Compare commits

..

1 Commits

Author SHA1 Message Date
Andrew Kane
0d8cc82908 Added HnswQuery struct [skip ci] 2024-02-04 22:30:59 -08:00
15 changed files with 75 additions and 161 deletions

View File

@@ -28,7 +28,7 @@ jobs:
dev-files: true dev-files: true
- run: make - run: make
env: 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: | - run: |
export PG_CONFIG=`which pg_config` export PG_CONFIG=`which pg_config`
sudo --preserve-env=PG_CONFIG make install sudo --preserve-env=PG_CONFIG make install
@@ -49,7 +49,7 @@ jobs:
postgres-version: 14 postgres-version: 14
- run: make - run: make
env: 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 install
- run: make installcheck - run: make installcheck
- if: ${{ failure() }} - if: ${{ failure() }}
@@ -60,9 +60,7 @@ jobs:
wget -q https://github.com/postgres/postgres/archive/refs/tags/REL_14_10.tar.gz wget -q https://github.com/postgres/postgres/archive/refs/tags/REL_14_10.tar.gz
tar xf REL_14_10.tar.gz tar xf REL_14_10.tar.gz
- run: make prove_installcheck PROVE_FLAGS="-I ./postgres-REL_14_10/src/test/perl" PERL5LIB="/Users/runner/perl5/lib/perl5" - run: make prove_installcheck PROVE_FLAGS="-I ./postgres-REL_14_10/src/test/perl" PERL5LIB="/Users/runner/perl5/lib/perl5"
- run: make clean && /usr/local/opt/llvm@15/bin/scan-build --status-bugs make - run: make clean && /usr/local/opt/llvm@15/bin/scan-build --status-bugs make PG_CFLAGS="-DUSE_ASSERT_CHECKING"
env:
PG_CFLAGS: -DUSE_ASSERT_CHECKING
windows: windows:
runs-on: windows-latest runs-on: windows-latest
if: ${{ !startsWith(github.ref_name, 'mac') }} if: ${{ !startsWith(github.ref_name, 'mac') }}
@@ -99,15 +97,4 @@ jobs:
sudo -u postgres make installcheck sudo -u postgres make installcheck
sudo -u postgres make prove_installcheck sudo -u postgres make prove_installcheck
env: 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
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

View File

@@ -1,12 +1,6 @@
## 0.6.2 (unreleased) ## 0.6.1 (unreleased)
- Reduced lock contention with parallel HNSW index builds
## 0.6.1 (2024-03-04)
- Fixed error with `ANALYZE` and vectors with different dimensions - Fixed error with `ANALYZE` and vectors with different dimensions
- Fixed error with `shared_preload_libraries`
- Fixed vector subtraction being marked as commutative
## 0.6.0 (2024-01-29) ## 0.6.0 (2024-01-29)

View File

@@ -1,4 +1,4 @@
Portions Copyright (c) 1996-2024, PostgreSQL Global Development Group Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group
Portions Copyright (c) 1994, The Regents of the University of California Portions Copyright (c) 1994, The Regents of the University of California

View File

@@ -2,7 +2,7 @@
"name": "vector", "name": "vector",
"abstract": "Open-source vector similarity search for Postgres", "abstract": "Open-source vector similarity search for Postgres",
"description": "Supports L2 distance, inner product, and cosine distance", "description": "Supports L2 distance, inner product, and cosine distance",
"version": "0.6.1", "version": "0.6.0",
"maintainer": [ "maintainer": [
"Andrew Kane <andrew@ankane.org>" "Andrew Kane <andrew@ankane.org>"
], ],
@@ -20,7 +20,7 @@
"vector": { "vector": {
"file": "sql/vector.sql", "file": "sql/vector.sql",
"docfile": "README.md", "docfile": "README.md",
"version": "0.6.1", "version": "0.6.0",
"abstract": "Open-source vector similarity search for Postgres" "abstract": "Open-source vector similarity search for Postgres"
} }
}, },

View File

@@ -1,5 +1,5 @@
EXTENSION = vector EXTENSION = vector
EXTVERSION = 0.6.1 EXTVERSION = 0.6.0
MODULE_big = vector MODULE_big = vector
DATA = $(wildcard sql/*--*.sql) DATA = $(wildcard sql/*--*.sql)
@@ -71,9 +71,11 @@ PG_MAJOR ?= 16
.PHONY: docker .PHONY: docker
docker: docker:
docker build --pull --no-cache --build-arg PG_MAJOR=$(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 .PHONY: docker-release
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

@@ -1,5 +1,5 @@
EXTENSION = vector EXTENSION = vector
EXTVERSION = 0.6.1 EXTVERSION = 0.6.0
OBJS = src\hnsw.obj src\hnswbuild.obj src\hnswinsert.obj src\hnswscan.obj src\hnswutils.obj src\hnswvacuum.obj src\ivfbuild.obj src\ivfflat.obj src\ivfinsert.obj src\ivfkmeans.obj src\ivfscan.obj src\ivfutils.obj src\ivfvacuum.obj src\vector.obj OBJS = src\hnsw.obj src\hnswbuild.obj src\hnswinsert.obj src\hnswscan.obj src\hnswutils.obj src\hnswvacuum.obj src\ivfbuild.obj src\ivfflat.obj src\ivfinsert.obj src\ivfkmeans.obj src\ivfscan.obj src\ivfutils.obj src\ivfvacuum.obj src\vector.obj
HEADERS = src\vector.h HEADERS = src\vector.h

View File

@@ -20,7 +20,7 @@ Compile and install the extension (supports Postgres 12+)
```sh ```sh
cd /tmp cd /tmp
git clone --branch v0.6.1 https://github.com/pgvector/pgvector.git git clone --branch v0.6.0 https://github.com/pgvector/pgvector.git
cd pgvector cd pgvector
make make
make install # may need sudo make install # may need sudo
@@ -28,7 +28,7 @@ make install # may need sudo
See the [installation notes](#installation-notes) if you run into issues 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 ### Windows
@@ -44,7 +44,7 @@ Then use `nmake` to build:
```cmd ```cmd
set "PGROOT=C:\Program Files\PostgreSQL\16" set "PGROOT=C:\Program Files\PostgreSQL\16"
git clone --branch v0.6.1 https://github.com/pgvector/pgvector.git git clone --branch v0.6.0 https://github.com/pgvector/pgvector.git
cd pgvector cd pgvector
nmake /F Makefile.win nmake /F Makefile.win
nmake /F Makefile.win install nmake /F Makefile.win install
@@ -102,12 +102,6 @@ Insert vectors
INSERT INTO items (embedding) VALUES ('[1,2,3]'), ('[4,5,6]'); INSERT INTO items (embedding) VALUES ('[1,2,3]'), ('[4,5,6]');
``` ```
Or load vectors in bulk using `COPY` ([example](https://github.com/pgvector/pgvector-python/blob/master/examples/bulk_loading.py))
```sql
COPY items (embedding) FROM STDIN WITH (FORMAT BINARY);
```
Upsert vectors Upsert vectors
```sql ```sql
@@ -270,8 +264,6 @@ HINT: Increase maintenance_work_mem to speed up builds.
Note: Do not set `maintenance_work_mem` so high that it exhausts the memory on the server Note: Do not set `maintenance_work_mem` so high that it exhausts the memory on the server
Like other index types, its faster to create an index after loading your initial data
Starting with 0.6.0, you can also speed up index creation by increasing the number of parallel workers (2 by default) Starting with 0.6.0, you can also speed up index creation by increasing the number of parallel workers (2 by default)
```sql ```sql
@@ -581,10 +573,6 @@ or choose to store vectors inline:
ALTER TABLE items ALTER COLUMN embedding SET STORAGE PLAIN; ALTER TABLE items ALTER COLUMN embedding SET STORAGE PLAIN;
``` ```
#### Why are there less results for a query after adding an HNSW index?
Results are limited by the size of the dynamic candidate list (`hnsw.ef_search`). There may be even less results due to dead tuples or filtering conditions in the query. We recommend setting `hnsw.ef_search` to at least twice the `LIMIT` of the query. If you need more than 500 results, use an IVFFlat index instead.
#### Why are there less results for a query after adding an IVFFlat index? #### Why are there less results for a query after adding an IVFFlat index?
The index was likely created with too little data for the number of lists. Drop the index until the table has more data. The index was likely created with too little data for the number of lists. Drop the index until the table has more data.
@@ -593,8 +581,6 @@ The index was likely created with too little data for the number of lists. Drop
DROP INDEX index_name; DROP INDEX index_name;
``` ```
Results can also be limited by the number of probes (`ivfflat.probes`).
## Reference ## Reference
### Vector Type ### Vector Type
@@ -670,14 +656,6 @@ Note: Replace `16` with your Postgres server version
If compilation fails and the output includes `warning: no such sysroot directory` on Mac, reinstall Xcode Command Line Tools. If compilation fails and the output includes `warning: no such sysroot directory` on Mac, reinstall Xcode Command Line Tools.
### Portability
To compile for portability, use:
```sh
make OPTFLAGS=""
```
## Additional Installation Methods ## Additional Installation Methods
### Docker ### Docker
@@ -693,7 +671,7 @@ This adds pgvector to the [Postgres image](https://hub.docker.com/_/postgres) (r
You can also build the image manually: You can also build the image manually:
```sh ```sh
git clone --branch v0.6.1 https://github.com/pgvector/pgvector.git git clone --branch v0.6.0 https://github.com/pgvector/pgvector.git
cd pgvector cd pgvector
docker build --build-arg PG_MAJOR=16 -t myuser/pgvector . docker build --build-arg PG_MAJOR=16 -t myuser/pgvector .
``` ```
@@ -738,21 +716,6 @@ sudo dnf install pgvector_16
Note: Replace `16` with your Postgres server version 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 ### conda-forge
With Conda Postgres, install from [conda-forge](https://anaconda.org/conda-forge/pgvector) with: With Conda Postgres, install from [conda-forge](https://anaconda.org/conda-forge/pgvector) with:

View File

@@ -1,16 +0,0 @@
-- complain if script is sourced in psql, rather than via CREATE EXTENSION
\echo Use "ALTER EXTENSION vector UPDATE TO '0.6.1'" to load this file. \quit
DROP OPERATOR - (vector, vector);
CREATE OPERATOR - (
LEFTARG = vector, RIGHTARG = vector, PROCEDURE = vector_sub
);
ALTER OPERATOR <= (vector, vector) SET (
RESTRICT = scalarlesel, JOIN = scalarlejoinsel
);
ALTER OPERATOR >= (vector, vector) SET (
RESTRICT = scalargesel, JOIN = scalargejoinsel
);

View File

@@ -180,7 +180,8 @@ CREATE OPERATOR + (
); );
CREATE OPERATOR - ( CREATE OPERATOR - (
LEFTARG = vector, RIGHTARG = vector, PROCEDURE = vector_sub LEFTARG = vector, RIGHTARG = vector, PROCEDURE = vector_sub,
COMMUTATOR = -
); );
CREATE OPERATOR * ( CREATE OPERATOR * (
@@ -194,10 +195,11 @@ CREATE OPERATOR < (
RESTRICT = scalarltsel, JOIN = scalarltjoinsel RESTRICT = scalarltsel, JOIN = scalarltjoinsel
); );
-- should use scalarlesel and scalarlejoinsel, but not supported in Postgres < 11
CREATE OPERATOR <= ( CREATE OPERATOR <= (
LEFTARG = vector, RIGHTARG = vector, PROCEDURE = vector_le, LEFTARG = vector, RIGHTARG = vector, PROCEDURE = vector_le,
COMMUTATOR = >= , NEGATOR = > , COMMUTATOR = >= , NEGATOR = > ,
RESTRICT = scalarlesel, JOIN = scalarlejoinsel RESTRICT = scalarltsel, JOIN = scalarltjoinsel
); );
CREATE OPERATOR = ( CREATE OPERATOR = (
@@ -212,10 +214,11 @@ CREATE OPERATOR <> (
RESTRICT = eqsel, JOIN = eqjoinsel RESTRICT = eqsel, JOIN = eqjoinsel
); );
-- should use scalargesel and scalargejoinsel, but not supported in Postgres < 11
CREATE OPERATOR >= ( CREATE OPERATOR >= (
LEFTARG = vector, RIGHTARG = vector, PROCEDURE = vector_ge, LEFTARG = vector, RIGHTARG = vector, PROCEDURE = vector_ge,
COMMUTATOR = <= , NEGATOR = < , COMMUTATOR = <= , NEGATOR = < ,
RESTRICT = scalargesel, JOIN = scalargejoinsel RESTRICT = scalargtsel, JOIN = scalargtjoinsel
); );
CREATE OPERATOR > ( CREATE OPERATOR > (

View File

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

View File

@@ -80,7 +80,7 @@
#if PG_VERSION_NUM < 130000 #if PG_VERSION_NUM < 130000
#define list_delete_last(list) list_truncate(list, list_length(list) - 1) #define list_delete_last(list) list_truncate(list, list_length(list) - 1)
#define list_sort(list, cmp) ((list) = list_qsort(list, cmp)) #define list_sort(list, cmp) list_qsort(list, cmp)
#endif #endif
#define HnswIsElementTuple(tup) ((tup)->type == HNSW_ELEMENT_TUPLE_TYPE) #define HnswIsElementTuple(tup) ((tup)->type == HNSW_ELEMENT_TUPLE_TYPE)
@@ -185,7 +185,6 @@ typedef struct HnswGraph
/* Entry state */ /* Entry state */
LWLock entryLock; LWLock entryLock;
LWLock entryWaitLock;
HnswElementPtr entryPoint; HnswElementPtr entryPoint;
/* Allocations state */ /* Allocations state */
@@ -363,6 +362,11 @@ typedef struct HnswVacuumState
MemoryContext tmpCtx; MemoryContext tmpCtx;
} HnswVacuumState; } HnswVacuumState;
typedef struct HnswQuery
{
Datum value;
} HnswQuery;
/* Methods */ /* Methods */
int HnswGetM(Relation index); int HnswGetM(Relation index);
int HnswGetEfConstruction(Relation index); int HnswGetEfConstruction(Relation index);
@@ -371,14 +375,14 @@ bool HnswNormValue(FmgrInfo *procinfo, Oid collation, Datum *value, Vector * re
Buffer HnswNewBuffer(Relation index, ForkNumber forkNum); Buffer HnswNewBuffer(Relation index, ForkNumber forkNum);
void HnswInitPage(Buffer buf, Page page); void HnswInitPage(Buffer buf, Page page);
void HnswInit(void); void HnswInit(void);
List *HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool inserting, HnswElement skipElement); List *HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool inserting, HnswElement skipElement);
HnswElement HnswGetEntryPoint(Relation index); HnswElement HnswGetEntryPoint(Relation index);
void HnswGetMetaPageInfo(Relation index, int *m, HnswElement * entryPoint); void HnswGetMetaPageInfo(Relation index, int *m, HnswElement * entryPoint);
void *HnswAlloc(HnswAllocator * allocator, Size size); void *HnswAlloc(HnswAllocator * allocator, Size size);
HnswElement HnswInitElement(char *base, ItemPointer tid, int m, double ml, int maxLevel, HnswAllocator * alloc); HnswElement HnswInitElement(char *base, ItemPointer tid, int m, double ml, int maxLevel, HnswAllocator * alloc);
HnswElement HnswInitElementFromBlock(BlockNumber blkno, OffsetNumber offno); 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); 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); HnswCandidate *HnswEntryCandidate(char *base, HnswElement em, HnswQuery * q, Relation rel, FmgrInfo *procinfo, Oid collation, bool loadVec);
void HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, BlockNumber insertPage, ForkNumber forkNum, bool building); 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 HnswSetNeighborTuple(char *base, HnswNeighborTuple ntup, HnswElement e, int m);
void HnswAddHeapTid(HnswElement element, ItemPointer heaptid); void HnswAddHeapTid(HnswElement element, ItemPointer heaptid);
@@ -386,11 +390,10 @@ void HnswInitNeighbors(char *base, HnswElement element, int m, HnswAllocator *
bool HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull, ItemPointer heap_tid, bool building); 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, FmgrInfo *procinfo, Oid collation, 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, float *distance, Datum *q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec); void HnswLoadElement(HnswElement element, float *distance, HnswQuery * q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec);
void HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element); 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, FmgrInfo *procinfo, Oid collation);
void HnswLoadNeighbors(HnswElement element, Relation index, int m); void HnswLoadNeighbors(HnswElement element, Relation index, int m);
void HnswInitLockTranche(void);
PGDLLEXPORT void HnswParallelBuildMain(dsm_segment *seg, shm_toc *toc); PGDLLEXPORT void HnswParallelBuildMain(dsm_segment *seg, shm_toc *toc);
/* Index access methods */ /* Index access methods */

View File

@@ -176,7 +176,7 @@ CreateGraphPages(HnswBuildState * buildstate)
Size etupSize; Size etupSize;
Size ntupSize; Size ntupSize;
Size combinedSize; Size combinedSize;
Pointer valuePtr = HnswPtrAccess(base, element->value); void *valuePtr = HnswPtrAccess(base, element->value);
/* Update iterator */ /* Update iterator */
iter = element->next; iter = element->next;
@@ -431,15 +431,10 @@ InsertTupleInMemory(HnswBuildState * buildstate, HnswElement element)
HnswGraph *graph = buildstate->graph; HnswGraph *graph = buildstate->graph;
HnswElement entryPoint; HnswElement entryPoint;
LWLock *entryLock = &graph->entryLock; LWLock *entryLock = &graph->entryLock;
LWLock *entryWaitLock = &graph->entryWaitLock;
int efConstruction = buildstate->efConstruction; int efConstruction = buildstate->efConstruction;
int m = buildstate->m; int m = buildstate->m;
char *base = buildstate->hnswarea; char *base = buildstate->hnswarea;
/* Wait if another process needs exclusive lock */
LWLockAcquire(entryWaitLock, LW_EXCLUSIVE);
LWLockRelease(entryWaitLock);
/* Get entry point */ /* Get entry point */
LWLockAcquire(entryLock, LW_SHARED); LWLockAcquire(entryLock, LW_SHARED);
entryPoint = HnswPtrAccess(base, graph->entryPoint); entryPoint = HnswPtrAccess(base, graph->entryPoint);
@@ -451,9 +446,7 @@ InsertTupleInMemory(HnswBuildState * buildstate, HnswElement element)
LWLockRelease(entryLock); LWLockRelease(entryLock);
/* Get exclusive lock */ /* Get exclusive lock */
LWLockAcquire(entryWaitLock, LW_EXCLUSIVE);
LWLockAcquire(entryLock, LW_EXCLUSIVE); LWLockAcquire(entryLock, LW_EXCLUSIVE);
LWLockRelease(entryWaitLock);
/* Get latest entry point after lock is acquired */ /* Get latest entry point after lock is acquired */
entryPoint = HnswPtrAccess(base, graph->entryPoint); entryPoint = HnswPtrAccess(base, graph->entryPoint);
@@ -608,9 +601,6 @@ BuildCallback(Relation index, CALLBACK_ITEM_POINTER, Datum *values,
static void static void
InitGraph(HnswGraph * graph, char *base, long memoryTotal) InitGraph(HnswGraph * graph, char *base, long memoryTotal)
{ {
/* Initialize the lock tranche if needed */
HnswInitLockTranche();
HnswPtrStore(base, graph->head, (HnswElement) NULL); HnswPtrStore(base, graph->head, (HnswElement) NULL);
HnswPtrStore(base, graph->entryPoint, (HnswElement) NULL); HnswPtrStore(base, graph->entryPoint, (HnswElement) NULL);
graph->memoryUsed = 0; graph->memoryUsed = 0;
@@ -619,7 +609,6 @@ InitGraph(HnswGraph * graph, char *base, long memoryTotal)
graph->indtuples = 0; graph->indtuples = 0;
SpinLockInit(&graph->lock); SpinLockInit(&graph->lock);
LWLockInitialize(&graph->entryLock, hnsw_lock_tranche_id); LWLockInitialize(&graph->entryLock, hnsw_lock_tranche_id);
LWLockInitialize(&graph->entryWaitLock, hnsw_lock_tranche_id);
LWLockInitialize(&graph->allocatorLock, hnsw_lock_tranche_id); LWLockInitialize(&graph->allocatorLock, hnsw_lock_tranche_id);
LWLockInitialize(&graph->flushLock, hnsw_lock_tranche_id); LWLockInitialize(&graph->flushLock, hnsw_lock_tranche_id);
} }
@@ -985,14 +974,6 @@ HnswBeginParallel(HnswBuildState * buildstate, bool isconcurrent, int request)
/* Report less than allocated so never fails */ /* Report less than allocated so never fails */
InitGraph(&hnswshared->graphData, hnswarea, esthnswarea - 1024 * 1024); 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_SHARED, hnswshared);
shm_toc_insert(pcxt->toc, PARALLEL_KEY_HNSW_AREA, hnswarea); shm_toc_insert(pcxt->toc, PARALLEL_KEY_HNSW_AREA, hnswarea);

View File

@@ -11,7 +11,7 @@
* Algorithm 5 from paper * Algorithm 5 from paper
*/ */
static List * static List *
GetScanItems(IndexScanDesc scan, Datum q) GetScanItems(IndexScanDesc scan, Datum value)
{ {
HnswScanOpaque so = (HnswScanOpaque) scan->opaque; HnswScanOpaque so = (HnswScanOpaque) scan->opaque;
Relation index = scan->indexRelation; Relation index = scan->indexRelation;
@@ -22,6 +22,9 @@ GetScanItems(IndexScanDesc scan, Datum q)
int m; int m;
HnswElement entryPoint; HnswElement entryPoint;
char *base = NULL; char *base = NULL;
HnswQuery q;
q.value = value;
/* Get m and entry point */ /* Get m and entry point */
HnswGetMetaPageInfo(index, &m, &entryPoint); HnswGetMetaPageInfo(index, &m, &entryPoint);
@@ -29,15 +32,15 @@ GetScanItems(IndexScanDesc scan, Datum q)
if (entryPoint == NULL) if (entryPoint == NULL)
return NIL; return NIL;
ep = list_make1(HnswEntryCandidate(base, entryPoint, q, index, procinfo, collation, false)); ep = list_make1(HnswEntryCandidate(base, entryPoint, &q, index, procinfo, collation, false));
for (int lc = entryPoint->level; lc >= 1; lc--) for (int lc = entryPoint->level; lc >= 1; lc--)
{ {
w = HnswSearchLayer(base, q, ep, 1, lc, index, procinfo, collation, m, false, NULL); w = HnswSearchLayer(base, &q, ep, 1, lc, index, procinfo, collation, m, false, NULL);
ep = w; ep = w;
} }
return HnswSearchLayer(base, q, ep, hnsw_ef_search, 0, index, procinfo, collation, m, false, NULL); return HnswSearchLayer(base, &q, ep, hnsw_ef_search, 0, index, procinfo, collation, m, false, NULL);
} }
/* /*

View File

@@ -555,7 +555,7 @@ HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHe
* Load an element and optionally get its distance from q * Load an element and optionally get its distance from q
*/ */
void void
HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec) HnswLoadElement(HnswElement element, float *distance, HnswQuery * q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec)
{ {
Buffer buf; Buffer buf;
Page page; Page page;
@@ -575,7 +575,7 @@ HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation index,
/* Calculate distance */ /* Calculate distance */
if (distance != NULL) if (distance != NULL)
*distance = (float) DatumGetFloat8(FunctionCall2Coll(procinfo, collation, *q, PointerGetDatum(&etup->data))); *distance = (float) DatumGetFloat8(FunctionCall2Coll(procinfo, collation, q->value, PointerGetDatum(&etup->data)));
UnlockReleaseBuffer(buf); UnlockReleaseBuffer(buf);
} }
@@ -584,19 +584,19 @@ HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation index,
* Get the distance for a candidate * Get the distance for a candidate
*/ */
static float static float
GetCandidateDistance(char *base, HnswCandidate * hc, Datum q, FmgrInfo *procinfo, Oid collation) GetCandidateDistance(char *base, HnswCandidate * hc, HnswQuery * q, FmgrInfo *procinfo, Oid collation)
{ {
HnswElement hce = HnswPtrAccess(base, hc->element); HnswElement hce = HnswPtrAccess(base, hc->element);
Datum value = HnswGetValue(base, hce); Datum value = HnswGetValue(base, hce);
return DatumGetFloat8(FunctionCall2Coll(procinfo, collation, q, value)); return DatumGetFloat8(FunctionCall2Coll(procinfo, collation, q->value, value));
} }
/* /*
* Create a candidate for the entry point * Create a candidate for the entry point
*/ */
HnswCandidate * HnswCandidate *
HnswEntryCandidate(char *base, HnswElement entryPoint, Datum q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec) HnswEntryCandidate(char *base, HnswElement entryPoint, HnswQuery * q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec)
{ {
HnswCandidate *hc = palloc(sizeof(HnswCandidate)); HnswCandidate *hc = palloc(sizeof(HnswCandidate));
@@ -604,7 +604,7 @@ HnswEntryCandidate(char *base, HnswElement entryPoint, Datum q, Relation index,
if (index == NULL) if (index == NULL)
hc->distance = GetCandidateDistance(base, hc, q, procinfo, collation); hc->distance = GetCandidateDistance(base, hc, q, procinfo, collation);
else else
HnswLoadElement(entryPoint, &hc->distance, &q, index, procinfo, collation, loadVec); HnswLoadElement(entryPoint, &hc->distance, q, index, procinfo, collation, loadVec);
return hc; return hc;
} }
@@ -722,7 +722,7 @@ CountElement(char *base, HnswElement skipElement, HnswCandidate * hc)
* Algorithm 2 from paper * Algorithm 2 from paper
*/ */
List * List *
HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool inserting, HnswElement skipElement) HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool inserting, HnswElement skipElement)
{ {
List *w = NIL; List *w = NIL;
pairingheap *C = pairingheap_allocate(CompareNearestCandidates, NULL); pairingheap *C = pairingheap_allocate(CompareNearestCandidates, NULL);
@@ -806,7 +806,7 @@ HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, F
if (index == NULL) if (index == NULL)
eDistance = GetCandidateDistance(base, e, q, procinfo, collation); eDistance = GetCandidateDistance(base, e, q, procinfo, collation);
else else
HnswLoadElement(eElement, &eDistance, &q, index, procinfo, collation, inserting); HnswLoadElement(eElement, &eDistance, q, index, procinfo, collation, inserting);
Assert(!eElement->deleted); Assert(!eElement->deleted);
@@ -860,15 +860,12 @@ HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, F
static int static int
#if PG_VERSION_NUM >= 130000 #if PG_VERSION_NUM >= 130000
CompareCandidateDistances(const ListCell *a, const ListCell *b) CompareCandidateDistances(const ListCell *a, const ListCell *b)
{
HnswCandidate *hca = lfirst(a);
HnswCandidate *hcb = lfirst(b);
#else #else
CompareCandidateDistances(const void *a, const void *b) CompareCandidateDistances(const void *a, const void *b)
{
HnswCandidate *hca = lfirst(*(ListCell **) a);
HnswCandidate *hcb = lfirst(*(ListCell **) b);
#endif #endif
{
HnswCandidate *hca = lfirst((ListCell *) a);
HnswCandidate *hcb = lfirst((ListCell *) b);
if (hca->distance < hcb->distance) if (hca->distance < hcb->distance)
return 1; return 1;
@@ -891,15 +888,12 @@ CompareCandidateDistances(const void *a, const void *b)
static int static int
#if PG_VERSION_NUM >= 130000 #if PG_VERSION_NUM >= 130000
CompareCandidateDistancesOffset(const ListCell *a, const ListCell *b) CompareCandidateDistancesOffset(const ListCell *a, const ListCell *b)
{
HnswCandidate *hca = lfirst(a);
HnswCandidate *hcb = lfirst(b);
#else #else
CompareCandidateDistancesOffset(const void *a, const void *b) CompareCandidateDistancesOffset(const void *a, const void *b)
{
HnswCandidate *hca = lfirst(*(ListCell **) a);
HnswCandidate *hcb = lfirst(*(ListCell **) b);
#endif #endif
{
HnswCandidate *hca = lfirst((ListCell *) a);
HnswCandidate *hcb = lfirst((ListCell *) b);
if (hca->distance < hcb->distance) if (hca->distance < hcb->distance)
return 1; return 1;
@@ -958,9 +952,7 @@ SelectNeighbors(char *base, List *c, int lm, int lc, FmgrInfo *procinfo, Oid col
{ {
List *r = NIL; List *r = NIL;
List *w = list_copy(c); List *w = list_copy(c);
HnswCandidate **wd; pairingheap *wd;
int wdlen = 0;
int wdoff = 0;
HnswNeighborArray *neighbors = HnswGetNeighbors(base, e2, lc); HnswNeighborArray *neighbors = HnswGetNeighbors(base, e2, lc);
bool mustCalculate = !neighbors->closerSet; bool mustCalculate = !neighbors->closerSet;
List *added = NIL; List *added = NIL;
@@ -969,7 +961,7 @@ SelectNeighbors(char *base, List *c, int lm, int lc, FmgrInfo *procinfo, Oid col
if (list_length(w) <= lm) if (list_length(w) <= lm)
return w; return w;
wd = palloc(sizeof(HnswCandidate *) * list_length(w)); wd = pairingheap_allocate(CompareNearestCandidates, NULL);
/* Ensure order of candidates is deterministic for closer caching */ /* Ensure order of candidates is deterministic for closer caching */
if (sortCandidates) if (sortCandidates)
@@ -1035,21 +1027,21 @@ SelectNeighbors(char *base, List *c, int lm, int lc, FmgrInfo *procinfo, Oid col
if (e->closer) if (e->closer)
r = lappend(r, e); r = lappend(r, e);
else else
wd[wdlen++] = e; pairingheap_add(wd, &(CreatePairingHeapNode(e)->ph_node));
} }
/* Cached value can only be used in future if sorted deterministically */ /* Cached value can only be used in future if sorted deterministically */
neighbors->closerSet = sortCandidates; neighbors->closerSet = sortCandidates;
/* Keep pruned connections */ /* Keep pruned connections */
while (wdoff < wdlen && list_length(r) < lm) while (!pairingheap_is_empty(wd) && list_length(r) < lm)
r = lappend(r, wd[wdoff++]); r = lappend(r, ((HnswPairingHeapNode *) pairingheap_remove_first(wd))->inner);
/* Return pruned for update connections */ /* Return pruned for update connections */
if (pruned != NULL) if (pruned != NULL)
{ {
if (wdoff < wdlen) if (!pairingheap_is_empty(wd))
*pruned = wd[wdoff]; *pruned = ((HnswPairingHeapNode *) pairingheap_first(wd))->inner;
else else
*pruned = linitial(w); *pruned = linitial(w);
} }
@@ -1099,7 +1091,9 @@ HnswUpdateConnection(char *base, HnswElement element, HnswCandidate * hc, int lm
/* Load elements on insert */ /* Load elements on insert */
if (index != NULL) if (index != NULL)
{ {
Datum q = HnswGetValue(base, hce); HnswQuery q;
q.value = HnswGetValue(base, hce);
for (int i = 0; i < currentNeighbors->length; i++) for (int i = 0; i < currentNeighbors->length; i++)
{ {
@@ -1109,7 +1103,7 @@ HnswUpdateConnection(char *base, HnswElement element, HnswCandidate * hc, int lm
if (HnswPtrIsNull(base, hc3Element->value)) if (HnswPtrIsNull(base, hc3Element->value))
HnswLoadElement(hc3Element, &hc3->distance, &q, index, procinfo, collation, true); HnswLoadElement(hc3Element, &hc3->distance, &q, index, procinfo, collation, true);
else else
hc3->distance = GetCandidateDistance(base, hc3, q, procinfo, collation); hc3->distance = GetCandidateDistance(base, hc3, &q, procinfo, collation);
/* Prune element if being deleted */ /* Prune element if being deleted */
if (hc3Element->heaptidsLength == 0) if (hc3Element->heaptidsLength == 0)
@@ -1209,9 +1203,11 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
List *w; List *w;
int level = element->level; int level = element->level;
int entryLevel; int entryLevel;
Datum q = HnswGetValue(base, element); HnswQuery q;
HnswElement skipElement = existing ? element : NULL; HnswElement skipElement = existing ? element : NULL;
q.value = HnswGetValue(base, element);
#if PG_VERSION_NUM >= 130000 #if PG_VERSION_NUM >= 130000
/* Precompute hash */ /* Precompute hash */
if (index == NULL) if (index == NULL)
@@ -1223,13 +1219,13 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
return; return;
/* Get entry point and level */ /* Get entry point and level */
ep = list_make1(HnswEntryCandidate(base, entryPoint, q, index, procinfo, collation, true)); ep = list_make1(HnswEntryCandidate(base, entryPoint, &q, index, procinfo, collation, true));
entryLevel = entryPoint->level; entryLevel = entryPoint->level;
/* 1st phase: greedy search to insert level */ /* 1st phase: greedy search to insert level */
for (int lc = entryLevel; lc >= level + 1; lc--) for (int lc = entryLevel; lc >= level + 1; lc--)
{ {
w = HnswSearchLayer(base, q, ep, 1, lc, index, procinfo, collation, m, true, skipElement); w = HnswSearchLayer(base, &q, ep, 1, lc, index, procinfo, collation, m, true, skipElement);
ep = w; ep = w;
} }
@@ -1247,7 +1243,7 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
List *neighbors; List *neighbors;
List *lw; List *lw;
w = HnswSearchLayer(base, q, ep, efConstruction, lc, index, procinfo, collation, m, true, skipElement); w = HnswSearchLayer(base, &q, ep, efConstruction, lc, index, procinfo, collation, m, true, skipElement);
/* Elements being deleted or skipped can help with search */ /* Elements being deleted or skipped can help with search */
/* but should be removed before selecting neighbors */ /* but should be removed before selecting neighbors */

View File

@@ -1,4 +1,4 @@
comment = 'vector data type and ivfflat and hnsw access methods' comment = 'vector data type and ivfflat and hnsw access methods'
default_version = '0.6.1' default_version = '0.6.0'
module_pathname = '$libdir/vector' module_pathname = '$libdir/vector'
relocatable = true relocatable = true