mirror of
https://github.com/pgvector/pgvector.git
synced 2026-07-22 03:57:34 +08:00
Compare commits
34 Commits
hnsw-suppo
...
hnsw-entry
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
c207a2d50e | ||
|
|
569fd36396 | ||
|
|
62350b1589 | ||
|
|
dd57309281 | ||
|
|
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
|
||||
- run: make
|
||||
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: |
|
||||
export PG_CONFIG=`which pg_config`
|
||||
sudo --preserve-env=PG_CONFIG make install
|
||||
@@ -49,7 +49,7 @@ jobs:
|
||||
postgres-version: 14
|
||||
- run: make
|
||||
env:
|
||||
PG_CFLAGS: -Wall -Wextra -Werror -Wno-unused-parameter
|
||||
PG_CFLAGS: -DUSE_ASSERT_CHECKING -Wall -Wextra -Werror -Wno-unused-parameter
|
||||
- run: make install
|
||||
- run: make installcheck
|
||||
- if: ${{ failure() }}
|
||||
@@ -60,7 +60,9 @@ jobs:
|
||||
wget -q https://github.com/postgres/postgres/archive/refs/tags/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 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:
|
||||
runs-on: windows-latest
|
||||
if: ${{ !startsWith(github.ref_name, 'mac') }}
|
||||
@@ -97,4 +99,15 @@ jobs:
|
||||
sudo -u postgres make installcheck
|
||||
sudo -u postgres make prove_installcheck
|
||||
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 +1,12 @@
|
||||
## 0.6.1 (unreleased)
|
||||
## 0.6.2 (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 `shared_preload_libraries`
|
||||
- Fixed vector subtraction being marked as commutative
|
||||
|
||||
## 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
|
||||
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
"name": "vector",
|
||||
"abstract": "Open-source vector similarity search for Postgres",
|
||||
"description": "Supports L2 distance, inner product, and cosine distance",
|
||||
"version": "0.6.0",
|
||||
"version": "0.6.1",
|
||||
"maintainer": [
|
||||
"Andrew Kane <andrew@ankane.org>"
|
||||
],
|
||||
@@ -20,7 +20,7 @@
|
||||
"vector": {
|
||||
"file": "sql/vector.sql",
|
||||
"docfile": "README.md",
|
||||
"version": "0.6.0",
|
||||
"version": "0.6.1",
|
||||
"abstract": "Open-source vector similarity search for Postgres"
|
||||
}
|
||||
},
|
||||
|
||||
8
Makefile
8
Makefile
@@ -1,5 +1,5 @@
|
||||
EXTENSION = vector
|
||||
EXTVERSION = 0.6.0
|
||||
EXTVERSION = 0.6.1
|
||||
|
||||
MODULE_big = vector
|
||||
DATA = $(wildcard sql/*--*.sql)
|
||||
@@ -71,11 +71,9 @@ PG_MAJOR ?= 16
|
||||
.PHONY: docker
|
||||
|
||||
docker:
|
||||
docker build --pull --no-cache --build-arg PG_MAJOR=$(PG_MAJOR) -t pgvector/pgvector:pg$(PG_MAJOR) .
|
||||
docker build --build-arg PG_MAJOR=$(PG_MAJOR) -t pgvector/pgvector:$(EXTVERSION)-pg$(PG_MAJOR) .
|
||||
docker build --pull --no-cache --build-arg PG_MAJOR=$(PG_MAJOR) -t pgvector/pgvector:pg$(PG_MAJOR) -t pgvector/pgvector:$(EXTVERSION)-pg$(PG_MAJOR) .
|
||||
|
||||
.PHONY: docker-release
|
||||
|
||||
docker-release:
|
||||
docker buildx build --push --pull --no-cache --platform linux/amd64,linux/arm64 --build-arg PG_MAJOR=$(PG_MAJOR) -t pgvector/pgvector:pg$(PG_MAJOR) .
|
||||
docker buildx build --push --platform linux/amd64,linux/arm64 --build-arg PG_MAJOR=$(PG_MAJOR) -t pgvector/pgvector:$(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$(PG_MAJOR) -t pgvector/pgvector:$(EXTVERSION)-pg$(PG_MAJOR) .
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
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
|
||||
HEADERS = src\vector.h
|
||||
|
||||
45
README.md
45
README.md
@@ -20,7 +20,7 @@ Compile and install the extension (supports Postgres 12+)
|
||||
|
||||
```sh
|
||||
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
|
||||
make
|
||||
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
|
||||
|
||||
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
|
||||
|
||||
@@ -44,7 +44,7 @@ Then use `nmake` to build:
|
||||
|
||||
```cmd
|
||||
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
|
||||
nmake /F Makefile.win
|
||||
nmake /F Makefile.win install
|
||||
@@ -102,6 +102,12 @@ Insert vectors
|
||||
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
|
||||
|
||||
```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
|
||||
|
||||
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)
|
||||
|
||||
```sql
|
||||
@@ -573,6 +581,10 @@ or choose to store vectors inline:
|
||||
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?
|
||||
|
||||
The index was likely created with too little data for the number of lists. Drop the index until the table has more data.
|
||||
@@ -581,6 +593,8 @@ The index was likely created with too little data for the number of lists. Drop
|
||||
DROP INDEX index_name;
|
||||
```
|
||||
|
||||
Results can also be limited by the number of probes (`ivfflat.probes`).
|
||||
|
||||
## Reference
|
||||
|
||||
### Vector Type
|
||||
@@ -656,6 +670,14 @@ 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.
|
||||
|
||||
### Portability
|
||||
|
||||
To compile for portability, use:
|
||||
|
||||
```sh
|
||||
make OPTFLAGS=""
|
||||
```
|
||||
|
||||
## Additional Installation Methods
|
||||
|
||||
### Docker
|
||||
@@ -671,7 +693,7 @@ This adds pgvector to the [Postgres image](https://hub.docker.com/_/postgres) (r
|
||||
You can also build the image manually:
|
||||
|
||||
```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
|
||||
docker build --build-arg PG_MAJOR=16 -t myuser/pgvector .
|
||||
```
|
||||
@@ -716,6 +738,21 @@ sudo dnf install pgvector_16
|
||||
|
||||
Note: Replace `16` with your Postgres server version
|
||||
|
||||
### pkg
|
||||
|
||||
Install the FreeBSD package with:
|
||||
|
||||
```sh
|
||||
pkg install postgresql15-pg_vector
|
||||
```
|
||||
|
||||
or the port with:
|
||||
|
||||
```sh
|
||||
cd /usr/ports/databases/pgvector
|
||||
make install
|
||||
```
|
||||
|
||||
### conda-forge
|
||||
|
||||
With Conda Postgres, install from [conda-forge](https://anaconda.org/conda-forge/pgvector) with:
|
||||
|
||||
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 - (
|
||||
LEFTARG = vector, RIGHTARG = vector, PROCEDURE = vector_sub,
|
||||
COMMUTATOR = -
|
||||
LEFTARG = vector, RIGHTARG = vector, PROCEDURE = vector_sub
|
||||
);
|
||||
|
||||
CREATE OPERATOR * (
|
||||
@@ -195,11 +194,10 @@ CREATE OPERATOR < (
|
||||
RESTRICT = scalarltsel, JOIN = scalarltjoinsel
|
||||
);
|
||||
|
||||
-- should use scalarlesel and scalarlejoinsel, but not supported in Postgres < 11
|
||||
CREATE OPERATOR <= (
|
||||
LEFTARG = vector, RIGHTARG = vector, PROCEDURE = vector_le,
|
||||
COMMUTATOR = >= , NEGATOR = > ,
|
||||
RESTRICT = scalarltsel, JOIN = scalarltjoinsel
|
||||
RESTRICT = scalarlesel, JOIN = scalarlejoinsel
|
||||
);
|
||||
|
||||
CREATE OPERATOR = (
|
||||
@@ -214,11 +212,10 @@ CREATE OPERATOR <> (
|
||||
RESTRICT = eqsel, JOIN = eqjoinsel
|
||||
);
|
||||
|
||||
-- should use scalargesel and scalargejoinsel, but not supported in Postgres < 11
|
||||
CREATE OPERATOR >= (
|
||||
LEFTARG = vector, RIGHTARG = vector, PROCEDURE = vector_ge,
|
||||
COMMUTATOR = <= , NEGATOR = < ,
|
||||
RESTRICT = scalargtsel, JOIN = scalargtjoinsel
|
||||
RESTRICT = scalargesel, JOIN = scalargejoinsel
|
||||
);
|
||||
|
||||
CREATE OPERATOR > (
|
||||
|
||||
@@ -8,6 +8,7 @@
|
||||
#include "commands/progress.h"
|
||||
#include "commands/vacuum.h"
|
||||
#include "hnsw.h"
|
||||
#include "miscadmin.h"
|
||||
#include "utils/guc.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
|
||||
* RequestAddinShmemSpace() to pre-reserve space for this.
|
||||
*/
|
||||
static void
|
||||
void
|
||||
HnswInitLockTranche(void)
|
||||
{
|
||||
int *tranche_ids;
|
||||
@@ -53,7 +54,8 @@ HnswInitLockTranche(void)
|
||||
void
|
||||
HnswInit(void)
|
||||
{
|
||||
HnswInitLockTranche();
|
||||
if (!process_shared_preload_libraries_in_progress)
|
||||
HnswInitLockTranche();
|
||||
|
||||
hnsw_relopt_kind = add_reloption_kind();
|
||||
add_int_reloption(hnsw_relopt_kind, "m", "Max number of connections",
|
||||
|
||||
30
src/hnsw.h
30
src/hnsw.h
@@ -80,7 +80,7 @@
|
||||
|
||||
#if PG_VERSION_NUM < 130000
|
||||
#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
|
||||
|
||||
#define HnswIsElementTuple(tup) ((tup)->type == HNSW_ELEMENT_TUPLE_TYPE)
|
||||
@@ -185,6 +185,7 @@ typedef struct HnswGraph
|
||||
|
||||
/* Entry state */
|
||||
LWLock entryLock;
|
||||
LWLock entryWaitLock;
|
||||
HnswElementPtr entryPoint;
|
||||
|
||||
/* Allocations state */
|
||||
@@ -234,12 +235,6 @@ typedef struct HnswAllocator
|
||||
void *state;
|
||||
} HnswAllocator;
|
||||
|
||||
typedef struct HnswSupport
|
||||
{
|
||||
FmgrInfo *procinfo;
|
||||
Oid collation;
|
||||
} HnswSupport;
|
||||
|
||||
typedef struct HnswBuildState
|
||||
{
|
||||
/* Info */
|
||||
@@ -258,7 +253,7 @@ typedef struct HnswBuildState
|
||||
double reltuples;
|
||||
|
||||
/* Support functions */
|
||||
HnswSupport support;
|
||||
FmgrInfo *procinfo;
|
||||
FmgrInfo *normprocinfo;
|
||||
Oid collation;
|
||||
|
||||
@@ -335,7 +330,7 @@ typedef struct HnswScanOpaqueData
|
||||
MemoryContext tmpCtx;
|
||||
|
||||
/* Support functions */
|
||||
HnswSupport support;
|
||||
FmgrInfo *procinfo;
|
||||
FmgrInfo *normprocinfo;
|
||||
Oid collation;
|
||||
} HnswScanOpaqueData;
|
||||
@@ -355,7 +350,8 @@ typedef struct HnswVacuumState
|
||||
int efConstruction;
|
||||
|
||||
/* Support functions */
|
||||
HnswSupport support;
|
||||
FmgrInfo *procinfo;
|
||||
Oid collation;
|
||||
|
||||
/* Variables */
|
||||
struct tidhash_hash *deleted;
|
||||
@@ -371,30 +367,30 @@ typedef struct HnswVacuumState
|
||||
int HnswGetM(Relation index);
|
||||
int HnswGetEfConstruction(Relation index);
|
||||
FmgrInfo *HnswOptionalProcInfo(Relation index, uint16 procnum);
|
||||
void HnswInitSupport(HnswSupport * support, Relation index);
|
||||
bool HnswNormValue(FmgrInfo *procinfo, Oid collation, Datum *value, Vector * result);
|
||||
Buffer HnswNewBuffer(Relation index, ForkNumber forkNum);
|
||||
void HnswInitPage(Buffer buf, Page page);
|
||||
void HnswInit(void);
|
||||
List *HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, 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);
|
||||
void HnswGetMetaPageInfo(Relation index, int *m, HnswElement * entryPoint);
|
||||
void *HnswAlloc(HnswAllocator * allocator, Size size);
|
||||
HnswElement HnswInitElement(char *base, ItemPointer tid, int m, double ml, int maxLevel, HnswAllocator * alloc);
|
||||
HnswElement HnswInitElementFromBlock(BlockNumber blkno, OffsetNumber offno);
|
||||
void HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, HnswSupport * support, int m, int efConstruction, bool existing);
|
||||
HnswCandidate *HnswEntryCandidate(char *base, HnswElement em, Datum q, Relation rel, HnswSupport * support, bool loadVec);
|
||||
void HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, FmgrInfo *procinfo, Oid collation, int m, int efConstruction, bool existing);
|
||||
HnswCandidate *HnswEntryCandidate(char *base, HnswElement em, Datum q, Relation rel, FmgrInfo *procinfo, Oid collation, bool loadVec);
|
||||
void HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, BlockNumber insertPage, ForkNumber forkNum, bool building);
|
||||
void HnswSetNeighborTuple(char *base, HnswNeighborTuple ntup, HnswElement e, int m);
|
||||
void HnswAddHeapTid(HnswElement element, ItemPointer heaptid);
|
||||
void HnswInitNeighbors(char *base, HnswElement element, int m, HnswAllocator * alloc);
|
||||
bool HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull, ItemPointer heap_tid, bool building);
|
||||
void HnswUpdateNeighborsOnDisk(Relation index, 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 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 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 HnswInitLockTranche(void);
|
||||
PGDLLEXPORT void HnswParallelBuildMain(dsm_segment *seg, shm_toc *toc);
|
||||
|
||||
/* Index access methods */
|
||||
|
||||
@@ -176,7 +176,7 @@ CreateGraphPages(HnswBuildState * buildstate)
|
||||
Size etupSize;
|
||||
Size ntupSize;
|
||||
Size combinedSize;
|
||||
void *valuePtr = HnswPtrAccess(base, element->value);
|
||||
Pointer valuePtr = HnswPtrAccess(base, element->value);
|
||||
|
||||
/* Update iterator */
|
||||
iter = element->next;
|
||||
@@ -373,7 +373,7 @@ AddElementInMemory(char *base, HnswGraph * graph, HnswElement element)
|
||||
* Update neighbors
|
||||
*/
|
||||
static void
|
||||
UpdateNeighborsInMemory(char *base, 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--)
|
||||
{
|
||||
@@ -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 */
|
||||
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);
|
||||
}
|
||||
}
|
||||
@@ -400,7 +400,7 @@ UpdateNeighborsInMemory(char *base, HnswSupport * support, HnswElement e, int m)
|
||||
* Update graph in memory
|
||||
*/
|
||||
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;
|
||||
char *base = buildstate->hnswarea;
|
||||
@@ -413,7 +413,7 @@ UpdateGraphInMemory(HnswSupport * support, HnswElement element, int m, int efCon
|
||||
AddElementInMemory(base, graph, element);
|
||||
|
||||
/* Update neighbors */
|
||||
UpdateNeighborsInMemory(base, support, element, m);
|
||||
UpdateNeighborsInMemory(base, procinfo, collation, element, m);
|
||||
|
||||
/* Update entry point if needed (already have lock) */
|
||||
if (entryPoint == NULL || element->level > entryPoint->level)
|
||||
@@ -426,13 +426,20 @@ UpdateGraphInMemory(HnswSupport * support, HnswElement element, int m, int efCon
|
||||
static void
|
||||
InsertTupleInMemory(HnswBuildState * buildstate, HnswElement element)
|
||||
{
|
||||
FmgrInfo *procinfo = buildstate->procinfo;
|
||||
Oid collation = buildstate->collation;
|
||||
HnswGraph *graph = buildstate->graph;
|
||||
HnswElement entryPoint;
|
||||
LWLock *entryLock = &graph->entryLock;
|
||||
LWLock *entryWaitLock = &graph->entryWaitLock;
|
||||
int efConstruction = buildstate->efConstruction;
|
||||
int m = buildstate->m;
|
||||
char *base = buildstate->hnswarea;
|
||||
|
||||
/* Wait if another process needs exclusive lock */
|
||||
if (LWLockAcquireOrWait(entryWaitLock, LW_EXCLUSIVE))
|
||||
LWLockRelease(entryWaitLock);
|
||||
|
||||
/* Get entry point */
|
||||
LWLockAcquire(entryLock, LW_SHARED);
|
||||
entryPoint = HnswPtrAccess(base, graph->entryPoint);
|
||||
@@ -444,17 +451,19 @@ InsertTupleInMemory(HnswBuildState * buildstate, HnswElement element)
|
||||
LWLockRelease(entryLock);
|
||||
|
||||
/* Get exclusive lock */
|
||||
LWLockAcquire(entryWaitLock, LW_EXCLUSIVE);
|
||||
LWLockAcquire(entryLock, LW_EXCLUSIVE);
|
||||
LWLockRelease(entryWaitLock);
|
||||
|
||||
/* Get latest entry point after lock is acquired */
|
||||
entryPoint = HnswPtrAccess(base, graph->entryPoint);
|
||||
}
|
||||
|
||||
/* 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 */
|
||||
UpdateGraphInMemory(&buildstate->support, element, m, efConstruction, entryPoint, buildstate);
|
||||
UpdateGraphInMemory(procinfo, collation, element, m, efConstruction, entryPoint, buildstate);
|
||||
|
||||
/* Release entry lock */
|
||||
LWLockRelease(entryLock);
|
||||
@@ -599,6 +608,9 @@ BuildCallback(Relation index, CALLBACK_ITEM_POINTER, Datum *values,
|
||||
static void
|
||||
InitGraph(HnswGraph * graph, char *base, long memoryTotal)
|
||||
{
|
||||
/* Initialize the lock tranche if needed */
|
||||
HnswInitLockTranche();
|
||||
|
||||
HnswPtrStore(base, graph->head, (HnswElement) NULL);
|
||||
HnswPtrStore(base, graph->entryPoint, (HnswElement) NULL);
|
||||
graph->memoryUsed = 0;
|
||||
@@ -607,6 +619,7 @@ InitGraph(HnswGraph * graph, char *base, long memoryTotal)
|
||||
graph->indtuples = 0;
|
||||
SpinLockInit(&graph->lock);
|
||||
LWLockInitialize(&graph->entryLock, hnsw_lock_tranche_id);
|
||||
LWLockInitialize(&graph->entryWaitLock, hnsw_lock_tranche_id);
|
||||
LWLockInitialize(&graph->allocatorLock, hnsw_lock_tranche_id);
|
||||
LWLockInitialize(&graph->flushLock, hnsw_lock_tranche_id);
|
||||
}
|
||||
@@ -681,7 +694,7 @@ InitBuildState(HnswBuildState * buildstate, Relation heap, Relation index, Index
|
||||
buildstate->indtuples = 0;
|
||||
|
||||
/* Get support functions */
|
||||
HnswInitSupport(&buildstate->support, index);
|
||||
buildstate->procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
|
||||
buildstate->normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
|
||||
buildstate->collation = index->rd_indcollation[0];
|
||||
|
||||
@@ -972,6 +985,14 @@ HnswBeginParallel(HnswBuildState * buildstate, bool isconcurrent, int request)
|
||||
/* Report less than allocated so never fails */
|
||||
InitGraph(&hnswshared->graphData, hnswarea, esthnswarea - 1024 * 1024);
|
||||
|
||||
/*
|
||||
* Avoid base address for relptr for Postgres < 14.5
|
||||
* https://github.com/postgres/postgres/commit/7201cd18627afc64850537806da7f22150d1a83b
|
||||
*/
|
||||
#if PG_VERSION_NUM < 140005
|
||||
hnswshared->graphData.memoryUsed += MAXALIGN(1);
|
||||
#endif
|
||||
|
||||
shm_toc_insert(pcxt->toc, PARALLEL_KEY_HNSW_SHARED, hnswshared);
|
||||
shm_toc_insert(pcxt->toc, PARALLEL_KEY_HNSW_AREA, hnswarea);
|
||||
|
||||
|
||||
@@ -340,7 +340,7 @@ ConnectionExists(HnswElement e, HnswNeighborTuple ntup, int startIdx, int lm)
|
||||
* Update neighbors
|
||||
*/
|
||||
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;
|
||||
|
||||
@@ -373,7 +373,7 @@ HnswUpdateNeighborsOnDisk(Relation index, HnswSupport * support, HnswElement e,
|
||||
*/
|
||||
|
||||
/* 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 */
|
||||
if (idx == -1)
|
||||
@@ -527,7 +527,7 @@ FindDuplicateOnDisk(Relation index, HnswElement element, bool building)
|
||||
* Update graph on disk
|
||||
*/
|
||||
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;
|
||||
|
||||
@@ -543,7 +543,7 @@ UpdateGraphOnDisk(Relation index, HnswSupport * support, HnswElement element, in
|
||||
HnswUpdateMetaPage(index, 0, NULL, newInsertPage, MAIN_FORKNUM, building);
|
||||
|
||||
/* Update neighbors */
|
||||
HnswUpdateNeighborsOnDisk(index, support, element, m, false, building);
|
||||
HnswUpdateNeighborsOnDisk(index, procinfo, collation, element, m, false, building);
|
||||
|
||||
/* Update entry point if needed */
|
||||
if (entryPoint == NULL || element->level > entryPoint->level)
|
||||
@@ -560,11 +560,10 @@ HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull,
|
||||
HnswElement element;
|
||||
int m;
|
||||
int efConstruction = HnswGetEfConstruction(index);
|
||||
FmgrInfo *procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
|
||||
Oid collation = index->rd_indcollation[0];
|
||||
LOCKMODE lockmode = ShareLock;
|
||||
char *base = NULL;
|
||||
HnswSupport support;
|
||||
|
||||
HnswInitSupport(&support, index);
|
||||
|
||||
/*
|
||||
* Get a shared lock. This allows vacuum to ensure no in-flight inserts
|
||||
@@ -595,10 +594,10 @@ HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull,
|
||||
}
|
||||
|
||||
/* 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 */
|
||||
UpdateGraphOnDisk(index, &support, element, m, efConstruction, entryPoint, building);
|
||||
UpdateGraphOnDisk(index, procinfo, collation, element, m, efConstruction, entryPoint, building);
|
||||
|
||||
/* Release lock */
|
||||
UnlockPage(index, HNSW_UPDATE_LOCK, lockmode);
|
||||
|
||||
@@ -15,6 +15,8 @@ GetScanItems(IndexScanDesc scan, Datum q)
|
||||
{
|
||||
HnswScanOpaque so = (HnswScanOpaque) scan->opaque;
|
||||
Relation index = scan->indexRelation;
|
||||
FmgrInfo *procinfo = so->procinfo;
|
||||
Oid collation = so->collation;
|
||||
List *ep;
|
||||
List *w;
|
||||
int m;
|
||||
@@ -27,15 +29,15 @@ GetScanItems(IndexScanDesc scan, Datum q)
|
||||
if (entryPoint == NULL)
|
||||
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--)
|
||||
{
|
||||
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;
|
||||
}
|
||||
|
||||
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);
|
||||
|
||||
/* Set support functions */
|
||||
HnswInitSupport(&so->support, index);
|
||||
so->procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
|
||||
so->normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
|
||||
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);
|
||||
}
|
||||
|
||||
/*
|
||||
* 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
|
||||
*
|
||||
@@ -565,7 +555,7 @@ HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHe
|
||||
* Load an element and optionally get its distance from q
|
||||
*/
|
||||
void
|
||||
HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation index, HnswSupport * support, bool loadVec)
|
||||
HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec)
|
||||
{
|
||||
Buffer buf;
|
||||
Page page;
|
||||
@@ -585,7 +575,7 @@ HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation index,
|
||||
|
||||
/* Calculate distance */
|
||||
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);
|
||||
}
|
||||
@@ -594,27 +584,27 @@ HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation index,
|
||||
* Get the distance for a candidate
|
||||
*/
|
||||
static float
|
||||
GetCandidateDistance(char *base, HnswCandidate * hc, Datum q, HnswSupport * support)
|
||||
GetCandidateDistance(char *base, HnswCandidate * hc, Datum q, FmgrInfo *procinfo, Oid collation)
|
||||
{
|
||||
HnswElement hce = HnswPtrAccess(base, hc->element);
|
||||
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
|
||||
*/
|
||||
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));
|
||||
|
||||
HnswPtrStore(base, hc->element, entryPoint);
|
||||
if (index == NULL)
|
||||
hc->distance = GetCandidateDistance(base, hc, q, support);
|
||||
hc->distance = GetCandidateDistance(base, hc, q, procinfo, collation);
|
||||
else
|
||||
HnswLoadElement(entryPoint, &hc->distance, &q, index, support, loadVec);
|
||||
HnswLoadElement(entryPoint, &hc->distance, &q, index, procinfo, collation, loadVec);
|
||||
return hc;
|
||||
}
|
||||
|
||||
@@ -732,7 +722,7 @@ CountElement(char *base, HnswElement skipElement, HnswCandidate * hc)
|
||||
* Algorithm 2 from paper
|
||||
*/
|
||||
List *
|
||||
HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, 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;
|
||||
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;
|
||||
|
||||
if (index == NULL)
|
||||
eDistance = GetCandidateDistance(base, e, q, support);
|
||||
eDistance = GetCandidateDistance(base, e, q, procinfo, collation);
|
||||
else
|
||||
HnswLoadElement(eElement, &eDistance, &q, index, support, inserting);
|
||||
HnswLoadElement(eElement, &eDistance, &q, index, procinfo, collation, inserting);
|
||||
|
||||
Assert(!eElement->deleted);
|
||||
|
||||
@@ -870,12 +860,15 @@ HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, H
|
||||
static int
|
||||
#if PG_VERSION_NUM >= 130000
|
||||
CompareCandidateDistances(const ListCell *a, const ListCell *b)
|
||||
{
|
||||
HnswCandidate *hca = lfirst(a);
|
||||
HnswCandidate *hcb = lfirst(b);
|
||||
#else
|
||||
CompareCandidateDistances(const void *a, const void *b)
|
||||
#endif
|
||||
{
|
||||
HnswCandidate *hca = lfirst((ListCell *) a);
|
||||
HnswCandidate *hcb = lfirst((ListCell *) b);
|
||||
HnswCandidate *hca = lfirst(*(ListCell **) a);
|
||||
HnswCandidate *hcb = lfirst(*(ListCell **) b);
|
||||
#endif
|
||||
|
||||
if (hca->distance < hcb->distance)
|
||||
return 1;
|
||||
@@ -898,12 +891,15 @@ CompareCandidateDistances(const void *a, const void *b)
|
||||
static int
|
||||
#if PG_VERSION_NUM >= 130000
|
||||
CompareCandidateDistancesOffset(const ListCell *a, const ListCell *b)
|
||||
{
|
||||
HnswCandidate *hca = lfirst(a);
|
||||
HnswCandidate *hcb = lfirst(b);
|
||||
#else
|
||||
CompareCandidateDistancesOffset(const void *a, const void *b)
|
||||
#endif
|
||||
{
|
||||
HnswCandidate *hca = lfirst((ListCell *) a);
|
||||
HnswCandidate *hcb = lfirst((ListCell *) b);
|
||||
HnswCandidate *hca = lfirst(*(ListCell **) a);
|
||||
HnswCandidate *hcb = lfirst(*(ListCell **) b);
|
||||
#endif
|
||||
|
||||
if (hca->distance < hcb->distance)
|
||||
return 1;
|
||||
@@ -924,19 +920,19 @@ CompareCandidateDistancesOffset(const void *a, const void *b)
|
||||
* Calculate the distance between elements
|
||||
*/
|
||||
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 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
|
||||
*/
|
||||
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);
|
||||
ListCell *lc2;
|
||||
@@ -945,7 +941,7 @@ CheckElementCloser(char *base, HnswCandidate * e, List *r, HnswSupport * support
|
||||
{
|
||||
HnswCandidate *ri = lfirst(lc2);
|
||||
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)
|
||||
return false;
|
||||
@@ -958,11 +954,13 @@ CheckElementCloser(char *base, HnswCandidate * e, List *r, HnswSupport * support
|
||||
* Algorithm 4 from paper
|
||||
*/
|
||||
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 *w = list_copy(c);
|
||||
pairingheap *wd;
|
||||
HnswCandidate **wd;
|
||||
int wdlen = 0;
|
||||
int wdoff = 0;
|
||||
HnswNeighborArray *neighbors = HnswGetNeighbors(base, e2, lc);
|
||||
bool mustCalculate = !neighbors->closerSet;
|
||||
List *added = NIL;
|
||||
@@ -971,7 +969,7 @@ SelectNeighbors(char *base, List *c, int lm, int lc, HnswSupport * support, Hnsw
|
||||
if (list_length(w) <= lm)
|
||||
return w;
|
||||
|
||||
wd = pairingheap_allocate(CompareNearestCandidates, NULL);
|
||||
wd = palloc(sizeof(HnswCandidate *) * list_length(w));
|
||||
|
||||
/* Ensure order of candidates is deterministic for closer caching */
|
||||
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 */
|
||||
if (mustCalculate)
|
||||
e->closer = CheckElementCloser(base, e, r, support);
|
||||
e->closer = CheckElementCloser(base, e, r, procinfo, collation);
|
||||
else if (list_length(added) > 0)
|
||||
{
|
||||
/* 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)
|
||||
{
|
||||
e->closer = CheckElementCloser(base, e, added, support);
|
||||
e->closer = CheckElementCloser(base, e, added, procinfo, collation);
|
||||
|
||||
if (!e->closer)
|
||||
removedAny = true;
|
||||
@@ -1017,7 +1015,7 @@ SelectNeighbors(char *base, List *c, int lm, int lc, HnswSupport * support, Hnsw
|
||||
*/
|
||||
if (removedAny)
|
||||
{
|
||||
e->closer = CheckElementCloser(base, e, r, support);
|
||||
e->closer = CheckElementCloser(base, e, r, procinfo, collation);
|
||||
if (e->closer)
|
||||
added = lappend(added, e);
|
||||
}
|
||||
@@ -1025,7 +1023,7 @@ SelectNeighbors(char *base, List *c, int lm, int lc, HnswSupport * support, Hnsw
|
||||
}
|
||||
else if (e == newCandidate)
|
||||
{
|
||||
e->closer = CheckElementCloser(base, e, r, support);
|
||||
e->closer = CheckElementCloser(base, e, r, procinfo, collation);
|
||||
if (e->closer)
|
||||
added = lappend(added, e);
|
||||
}
|
||||
@@ -1037,21 +1035,21 @@ SelectNeighbors(char *base, List *c, int lm, int lc, HnswSupport * support, Hnsw
|
||||
if (e->closer)
|
||||
r = lappend(r, e);
|
||||
else
|
||||
pairingheap_add(wd, &(CreatePairingHeapNode(e)->ph_node));
|
||||
wd[wdlen++] = e;
|
||||
}
|
||||
|
||||
/* Cached value can only be used in future if sorted deterministically */
|
||||
neighbors->closerSet = sortCandidates;
|
||||
|
||||
/* Keep pruned connections */
|
||||
while (!pairingheap_is_empty(wd) && list_length(r) < lm)
|
||||
r = lappend(r, ((HnswPairingHeapNode *) pairingheap_remove_first(wd))->inner);
|
||||
while (wdoff < wdlen && list_length(r) < lm)
|
||||
r = lappend(r, wd[wdoff++]);
|
||||
|
||||
/* Return pruned for update connections */
|
||||
if (pruned != NULL)
|
||||
{
|
||||
if (!pairingheap_is_empty(wd))
|
||||
*pruned = ((HnswPairingHeapNode *) pairingheap_first(wd))->inner;
|
||||
if (wdoff < wdlen)
|
||||
*pruned = wd[wdoff];
|
||||
else
|
||||
*pruned = linitial(w);
|
||||
}
|
||||
@@ -1076,7 +1074,7 @@ AddConnections(char *base, HnswElement element, List *neighbors, int lc)
|
||||
* Update connections
|
||||
*/
|
||||
void
|
||||
HnswUpdateConnection(char *base, HnswElement element, HnswCandidate * hc, int lm, int lc, int *updateIdx, Relation index, 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);
|
||||
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);
|
||||
|
||||
if (HnswPtrIsNull(base, hc3Element->value))
|
||||
HnswLoadElement(hc3Element, &hc3->distance, &q, index, support, true);
|
||||
HnswLoadElement(hc3Element, &hc3->distance, &q, index, procinfo, collation, true);
|
||||
else
|
||||
hc3->distance = GetCandidateDistance(base, hc3, q, support);
|
||||
hc3->distance = GetCandidateDistance(base, hc3, q, procinfo, collation);
|
||||
|
||||
/* Prune element if being deleted */
|
||||
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, &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 */
|
||||
if (pruned == NULL)
|
||||
@@ -1205,7 +1203,7 @@ PrecomputeHash(char *base, HnswElement element)
|
||||
* Algorithm 1 from paper
|
||||
*/
|
||||
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 *w;
|
||||
@@ -1225,13 +1223,13 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
|
||||
return;
|
||||
|
||||
/* 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;
|
||||
|
||||
/* 1st phase: greedy search to insert level */
|
||||
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;
|
||||
}
|
||||
|
||||
@@ -1249,7 +1247,7 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
|
||||
List *neighbors;
|
||||
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 */
|
||||
/* 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
|
||||
* 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);
|
||||
|
||||
|
||||
@@ -189,6 +189,8 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
|
||||
GenericXLogState *state;
|
||||
int m = vacuumstate->m;
|
||||
int efConstruction = vacuumstate->efConstruction;
|
||||
FmgrInfo *procinfo = vacuumstate->procinfo;
|
||||
Oid collation = vacuumstate->collation;
|
||||
BufferAccessStrategy bas = vacuumstate->bas;
|
||||
HnswNeighborTuple ntup = vacuumstate->ntup;
|
||||
Size ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(element->level, m);
|
||||
@@ -203,7 +205,7 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
|
||||
element->heaptidsLength = 0;
|
||||
|
||||
/* 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 */
|
||||
MemSet(ntup, 0, HNSW_TUPLE_ALLOC_SIZE);
|
||||
@@ -227,7 +229,7 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
|
||||
UnlockReleaseBuffer(buf);
|
||||
|
||||
/* 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);
|
||||
|
||||
/* Load element */
|
||||
HnswLoadElement(highestPoint, NULL, NULL, index, &vacuumstate->support, true);
|
||||
HnswLoadElement(highestPoint, NULL, NULL, index, vacuumstate->procinfo, vacuumstate->collation, true);
|
||||
|
||||
/* Repair if needed */
|
||||
if (NeedsUpdated(vacuumstate, highestPoint))
|
||||
@@ -292,7 +294,7 @@ RepairGraphEntryPoint(HnswVacuumState * vacuumstate)
|
||||
* is outdated, this can remove connections at higher levels in
|
||||
* the graph until they are repaired, but this should be fine.
|
||||
*/
|
||||
HnswLoadElement(entryPoint, NULL, NULL, index, &vacuumstate->support, true);
|
||||
HnswLoadElement(entryPoint, NULL, NULL, index, vacuumstate->procinfo, vacuumstate->collation, true);
|
||||
|
||||
if (NeedsUpdated(vacuumstate, entryPoint))
|
||||
{
|
||||
@@ -571,8 +573,8 @@ InitVacuumState(HnswVacuumState * vacuumstate, IndexVacuumInfo *info, IndexBulkD
|
||||
vacuumstate->callback_state = callback_state;
|
||||
vacuumstate->efConstruction = HnswGetEfConstruction(index);
|
||||
vacuumstate->bas = GetAccessStrategy(BAS_BULKREAD);
|
||||
vacuumstate->support.procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
|
||||
vacuumstate->support.collation = index->rd_indcollation[0];
|
||||
vacuumstate->procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
|
||||
vacuumstate->collation = index->rd_indcollation[0];
|
||||
vacuumstate->ntup = palloc0(HNSW_TUPLE_ALLOC_SIZE);
|
||||
vacuumstate->tmpCtx = AllocSetContextCreate(CurrentMemoryContext,
|
||||
"Hnsw vacuum temporary context",
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
comment = 'vector data type and ivfflat and hnsw access methods'
|
||||
default_version = '0.6.0'
|
||||
default_version = '0.6.1'
|
||||
module_pathname = '$libdir/vector'
|
||||
relocatable = true
|
||||
|
||||
Reference in New Issue
Block a user