mirror of
https://github.com/pgvector/pgvector.git
synced 2026-07-22 12:07:34 +08:00
Compare commits
30 Commits
hnsw-suppo
...
v0.6.1
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
c6ddf62a29 | ||
|
|
801be04d8b | ||
|
|
587e9ba97c | ||
|
|
d57047a935 | ||
|
|
f1db1f17e3 | ||
|
|
2f48c0fac4 | ||
|
|
84a8aa8176 | ||
|
|
f64ebbef50 | ||
|
|
ac8156509b | ||
|
|
82bf69b479 | ||
|
|
4be2f57916 | ||
|
|
91e3d2905f | ||
|
|
fe2406564f | ||
|
|
fa52511eaa | ||
|
|
447ef4d27a | ||
|
|
b36cd22ccc | ||
|
|
b447ae4989 | ||
|
|
efed873a3e | ||
|
|
14b278dec9 | ||
|
|
133a728e48 | ||
|
|
ca10cbaa7d | ||
|
|
eb29019a14 | ||
|
|
334c386a45 | ||
|
|
1cbd204f52 | ||
|
|
5ba62fca84 | ||
|
|
22cb2a3fe7 | ||
|
|
72b144906a | ||
|
|
a618c1bc78 | ||
|
|
f43cd0ed98 | ||
|
|
51df640961 |
21
.github/workflows/build.yml
vendored
21
.github/workflows/build.yml
vendored
@@ -28,7 +28,7 @@ jobs:
|
|||||||
dev-files: true
|
dev-files: true
|
||||||
- run: make
|
- run: make
|
||||||
env:
|
env:
|
||||||
PG_CFLAGS: -Wall -Wextra -Werror -Wno-unused-parameter -Wno-sign-compare
|
PG_CFLAGS: -DUSE_ASSERT_CHECKING -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: -Wall -Wextra -Werror -Wno-unused-parameter
|
PG_CFLAGS: -DUSE_ASSERT_CHECKING -Wall -Wextra -Werror -Wno-unused-parameter
|
||||||
- run: make install
|
- run: make install
|
||||||
- run: make installcheck
|
- run: make installcheck
|
||||||
- if: ${{ failure() }}
|
- if: ${{ failure() }}
|
||||||
@@ -60,7 +60,9 @@ 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 PG_CFLAGS="-DUSE_ASSERT_CHECKING"
|
- run: make clean && /usr/local/opt/llvm@15/bin/scan-build --status-bugs make
|
||||||
|
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') }}
|
||||||
@@ -97,4 +99,15 @@ 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: -Wall -Wextra -Werror -Wno-unused-parameter -Wno-sign-compare
|
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
|
||||||
|
|||||||
@@ -1,6 +1,8 @@
|
|||||||
## 0.6.1 (unreleased)
|
## 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)
|
||||||
|
|
||||||
|
|||||||
2
LICENSE
2
LICENSE
@@ -1,4 +1,4 @@
|
|||||||
Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group
|
Portions Copyright (c) 1996-2024, 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
|
||||||
|
|
||||||
|
|||||||
@@ -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": "0.6.0",
|
"version": "0.6.1",
|
||||||
"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": "0.6.0",
|
"version": "0.6.1",
|
||||||
"abstract": "Open-source vector similarity search for Postgres"
|
"abstract": "Open-source vector similarity search for Postgres"
|
||||||
}
|
}
|
||||||
},
|
},
|
||||||
|
|||||||
8
Makefile
8
Makefile
@@ -1,5 +1,5 @@
|
|||||||
EXTENSION = vector
|
EXTENSION = vector
|
||||||
EXTVERSION = 0.6.0
|
EXTVERSION = 0.6.1
|
||||||
|
|
||||||
MODULE_big = vector
|
MODULE_big = vector
|
||||||
DATA = $(wildcard sql/*--*.sql)
|
DATA = $(wildcard sql/*--*.sql)
|
||||||
@@ -71,11 +71,9 @@ PG_MAJOR ?= 16
|
|||||||
.PHONY: docker
|
.PHONY: docker
|
||||||
|
|
||||||
docker:
|
docker:
|
||||||
docker build --pull --no-cache --build-arg PG_MAJOR=$(PG_MAJOR) -t pgvector/pgvector:pg$(PG_MAJOR) .
|
docker build --pull --no-cache --build-arg PG_MAJOR=$(PG_MAJOR) -t pgvector/pgvector:pg$(PG_MAJOR) -t pgvector/pgvector:$(EXTVERSION)-pg$(PG_MAJOR) .
|
||||||
docker build --build-arg PG_MAJOR=$(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) .
|
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 --platform linux/amd64,linux/arm64 --build-arg PG_MAJOR=$(PG_MAJOR) -t pgvector/pgvector:$(EXTVERSION)-pg$(PG_MAJOR) .
|
|
||||||
|
|||||||
@@ -1,5 +1,5 @@
|
|||||||
EXTENSION = vector
|
EXTENSION = vector
|
||||||
EXTVERSION = 0.6.0
|
EXTVERSION = 0.6.1
|
||||||
|
|
||||||
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
|
||||||
|
|||||||
39
README.md
39
README.md
@@ -20,7 +20,7 @@ Compile and install the extension (supports Postgres 12+)
|
|||||||
|
|
||||||
```sh
|
```sh
|
||||||
cd /tmp
|
cd /tmp
|
||||||
git clone --branch v0.6.0 https://github.com/pgvector/pgvector.git
|
git clone --branch v0.6.1 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), 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), [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).
|
||||||
|
|
||||||
### 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 v0.6.0 https://github.com/pgvector/pgvector.git
|
git clone --branch v0.6.1 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
|
||||||
@@ -102,6 +102,12 @@ 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
|
||||||
@@ -264,6 +270,8 @@ 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, it’s 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
|
||||||
@@ -656,6 +664,14 @@ 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
|
||||||
@@ -671,7 +687,7 @@ 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 v0.6.0 https://github.com/pgvector/pgvector.git
|
git clone --branch v0.6.1 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 .
|
||||||
```
|
```
|
||||||
@@ -716,6 +732,21 @@ 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:
|
||||||
|
|||||||
16
sql/vector--0.6.0--0.6.1.sql
Normal file
16
sql/vector--0.6.0--0.6.1.sql
Normal file
@@ -0,0 +1,16 @@
|
|||||||
|
-- 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
|
||||||
|
);
|
||||||
@@ -180,8 +180,7 @@ 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 * (
|
||||||
@@ -195,11 +194,10 @@ 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 = scalarltsel, JOIN = scalarltjoinsel
|
RESTRICT = scalarlesel, JOIN = scalarlejoinsel
|
||||||
);
|
);
|
||||||
|
|
||||||
CREATE OPERATOR = (
|
CREATE OPERATOR = (
|
||||||
@@ -214,11 +212,10 @@ 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 = scalargtsel, JOIN = scalargtjoinsel
|
RESTRICT = scalargesel, JOIN = scalargejoinsel
|
||||||
);
|
);
|
||||||
|
|
||||||
CREATE OPERATOR > (
|
CREATE OPERATOR > (
|
||||||
|
|||||||
@@ -8,6 +8,7 @@
|
|||||||
#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"
|
||||||
|
|
||||||
@@ -28,7 +29,7 @@ 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.
|
||||||
*/
|
*/
|
||||||
static void
|
void
|
||||||
HnswInitLockTranche(void)
|
HnswInitLockTranche(void)
|
||||||
{
|
{
|
||||||
int *tranche_ids;
|
int *tranche_ids;
|
||||||
@@ -53,6 +54,7 @@ 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();
|
||||||
|
|||||||
29
src/hnsw.h
29
src/hnsw.h
@@ -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_qsort(list, cmp)
|
#define list_sort(list, cmp) ((list) = list_qsort(list, cmp))
|
||||||
#endif
|
#endif
|
||||||
|
|
||||||
#define HnswIsElementTuple(tup) ((tup)->type == HNSW_ELEMENT_TUPLE_TYPE)
|
#define HnswIsElementTuple(tup) ((tup)->type == HNSW_ELEMENT_TUPLE_TYPE)
|
||||||
@@ -234,12 +234,6 @@ typedef struct HnswAllocator
|
|||||||
void *state;
|
void *state;
|
||||||
} HnswAllocator;
|
} HnswAllocator;
|
||||||
|
|
||||||
typedef struct HnswSupport
|
|
||||||
{
|
|
||||||
FmgrInfo *procinfo;
|
|
||||||
Oid collation;
|
|
||||||
} HnswSupport;
|
|
||||||
|
|
||||||
typedef struct HnswBuildState
|
typedef struct HnswBuildState
|
||||||
{
|
{
|
||||||
/* Info */
|
/* Info */
|
||||||
@@ -258,7 +252,7 @@ typedef struct HnswBuildState
|
|||||||
double reltuples;
|
double reltuples;
|
||||||
|
|
||||||
/* Support functions */
|
/* Support functions */
|
||||||
HnswSupport support;
|
FmgrInfo *procinfo;
|
||||||
FmgrInfo *normprocinfo;
|
FmgrInfo *normprocinfo;
|
||||||
Oid collation;
|
Oid collation;
|
||||||
|
|
||||||
@@ -335,7 +329,7 @@ typedef struct HnswScanOpaqueData
|
|||||||
MemoryContext tmpCtx;
|
MemoryContext tmpCtx;
|
||||||
|
|
||||||
/* Support functions */
|
/* Support functions */
|
||||||
HnswSupport support;
|
FmgrInfo *procinfo;
|
||||||
FmgrInfo *normprocinfo;
|
FmgrInfo *normprocinfo;
|
||||||
Oid collation;
|
Oid collation;
|
||||||
} HnswScanOpaqueData;
|
} HnswScanOpaqueData;
|
||||||
@@ -355,7 +349,8 @@ typedef struct HnswVacuumState
|
|||||||
int efConstruction;
|
int efConstruction;
|
||||||
|
|
||||||
/* Support functions */
|
/* Support functions */
|
||||||
HnswSupport support;
|
FmgrInfo *procinfo;
|
||||||
|
Oid collation;
|
||||||
|
|
||||||
/* Variables */
|
/* Variables */
|
||||||
struct tidhash_hash *deleted;
|
struct tidhash_hash *deleted;
|
||||||
@@ -371,30 +366,30 @@ typedef struct HnswVacuumState
|
|||||||
int HnswGetM(Relation index);
|
int HnswGetM(Relation index);
|
||||||
int HnswGetEfConstruction(Relation index);
|
int HnswGetEfConstruction(Relation index);
|
||||||
FmgrInfo *HnswOptionalProcInfo(Relation index, uint16 procnum);
|
FmgrInfo *HnswOptionalProcInfo(Relation index, uint16 procnum);
|
||||||
void HnswInitSupport(HnswSupport * support, Relation index);
|
|
||||||
bool HnswNormValue(FmgrInfo *procinfo, Oid collation, Datum *value, Vector * result);
|
bool HnswNormValue(FmgrInfo *procinfo, Oid collation, Datum *value, Vector * result);
|
||||||
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, HnswSupport * support, int m, bool inserting, HnswElement skipElement);
|
List *HnswSearchLayer(char *base, Datum 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, HnswSupport * support, 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, HnswSupport * support, bool loadVec);
|
HnswCandidate *HnswEntryCandidate(char *base, HnswElement em, Datum 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);
|
||||||
void HnswInitNeighbors(char *base, HnswElement element, int m, HnswAllocator * alloc);
|
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);
|
bool HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull, ItemPointer heap_tid, bool building);
|
||||||
void HnswUpdateNeighborsOnDisk(Relation index, HnswSupport * support, 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, HnswSupport * support, bool loadVec);
|
void HnswLoadElement(HnswElement element, float *distance, Datum *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, HnswSupport * support);
|
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 */
|
||||||
|
|||||||
@@ -176,7 +176,7 @@ CreateGraphPages(HnswBuildState * buildstate)
|
|||||||
Size etupSize;
|
Size etupSize;
|
||||||
Size ntupSize;
|
Size ntupSize;
|
||||||
Size combinedSize;
|
Size combinedSize;
|
||||||
void *valuePtr = HnswPtrAccess(base, element->value);
|
Pointer valuePtr = HnswPtrAccess(base, element->value);
|
||||||
|
|
||||||
/* Update iterator */
|
/* Update iterator */
|
||||||
iter = element->next;
|
iter = element->next;
|
||||||
@@ -373,7 +373,7 @@ AddElementInMemory(char *base, HnswGraph * graph, HnswElement element)
|
|||||||
* Update neighbors
|
* Update neighbors
|
||||||
*/
|
*/
|
||||||
static void
|
static void
|
||||||
UpdateNeighborsInMemory(char *base, HnswSupport * support, HnswElement e, int m)
|
UpdateNeighborsInMemory(char *base, FmgrInfo *procinfo, Oid collation, HnswElement e, int m)
|
||||||
{
|
{
|
||||||
for (int lc = e->level; lc >= 0; lc--)
|
for (int lc = e->level; lc >= 0; lc--)
|
||||||
{
|
{
|
||||||
@@ -390,7 +390,7 @@ UpdateNeighborsInMemory(char *base, HnswSupport * support, HnswElement e, int m)
|
|||||||
|
|
||||||
/* Use element for lock instead of hc since hc can be replaced */
|
/* Use element for lock instead of hc since hc can be replaced */
|
||||||
LWLockAcquire(&neighborElement->lock, LW_EXCLUSIVE);
|
LWLockAcquire(&neighborElement->lock, LW_EXCLUSIVE);
|
||||||
HnswUpdateConnection(base, e, hc, lm, lc, NULL, NULL, support);
|
HnswUpdateConnection(base, e, hc, lm, lc, NULL, NULL, procinfo, collation);
|
||||||
LWLockRelease(&neighborElement->lock);
|
LWLockRelease(&neighborElement->lock);
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
@@ -400,7 +400,7 @@ UpdateNeighborsInMemory(char *base, HnswSupport * support, HnswElement e, int m)
|
|||||||
* Update graph in memory
|
* Update graph in memory
|
||||||
*/
|
*/
|
||||||
static void
|
static void
|
||||||
UpdateGraphInMemory(HnswSupport * support, HnswElement element, int m, int efConstruction, HnswElement entryPoint, HnswBuildState * buildstate)
|
UpdateGraphInMemory(FmgrInfo *procinfo, Oid collation, HnswElement element, int m, int efConstruction, HnswElement entryPoint, HnswBuildState * buildstate)
|
||||||
{
|
{
|
||||||
HnswGraph *graph = buildstate->graph;
|
HnswGraph *graph = buildstate->graph;
|
||||||
char *base = buildstate->hnswarea;
|
char *base = buildstate->hnswarea;
|
||||||
@@ -413,7 +413,7 @@ UpdateGraphInMemory(HnswSupport * support, HnswElement element, int m, int efCon
|
|||||||
AddElementInMemory(base, graph, element);
|
AddElementInMemory(base, graph, element);
|
||||||
|
|
||||||
/* Update neighbors */
|
/* Update neighbors */
|
||||||
UpdateNeighborsInMemory(base, support, element, m);
|
UpdateNeighborsInMemory(base, procinfo, collation, element, m);
|
||||||
|
|
||||||
/* Update entry point if needed (already have lock) */
|
/* Update entry point if needed (already have lock) */
|
||||||
if (entryPoint == NULL || element->level > entryPoint->level)
|
if (entryPoint == NULL || element->level > entryPoint->level)
|
||||||
@@ -426,6 +426,8 @@ UpdateGraphInMemory(HnswSupport * support, HnswElement element, int m, int efCon
|
|||||||
static void
|
static void
|
||||||
InsertTupleInMemory(HnswBuildState * buildstate, HnswElement element)
|
InsertTupleInMemory(HnswBuildState * buildstate, HnswElement element)
|
||||||
{
|
{
|
||||||
|
FmgrInfo *procinfo = buildstate->procinfo;
|
||||||
|
Oid collation = buildstate->collation;
|
||||||
HnswGraph *graph = buildstate->graph;
|
HnswGraph *graph = buildstate->graph;
|
||||||
HnswElement entryPoint;
|
HnswElement entryPoint;
|
||||||
LWLock *entryLock = &graph->entryLock;
|
LWLock *entryLock = &graph->entryLock;
|
||||||
@@ -451,10 +453,10 @@ InsertTupleInMemory(HnswBuildState * buildstate, HnswElement element)
|
|||||||
}
|
}
|
||||||
|
|
||||||
/* Find neighbors for element */
|
/* Find neighbors for element */
|
||||||
HnswFindElementNeighbors(base, element, entryPoint, NULL, &buildstate->support, m, efConstruction, false);
|
HnswFindElementNeighbors(base, element, entryPoint, NULL, procinfo, collation, m, efConstruction, false);
|
||||||
|
|
||||||
/* Update graph in memory */
|
/* Update graph in memory */
|
||||||
UpdateGraphInMemory(&buildstate->support, element, m, efConstruction, entryPoint, buildstate);
|
UpdateGraphInMemory(procinfo, collation, element, m, efConstruction, entryPoint, buildstate);
|
||||||
|
|
||||||
/* Release entry lock */
|
/* Release entry lock */
|
||||||
LWLockRelease(entryLock);
|
LWLockRelease(entryLock);
|
||||||
@@ -599,6 +601,9 @@ 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;
|
||||||
@@ -681,7 +686,7 @@ InitBuildState(HnswBuildState * buildstate, Relation heap, Relation index, Index
|
|||||||
buildstate->indtuples = 0;
|
buildstate->indtuples = 0;
|
||||||
|
|
||||||
/* Get support functions */
|
/* Get support functions */
|
||||||
HnswInitSupport(&buildstate->support, index);
|
buildstate->procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
|
||||||
buildstate->normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
|
buildstate->normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
|
||||||
buildstate->collation = index->rd_indcollation[0];
|
buildstate->collation = index->rd_indcollation[0];
|
||||||
|
|
||||||
@@ -972,6 +977,14 @@ 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);
|
||||||
|
|
||||||
|
|||||||
@@ -340,7 +340,7 @@ ConnectionExists(HnswElement e, HnswNeighborTuple ntup, int startIdx, int lm)
|
|||||||
* Update neighbors
|
* Update neighbors
|
||||||
*/
|
*/
|
||||||
void
|
void
|
||||||
HnswUpdateNeighborsOnDisk(Relation index, HnswSupport * support, HnswElement e, int m, bool checkExisting, bool building)
|
HnswUpdateNeighborsOnDisk(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement e, int m, bool checkExisting, bool building)
|
||||||
{
|
{
|
||||||
char *base = NULL;
|
char *base = NULL;
|
||||||
|
|
||||||
@@ -373,7 +373,7 @@ HnswUpdateNeighborsOnDisk(Relation index, HnswSupport * support, HnswElement e,
|
|||||||
*/
|
*/
|
||||||
|
|
||||||
/* Select neighbors */
|
/* Select neighbors */
|
||||||
HnswUpdateConnection(NULL, e, hc, lm, lc, &idx, index, support);
|
HnswUpdateConnection(NULL, e, hc, lm, lc, &idx, index, procinfo, collation);
|
||||||
|
|
||||||
/* New element was not selected as a neighbor */
|
/* New element was not selected as a neighbor */
|
||||||
if (idx == -1)
|
if (idx == -1)
|
||||||
@@ -527,7 +527,7 @@ FindDuplicateOnDisk(Relation index, HnswElement element, bool building)
|
|||||||
* Update graph on disk
|
* Update graph on disk
|
||||||
*/
|
*/
|
||||||
static void
|
static void
|
||||||
UpdateGraphOnDisk(Relation index, HnswSupport * support, HnswElement element, int m, int efConstruction, HnswElement entryPoint, bool building)
|
UpdateGraphOnDisk(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement element, int m, int efConstruction, HnswElement entryPoint, bool building)
|
||||||
{
|
{
|
||||||
BlockNumber newInsertPage = InvalidBlockNumber;
|
BlockNumber newInsertPage = InvalidBlockNumber;
|
||||||
|
|
||||||
@@ -543,7 +543,7 @@ UpdateGraphOnDisk(Relation index, HnswSupport * support, HnswElement element, in
|
|||||||
HnswUpdateMetaPage(index, 0, NULL, newInsertPage, MAIN_FORKNUM, building);
|
HnswUpdateMetaPage(index, 0, NULL, newInsertPage, MAIN_FORKNUM, building);
|
||||||
|
|
||||||
/* Update neighbors */
|
/* Update neighbors */
|
||||||
HnswUpdateNeighborsOnDisk(index, support, element, m, false, building);
|
HnswUpdateNeighborsOnDisk(index, procinfo, collation, element, m, false, building);
|
||||||
|
|
||||||
/* Update entry point if needed */
|
/* Update entry point if needed */
|
||||||
if (entryPoint == NULL || element->level > entryPoint->level)
|
if (entryPoint == NULL || element->level > entryPoint->level)
|
||||||
@@ -560,11 +560,10 @@ HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull,
|
|||||||
HnswElement element;
|
HnswElement element;
|
||||||
int m;
|
int m;
|
||||||
int efConstruction = HnswGetEfConstruction(index);
|
int efConstruction = HnswGetEfConstruction(index);
|
||||||
|
FmgrInfo *procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
|
||||||
|
Oid collation = index->rd_indcollation[0];
|
||||||
LOCKMODE lockmode = ShareLock;
|
LOCKMODE lockmode = ShareLock;
|
||||||
char *base = NULL;
|
char *base = NULL;
|
||||||
HnswSupport support;
|
|
||||||
|
|
||||||
HnswInitSupport(&support, index);
|
|
||||||
|
|
||||||
/*
|
/*
|
||||||
* Get a shared lock. This allows vacuum to ensure no in-flight inserts
|
* Get a shared lock. This allows vacuum to ensure no in-flight inserts
|
||||||
@@ -595,10 +594,10 @@ HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull,
|
|||||||
}
|
}
|
||||||
|
|
||||||
/* Find neighbors for element */
|
/* Find neighbors for element */
|
||||||
HnswFindElementNeighbors(base, element, entryPoint, index, &support, m, efConstruction, false);
|
HnswFindElementNeighbors(base, element, entryPoint, index, procinfo, collation, m, efConstruction, false);
|
||||||
|
|
||||||
/* Update graph on disk */
|
/* Update graph on disk */
|
||||||
UpdateGraphOnDisk(index, &support, element, m, efConstruction, entryPoint, building);
|
UpdateGraphOnDisk(index, procinfo, collation, element, m, efConstruction, entryPoint, building);
|
||||||
|
|
||||||
/* Release lock */
|
/* Release lock */
|
||||||
UnlockPage(index, HNSW_UPDATE_LOCK, lockmode);
|
UnlockPage(index, HNSW_UPDATE_LOCK, lockmode);
|
||||||
|
|||||||
@@ -15,6 +15,8 @@ GetScanItems(IndexScanDesc scan, Datum q)
|
|||||||
{
|
{
|
||||||
HnswScanOpaque so = (HnswScanOpaque) scan->opaque;
|
HnswScanOpaque so = (HnswScanOpaque) scan->opaque;
|
||||||
Relation index = scan->indexRelation;
|
Relation index = scan->indexRelation;
|
||||||
|
FmgrInfo *procinfo = so->procinfo;
|
||||||
|
Oid collation = so->collation;
|
||||||
List *ep;
|
List *ep;
|
||||||
List *w;
|
List *w;
|
||||||
int m;
|
int m;
|
||||||
@@ -27,15 +29,15 @@ GetScanItems(IndexScanDesc scan, Datum q)
|
|||||||
if (entryPoint == NULL)
|
if (entryPoint == NULL)
|
||||||
return NIL;
|
return NIL;
|
||||||
|
|
||||||
ep = list_make1(HnswEntryCandidate(base, entryPoint, q, index, &so->support, 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, &so->support, 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, &so->support, m, false, NULL);
|
return HnswSearchLayer(base, q, ep, hnsw_ef_search, 0, index, procinfo, collation, m, false, NULL);
|
||||||
}
|
}
|
||||||
|
|
||||||
/*
|
/*
|
||||||
@@ -106,7 +108,7 @@ hnswbeginscan(Relation index, int nkeys, int norderbys)
|
|||||||
ALLOCSET_DEFAULT_SIZES);
|
ALLOCSET_DEFAULT_SIZES);
|
||||||
|
|
||||||
/* Set support functions */
|
/* Set support functions */
|
||||||
HnswInitSupport(&so->support, index);
|
so->procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
|
||||||
so->normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
|
so->normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
|
||||||
so->collation = index->rd_indcollation[0];
|
so->collation = index->rd_indcollation[0];
|
||||||
|
|
||||||
|
|||||||
100
src/hnswutils.c
100
src/hnswutils.c
@@ -149,16 +149,6 @@ HnswOptionalProcInfo(Relation index, uint16 procnum)
|
|||||||
return index_getprocinfo(index, 1, 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
|
* Divide by the norm
|
||||||
*
|
*
|
||||||
@@ -565,7 +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, HnswSupport * support, bool loadVec)
|
HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec)
|
||||||
{
|
{
|
||||||
Buffer buf;
|
Buffer buf;
|
||||||
Page page;
|
Page page;
|
||||||
@@ -585,7 +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(support->procinfo, support->collation, *q, PointerGetDatum(&etup->data)));
|
*distance = (float) DatumGetFloat8(FunctionCall2Coll(procinfo, collation, *q, PointerGetDatum(&etup->data)));
|
||||||
|
|
||||||
UnlockReleaseBuffer(buf);
|
UnlockReleaseBuffer(buf);
|
||||||
}
|
}
|
||||||
@@ -594,27 +584,27 @@ 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, HnswSupport * support)
|
GetCandidateDistance(char *base, HnswCandidate * hc, Datum 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(support->procinfo, support->collation, q, value));
|
return DatumGetFloat8(FunctionCall2Coll(procinfo, collation, q, 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, HnswSupport * support, bool loadVec)
|
HnswEntryCandidate(char *base, HnswElement entryPoint, Datum q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec)
|
||||||
{
|
{
|
||||||
HnswCandidate *hc = palloc(sizeof(HnswCandidate));
|
HnswCandidate *hc = palloc(sizeof(HnswCandidate));
|
||||||
|
|
||||||
HnswPtrStore(base, hc->element, entryPoint);
|
HnswPtrStore(base, hc->element, entryPoint);
|
||||||
if (index == NULL)
|
if (index == NULL)
|
||||||
hc->distance = GetCandidateDistance(base, hc, q, support);
|
hc->distance = GetCandidateDistance(base, hc, q, procinfo, collation);
|
||||||
else
|
else
|
||||||
HnswLoadElement(entryPoint, &hc->distance, &q, index, support, loadVec);
|
HnswLoadElement(entryPoint, &hc->distance, &q, index, procinfo, collation, loadVec);
|
||||||
return hc;
|
return hc;
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -732,7 +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, HnswSupport * support, int m, bool inserting, HnswElement skipElement)
|
HnswSearchLayer(char *base, Datum 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);
|
||||||
@@ -814,9 +804,9 @@ HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, H
|
|||||||
f = ((HnswPairingHeapNode *) pairingheap_first(W))->inner;
|
f = ((HnswPairingHeapNode *) pairingheap_first(W))->inner;
|
||||||
|
|
||||||
if (index == NULL)
|
if (index == NULL)
|
||||||
eDistance = GetCandidateDistance(base, e, q, support);
|
eDistance = GetCandidateDistance(base, e, q, procinfo, collation);
|
||||||
else
|
else
|
||||||
HnswLoadElement(eElement, &eDistance, &q, index, support, inserting);
|
HnswLoadElement(eElement, &eDistance, &q, index, procinfo, collation, inserting);
|
||||||
|
|
||||||
Assert(!eElement->deleted);
|
Assert(!eElement->deleted);
|
||||||
|
|
||||||
@@ -870,12 +860,15 @@ HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, H
|
|||||||
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)
|
||||||
#endif
|
|
||||||
{
|
{
|
||||||
HnswCandidate *hca = lfirst((ListCell *) a);
|
HnswCandidate *hca = lfirst(*(ListCell **) a);
|
||||||
HnswCandidate *hcb = lfirst((ListCell *) b);
|
HnswCandidate *hcb = lfirst(*(ListCell **) b);
|
||||||
|
#endif
|
||||||
|
|
||||||
if (hca->distance < hcb->distance)
|
if (hca->distance < hcb->distance)
|
||||||
return 1;
|
return 1;
|
||||||
@@ -898,12 +891,15 @@ 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)
|
||||||
#endif
|
|
||||||
{
|
{
|
||||||
HnswCandidate *hca = lfirst((ListCell *) a);
|
HnswCandidate *hca = lfirst(*(ListCell **) a);
|
||||||
HnswCandidate *hcb = lfirst((ListCell *) b);
|
HnswCandidate *hcb = lfirst(*(ListCell **) b);
|
||||||
|
#endif
|
||||||
|
|
||||||
if (hca->distance < hcb->distance)
|
if (hca->distance < hcb->distance)
|
||||||
return 1;
|
return 1;
|
||||||
@@ -924,19 +920,19 @@ CompareCandidateDistancesOffset(const void *a, const void *b)
|
|||||||
* Calculate the distance between elements
|
* Calculate the distance between elements
|
||||||
*/
|
*/
|
||||||
static float
|
static float
|
||||||
HnswGetDistance(char *base, HnswElement a, HnswElement b, HnswSupport * support)
|
HnswGetDistance(char *base, HnswElement a, HnswElement b, FmgrInfo *procinfo, Oid collation)
|
||||||
{
|
{
|
||||||
Datum aValue = HnswGetValue(base, a);
|
Datum aValue = HnswGetValue(base, a);
|
||||||
Datum bValue = HnswGetValue(base, b);
|
Datum bValue = HnswGetValue(base, b);
|
||||||
|
|
||||||
return DatumGetFloat8(FunctionCall2Coll(support->procinfo, support->collation, aValue, bValue));
|
return DatumGetFloat8(FunctionCall2Coll(procinfo, collation, aValue, bValue));
|
||||||
}
|
}
|
||||||
|
|
||||||
/*
|
/*
|
||||||
* Check if an element is closer to q than any element from R
|
* Check if an element is closer to q than any element from R
|
||||||
*/
|
*/
|
||||||
static bool
|
static bool
|
||||||
CheckElementCloser(char *base, HnswCandidate * e, List *r, HnswSupport * support)
|
CheckElementCloser(char *base, HnswCandidate * e, List *r, FmgrInfo *procinfo, Oid collation)
|
||||||
{
|
{
|
||||||
HnswElement eElement = HnswPtrAccess(base, e->element);
|
HnswElement eElement = HnswPtrAccess(base, e->element);
|
||||||
ListCell *lc2;
|
ListCell *lc2;
|
||||||
@@ -945,7 +941,7 @@ CheckElementCloser(char *base, HnswCandidate * e, List *r, HnswSupport * support
|
|||||||
{
|
{
|
||||||
HnswCandidate *ri = lfirst(lc2);
|
HnswCandidate *ri = lfirst(lc2);
|
||||||
HnswElement riElement = HnswPtrAccess(base, ri->element);
|
HnswElement riElement = HnswPtrAccess(base, ri->element);
|
||||||
float distance = HnswGetDistance(base, eElement, riElement, support);
|
float distance = HnswGetDistance(base, eElement, riElement, procinfo, collation);
|
||||||
|
|
||||||
if (distance <= e->distance)
|
if (distance <= e->distance)
|
||||||
return false;
|
return false;
|
||||||
@@ -958,11 +954,13 @@ CheckElementCloser(char *base, HnswCandidate * e, List *r, HnswSupport * support
|
|||||||
* Algorithm 4 from paper
|
* Algorithm 4 from paper
|
||||||
*/
|
*/
|
||||||
static List *
|
static List *
|
||||||
SelectNeighbors(char *base, List *c, int lm, int lc, HnswSupport * support, HnswElement e2, HnswCandidate * newCandidate, HnswCandidate * *pruned, bool sortCandidates)
|
SelectNeighbors(char *base, List *c, int lm, int lc, FmgrInfo *procinfo, Oid collation, HnswElement e2, HnswCandidate * newCandidate, HnswCandidate * *pruned, bool sortCandidates)
|
||||||
{
|
{
|
||||||
List *r = NIL;
|
List *r = NIL;
|
||||||
List *w = list_copy(c);
|
List *w = list_copy(c);
|
||||||
pairingheap *wd;
|
HnswCandidate **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;
|
||||||
@@ -971,7 +969,7 @@ SelectNeighbors(char *base, List *c, int lm, int lc, HnswSupport * support, Hnsw
|
|||||||
if (list_length(w) <= lm)
|
if (list_length(w) <= lm)
|
||||||
return w;
|
return w;
|
||||||
|
|
||||||
wd = pairingheap_allocate(CompareNearestCandidates, NULL);
|
wd = palloc(sizeof(HnswCandidate *) * list_length(w));
|
||||||
|
|
||||||
/* Ensure order of candidates is deterministic for closer caching */
|
/* Ensure order of candidates is deterministic for closer caching */
|
||||||
if (sortCandidates)
|
if (sortCandidates)
|
||||||
@@ -991,7 +989,7 @@ SelectNeighbors(char *base, List *c, int lm, int lc, HnswSupport * support, Hnsw
|
|||||||
|
|
||||||
/* Use previous state of r and wd to skip work when possible */
|
/* Use previous state of r and wd to skip work when possible */
|
||||||
if (mustCalculate)
|
if (mustCalculate)
|
||||||
e->closer = CheckElementCloser(base, e, r, support);
|
e->closer = CheckElementCloser(base, e, r, procinfo, collation);
|
||||||
else if (list_length(added) > 0)
|
else if (list_length(added) > 0)
|
||||||
{
|
{
|
||||||
/* Keep Valgrind happy for in-memory, parallel builds */
|
/* Keep Valgrind happy for in-memory, parallel builds */
|
||||||
@@ -1004,7 +1002,7 @@ SelectNeighbors(char *base, List *c, int lm, int lc, HnswSupport * support, Hnsw
|
|||||||
*/
|
*/
|
||||||
if (e->closer)
|
if (e->closer)
|
||||||
{
|
{
|
||||||
e->closer = CheckElementCloser(base, e, added, support);
|
e->closer = CheckElementCloser(base, e, added, procinfo, collation);
|
||||||
|
|
||||||
if (!e->closer)
|
if (!e->closer)
|
||||||
removedAny = true;
|
removedAny = true;
|
||||||
@@ -1017,7 +1015,7 @@ SelectNeighbors(char *base, List *c, int lm, int lc, HnswSupport * support, Hnsw
|
|||||||
*/
|
*/
|
||||||
if (removedAny)
|
if (removedAny)
|
||||||
{
|
{
|
||||||
e->closer = CheckElementCloser(base, e, r, support);
|
e->closer = CheckElementCloser(base, e, r, procinfo, collation);
|
||||||
if (e->closer)
|
if (e->closer)
|
||||||
added = lappend(added, e);
|
added = lappend(added, e);
|
||||||
}
|
}
|
||||||
@@ -1025,7 +1023,7 @@ SelectNeighbors(char *base, List *c, int lm, int lc, HnswSupport * support, Hnsw
|
|||||||
}
|
}
|
||||||
else if (e == newCandidate)
|
else if (e == newCandidate)
|
||||||
{
|
{
|
||||||
e->closer = CheckElementCloser(base, e, r, support);
|
e->closer = CheckElementCloser(base, e, r, procinfo, collation);
|
||||||
if (e->closer)
|
if (e->closer)
|
||||||
added = lappend(added, e);
|
added = lappend(added, e);
|
||||||
}
|
}
|
||||||
@@ -1037,21 +1035,21 @@ SelectNeighbors(char *base, List *c, int lm, int lc, HnswSupport * support, Hnsw
|
|||||||
if (e->closer)
|
if (e->closer)
|
||||||
r = lappend(r, e);
|
r = lappend(r, e);
|
||||||
else
|
else
|
||||||
pairingheap_add(wd, &(CreatePairingHeapNode(e)->ph_node));
|
wd[wdlen++] = e;
|
||||||
}
|
}
|
||||||
|
|
||||||
/* 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 (!pairingheap_is_empty(wd) && list_length(r) < lm)
|
while (wdoff < wdlen && list_length(r) < lm)
|
||||||
r = lappend(r, ((HnswPairingHeapNode *) pairingheap_remove_first(wd))->inner);
|
r = lappend(r, wd[wdoff++]);
|
||||||
|
|
||||||
/* Return pruned for update connections */
|
/* Return pruned for update connections */
|
||||||
if (pruned != NULL)
|
if (pruned != NULL)
|
||||||
{
|
{
|
||||||
if (!pairingheap_is_empty(wd))
|
if (wdoff < wdlen)
|
||||||
*pruned = ((HnswPairingHeapNode *) pairingheap_first(wd))->inner;
|
*pruned = wd[wdoff];
|
||||||
else
|
else
|
||||||
*pruned = linitial(w);
|
*pruned = linitial(w);
|
||||||
}
|
}
|
||||||
@@ -1076,7 +1074,7 @@ AddConnections(char *base, HnswElement element, List *neighbors, int lc)
|
|||||||
* Update connections
|
* Update connections
|
||||||
*/
|
*/
|
||||||
void
|
void
|
||||||
HnswUpdateConnection(char *base, HnswElement element, HnswCandidate * hc, int lm, int lc, int *updateIdx, Relation index, HnswSupport * support)
|
HnswUpdateConnection(char *base, HnswElement element, HnswCandidate * hc, int lm, int lc, int *updateIdx, Relation index, FmgrInfo *procinfo, Oid collation)
|
||||||
{
|
{
|
||||||
HnswElement hce = HnswPtrAccess(base, hc->element);
|
HnswElement hce = HnswPtrAccess(base, hc->element);
|
||||||
HnswNeighborArray *currentNeighbors = HnswGetNeighbors(base, hce, lc);
|
HnswNeighborArray *currentNeighbors = HnswGetNeighbors(base, hce, lc);
|
||||||
@@ -1109,9 +1107,9 @@ HnswUpdateConnection(char *base, HnswElement element, HnswCandidate * hc, int lm
|
|||||||
HnswElement hc3Element = HnswPtrAccess(base, hc3->element);
|
HnswElement hc3Element = HnswPtrAccess(base, hc3->element);
|
||||||
|
|
||||||
if (HnswPtrIsNull(base, hc3Element->value))
|
if (HnswPtrIsNull(base, hc3Element->value))
|
||||||
HnswLoadElement(hc3Element, &hc3->distance, &q, index, support, true);
|
HnswLoadElement(hc3Element, &hc3->distance, &q, index, procinfo, collation, true);
|
||||||
else
|
else
|
||||||
hc3->distance = GetCandidateDistance(base, hc3, q, support);
|
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)
|
||||||
@@ -1131,7 +1129,7 @@ HnswUpdateConnection(char *base, HnswElement element, HnswCandidate * hc, int lm
|
|||||||
c = lappend(c, ¤tNeighbors->items[i]);
|
c = lappend(c, ¤tNeighbors->items[i]);
|
||||||
c = lappend(c, &hc2);
|
c = lappend(c, &hc2);
|
||||||
|
|
||||||
SelectNeighbors(base, c, lm, lc, support, hce, &hc2, &pruned, true);
|
SelectNeighbors(base, c, lm, lc, procinfo, collation, hce, &hc2, &pruned, true);
|
||||||
|
|
||||||
/* Should not happen */
|
/* Should not happen */
|
||||||
if (pruned == NULL)
|
if (pruned == NULL)
|
||||||
@@ -1205,7 +1203,7 @@ PrecomputeHash(char *base, HnswElement element)
|
|||||||
* Algorithm 1 from paper
|
* Algorithm 1 from paper
|
||||||
*/
|
*/
|
||||||
void
|
void
|
||||||
HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, HnswSupport * support, int m, int efConstruction, bool existing)
|
HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, FmgrInfo *procinfo, Oid collation, int m, int efConstruction, bool existing)
|
||||||
{
|
{
|
||||||
List *ep;
|
List *ep;
|
||||||
List *w;
|
List *w;
|
||||||
@@ -1225,13 +1223,13 @@ 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, support, 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, support, m, true, skipElement);
|
w = HnswSearchLayer(base, q, ep, 1, lc, index, procinfo, collation, m, true, skipElement);
|
||||||
ep = w;
|
ep = w;
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -1249,7 +1247,7 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
|
|||||||
List *neighbors;
|
List *neighbors;
|
||||||
List *lw;
|
List *lw;
|
||||||
|
|
||||||
w = HnswSearchLayer(base, q, ep, efConstruction, lc, index, support, 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 */
|
||||||
@@ -1263,7 +1261,7 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
|
|||||||
* sortCandidates to true for in-memory builds to enable closer
|
* sortCandidates to true for in-memory builds to enable closer
|
||||||
* caching, but there does not seem to be a difference in performance.
|
* caching, but there does not seem to be a difference in performance.
|
||||||
*/
|
*/
|
||||||
neighbors = SelectNeighbors(base, lw, lm, lc, support, element, NULL, NULL, false);
|
neighbors = SelectNeighbors(base, lw, lm, lc, procinfo, collation, element, NULL, NULL, false);
|
||||||
|
|
||||||
AddConnections(base, element, neighbors, lc);
|
AddConnections(base, element, neighbors, lc);
|
||||||
|
|
||||||
|
|||||||
@@ -189,6 +189,8 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
|
|||||||
GenericXLogState *state;
|
GenericXLogState *state;
|
||||||
int m = vacuumstate->m;
|
int m = vacuumstate->m;
|
||||||
int efConstruction = vacuumstate->efConstruction;
|
int efConstruction = vacuumstate->efConstruction;
|
||||||
|
FmgrInfo *procinfo = vacuumstate->procinfo;
|
||||||
|
Oid collation = vacuumstate->collation;
|
||||||
BufferAccessStrategy bas = vacuumstate->bas;
|
BufferAccessStrategy bas = vacuumstate->bas;
|
||||||
HnswNeighborTuple ntup = vacuumstate->ntup;
|
HnswNeighborTuple ntup = vacuumstate->ntup;
|
||||||
Size ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(element->level, m);
|
Size ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(element->level, m);
|
||||||
@@ -203,7 +205,7 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
|
|||||||
element->heaptidsLength = 0;
|
element->heaptidsLength = 0;
|
||||||
|
|
||||||
/* Find neighbors for element, skipping itself */
|
/* Find neighbors for element, skipping itself */
|
||||||
HnswFindElementNeighbors(base, element, entryPoint, index, &vacuumstate->support, m, efConstruction, true);
|
HnswFindElementNeighbors(base, element, entryPoint, index, procinfo, collation, m, efConstruction, true);
|
||||||
|
|
||||||
/* Zero memory for each element */
|
/* Zero memory for each element */
|
||||||
MemSet(ntup, 0, HNSW_TUPLE_ALLOC_SIZE);
|
MemSet(ntup, 0, HNSW_TUPLE_ALLOC_SIZE);
|
||||||
@@ -227,7 +229,7 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
|
|||||||
UnlockReleaseBuffer(buf);
|
UnlockReleaseBuffer(buf);
|
||||||
|
|
||||||
/* Update neighbors */
|
/* Update neighbors */
|
||||||
HnswUpdateNeighborsOnDisk(index, &vacuumstate->support, element, m, true, false);
|
HnswUpdateNeighborsOnDisk(index, procinfo, collation, element, m, true, false);
|
||||||
}
|
}
|
||||||
|
|
||||||
/*
|
/*
|
||||||
@@ -254,7 +256,7 @@ RepairGraphEntryPoint(HnswVacuumState * vacuumstate)
|
|||||||
LockPage(index, HNSW_UPDATE_LOCK, ShareLock);
|
LockPage(index, HNSW_UPDATE_LOCK, ShareLock);
|
||||||
|
|
||||||
/* Load element */
|
/* Load element */
|
||||||
HnswLoadElement(highestPoint, NULL, NULL, index, &vacuumstate->support, true);
|
HnswLoadElement(highestPoint, NULL, NULL, index, vacuumstate->procinfo, vacuumstate->collation, true);
|
||||||
|
|
||||||
/* Repair if needed */
|
/* Repair if needed */
|
||||||
if (NeedsUpdated(vacuumstate, highestPoint))
|
if (NeedsUpdated(vacuumstate, highestPoint))
|
||||||
@@ -292,7 +294,7 @@ RepairGraphEntryPoint(HnswVacuumState * vacuumstate)
|
|||||||
* is outdated, this can remove connections at higher levels in
|
* is outdated, this can remove connections at higher levels in
|
||||||
* the graph until they are repaired, but this should be fine.
|
* the graph until they are repaired, but this should be fine.
|
||||||
*/
|
*/
|
||||||
HnswLoadElement(entryPoint, NULL, NULL, index, &vacuumstate->support, true);
|
HnswLoadElement(entryPoint, NULL, NULL, index, vacuumstate->procinfo, vacuumstate->collation, true);
|
||||||
|
|
||||||
if (NeedsUpdated(vacuumstate, entryPoint))
|
if (NeedsUpdated(vacuumstate, entryPoint))
|
||||||
{
|
{
|
||||||
@@ -571,8 +573,8 @@ InitVacuumState(HnswVacuumState * vacuumstate, IndexVacuumInfo *info, IndexBulkD
|
|||||||
vacuumstate->callback_state = callback_state;
|
vacuumstate->callback_state = callback_state;
|
||||||
vacuumstate->efConstruction = HnswGetEfConstruction(index);
|
vacuumstate->efConstruction = HnswGetEfConstruction(index);
|
||||||
vacuumstate->bas = GetAccessStrategy(BAS_BULKREAD);
|
vacuumstate->bas = GetAccessStrategy(BAS_BULKREAD);
|
||||||
vacuumstate->support.procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
|
vacuumstate->procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
|
||||||
vacuumstate->support.collation = index->rd_indcollation[0];
|
vacuumstate->collation = index->rd_indcollation[0];
|
||||||
vacuumstate->ntup = palloc0(HNSW_TUPLE_ALLOC_SIZE);
|
vacuumstate->ntup = palloc0(HNSW_TUPLE_ALLOC_SIZE);
|
||||||
vacuumstate->tmpCtx = AllocSetContextCreate(CurrentMemoryContext,
|
vacuumstate->tmpCtx = AllocSetContextCreate(CurrentMemoryContext,
|
||||||
"Hnsw vacuum temporary context",
|
"Hnsw vacuum temporary context",
|
||||||
|
|||||||
@@ -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 = '0.6.0'
|
default_version = '0.6.1'
|
||||||
module_pathname = '$libdir/vector'
|
module_pathname = '$libdir/vector'
|
||||||
relocatable = true
|
relocatable = true
|
||||||
|
|||||||
Reference in New Issue
Block a user