Compare commits

..

15 Commits

Author SHA1 Message Date
Andrew Kane
4b2c593873 Updated number of parallel workers for IVFFlat index builds 2024-02-28 15:03:50 -08:00
Andrew Kane
447ef4d27a Specify Postgres version for Valgrind [skip ci] 2024-02-28 14:16:48 -08:00
Andrew Kane
b36cd22ccc Enable assertions on CI 2024-02-28 14:15:34 -08:00
Andrew Kane
b447ae4989 Avoid base address for relptr for Postgres < 14.5 2024-02-28 14:10:14 -08:00
Andrew Kane
efed873a3e Revert "Replaced pairing heap with array in SelectNeighbors - closes #447"
This reverts commit 14b278dec9.
2024-02-28 11:33:14 -08:00
Andrew Kane
14b278dec9 Replaced pairing heap with array in SelectNeighbors - closes #447
Co-authored-by: Heikki Linnakangas <heikki.linnakangas@iki.fi>
2024-02-28 11:25:12 -08:00
Andrew Kane
133a728e48 Updated changelog [skip ci] 2024-02-20 16:38:05 -08:00
Andrew Kane
ca10cbaa7d Revert "Remove offsethash"
This reverts commit 1cbd204f52.
2024-02-20 16:07:32 -08:00
Andrew Kane
eb29019a14 Revert "Eliminate a few HnswPtrAccess invocations"
This reverts commit 334c386a45.
2024-02-20 16:07:21 -08:00
Heikki Linnakangas
334c386a45 Eliminate a few HnswPtrAccess invocations
HnswPtrAccess() is pretty cheap, but it stills seems worthwhile to
avoid repeated calls in the hot paths when it can be easily avoided.
2024-02-19 14:13:18 +02:00
Heikki Linnakangas
1cbd204f52 Remove offsethash
The original motivation was to eliminate the superfluous HnswPtrAccess
call from AddToVisited. The caller has to call HnswPtrAccess() anyway,
so it makes sense to pass the HnswElement rather than HnswElementPtr
to AddToVisited(). But then I realized that we can use the
pointer-variant even with shared memory, because the visited-hash is
backend-private, and the addresses where the elements are mapped to in
shared memory are stable within the backend.
2024-02-19 14:12:26 +02:00
Andrew Kane
5ba62fca84 Fixed crash with shared_preload_libraries - fixes #460 2024-02-14 17:13:30 -08:00
Andrew Kane
22cb2a3fe7 Simplified Docker tasks [skip ci] 2024-02-07 12:03:33 -08:00
Andrew Kane
72b144906a Added Valgrind to CI 2024-02-07 09:43:01 -08:00
Andrew Kane
a618c1bc78 Updated port name [skip ci] 2024-02-06 12:43:20 -08:00
8 changed files with 116 additions and 10 deletions

View File

@@ -28,8 +28,10 @@ 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: sudo make install - run: |
export PG_CONFIG=`which pg_config`
sudo --preserve-env=PG_CONFIG make install
- run: make installcheck - run: make installcheck
- if: ${{ failure() }} - if: ${{ failure() }}
run: cat regression.diffs run: cat regression.diffs
@@ -37,3 +39,73 @@ jobs:
sudo apt-get update sudo apt-get update
sudo apt-get install libipc-run-perl sudo apt-get install libipc-run-perl
- run: make prove_installcheck - run: make prove_installcheck
mac:
runs-on: macos-latest
if: ${{ !startsWith(github.ref_name, 'windows') }}
steps:
- uses: actions/checkout@v4
- uses: ankane/setup-postgres@v1
with:
postgres-version: 14
- run: make
env:
PG_CFLAGS: -DUSE_ASSERT_CHECKING -Wall -Wextra -Werror -Wno-unused-parameter
- run: make install
- run: make installcheck
- if: ${{ failure() }}
run: cat regression.diffs
- run: |
brew install cpanm
cpanm --notest IPC::Run
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"
windows:
runs-on: windows-latest
if: ${{ !startsWith(github.ref_name, 'mac') }}
steps:
- uses: actions/checkout@v4
- uses: ankane/setup-postgres@v1
with:
postgres-version: 14
- run: |
call "C:\Program Files\Microsoft Visual Studio\2022\Enterprise\VC\Auxiliary\Build\vcvars64.bat" && ^
nmake /NOLOGO /F Makefile.win && ^
nmake /NOLOGO /F Makefile.win install && ^
nmake /NOLOGO /F Makefile.win installcheck && ^
nmake /NOLOGO /F Makefile.win clean && ^
nmake /NOLOGO /F Makefile.win uninstall
shell: cmd
i386:
if: ${{ !startsWith(github.ref_name, 'mac') && !startsWith(github.ref_name, 'windows') }}
runs-on: ubuntu-latest
container:
image: debian:12
options: --platform linux/386
steps:
- run: apt-get update && apt-get install -y build-essential git libipc-run-perl postgresql-15 postgresql-server-dev-15 sudo
- run: service postgresql start
- run: |
git clone https://github.com/${{ github.repository }}.git pgvector
cd pgvector
git fetch origin ${{ github.ref }}
git reset --hard FETCH_HEAD
make
make install
chown -R postgres .
sudo -u postgres make installcheck
sudo -u postgres make prove_installcheck
env:
PG_CFLAGS: -DUSE_ASSERT_CHECKING -Wall -Wextra -Werror -Wno-unused-parameter -Wno-sign-compare
valgrind:
if: ${{ !startsWith(github.ref_name, 'mac') && !startsWith(github.ref_name, 'windows') }}
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: ankane/setup-postgres-valgrind@v1
with:
postgres-version: 16
- run: make
- run: sudo --preserve-env=PG_CONFIG make install
- run: make installcheck

View File

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

View File

@@ -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) .

View File

@@ -727,7 +727,7 @@ pkg install postgresql15-pg_vector
or the port with: or the port with:
```sh ```sh
cd /usr/ports/databases/pg_vector cd /usr/ports/databases/pgvector
make install make install
``` ```

View File

@@ -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;
@@ -53,7 +54,8 @@ HnswInitLockTranche(void)
void void
HnswInit(void) HnswInit(void)
{ {
HnswInitLockTranche(); if (!process_shared_preload_libraries_in_progress)
HnswInitLockTranche();
hnsw_relopt_kind = add_reloption_kind(); hnsw_relopt_kind = add_reloption_kind();
add_int_reloption(hnsw_relopt_kind, "m", "Max number of connections", add_int_reloption(hnsw_relopt_kind, "m", "Max number of connections",

View File

@@ -389,6 +389,7 @@ void HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation i
void HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element); void HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element);
void HnswUpdateConnection(char *base, HnswElement element, HnswCandidate * hc, int lm, int lc, int *updateIdx, Relation index, FmgrInfo *procinfo, Oid collation); void HnswUpdateConnection(char *base, HnswElement element, HnswCandidate * hc, int lm, int lc, int *updateIdx, Relation index, FmgrInfo *procinfo, Oid collation);
void HnswLoadNeighbors(HnswElement element, Relation index, int m); void HnswLoadNeighbors(HnswElement element, Relation index, int m);
void HnswInitLockTranche(void);
PGDLLEXPORT void HnswParallelBuildMain(dsm_segment *seg, shm_toc *toc); PGDLLEXPORT void HnswParallelBuildMain(dsm_segment *seg, shm_toc *toc);
/* Index access methods */ /* Index access methods */

View File

@@ -601,6 +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;
@@ -974,6 +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);

View File

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