -Wextra -Werror -Wno-unused-parameter
PG_CFLAGS: -Wall -Wextra -Werror -Wno-unused-parameter
- run: make install
- run: make installcheck
- if: ${{ failure() }}
@@ -97,15 +97,4 @@ jobs:
sudo -u postgres make installcheck
sudo -u postgres make prove_installcheck
env:
PG_CFLAGS: -DUSE_ASSERT_CHECKING -Wall -Wextra -Werror -Wno-unused-parameter -Wno-sign-compare
valgrind:
if: ${{ !startsWith(github.ref_name, 'mac') && !startsWith(github.ref_name, 'windows') }}
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: ankane/setup-postgres-valgrind@v1
with:
postgres-version: 16
- run: make
- run: sudo --preserve-env=PG_CONFIG make install
- run: make installcheck
PG_CFLAGS: -Wall -Wextra -Werror -Wno-unused-parameter -Wno-sign-compare

View File

@@ -1,7 +1,6 @@
## 0.6.1 (unreleased)
- Fixed error with `ANALYZE` and vectors with different dimensions
- Fixed error with `shared_preload_libraries`
## 0.6.0 (2024-01-29)

View File

@@ -71,9 +71,11 @@ PG_MAJOR ?= 16
.PHONY: docker
docker:
docker build --pull --no-cache --build-arg PG_MAJOR=$(PG_MAJOR) -t pgvector/pgvector:pg$(PG_MAJOR) -t pgvector/pgvector:$(EXTVERSION)-pg$(PG_MAJOR) .
docker build --pull --no-cache --build-arg PG_MAJOR=$(PG_MAJOR) -t pgvector/pgvector:pg$(PG_MAJOR) .
docker build --build-arg PG_MAJOR=$(PG_MAJOR) -t pgvector/pgvector:$(EXTVERSION)-pg$(PG_MAJOR) .
.PHONY: docker-release
docker-release:
docker buildx build --push --pull --no-cache --platform linux/amd64,linux/arm64 --build-arg PG_MAJOR=$(PG_MAJOR) -t pgvector/pgvector:pg$(PG_MAJOR) -t pgvector/pgvector:$(EXTVERSION)-pg$(PG_MAJOR) .
docker buildx build --push --pull --no-cache --platform linux/amd64,linux/arm64 --build-arg PG_MAJOR=$(PG_MAJOR) -t pgvector/pgvector:pg$(PG_MAJOR) .
docker buildx build --push --platform linux/amd64,linux/arm64 --build-arg PG_MAJOR=$(PG_MAJOR) -t pgvector/pgvector:$(EXTVERSION)-pg$(PG_MAJOR) .

View File

@@ -28,7 +28,7 @@ make install # may need sudo
See the [installation notes](#installation-notes) if you run into issues
You can also install it with [Docker](#docker), [Homebrew](#homebrew), [PGXN](#pgxn), [APT](#apt), [Yum](#yum), [pkg](#pkg), or [conda-forge](#conda-forge), and it comes preinstalled with [Postgres.app](#postgresapp) and many [hosted providers](#hosted-postgres). There are also instructions for [GitHub Actions](https://github.com/pgvector/setup-pgvector).
You can also install it with [Docker](#docker), [Homebrew](#homebrew), [PGXN](#pgxn), [APT](#apt), [Yum](#yum), or [conda-forge](#conda-forge), and it comes preinstalled with [Postgres.app](#postgresapp) and many [hosted providers](#hosted-postgres). There are also instructions for [GitHub Actions](https://github.com/pgvector/setup-pgvector).
### Windows
@@ -716,21 +716,6 @@ sudo dnf install pgvector_16
Note: Replace `16` with your Postgres server version
### pkg
Install the FreeBSD package with:
```sh
pkg install postgresql15-pg_vector
```
or the port with:
```sh
cd /usr/ports/databases/pgvector
make install
```
### conda-forge
With Conda Postgres, install from [conda-forge](https://anaconda.org/conda-forge/pgvector) with:

View File

@@ -8,7 +8,6 @@
#include "commands/progress.h"
#include "commands/vacuum.h"
#include "hnsw.h"
#include "miscadmin.h"
#include "utils/guc.h"
#include "utils/selfuncs.h"
@@ -29,7 +28,7 @@ static relopt_kind hnsw_relopt_kind;
* this grows bigger, we should use a shmem_request_hook and
* RequestAddinShmemSpace() to pre-reserve space for this.
*/
void
static void
HnswInitLockTranche(void)
{
int *tranche_ids;
@@ -54,8 +53,7 @@ HnswInitLockTranche(void)
void
HnswInit(void)
{
if (!process_shared_preload_libraries_in_progress)
HnswInitLockTranche();
HnswInitLockTranche();
hnsw_relopt_kind = add_reloption_kind();
add_int_reloption(hnsw_relopt_kind, "m", "Max number of connections",

View File

@@ -234,6 +234,12 @@ typedef struct HnswAllocator
void *state;
} HnswAllocator;
typedef struct HnswSupport
{
FmgrInfo *procinfo;
Oid collation;
} HnswSupport;
typedef struct HnswBuildState
{
/* Info */
@@ -252,7 +258,7 @@ typedef struct HnswBuildState
double reltuples;
/* Support functions */
FmgrInfo *procinfo;
HnswSupport support;
FmgrInfo *normprocinfo;
Oid collation;
@@ -329,7 +335,7 @@ typedef struct HnswScanOpaqueData
MemoryContext tmpCtx;
/* Support functions */
FmgrInfo *procinfo;
HnswSupport support;
FmgrInfo *normprocinfo;
Oid collation;
} HnswScanOpaqueData;
@@ -349,8 +355,7 @@ typedef struct HnswVacuumState
int efConstruction;
/* Support functions */
FmgrInfo *procinfo;
Oid collation;
HnswSupport support;
/* Variables */
struct tidhash_hash *deleted;
@@ -366,30 +371,30 @@ typedef struct HnswVacuumState
int HnswGetM(Relation index);
int HnswGetEfConstruction(Relation index);
FmgrInfo *HnswOptionalProcInfo(Relation index, uint16 procnum);
void HnswInitSupport(HnswSupport * support, Relation index);
bool HnswNormValue(FmgrInfo *procinfo, Oid collation, Datum *value, Vector * result);
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);
HnswCandidate *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);
HnswCandidate *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);
void HnswInitNeighbors(char *base, HnswElement element, int m, HnswAllocator * alloc);
bool HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull, ItemPointer heap_tid, bool building);
void HnswUpdateNeighborsOnDisk(Relation index, FmgrInfo *procinfo, Oid collation, 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 HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec);
void HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation index, HnswSupport * support, bool loadVec);
void HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element);
void HnswUpdateConnection(char *base, HnswElement element, HnswCandidate * hc, int lm, int lc, int *updateIdx, Relation index, FmgrInfo *procinfo, Oid collation);
void HnswUpdateConnection(char *base, HnswElement element, HnswCandidate * hc, int lm, int lc, int *updateIdx, Relation index, HnswSupport * support);
void HnswLoadNeighbors(HnswElement element, Relation index, int m);
void HnswInitLockTranche(void);
PGDLLEXPORT void HnswParallelBuildMain(dsm_segment *seg, shm_toc *toc);
/* Index access methods */

View File

@@ -176,7 +176,7 @@ CreateGraphPages(HnswBuildState * buildstate)
Size etupSize;
Size ntupSize;
Size combinedSize;
Pointer valuePtr = HnswPtrAccess(base, element->value);
void *valuePtr = HnswPtrAccess(base, element->value);
/* Update iterator */
iter = element->next;
@@ -373,7 +373,7 @@ 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--)
{
@@ -390,7 +390,7 @@ UpdateNeighborsInMemory(char *base, FmgrInfo *procinfo, Oid collation, HnswEleme
/* Use element for lock instead of hc since hc can be replaced */
LWLockAcquire(&neighborElement->lock, LW_EXCLUSIVE);
HnswUpdateConnection(base, e, hc, lm, lc, NULL, NULL, procinfo, collation);
HnswUpdateConnection(base, e, hc, lm, lc, NULL, NULL, support);
LWLockRelease(&neighborElement->lock);
}
}
@@ -400,7 +400,7 @@ 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;
@@ -413,7 +413,7 @@ 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)
@@ -426,8 +426,6 @@ 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;
HnswElement entryPoint;
LWLock *entryLock = &graph->entryLock;
@@ -453,10 +451,10 @@ InsertTupleInMemory(HnswBuildState * buildstate, HnswElement element)
}
/* Find neighbors for element */
HnswFindElementNeighbors(base, element, entryPoint, NULL, procinfo, collation, m, efConstruction, false);
HnswFindElementNeighbors(base, element, entryPoint, NULL, &buildstate->support, m, efConstruction, false);
/* Update graph in memory */
UpdateGraphInMemory(procinfo, collation, element, m, efConstruction, entryPoint, buildstate);
UpdateGraphInMemory(&buildstate->support, element, m, efConstruction, entryPoint, buildstate);
/* Release entry lock */
LWLockRelease(entryLock);
@@ -601,9 +599,6 @@ BuildCallback(Relation index, CALLBACK_ITEM_POINTER, Datum *values,
static void
InitGraph(HnswGraph * graph, char *base, long memoryTotal)
{
/* Initialize the lock tranche if needed */
HnswInitLockTranche();
HnswPtrStore(base, graph->head, (HnswElement) NULL);
HnswPtrStore(base, graph->entryPoint, (HnswElement) NULL);
graph->memoryUsed = 0;
@@ -686,7 +681,7 @@ InitBuildState(HnswBuildState * buildstate, Relation heap, Relation index, Index
buildstate->indtuples = 0;
/* Get support functions */
buildstate->procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
HnswInitSupport(&buildstate->support, index);
buildstate->normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
buildstate->collation = index->rd_indcollation[0];
@@ -977,14 +972,6 @@ HnswBeginParallel(HnswBuildState * buildstate, bool isconcurrent, int request)
/* Report less than allocated so never fails */
InitGraph(&hnswshared->graphData, hnswarea, esthnswarea - 1024 * 1024);
/*
* Avoid base address for relptr for Postgres < 14.5
* https://github.com/postgres/postgres/commit/7201cd18627afc64850537806da7f22150d1a83b
*/
#if PG_VERSION_NUM < 140005
hnswshared->graphData.memoryUsed += MAXALIGN(1);
#endif
shm_toc_insert(pcxt->toc, PARALLEL_KEY_HNSW_SHARED, hnswshared);
shm_toc_insert(pcxt->toc, PARALLEL_KEY_HNSW_AREA, hnswarea);

View File

@@ -340,7 +340,7 @@ ConnectionExists(HnswElement e, HnswNeighborTuple ntup, int startIdx, int lm)
* 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;
@@ -373,7 +373,7 @@ HnswUpdateNeighborsOnDisk(Relation index, FmgrInfo *procinfo, Oid collation, Hns
*/
/* Select neighbors */
HnswUpdateConnection(NULL, e, hc, lm, lc, &idx, index, procinfo, collation);
HnswUpdateConnection(NULL, e, hc, lm, lc, &idx, index, support);
/* New element was not selected as a neighbor */
if (idx == -1)
@@ -527,7 +527,7 @@ 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;
@@ -543,7 +543,7 @@ 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)
@@ -560,10 +560,11 @@ HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull,
HnswElement element;
int m;
int efConstruction = HnswGetEfConstruction(index);
FmgrInfo *procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
Oid collation = index->rd_indcollation[0];
LOCKMODE lockmode = ShareLock;
char *base = NULL;
HnswSupport support;
HnswInitSupport(&support, index);
/*
* Get a shared lock. This allows vacuum to ensure no in-flight inserts
@@ -594,10 +595,10 @@ HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull,
}
/* 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);

View File

@@ -15,8 +15,6 @@ GetScanItems(IndexScanDesc scan, Datum q)
{
HnswScanOpaque so = (HnswScanOpaque) scan->opaque;
Relation index = scan->indexRelation;
FmgrInfo *procinfo = so->procinfo;
Oid collation = so->collation;
List *ep;
List *w;
int m;
@@ -29,15 +27,15 @@ 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, &so->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, &so->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, &so->support, m, false, NULL);
}
/*
@@ -108,7 +106,7 @@ hnswbeginscan(Relation index, int nkeys, int norderbys)
ALLOCSET_DEFAULT_SIZES);
/* Set support functions */
so->procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
HnswInitSupport(&so->support, index);
so->normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
so->collation = index->rd_indcollation[0];

View File

@@ -149,6 +149,16 @@ HnswOptionalProcInfo(Relation index, uint16 procnum)
return index_getprocinfo(index, 1, procnum);
}
/*
* Init support function
*/
void
HnswInitSupport(HnswSupport * support, Relation index)
{
support->procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
support->collation = index->rd_indcollation[0];
}
/*
* Divide by the norm
*
@@ -555,7 +565,7 @@ HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHe
* Load an element and optionally get its distance from q
*/
void
HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec)
HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation index, HnswSupport * support, bool loadVec)
{
Buffer buf;
Page page;
@@ -575,7 +585,7 @@ HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation index,
/* Calculate distance */
if (distance != NULL)
*distance = (float) DatumGetFloat8(FunctionCall2Coll(procinfo, collation, *q, PointerGetDatum(&etup->data)));
*distance = (float) DatumGetFloat8(FunctionCall2Coll(support->procinfo, support->collation, *q, PointerGetDatum(&etup->data)));
UnlockReleaseBuffer(buf);
}
@@ -584,27 +594,27 @@ HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation index,
* Get the distance for a candidate
*/
static float
GetCandidateDistance(char *base, HnswCandidate * hc, Datum q, FmgrInfo *procinfo, Oid collation)
GetCandidateDistance(char *base, HnswCandidate * hc, Datum q, HnswSupport * support)
{
HnswElement hce = HnswPtrAccess(base, hc->element);
Datum value = HnswGetValue(base, hce);
return DatumGetFloat8(FunctionCall2Coll(procinfo, collation, q, value));
return DatumGetFloat8(FunctionCall2Coll(support->procinfo, support->collation, q, value));
}
/*
* Create a candidate for the entry point
*/
HnswCandidate *
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)
{
HnswCandidate *hc = palloc(sizeof(HnswCandidate));
HnswPtrStore(base, hc->element, entryPoint);
if (index == NULL)
hc->distance = GetCandidateDistance(base, hc, q, procinfo, collation);
hc->distance = GetCandidateDistance(base, hc, q, support);
else
HnswLoadElement(entryPoint, &hc->distance, &q, index, procinfo, collation, loadVec);
HnswLoadElement(entryPoint, &hc->distance, &q, index, support, loadVec);
return hc;
}
@@ -722,7 +732,7 @@ CountElement(char *base, HnswElement skipElement, HnswCandidate * hc)
* 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);
@@ -804,9 +814,9 @@ HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, F
f = ((HnswPairingHeapNode *) pairingheap_first(W))->inner;
if (index == NULL)
eDistance = GetCandidateDistance(base, e, q, procinfo, collation);
eDistance = GetCandidateDistance(base, e, q, support);
else
HnswLoadElement(eElement, &eDistance, &q, index, procinfo, collation, inserting);
HnswLoadElement(eElement, &eDistance, &q, index, support, inserting);
Assert(!eElement->deleted);
@@ -914,19 +924,19 @@ CompareCandidateDistancesOffset(const void *a, const void *b)
* Calculate the distance between elements
*/
static float
HnswGetDistance(char *base, HnswElement a, HnswElement b, FmgrInfo *procinfo, Oid collation)
HnswGetDistance(char *base, HnswElement a, HnswElement b, HnswSupport * support)
{
Datum aValue = HnswGetValue(base, a);
Datum bValue = HnswGetValue(base, b);
return DatumGetFloat8(FunctionCall2Coll(procinfo, collation, aValue, bValue));
return DatumGetFloat8(FunctionCall2Coll(support->procinfo, support->collation, aValue, bValue));
}
/*
* 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);
ListCell *lc2;
@@ -935,7 +945,7 @@ CheckElementCloser(char *base, HnswCandidate * e, List *r, FmgrInfo *procinfo, O
{
HnswCandidate *ri = lfirst(lc2);
HnswElement riElement = HnswPtrAccess(base, ri->element);
float distance = HnswGetDistance(base, eElement, riElement, procinfo, collation);
float distance = HnswGetDistance(base, eElement, riElement, support);
if (distance <= e->distance)
return false;
@@ -948,7 +958,7 @@ CheckElementCloser(char *base, HnswCandidate * e, List *r, FmgrInfo *procinfo, O
* Algorithm 4 from paper
*/
static List *
SelectNeighbors(char *base, List *c, int lm, int lc, FmgrInfo *procinfo, Oid collation, HnswElement e2, HnswCandidate * newCandidate, HnswCandidate * *pruned, bool sortCandidates)
SelectNeighbors(char *base, List *c, int lm, int lc, HnswSupport * support, HnswElement e2, HnswCandidate * newCandidate, HnswCandidate * *pruned, bool sortCandidates)
{
List *r = NIL;
List *w = list_copy(c);
@@ -981,7 +991,7 @@ SelectNeighbors(char *base, List *c, int lm, int lc, FmgrInfo *procinfo, Oid col
/* 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 */
@@ -994,7 +1004,7 @@ SelectNeighbors(char *base, List *c, int lm, int lc, FmgrInfo *procinfo, Oid col
*/
if (e->closer)
{
e->closer = CheckElementCloser(base, e, added, procinfo, collation);
e->closer = CheckElementCloser(base, e, added, support);
if (!e->closer)
removedAny = true;
@@ -1007,7 +1017,7 @@ SelectNeighbors(char *base, List *c, int lm, int lc, FmgrInfo *procinfo, Oid col
*/
if (removedAny)
{
e->closer = CheckElementCloser(base, e, r, procinfo, collation);
e->closer = CheckElementCloser(base, e, r, support);
if (e->closer)
added = lappend(added, e);
}
@@ -1015,7 +1025,7 @@ SelectNeighbors(char *base, List *c, int lm, int lc, FmgrInfo *procinfo, Oid col
}
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);
}
@@ -1066,7 +1076,7 @@ AddConnections(char *base, HnswElement element, List *neighbors, int lc)
* Update connections
*/
void
HnswUpdateConnection(char *base, HnswElement element, HnswCandidate * hc, int lm, int lc, int *updateIdx, Relation index, FmgrInfo *procinfo, Oid collation)
HnswUpdateConnection(char *base, HnswElement element, HnswCandidate * hc, int lm, int lc, int *updateIdx, Relation index, HnswSupport * support)
{
HnswElement hce = HnswPtrAccess(base, hc->element);
HnswNeighborArray *currentNeighbors = HnswGetNeighbors(base, hce, lc);
@@ -1099,9 +1109,9 @@ HnswUpdateConnection(char *base, HnswElement element, HnswCandidate * hc, int lm
HnswElement hc3Element = HnswPtrAccess(base, hc3->element);
if (HnswPtrIsNull(base, hc3Element->value))
HnswLoadElement(hc3Element, &hc3->distance, &q, index, procinfo, collation, true);
HnswLoadElement(hc3Element, &hc3->distance, &q, index, support, true);
else
hc3->distance = GetCandidateDistance(base, hc3, q, procinfo, collation);
hc3->distance = GetCandidateDistance(base, hc3, q, support);
/* Prune element if being deleted */
if (hc3Element->heaptidsLength == 0)
@@ -1121,7 +1131,7 @@ HnswUpdateConnection(char *base, HnswElement element, HnswCandidate * hc, int lm
c = lappend(c, &currentNeighbors->items[i]);
c = lappend(c, &hc2);
SelectNeighbors(base, c, lm, lc, procinfo, collation, hce, &hc2, &pruned, true);
SelectNeighbors(base, c, lm, lc, support, hce, &hc2, &pruned, true);
/* Should not happen */
if (pruned == NULL)
@@ -1195,7 +1205,7 @@ 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;
@@ -1215,13 +1225,13 @@ 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;
}
@@ -1239,7 +1249,7 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
List *neighbors;
List *lw;
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);
/* Elements being deleted or skipped can help with search */
/* but should be removed before selecting neighbors */
@@ -1253,7 +1263,7 @@ 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, lc, procinfo, collation, element, NULL, NULL, false);
neighbors = SelectNeighbors(base, lw, lm, lc, support, element, NULL, NULL, false);
AddConnections(base, element, neighbors, lc);

View File

@@ -189,8 +189,6 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
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 +203,7 @@ 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, &vacuumstate->support, m, efConstruction, true);
/* Zero memory for each element */
MemSet(ntup, 0, HNSW_TUPLE_ALLOC_SIZE);
@@ -229,7 +227,7 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
UnlockReleaseBuffer(buf);
/* Update neighbors */
HnswUpdateNeighborsOnDisk(index, procinfo, collation, element, m, true, false);
HnswUpdateNeighborsOnDisk(index, &vacuumstate->support, element, m, true, false);
}
/*
@@ -256,7 +254,7 @@ RepairGraphEntryPoint(HnswVacuumState * vacuumstate)
LockPage(index, HNSW_UPDATE_LOCK, ShareLock);
/* Load element */
HnswLoadElement(highestPoint, NULL, NULL, index, vacuumstate->procinfo, vacuumstate->collation, true);
HnswLoadElement(highestPoint, NULL, NULL, index, &vacuumstate->support, true);
/* Repair if needed */
if (NeedsUpdated(vacuumstate, highestPoint))
@@ -294,7 +292,7 @@ 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);
HnswLoadElement(entryPoint, NULL, NULL, index, &vacuumstate->support, true);
if (NeedsUpdated(vacuumstate, entryPoint))
{
@@ -573,8 +571,8 @@ InitVacuumState(HnswVacuumState * vacuumstate, IndexVacuumInfo *info, IndexBulkD
vacuumstate->callback_state = callback_state;
vacuumstate->efConstruction = HnswGetEfConstruction(index);
vacuumstate->bas = GetAccessStrategy(BAS_BULKREAD);
vacuumstate->procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
vacuumstate->collation = index->rd_indcollation[0];
vacuumstate->support.procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
vacuumstate->support.collation = index->rd_indcollation[0];
vacuumstate->ntup = palloc0(HNSW_TUPLE_ALLOC_SIZE);
vacuumstate->tmpCtx = AllocSetContextCreate(CurrentMemoryContext,
"Hnsw vacuum temporary context",

View File

@@ -904,27 +904,6 @@ IvfflatBeginParallel(IvfflatBuildState * buildstate, bool isconcurrent, int requ
WaitForParallelWorkersToAttach(pcxt);
}
/*
* Compute parallel workers
*/
static int
ComputeParallelWorkers(Relation heap, Relation index)
{
int parallel_workers;
/* Make sure it's safe to use parallel workers */
parallel_workers = plan_create_index_workers(RelationGetRelid(heap), RelationGetRelid(index));
if (parallel_workers == 0)
return 0;
/* Use parallel_workers storage parameter on table if set */
parallel_workers = RelationGetParallelWorkers(heap, -1);
if (parallel_workers != -1)
return Min(parallel_workers, max_parallel_maintenance_workers);
return max_parallel_maintenance_workers;
}
/*
* Scan table for tuples to index
*/
@@ -944,7 +923,7 @@ AssignTuples(IvfflatBuildState * buildstate)
/* Calculate parallel workers */
if (buildstate->heap != NULL)
parallel_workers = ComputeParallelWorkers(buildstate->heap, buildstate->index);
parallel_workers = plan_create_index_workers(RelationGetRelid(buildstate->heap), RelationGetRelid(buildstate->index));
/* Attempt to launch parallel worker scan when required */
if (parallel_workers > 0)