Added concatenate operator for vectors

Redefining a typedef is a C11 feature:

    In file included from src/hnsw.c:10:
    src/hnsw.h:147:5: warning: redefinition of typedef 'HnswElementData' is a C11 feature [-Wtypedef-redefinition]
    }                       HnswElementData;
                            ^
    src/hnsw.h:118:32: note: previous definition is here
    typedef struct HnswElementData HnswElementData;
                                   ^
    src/hnsw.h:163:5: warning: redefinition of typedef 'HnswNeighborArray' is a C11 feature [-Wtypedef-redefinition]
    }                       HnswNeighborArray;
                            ^
    src/hnsw.h:119:34: note: previous definition is here
    typedef struct HnswNeighborArray HnswNeighborArray;
                                     ^
    2 warnings generated.

I got these warnings when I built PostgreSQL with "CC=clang
CFLAGS=-std=gnu99"; other similar options would surely produce the
warnings too.

.github/workflows/build.yml

@@ -20,8 +20,6 @@ jobs:
             os: ubuntu-20.04
           - postgres: 12
             os: ubuntu-20.04
-          - postgres: 11
-            os: ubuntu-20.04
     steps:
       - uses: actions/checkout@v4
       - uses: ankane/setup-postgres@v1
@@ -30,7 +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
@@ -51,7 +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() }}
@@ -59,10 +57,12 @@ jobs:
       - run: |
           brew install cpanm
           cpanm --notest IPC::Run
-          wget -q https://github.com/postgres/postgres/archive/refs/tags/REL_14_5.tar.gz
+          wget -q https://github.com/postgres/postgres/archive/refs/tags/REL_14_10.tar.gz
-          tar xf REL_14_5.tar.gz
+          tar xf REL_14_10.tar.gz
-      - run: make prove_installcheck PROVE_FLAGS="-I ./postgres-REL_14_5/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:
     runs-on: windows-latest
     if: ${{ !startsWith(github.ref_name, 'mac') }}
@@ -73,6 +73,7 @@ jobs:
           postgres-version: 14
       - run: |
           call "C:\Program Files\Microsoft Visual Studio\2022\Enterprise\VC\Auxiliary\Build\vcvars64.bat" && ^
+          cd %TEMP% && ^
           nmake /NOLOGO /F Makefile.win && ^
           nmake /NOLOGO /F Makefile.win install && ^
           nmake /NOLOGO /F Makefile.win installcheck && ^
@@ -83,10 +84,10 @@ jobs:
     if: ${{ !startsWith(github.ref_name, 'mac') && !startsWith(github.ref_name, 'windows') }}
     runs-on: ubuntu-latest
     container:
-      image: debian:11
+      image: debian:12
       options: --platform linux/386
     steps:
-      - run: apt-get update && apt-get install -y build-essential git libipc-run-perl postgresql-13 postgresql-server-dev-13 sudo
+      - run: apt-get update && apt-get install -y build-essential git libipc-run-perl postgresql-15 postgresql-server-dev-15 sudo
       - run: service postgresql start
       - run: |
           git clone https://github.com/${{ github.repository }}.git pgvector
@@ -99,4 +100,15 @@ 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

CHANGELOG.md

@@ -1,10 +1,32 @@
-## 0.5.2 (unreleased)
+## 0.7.0 (unreleased)
+
+- Added concatenate operator for vectors
+
+## 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)
+
+If upgrading with Postgres 12 or Docker, see [these notes](https://github.com/pgvector/pgvector#060).
 
-- Improved performance of HNSW
 - Added support for parallel index builds for HNSW
+- Added validation for GUC parameters
+- Changed storage for vector from `extended` to `external`
+- Improved performance of HNSW
 - Reduced memory usage for HNSW index builds
 - Reduced WAL generation for HNSW index builds
-- Fixed `invalid memory alloc request size` error with HNSW index build
+- Fixed error with logical replication
+- Fixed `invalid memory alloc request size` error with HNSW index builds
+- Moved Docker image to `pgvector` org
+- Added Docker tags for each supported version of Postgres
+- Dropped support for Postgres 11
 
 ## 0.5.1 (2023-10-10)
 
@@ -52,7 +74,7 @@
 
 ## 0.4.0 (2023-01-11)
 
-If upgrading with Postgres < 13, see [this note](https://github.com/pgvector/pgvector#040).
+If upgrading with Postgres < 13, see [this note](https://github.com/pgvector/pgvector/blob/v0.4.0/README.md#040).
 
 - Changed text representation for vector elements to match `real`
 - Changed storage for vector from `plain` to `extended`
@@ -69,7 +91,7 @@ If upgrading with Postgres < 13, see [this note](https://github.com/pgvector/pgv
 
 ## 0.3.1 (2022-11-02)
 
-If upgrading from 0.2.7 or 0.3.0, [recreate](https://github.com/pgvector/pgvector#031) all `ivfflat` indexes after upgrading to ensure all data is indexed.
+If upgrading from 0.2.7 or 0.3.0, [recreate](https://github.com/pgvector/pgvector/blob/v0.3.1/README.md#031) all `ivfflat` indexes after upgrading to ensure all data is indexed.
 
 - Fixed issue with inserts silently corrupting `ivfflat` indexes (introduced in 0.2.7)
 - Fixed segmentation fault with index creation when lists > 6500

Dockerfile

@@ -1,4 +1,4 @@
-ARG PG_MAJOR=15
+ARG PG_MAJOR=16
 FROM postgres:$PG_MAJOR
 ARG PG_MAJOR
 

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
 

META.json

@@ -2,7 +2,7 @@
 	"name": "vector",
 	"abstract": "Open-source vector similarity search for Postgres",
 	"description": "Supports L2 distance, inner product, and cosine distance",
-	"version": "0.5.1",
+	"version": "0.6.1",
 	"maintainer": [
 		"Andrew Kane <andrew@ankane.org>"
 	],
@@ -12,7 +12,7 @@
 	"prereqs": {
 		"runtime": {
 			"requires": {
-				"PostgreSQL": "11.0.0"
+				"PostgreSQL": "12.0.0"
 			}
 		}
 	},
@@ -20,7 +20,7 @@
 		"vector": {
 			"file": "sql/vector.sql",
 			"docfile": "README.md",
-			"version": "0.5.1",
+			"version": "0.6.1",
 			"abstract": "Open-source vector similarity search for Postgres"
 		}
 	},

Makefile

@@ -1,5 +1,5 @@
 EXTENSION = vector
-EXTVERSION = 0.5.1
+EXTVERSION = 0.6.1
 
 MODULE_big = vector
 DATA = $(wildcard sql/*--*.sql)
@@ -65,13 +65,15 @@ dist:
 	mkdir -p dist
 	git archive --format zip --prefix=$(EXTENSION)-$(EXTVERSION)/ --output dist/$(EXTENSION)-$(EXTVERSION).zip master
 
+# for Docker
+PG_MAJOR ?= 16
+
 .PHONY: docker
 
 docker:
-	docker build --pull --no-cache --platform linux/amd64 -t ankane/pgvector:latest .
+	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 -t ankane/pgvector:latest .
+	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 -t ankane/pgvector:v$(EXTVERSION) .

Makefile.win

@@ -1,5 +1,5 @@
 EXTENSION = vector
-EXTVERSION = 0.5.1
+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

README.md

@@ -14,19 +14,46 @@ Plus [ACID](https://en.wikipedia.org/wiki/ACID) compliance, point-in-time recove
 
 ## Installation
 
-Compile and install the extension (supports Postgres 11+)
+### Linux and Mac
+
+Compile and install the extension (supports Postgres 12+)
 
 ```sh
 cd /tmp
-git clone --branch v0.5.1 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
 ```
 
-See the [installation notes](#installation-notes) if you run into issues
+See the [installation notes](#installation-notes---linux-and-mac) 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
+
+Ensure [C++ support in Visual Studio](https://learn.microsoft.com/en-us/cpp/build/building-on-the-command-line?view=msvc-170#download-and-install-the-tools) is installed, and run:
+
+```cmd
+call "C:\Program Files\Microsoft Visual Studio\2022\Community\VC\Auxiliary\Build\vcvars64.bat"
+```
+
+Note: The exact path will vary depending on your Visual Studio version and edition
+
+Then use `nmake` to build:
+
+```cmd
+set "PGROOT=C:\Program Files\PostgreSQL\16"
+cd %TEMP%
+git clone --branch v0.6.1 https://github.com/pgvector/pgvector.git
+cd pgvector
+nmake /F Makefile.win
+nmake /F Makefile.win install
+```
+
+See the [installation notes](#installation-notes---windows) if you run into issues
+
+You can also install it with [Docker](#docker) or [conda-forge](#conda-forge).
 
 ## Getting Started
 
@@ -78,6 +105,12 @@ 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
@@ -240,6 +273,16 @@ 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
+SET max_parallel_maintenance_workers = 7; -- plus leader
+```
+
+For a large number of workers, you may also need to increase `max_parallel_workers` (8 by default)
+
 ### Indexing Progress
 
 Check [indexing progress](https://www.postgresql.org/docs/current/progress-reporting.html#CREATE-INDEX-PROGRESS-REPORTING) with Postgres 12+
@@ -304,6 +347,16 @@ SELECT ...
 COMMIT;
 ```
 
+### Index Build Time
+
+Speed up index creation on large tables by increasing the number of parallel workers (2 by default)
+
+```sql
+SET max_parallel_maintenance_workers = 7; -- plus leader
+```
+
+For a large number of workers, you may also need to increase `max_parallel_workers` (8 by default)
+
 ### Indexing Progress
 
 Check [indexing progress](https://www.postgresql.org/docs/current/progress-reporting.html#CREATE-INDEX-PROGRESS-REPORTING) with Postgres 12+
@@ -360,13 +413,39 @@ You can use [Reciprocal Rank Fusion](https://github.com/pgvector/pgvector-python
 
 ## Performance
 
+### Tuning
+
+Use a tool like [PgTune](https://pgtune.leopard.in.ua/) to set initial values for Postgres server parameters.
+
+### Loading
+
+Use `COPY` for bulk loading data ([example](https://github.com/pgvector/pgvector-python/blob/master/examples/bulk_loading.py)).
+
+```sql
+COPY items (embedding) FROM STDIN WITH (FORMAT BINARY);
+```
+
+Add any indexes *after* loading the initial data for best performance.
+
+### Indexing
+
+See index build time for [HNSW](#index-build-time) and [IVFFlat](#index-build-time-1).
+
+In production environments, create indexes concurrently to avoid blocking writes.
+
+```sql
+CREATE INDEX CONCURRENTLY ...
+```
+
+### Querying
+
 Use `EXPLAIN ANALYZE` to debug performance.
 
 ```sql
 EXPLAIN ANALYZE SELECT * FROM items ORDER BY embedding <-> '[3,1,2]' LIMIT 5;
 ```
 
-### Exact Search
+#### Exact Search
 
 To speed up queries without an index, increase `max_parallel_workers_per_gather`.
 
@@ -380,7 +459,7 @@ If vectors are normalized to length 1 (like [OpenAI embeddings](https://platform
 SELECT * FROM items ORDER BY embedding <#> '[3,1,2]' LIMIT 5;
 ```
 
-### Approximate Search
+#### Approximate Search
 
 To speed up queries with an IVFFlat index, increase the number of inverted lists (at the expense of recall).
 
@@ -388,6 +467,50 @@ To speed up queries with an IVFFlat index, increase the number of inverted lists
 CREATE INDEX ON items USING ivfflat (embedding vector_l2_ops) WITH (lists = 1000);
 ```
 
+### Vacuuming
+
+Vacuuming can take a while for HNSW indexes. Speed it up by reindexing first.
+
+```sql
+REINDEX INDEX CONCURRENTLY index_name;
+VACUUM table_name;
+```
+
+## Monitoring
+
+Monitor performance with [pg_stat_statements](https://www.postgresql.org/docs/current/pgstatstatements.html) (be sure to add it to `shared_preload_libraries`).
+
+```sql
+CREATE EXTENSION pg_stat_statements;
+```
+
+Get the most time-consuming queries with:
+
+```sql
+SELECT query, calls, ROUND((total_plan_time + total_exec_time) / calls) AS avg_time_ms,
+    ROUND((total_plan_time + total_exec_time) / 60000) AS total_time_min
+    FROM pg_stat_statements ORDER BY total_plan_time + total_exec_time DESC LIMIT 20;
+```
+
+Note: Replace `total_plan_time + total_exec_time` with `total_time` for Postgres < 13
+
+Monitor recall by comparing results from approximate search with exact search.
+
+```sql
+BEGIN;
+SET LOCAL enable_indexscan = off; -- use exact search
+SELECT ...
+COMMIT;
+```
+
+## Scaling
+
+Scale pgvector the same way you scale Postgres.
+
+Scale vertically by increasing memory, CPU, and storage on a single instance. Use existing tools to [tune parameters](#tuning) and [monitor performance](#monitoring).
+
+Scale horizontally with [replicas](https://www.postgresql.org/docs/current/hot-standby.html), or use [Citus](https://github.com/citusdata/citus) or another approach for sharding ([example](https://github.com/pgvector/pgvector-python/blob/master/examples/citus.py)).
+
 ## Languages
 
 Use pgvector from any language with a Postgres client. You can even generate and store vectors in one language and query them in another.
@@ -493,7 +616,17 @@ SELECT pg_size_pretty(pg_relation_size('index_name'));
 
 #### Why isn’t a query using an index?
 
-The cost estimation in pgvector < 0.4.3 does not always work well with the planner. You can encourage the planner to use an index for a query with:
+The query needs to have an `ORDER BY` and `LIMIT`, and the `ORDER BY` must be the result of a distance operator, not an expression.
+
+```sql
+-- index
+ORDER BY embedding <=> '[3,1,2]' LIMIT 5;
+
+-- no index
+ORDER BY 1 - (embedding <=> '[3,1,2]') DESC LIMIT 5;
+```
+
+You can encourage the planner to use an index for a query with:
 
 ```sql
 BEGIN;
@@ -522,6 +655,10 @@ 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.
@@ -530,6 +667,8 @@ 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
@@ -543,6 +682,7 @@ Operator | Description | Added
 \+ | element-wise addition |
 \- | element-wise subtraction |
 \* | element-wise multiplication | 0.5.0
+\|\| | concatenate | 0.7.0
 <-> | Euclidean distance |
 <#> | negative inner product |
 <=> | cosine distance |
@@ -565,14 +705,14 @@ Function | Description | Added
 avg(vector) → vector | average |
 sum(vector) → vector | sum | 0.5.0
 
-## Installation Notes
+## Installation Notes - Linux and Mac
 
 ### Postgres Location
 
 If your machine has multiple Postgres installations, specify the path to [pg_config](https://www.postgresql.org/docs/current/app-pgconfig.html) with:
 
 ```sh
-export PG_CONFIG=/Applications/Postgres.app/Contents/Versions/latest/bin/pg_config
+export PG_CONFIG=/Library/PostgreSQL/16/bin/pg_config
 ```
 
 Then re-run the installation instructions (run `make clean` before `make` if needed). If `sudo` is needed for `make install`, use:
@@ -581,6 +721,14 @@ Then re-run the installation instructions (run `make clean` before `make` if nee
 sudo --preserve-env=PG_CONFIG make install
 ```
 
+A few common paths on Mac are:
+
+- EDB installer - `/Library/PostgreSQL/16/bin/pg_config`
+- Homebrew (arm64) - `/opt/homebrew/opt/postgresql@16/bin/pg_config`
+- Homebrew (x86-64) - `/usr/local/opt/postgresql@16/bin/pg_config`
+
+Note: Replace `16` with your Postgres server version
+
 ### Missing Header
 
 If compilation fails with `fatal error: postgres.h: No such file or directory`, make sure Postgres development files are installed on the server.
@@ -593,44 +741,48 @@ sudo apt install postgresql-server-dev-16
 
 Note: Replace `16` with your Postgres server version
 
-### Windows
+### Missing SDK
 
-Support for Windows is currently experimental. Ensure [C++ support in Visual Studio](https://learn.microsoft.com/en-us/cpp/build/building-on-the-command-line?view=msvc-170#download-and-install-the-tools) is installed, and run:
+If compilation fails and the output includes `warning: no such sysroot directory` on Mac, reinstall Xcode Command Line Tools.
 
-```cmd
+### Portability
-call "C:\Program Files\Microsoft Visual Studio\2022\Community\VC\Auxiliary\Build\vcvars64.bat"
+
+By default, pgvector compiles with `-march=native` on some platforms for best performance. However, this can lead to `Illegal instruction` errors if trying to run the compiled extension on a different machine.
+
+To compile for portability, use:
+
+```sh
+make OPTFLAGS=""
 ```
 
-Note: The exact path will vary depending on your Visual Studio version and edition
+## Installation Notes - Windows
 
-Then use `nmake` to build:
+### Missing Header
 
-```cmd
+If compilation fails with `Cannot open include file: 'postgres.h': No such file or directory`, make sure `PGROOT` is correct.
-set "PGROOT=C:\Program Files\PostgreSQL\16"
+
-git clone --branch v0.5.1 https://github.com/pgvector/pgvector.git
+### Permissions
-cd pgvector
+
-nmake /F Makefile.win
+If installation fails with `Access is denied`, re-run the installation instructions as an administrator.
-nmake /F Makefile.win install
-```
 
 ## Additional Installation Methods
 
 ### Docker
 
-Get the [Docker image](https://hub.docker.com/r/ankane/pgvector) with:
+Get the [Docker image](https://hub.docker.com/r/pgvector/pgvector) with:
 
 ```sh
-docker pull ankane/pgvector
+docker pull pgvector/pgvector:pg16
 ```
 
-This adds pgvector to the [Postgres image](https://hub.docker.com/_/postgres) (run it the same way).
+This adds pgvector to the [Postgres image](https://hub.docker.com/_/postgres) (replace `16` with your Postgres server version, and run it the same way).
 
 You can also build the image manually:
 
 ```sh
-git clone --branch v0.5.1 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=15 -t myuser/pgvector .
+docker build --build-arg PG_MAJOR=16 -t myuser/pgvector .
 ```
 
 ### Homebrew
@@ -673,6 +825,21 @@ 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:
@@ -707,28 +874,32 @@ SELECT extversion FROM pg_extension WHERE extname = 'vector';
 
 ## Upgrade Notes
 
-### 0.4.0
+### 0.6.0
 
-If upgrading with Postgres < 13, remove this line from `sql/vector--0.3.2--0.4.0.sql`:
+#### Postgres 12
+
+If upgrading with Postgres 12, remove this line from `sql/vector--0.5.1--0.6.0.sql`:
 
 ```sql
-ALTER TYPE vector SET (STORAGE = extended);
+ALTER TYPE vector SET (STORAGE = external);
 ```
 
 Then run `make install` and `ALTER EXTENSION vector UPDATE;`.
 
-### 0.3.1
+#### Docker
 
-If upgrading from 0.2.7 or 0.3.0, recreate all `ivfflat` indexes after upgrading to ensure all data is indexed.
+The Docker image is now published in the `pgvector` org, and there are tags for each supported version of Postgres (rather than a `latest` tag).
 
-```sql
+```sh
--- Postgres 12+
+docker pull pgvector/pgvector:pg16
-REINDEX INDEX CONCURRENTLY index_name;
+# or
+docker pull pgvector/pgvector:0.6.0-pg16
+```
 
--- Postgres < 12
+Also, if you’ve increased `maintenance_work_mem`, make sure `--shm-size` is at least that size to avoid an error with parallel HNSW index builds.
-CREATE INDEX CONCURRENTLY temp_name ON table USING ivfflat (column opclass);
+
-DROP INDEX CONCURRENTLY index_name;
+```sh
-ALTER INDEX temp_name RENAME TO index_name;
+docker run --shm-size=1g ...
 ```
 
 ## Thanks
@@ -774,14 +945,32 @@ make prove_installcheck  # TAP tests
 To run single tests:
 
 ```sh
-make installcheck REGRESS=functions                    # regression test
+make installcheck REGRESS=functions                            # regression test
-make prove_installcheck PROVE_TESTS=test/t/001_wal.pl  # TAP test
+make prove_installcheck PROVE_TESTS=test/t/001_ivfflat_wal.pl  # TAP test
+```
+
+To enable assertions:
+
+```sh
+make clean && PG_CFLAGS="-DUSE_ASSERT_CHECKING" make && make install
 ```
 
 To enable benchmarking:
 
 ```sh
-make clean && PG_CFLAGS=-DIVFFLAT_BENCH make && make install
+make clean && PG_CFLAGS="-DIVFFLAT_BENCH" make && make install
+```
+
+To show memory usage:
+
+```sh
+make clean && PG_CFLAGS="-DHNSW_MEMORY -DIVFFLAT_MEMORY" make && make install
+```
+
+To get k-means metrics:
+
+```sh
+make clean && PG_CFLAGS="-DIVFFLAT_KMEANS_DEBUG" make && make install
 ```
 
 Resources for contributors

sql/vector--0.5.1--0.6.0.sql

@@ -0,0 +1,5 @@
+-- complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "ALTER EXTENSION vector UPDATE TO '0.6.0'" to load this file. \quit
+
+-- remove this single line for Postgres < 13
+ALTER TYPE vector SET (STORAGE = external);

sql/vector--0.6.0--0.6.1.sql

@@ -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
+);

sql/vector--0.6.2--0.7.0.sql

@@ -0,0 +1,9 @@
+-- complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "ALTER EXTENSION vector UPDATE TO '0.7.0'" to load this file. \quit
+
+CREATE FUNCTION vector_concat(vector, vector) RETURNS vector
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE OPERATOR || (
+	LEFTARG = vector, RIGHTARG = vector, PROCEDURE = vector_concat
+);

sql/vector.sql

@@ -26,7 +26,7 @@ CREATE TYPE vector (
 	TYPMOD_IN = vector_typmod_in,
 	RECEIVE   = vector_recv,
 	SEND      = vector_send,
-	STORAGE   = extended
+	STORAGE   = external
 );
 
 -- functions
@@ -99,6 +99,9 @@ CREATE FUNCTION vector_avg(double precision[]) RETURNS vector
 CREATE FUNCTION vector_combine(double precision[], double precision[]) RETURNS double precision[]
 	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
 
+CREATE FUNCTION vector_concat(vector, vector) RETURNS vector
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
 -- aggregates
 
 CREATE AGGREGATE avg(vector) (
@@ -180,8 +183,7 @@ CREATE OPERATOR + (
 );
 
 CREATE OPERATOR - (
-	LEFTARG = vector, RIGHTARG = vector, PROCEDURE = vector_sub,
+	LEFTARG = vector, RIGHTARG = vector, PROCEDURE = vector_sub
-	COMMUTATOR = -
 );
 
 CREATE OPERATOR * (
@@ -195,11 +197,10 @@ 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 +215,10 @@ 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 > (
@@ -227,6 +227,10 @@ CREATE OPERATOR > (
 	RESTRICT = scalargtsel, JOIN = scalargtjoinsel
 );
 
+CREATE OPERATOR || (
+	LEFTARG = vector, RIGHTARG = vector, PROCEDURE = vector_concat
+);
+
 -- access methods
 
 CREATE FUNCTION ivfflathandler(internal) RETURNS index_am_handler

src/hnsw.c

@@ -4,13 +4,16 @@
 #include <math.h>
 
 #include "access/amapi.h"
+#include "access/reloptions.h"
+#include "commands/progress.h"
 #include "commands/vacuum.h"
 #include "hnsw.h"
+#include "miscadmin.h"
 #include "utils/guc.h"
 #include "utils/selfuncs.h"
 
-#if PG_VERSION_NUM >= 120000
+#if PG_VERSION_NUM < 150000
-#include "commands/progress.h"
+#define MarkGUCPrefixReserved(x) EmitWarningsOnPlaceholders(x)
 #endif
 
 int			hnsw_ef_search;
@@ -26,7 +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;
@@ -51,7 +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",
@@ -70,12 +74,13 @@ HnswInit(void)
 	DefineCustomIntVariable("hnsw.ef_search", "Sets the size of the dynamic candidate list for search",
 							"Valid range is 1..1000.", &hnsw_ef_search,
 							HNSW_DEFAULT_EF_SEARCH, HNSW_MIN_EF_SEARCH, HNSW_MAX_EF_SEARCH, PGC_USERSET, 0, NULL, NULL, NULL);
+
+	MarkGUCPrefixReserved("hnsw");
 }
 
 /*
  * Get the name of index build phase
  */
-#if PG_VERSION_NUM >= 120000
 static char *
 hnswbuildphasename(int64 phasenum)
 {
@@ -89,7 +94,6 @@ hnswbuildphasename(int64 phasenum)
 			return NULL;
 	}
 }
-#endif
 
 /*
  * Estimate the cost of an index scan
@@ -104,9 +108,6 @@ hnswcostestimate(PlannerInfo *root, IndexPath *path, double loop_count,
 	int			m;
 	int			entryLevel;
 	Relation	index;
-#if PG_VERSION_NUM < 120000
-	List	   *qinfos;
-#endif
 
 	/* Never use index without order */
 	if (path->indexorderbys == NULL)
@@ -132,12 +133,7 @@ hnswcostestimate(PlannerInfo *root, IndexPath *path, double loop_count,
 	/* Account for number of tuples (or entry level), m, and ef_search */
 	costs.numIndexTuples = (entryLevel + 2) * m;
 
-#if PG_VERSION_NUM >= 120000
 	genericcostestimate(root, path, loop_count, &costs);
-#else
-	qinfos = deconstruct_indexquals(path);
-	genericcostestimate(root, path, loop_count, qinfos, &costs);
-#endif
 
 	/* Use total cost since most work happens before first tuple is returned */
 	*indexStartupCost = costs.indexTotalCost;
@@ -231,9 +227,7 @@ hnswhandler(PG_FUNCTION_ARGS)
 	amroutine->amcostestimate = hnswcostestimate;
 	amroutine->amoptions = hnswoptions;
 	amroutine->amproperty = NULL;	/* TODO AMPROP_DISTANCE_ORDERABLE */
-#if PG_VERSION_NUM >= 120000
 	amroutine->ambuildphasename = hnswbuildphasename;
-#endif
 	amroutine->amvalidate = hnswvalidate;
 #if PG_VERSION_NUM >= 140000
 	amroutine->amadjustmembers = NULL;

src/hnsw.h

@@ -3,21 +3,17 @@
 
 #include "postgres.h"
 
-#include "access/generic_xlog.h"
+#include "access/genam.h"
 #include "access/parallel.h"
-#include "access/reloptions.h"
+#include "lib/pairingheap.h"
 #include "nodes/execnodes.h"
 #include "port.h"				/* for random() */
 #include "utils/relptr.h"
 #include "utils/sampling.h"
 #include "vector.h"
 
-#if PG_VERSION_NUM < 110000
-#error "Requires PostgreSQL 11+"
-#endif
-
 #if PG_VERSION_NUM < 120000
-#include "access/relscan.h"
+#error "Requires PostgreSQL 12+"
 #endif
 
 #define HNSW_MAX_DIM 2000
@@ -64,10 +60,13 @@
 #define PROGRESS_HNSW_PHASE_LOAD		2
 
 #define HNSW_MAX_SIZE (BLCKSZ - MAXALIGN(SizeOfPageHeaderData) - MAXALIGN(sizeof(HnswPageOpaqueData)) - sizeof(ItemIdData))
+#define HNSW_TUPLE_ALLOC_SIZE BLCKSZ
 
 #define HNSW_ELEMENT_TUPLE_SIZE(size)	MAXALIGN(offsetof(HnswElementTupleData, data) + (size))
 #define HNSW_NEIGHBOR_TUPLE_SIZE(level, m)	MAXALIGN(offsetof(HnswNeighborTupleData, indextids) + ((level) + 2) * (m) * sizeof(ItemPointerData))
 
+#define HNSW_NEIGHBOR_ARRAY_SIZE(lm)	(offsetof(HnswNeighborArray, items) + sizeof(HnswCandidate) * (lm))
+
 #define HnswPageGetOpaque(page)	((HnswPageOpaque) PageGetSpecialPointer(page))
 #define HnswPageGetMeta(page)	((HnswMetaPageData *) PageGetContents(page))
 
@@ -81,7 +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)
@@ -114,8 +113,6 @@
 
 /* Variables */
 extern int	hnsw_ef_search;
-
-/* This is initialized when the module is loaded */
 extern int	hnsw_lock_tranche_id;
 
 typedef struct HnswElementData HnswElementData;
@@ -132,7 +129,7 @@ HnswPtrDeclare(HnswNeighborArray, HnswNeighborArrayRelptr, HnswNeighborArrayPtr)
 HnswPtrDeclare(HnswNeighborArrayPtr, HnswNeighborsRelptr, HnswNeighborsPtr);
 HnswPtrDeclare(char, DatumRelptr, DatumPtr);
 
-typedef struct HnswElementData
+struct HnswElementData
 {
 	HnswElementPtr next;
 	ItemPointerData heaptids[HNSW_HEAPTIDS];
@@ -147,7 +144,7 @@ typedef struct HnswElementData
 	BlockNumber neighborPage;
 	DatumPtr	value;
 	LWLock		lock;
-}			HnswElementData;
+};
 
 typedef HnswElementData * HnswElement;
 
@@ -158,12 +155,12 @@ typedef struct HnswCandidate
 	bool		closer;
 }			HnswCandidate;
 
-typedef struct HnswNeighborArray
+struct HnswNeighborArray
 {
 	int			length;
 	bool		closerSet;
 	HnswCandidate items[FLEXIBLE_ARRAY_MEMBER];
-}			HnswNeighborArray;
+};
 
 typedef struct HnswPairingHeapNode
 {
@@ -188,6 +185,7 @@ typedef struct HnswGraph
 
 	/* Entry state */
 	LWLock		entryLock;
+	LWLock		entryWaitLock;
 	HnswElementPtr entryPoint;
 
 	/* Allocations state */
@@ -200,20 +198,12 @@ typedef struct HnswGraph
 	bool		flushed;
 }			HnswGraph;
 
-typedef struct HnswSpool
-{
-	Relation	heap;
-	Relation	index;
-}			HnswSpool;
-
 typedef struct HnswShared
 {
 	/* Immutable state */
 	Oid			heaprelid;
 	Oid			indexrelid;
 	bool		isconcurrent;
-	int			scantuplesortstates;
-	dsa_pointer dsaptr;
 
 	/* Worker progress */
 	ConditionVariable workersdonecv;
@@ -225,16 +215,10 @@ typedef struct HnswShared
 	int			nparticipantsdone;
 	double		reltuples;
 	HnswGraph	graphData;
-
-#if PG_VERSION_NUM < 120000
-	ParallelHeapScanDescData heapdesc;	/* must come last */
-#endif
 }			HnswShared;
 
-#if PG_VERSION_NUM >= 120000
 #define ParallelTableScanFromHnswShared(shared) \
 	(ParallelTableScanDesc) ((char *) (shared) + BUFFERALIGN(sizeof(HnswShared)))
-#endif
 
 typedef struct HnswLeader
 {
@@ -393,19 +377,20 @@ 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		HnswInsertElement(char *base, HnswElement element, HnswElement entryPoint, Relation index, FmgrInfo *procinfo, Oid collation, int m, int efConstruction, bool existing);
+void		HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, FmgrInfo *procinfo, Oid collation, int m, int efConstruction, bool existing);
 HnswCandidate *HnswEntryCandidate(char *base, HnswElement em, Datum q, Relation rel, FmgrInfo *procinfo, Oid collation, bool loadVec);
 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, Relation heapRel, bool building);
+bool		HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull, ItemPointer heap_tid, bool building);
-void		HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement e, int m, bool checkExisting, bool building);
+void		HnswUpdateNeighborsOnDisk(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement e, int m, bool checkExisting, bool building);
 void		HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHeaptids, bool loadVec);
 void		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 m, 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		HnswInitLockTranche(void);
 PGDLLEXPORT void HnswParallelBuildMain(dsm_segment *seg, shm_toc *toc);
 
 /* Index access methods */

src/hnswbuild.c

@@ -1,14 +1,53 @@
+/*
+ * The HNSW build happens in two phases:
+ *
+ * 1. In-memory phase
+ *
+ * In this first phase, the graph is held completely in memory. When the graph
+ * is fully built, or we run out of memory reserved for the build (determined
+ * by maintenance_work_mem), we materialize the graph to disk (see
+ * FlushPages()), and switch to the on-disk phase.
+ *
+ * In a parallel build, a large contiguous chunk of shared memory is allocated
+ * to hold the graph. Each worker process has its own HnswBuildState struct in
+ * private memory, which contains information that doesn't change throughout
+ * the build, and pointers to the shared structs in shared memory. The shared
+ * memory area is mapped to a different address in each worker process, and
+ * 'HnswBuildState.hnswarea' points to the beginning of the shared area in the
+ * worker process's address space. All pointers used in the graph are
+ * "relative pointers", stored as an offset from 'hnswarea'.
+ *
+ * Each element is protected by an LWLock. It must be held when reading or
+ * modifying the element's neighbors or 'heaptids'.
+ *
+ * In a non-parallel build, the graph is held in backend-private memory. All
+ * the elements are allocated in a dedicated memory context, 'graphCtx', and
+ * the pointers used in the graph are regular pointers.
+ *
+ * 2. On-disk phase
+ *
+ * In the on-disk phase, the index is built by inserting each vector to the
+ * index one by one, just like on INSERT. The only difference is that we don't
+ * WAL-log the individual inserts. If the graph fit completely in memory and
+ * was fully built in the in-memory phase, the on-disk phase is skipped.
+ *
+ * After we have finished building the graph, we perform one more scan through
+ * the index and write all the pages to the WAL.
+ */
 #include "postgres.h"
 
 #include <math.h>
 
 #include "access/parallel.h"
+#include "access/table.h"
+#include "access/tableam.h"
 #include "access/xact.h"
+#include "access/xloginsert.h"
 #include "catalog/index.h"
+#include "commands/progress.h"
 #include "hnsw.h"
 #include "miscadmin.h"
-#include "lib/pairingheap.h"
+#include "optimizer/optimizer.h"
-#include "nodes/pg_list.h"
 #include "storage/bufmgr.h"
 #include "tcop/tcopprot.h"
 #include "utils/datum.h"
@@ -16,15 +55,8 @@
 
 #if PG_VERSION_NUM >= 140000
 #include "utils/backend_progress.h"
-#elif PG_VERSION_NUM >= 120000
-#include "pgstat.h"
-#endif
-
-#if PG_VERSION_NUM >= 120000
-#include "access/tableam.h"
-#include "commands/progress.h"
 #else
-#define PROGRESS_CREATEIDX_TUPLES_DONE 0
+#include "pgstat.h"
 #endif
 
 #if PG_VERSION_NUM >= 130000
@@ -33,26 +65,11 @@
 #define CALLBACK_ITEM_POINTER HeapTuple hup
 #endif
 
-#if PG_VERSION_NUM >= 120000
-#define UpdateProgress(index, val) pgstat_progress_update_param(index, val)
-#else
-#define UpdateProgress(index, val) ((void)val)
-#endif
-
 #if PG_VERSION_NUM >= 140000
 #include "utils/backend_status.h"
 #include "utils/wait_event.h"
 #endif
 
-#if PG_VERSION_NUM >= 120000
-#include "access/table.h"
-#include "optimizer/optimizer.h"
-#else
-#include "access/heapam.h"
-#include "optimizer/planner.h"
-#include "pgstat.h"
-#endif
-
 #define PARALLEL_KEY_HNSW_SHARED		UINT64CONST(0xA000000000000001)
 #define PARALLEL_KEY_HNSW_AREA			UINT64CONST(0xA000000000000002)
 #define PARALLEL_KEY_QUERY_TEXT			UINT64CONST(0xA000000000000003)
@@ -124,14 +141,13 @@ HnswBuildAppendPage(Relation index, Buffer *buf, Page *page, ForkNumber forkNum)
 }
 
 /*
- * Create element pages
+ * Create graph pages
  */
 static void
-CreateElementPages(HnswBuildState * buildstate)
+CreateGraphPages(HnswBuildState * buildstate)
 {
 	Relation	index = buildstate->index;
 	ForkNumber	forkNum = buildstate->forkNum;
-	Size		etupAllocSize;
 	Size		maxSize;
 	HnswElementTuple etup;
 	HnswNeighborTuple ntup;
@@ -143,12 +159,11 @@ CreateElementPages(HnswBuildState * buildstate)
 	char	   *base = buildstate->hnswarea;
 
 	/* Calculate sizes */
-	etupAllocSize = BLCKSZ;
 	maxSize = HNSW_MAX_SIZE;
 
 	/* Allocate once */
-	etup = palloc0(etupAllocSize);
+	etup = palloc0(HNSW_TUPLE_ALLOC_SIZE);
-	ntup = palloc0(BLCKSZ);
+	ntup = palloc0(HNSW_TUPLE_ALLOC_SIZE);
 
 	/* Prepare first page */
 	buf = HnswNewBuffer(index, forkNum);
@@ -161,13 +176,13 @@ CreateElementPages(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;
 
 		/* Zero memory for each element */
-		MemSet(etup, 0, etupAllocSize);
+		MemSet(etup, 0, HNSW_TUPLE_ALLOC_SIZE);
 
 		/* Calculate sizes */
 		etupSize = HNSW_ELEMENT_TUPLE_SIZE(VARSIZE_ANY(valuePtr));
@@ -175,7 +190,7 @@ CreateElementPages(HnswBuildState * buildstate)
 		combinedSize = etupSize + ntupSize + sizeof(ItemIdData);
 
 		/* Initial size check */
-		if (etupSize > etupAllocSize)
+		if (etupSize > HNSW_TUPLE_ALLOC_SIZE)
 			elog(ERROR, "index tuple too large");
 
 		HnswSetElementTuple(base, etup, element);
@@ -227,10 +242,10 @@ CreateElementPages(HnswBuildState * buildstate)
 }
 
 /*
- * Create neighbor pages
+ * Write neighbor tuples
  */
 static void
-CreateNeighborPages(HnswBuildState * buildstate)
+WriteNeighborTuples(HnswBuildState * buildstate)
 {
 	Relation	index = buildstate->index;
 	ForkNumber	forkNum = buildstate->forkNum;
@@ -240,29 +255,32 @@ CreateNeighborPages(HnswBuildState * buildstate)
 	HnswNeighborTuple ntup;
 
 	/* Allocate once */
-	ntup = palloc0(BLCKSZ);
+	ntup = palloc0(HNSW_TUPLE_ALLOC_SIZE);
 
 	while (!HnswPtrIsNull(base, iter))
 	{
-		HnswElement e = HnswPtrAccess(base, iter);
+		HnswElement element = HnswPtrAccess(base, iter);
 		Buffer		buf;
 		Page		page;
-		Size		ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(e->level, m);
+		Size		ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(element->level, m);
 
 		/* Update iterator */
-		iter = e->next;
+		iter = element->next;
+
+		/* Zero memory for each element */
+		MemSet(ntup, 0, HNSW_TUPLE_ALLOC_SIZE);
 
 		/* Can take a while, so ensure we can interrupt */
 		/* Needs to be called when no buffer locks are held */
 		CHECK_FOR_INTERRUPTS();
 
-		buf = ReadBufferExtended(index, forkNum, e->neighborPage, RBM_NORMAL, NULL);
+		buf = ReadBufferExtended(index, forkNum, element->neighborPage, RBM_NORMAL, NULL);
 		LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
 		page = BufferGetPage(buf);
 
-		HnswSetNeighborTuple(base, ntup, e, m);
+		HnswSetNeighborTuple(base, ntup, element, m);
 
-		if (!PageIndexTupleOverwrite(page, e->neighborOffno, (Item) ntup, ntupSize))
+		if (!PageIndexTupleOverwrite(page, element->neighborOffno, (Item) ntup, ntupSize))
 			elog(ERROR, "failed to add index item to \"%s\"", RelationGetRelationName(index));
 
 		/* Commit */
@@ -284,8 +302,8 @@ FlushPages(HnswBuildState * buildstate)
 #endif
 
 	CreateMetaPage(buildstate);
-	CreateElementPages(buildstate);
+	CreateGraphPages(buildstate);
-	CreateNeighborPages(buildstate);
+	WriteNeighborTuples(buildstate);
 
 	buildstate->graph->flushed = true;
 	MemoryContextReset(buildstate->graphCtx);
@@ -295,7 +313,7 @@ FlushPages(HnswBuildState * buildstate)
  * Add a heap TID to an existing element
  */
 static bool
-HnswAddDuplicateInMemory(HnswElement element, HnswElement dup)
+AddDuplicateInMemory(HnswElement element, HnswElement dup)
 {
 	LWLockAcquire(&dup->lock, LW_EXCLUSIVE);
 
@@ -316,15 +334,15 @@ HnswAddDuplicateInMemory(HnswElement element, HnswElement dup)
  * Find duplicate element
  */
 static bool
-HnswFindDuplicateInMemory(char *base, HnswElement element)
+FindDuplicateInMemory(char *base, HnswElement element)
 {
 	HnswNeighborArray *neighbors = HnswGetNeighbors(base, element, 0);
+	Datum		value = HnswGetValue(base, element);
 
 	for (int i = 0; i < neighbors->length; i++)
 	{
 		HnswCandidate *neighbor = &neighbors->items[i];
 		HnswElement neighborElement = HnswPtrAccess(base, neighbor->element);
-		Datum		value = HnswGetValue(base, element);
 		Datum		neighborValue = HnswGetValue(base, neighborElement);
 
 		/* Exit early since ordered by distance */
@@ -332,7 +350,7 @@ HnswFindDuplicateInMemory(char *base, HnswElement element)
 			return false;
 
 		/* Check for space */
-		if (HnswAddDuplicateInMemory(element, neighborElement))
+		if (AddDuplicateInMemory(element, neighborElement))
 			return true;
 	}
 
@@ -340,10 +358,10 @@ HnswFindDuplicateInMemory(char *base, HnswElement element)
 }
 
 /*
- * Add to element and neighbor pages
+ * Add to element list
  */
 static void
-WriteNewElementPagesInMemory(char *base, HnswGraph * graph, HnswElement element)
+AddElementInMemory(char *base, HnswGraph * graph, HnswElement element)
 {
 	SpinLockAcquire(&graph->lock);
 	element->next = graph->head;
@@ -355,7 +373,7 @@ WriteNewElementPagesInMemory(char *base, HnswGraph * graph, HnswElement element)
  * Update neighbors
  */
 static void
-HnswUpdateNeighborPagesInMemory(char *base, FmgrInfo *procinfo, Oid collation, HnswElement e, int m)
+UpdateNeighborsInMemory(char *base, FmgrInfo *procinfo, Oid collation, HnswElement e, int m)
 {
 	for (int lc = e->level; lc >= 0; lc--)
 	{
@@ -379,45 +397,89 @@ HnswUpdateNeighborPagesInMemory(char *base, FmgrInfo *procinfo, Oid collation, H
 }
 
 /*
- * Write changes in memory
+ * Update graph in memory
  */
 static void
-WriteElementInMemory(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement element, int m, int efConstruction, HnswElement entryPoint, HnswBuildState * buildstate, HnswGraph * graph, bool updateEntryPoint)
+UpdateGraphInMemory(FmgrInfo *procinfo, Oid collation, HnswElement element, int m, int efConstruction, HnswElement entryPoint, HnswBuildState * buildstate)
 {
+	HnswGraph  *graph = buildstate->graph;
 	char	   *base = buildstate->hnswarea;
 
-	/* Try to add to existing page */
+	/* Look for duplicate */
-	if (HnswFindDuplicateInMemory(base, element))
+	if (FindDuplicateInMemory(base, element))
 		return;
 
-	/* Write element and neighbor tuples */
+	/* Add element */
-	WriteNewElementPagesInMemory(base, graph, element);
+	AddElementInMemory(base, graph, element);
 
 	/* Update neighbors */
-	HnswUpdateNeighborPagesInMemory(base, procinfo, collation, element, m);
+	UpdateNeighborsInMemory(base, procinfo, collation, element, m);
 
 	/* Update entry point if needed (already have lock) */
-	if (updateEntryPoint)
+	if (entryPoint == NULL || element->level > entryPoint->level)
 		HnswPtrStore(base, graph->entryPoint, element);
 }
 
+/*
+ * Insert tuple in memory
+ */
+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 on entry lock */
+	LWLockAcquire(entryWaitLock, LW_EXCLUSIVE);
+	LWLockRelease(entryWaitLock);
+
+	/* Get entry point */
+	LWLockAcquire(entryLock, LW_SHARED);
+	entryPoint = HnswPtrAccess(base, graph->entryPoint);
+
+	/* Prevent concurrent inserts when likely updating entry point */
+	if (entryPoint == NULL || element->level > entryPoint->level)
+	{
+		/* Release shared lock */
+		LWLockRelease(entryLock);
+
+		/* Tell other processes to wait and 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, procinfo, collation, m, efConstruction, false);
+
+	/* Update graph in memory */
+	UpdateGraphInMemory(procinfo, collation, element, m, efConstruction, entryPoint, buildstate);
+
+	/* Release entry lock */
+	LWLockRelease(entryLock);
+}
+
 /*
  * Insert tuple
  */
 static bool
 InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, HnswBuildState * buildstate)
 {
-	FmgrInfo   *procinfo = buildstate->procinfo;
-	Oid			collation = buildstate->collation;
 	HnswGraph  *graph = buildstate->graph;
-	HnswElement entryPoint;
-	int			efConstruction = buildstate->efConstruction;
-	int			m = buildstate->m;
 	HnswElement element;
 	HnswAllocator *allocator = &buildstate->allocator;
 	Size		valueSize;
 	Pointer		valuePtr;
-	bool		updateEntryPoint;
 	LWLock	   *flushLock = &graph->flushLock;
 	char	   *base = buildstate->hnswarea;
 
@@ -427,7 +489,7 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
 	/* Normalize if needed */
 	if (buildstate->normprocinfo != NULL)
 	{
-		if (!HnswNormValue(buildstate->normprocinfo, collation, &value, buildstate->normvec))
+		if (!HnswNormValue(buildstate->normprocinfo, buildstate->collation, &value, buildstate->normvec))
 			return false;
 	}
 
@@ -437,17 +499,24 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
 	/* Ensure graph not flushed when inserting */
 	LWLockAcquire(flushLock, LW_SHARED);
 
+	/* Are we in the on-disk phase? */
 	if (graph->flushed)
 	{
 		LWLockRelease(flushLock);
 
-		return HnswInsertTupleOnDisk(index, value, values, isnull, heaptid, buildstate->heap, true);
+		return HnswInsertTupleOnDisk(index, value, values, isnull, heaptid, true);
 	}
 
-	/* Get lock for allocator */
+	/*
+	 * In a parallel build, the HnswElement is allocated from the shared
+	 * memory area, so we need to coordinate with other processes.
+	 */
 	LWLockAcquire(&graph->allocatorLock, LW_EXCLUSIVE);
 
-	/* Flush pages if needed */
+	/*
+	 * Check that we have enough memory available for the new element now that
+	 * we have the allocator lock, and flush pages if needed.
+	 */
 	if (graph->memoryUsed >= graph->memoryTotal)
 	{
 		LWLockRelease(&graph->allocatorLock);
@@ -467,41 +536,29 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
 
 		LWLockRelease(flushLock);
 
-		return HnswInsertTupleOnDisk(index, value, values, isnull, heaptid, buildstate->heap, true);
+		return HnswInsertTupleOnDisk(index, value, values, isnull, heaptid, true);
 	}
 
-	/* Create an element */
+	/* Ok, we can proceed to allocate the element */
 	element = HnswInitElement(base, heaptid, buildstate->m, buildstate->ml, buildstate->maxLevel, allocator);
 	valuePtr = HnswAlloc(allocator, valueSize);
 
-	/* Release allocator lock */
+	/*
+	 * We have now allocated the space needed for the element, so we don't
+	 * need the allocator lock anymore. Release it and initialize the rest of
+	 * the element.
+	 */
 	LWLockRelease(&graph->allocatorLock);
 
-	/* Copy datum */
+	/* Copy the datum */
 	memcpy(valuePtr, DatumGetPointer(value), valueSize);
 	HnswPtrStore(base, element->value, valuePtr);
 
-	/* Create element lock */
+	/* Create a lock for the element */
 	LWLockInitialize(&element->lock, hnsw_lock_tranche_id);
 
-	/* Get entry point */
+	/* Insert tuple */
-	LWLockAcquire(&graph->entryLock, LW_EXCLUSIVE);
+	InsertTupleInMemory(buildstate, element);
-	entryPoint = HnswPtrAccess(base, graph->entryPoint);
-	updateEntryPoint = entryPoint == NULL || element->level > entryPoint->level;
-
-	/* Release lock if not updating entry point */
-	if (!updateEntryPoint)
-		LWLockRelease(&graph->entryLock);
-
-	/* Insert element in graph */
-	HnswInsertElement(base, element, entryPoint, NULL, procinfo, collation, m, efConstruction, false);
-
-	/* Write to memory */
-	WriteElementInMemory(index, procinfo, collation, element, m, efConstruction, entryPoint, buildstate, graph, updateEntryPoint);
-
-	/* Release lock if needed */
-	if (updateEntryPoint)
-		LWLockRelease(&graph->entryLock);
 
 	/* Release flush lock */
 	LWLockRelease(flushLock);
@@ -536,7 +593,7 @@ BuildCallback(Relation index, CALLBACK_ITEM_POINTER, Datum *values,
 	{
 		/* Update progress */
 		SpinLockAcquire(&graph->lock);
-		UpdateProgress(PROGRESS_CREATEIDX_TUPLES_DONE, ++graph->indtuples);
+		pgstat_progress_update_param(PROGRESS_CREATEIDX_TUPLES_DONE, ++graph->indtuples);
 		SpinLockRelease(&graph->lock);
 	}
 
@@ -551,6 +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;
@@ -559,6 +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);
 }
@@ -710,36 +771,25 @@ ParallelHeapScan(HnswBuildState * buildstate)
  * Perform a worker's portion of a parallel insert
  */
 static void
-HnswParallelScanAndInsert(HnswSpool * hnswspool, HnswShared * hnswshared, char *hnswarea, bool progress)
+HnswParallelScanAndInsert(Relation heapRel, Relation indexRel, HnswShared * hnswshared, char *hnswarea, bool progress)
 {
 	HnswBuildState buildstate;
-#if PG_VERSION_NUM >= 120000
 	TableScanDesc scan;
-#else
-	HeapScanDesc scan;
-#endif
 	double		reltuples;
 	IndexInfo  *indexInfo;
 
 	/* Join parallel scan */
-	indexInfo = BuildIndexInfo(hnswspool->index);
+	indexInfo = BuildIndexInfo(indexRel);
 	indexInfo->ii_Concurrent = hnswshared->isconcurrent;
-	InitBuildState(&buildstate, hnswspool->heap, hnswspool->index, indexInfo, MAIN_FORKNUM);
+	InitBuildState(&buildstate, heapRel, indexRel, indexInfo, MAIN_FORKNUM);
 	buildstate.graph = &hnswshared->graphData;
 	buildstate.hnswarea = hnswarea;
 	InitAllocator(&buildstate.allocator, &HnswSharedMemoryAlloc, &buildstate);
-#if PG_VERSION_NUM >= 120000
+	scan = table_beginscan_parallel(heapRel,
-	scan = table_beginscan_parallel(hnswspool->heap,
 									ParallelTableScanFromHnswShared(hnswshared));
-	reltuples = table_index_build_scan(hnswspool->heap, hnswspool->index, indexInfo,
+	reltuples = table_index_build_scan(heapRel, indexRel, indexInfo,
 									   true, progress, BuildCallback,
 									   (void *) &buildstate, scan);
-#else
-	scan = heap_beginscan_parallel(hnswspool->heap, &hnswshared->heapdesc);
-	reltuples = IndexBuildHeapScan(hnswspool->heap, hnswspool->index, indexInfo,
-								   true, BuildCallback,
-								   (void *) &buildstate, scan);
-#endif
 
 	/* Record statistics */
 	SpinLockAcquire(&hnswshared->mutex);
@@ -766,10 +816,7 @@ void
 HnswParallelBuildMain(dsm_segment *seg, shm_toc *toc)
 {
 	char	   *sharedquery;
-	HnswSpool  *hnswspool;
 	HnswShared *hnswshared;
-	dsa_area   *dsa;
-	void	   *dsaspace;
 	char	   *hnswarea;
 	Relation	heapRel;
 	Relation	indexRel;
@@ -799,32 +846,17 @@ HnswParallelBuildMain(dsm_segment *seg, shm_toc *toc)
 	}
 
 	/* Open relations within worker */
-#if PG_VERSION_NUM >= 120000
 	heapRel = table_open(hnswshared->heaprelid, heapLockmode);
-#else
-	heapRel = heap_open(hnswshared->heaprelid, heapLockmode);
-#endif
 	indexRel = index_open(hnswshared->indexrelid, indexLockmode);
 
-	/* Initialize worker's own spool */
+	hnswarea = shm_toc_lookup(toc, PARALLEL_KEY_HNSW_AREA, false);
-	hnswspool = (HnswSpool *) palloc0(sizeof(HnswSpool));
-	hnswspool->heap = heapRel;
-	hnswspool->index = indexRel;
-
-	dsaspace = shm_toc_lookup(toc, PARALLEL_KEY_HNSW_AREA, false);
-	dsa = dsa_attach_in_place(dsaspace, seg);
-	hnswarea = dsa_get_address(dsa, hnswshared->dsaptr);
 
 	/* Perform inserts */
-	HnswParallelScanAndInsert(hnswspool, hnswshared, hnswarea, false);
+	HnswParallelScanAndInsert(heapRel, indexRel, hnswshared, hnswarea, false);
 
 	/* Close relations within worker */
 	index_close(indexRel, indexLockmode);
-#if PG_VERSION_NUM >= 120000
 	table_close(heapRel, heapLockmode);
-#else
-	heap_close(heapRel, heapLockmode);
-#endif
 }
 
 /*
@@ -849,19 +881,7 @@ HnswEndParallel(HnswLeader * hnswleader)
 static Size
 ParallelEstimateShared(Relation heap, Snapshot snapshot)
 {
-#if PG_VERSION_NUM >= 120000
 	return add_size(BUFFERALIGN(sizeof(HnswShared)), table_parallelscan_estimate(heap, snapshot));
-#else
-	if (!IsMVCCSnapshot(snapshot))
-	{
-		Assert(snapshot == SnapshotAny);
-		return sizeof(HnswShared);
-	}
-
-	return add_size(offsetof(HnswShared, heapdesc) +
-					offsetof(ParallelHeapScanDescData, phs_snapshot_data),
-					EstimateSnapshotSpace(snapshot));
-#endif
 }
 
 /*
@@ -871,15 +891,9 @@ static void
 HnswLeaderParticipateAsWorker(HnswBuildState * buildstate)
 {
 	HnswLeader *hnswleader = buildstate->hnswleader;
-	HnswSpool  *leaderworker;
-
-	/* Allocate memory and initialize private spool */
-	leaderworker = (HnswSpool *) palloc0(sizeof(HnswSpool));
-	leaderworker->heap = buildstate->heap;
-	leaderworker->index = buildstate->index;
 
 	/* Perform work common to all participants */
-	HnswParallelScanAndInsert(leaderworker, hnswleader->hnswshared, hnswleader->hnswarea, true);
+	HnswParallelScanAndInsert(buildstate->heap, buildstate->index, hnswleader->hnswshared, hnswleader->hnswarea, true);
 }
 
 /*
@@ -889,14 +903,11 @@ static void
 HnswBeginParallel(HnswBuildState * buildstate, bool isconcurrent, int request)
 {
 	ParallelContext *pcxt;
-	int			scantuplesortstates;
 	Snapshot	snapshot;
 	Size		esthnswshared;
 	Size		esthnswarea;
-	Size		estdsaspace;
+	Size		estother;
 	HnswShared *hnswshared;
-	void	   *dsaspace;
-	dsa_area   *dsa;
 	char	   *hnswarea;
 	HnswLeader *hnswleader = (HnswLeader *) palloc0(sizeof(HnswLeader));
 	bool		leaderparticipates = true;
@@ -909,13 +920,7 @@ HnswBeginParallel(HnswBuildState * buildstate, bool isconcurrent, int request)
 	/* Enter parallel mode and create context */
 	EnterParallelMode();
 	Assert(request > 0);
-#if PG_VERSION_NUM >= 120000
 	pcxt = CreateParallelContext("vector", "HnswParallelBuildMain", request);
-#else
-	pcxt = CreateParallelContext("vector", "HnswParallelBuildMain", request, true);
-#endif
-
-	scantuplesortstates = leaderparticipates ? request + 1 : request;
 
 	/* Get snapshot for table scan */
 	if (!isconcurrent)
@@ -927,9 +932,15 @@ HnswBeginParallel(HnswBuildState * buildstate, bool isconcurrent, int request)
 	esthnswshared = ParallelEstimateShared(buildstate->heap, snapshot);
 	shm_toc_estimate_chunk(&pcxt->estimator, esthnswshared);
 
-	/* Start with a minimal DSA so InitializeParallelDSM does not fail */
+	/* Leave space for other objects in shared memory */
-	estdsaspace = dsa_minimum_size();
+	/* Docker has a default limit of 64 MB for shm_size */
-	shm_toc_estimate_chunk(&pcxt->estimator, estdsaspace);
+	/* which happens to be the default value of maintenance_work_mem */
+	esthnswarea = maintenance_work_mem * 1024L;
+	estother = 3 * 1024 * 1024;
+	if (esthnswarea > estother)
+		esthnswarea -= estother;
+
+	shm_toc_estimate_chunk(&pcxt->estimator, esthnswarea);
 	shm_toc_estimate_keys(&pcxt->estimator, 2);
 
 	/* Finally, estimate PARALLEL_KEY_QUERY_TEXT space */
@@ -961,42 +972,29 @@ HnswBeginParallel(HnswBuildState * buildstate, bool isconcurrent, int request)
 	hnswshared->heaprelid = RelationGetRelid(buildstate->heap);
 	hnswshared->indexrelid = RelationGetRelid(buildstate->index);
 	hnswshared->isconcurrent = isconcurrent;
-	hnswshared->scantuplesortstates = scantuplesortstates;
 	ConditionVariableInit(&hnswshared->workersdonecv);
 	SpinLockInit(&hnswshared->mutex);
 	/* Initialize mutable state */
 	hnswshared->nparticipantsdone = 0;
 	hnswshared->reltuples = 0;
-#if PG_VERSION_NUM >= 120000
 	table_parallelscan_initialize(buildstate->heap,
 								  ParallelTableScanFromHnswShared(hnswshared),
 								  snapshot);
-#else
-	heap_parallelscan_initialize(&hnswshared->heapdesc, buildstate->heap, snapshot);
-#endif
 
-	dsaspace = shm_toc_allocate(pcxt->toc, estdsaspace);
+	hnswarea = (char *) shm_toc_allocate(pcxt->toc, esthnswarea);
-	dsa = dsa_create_in_place(dsaspace, estdsaspace, hnsw_lock_tranche_id, pcxt->seg);
-
-	esthnswarea = maintenance_work_mem * 1024L;
-	hnswshared->dsaptr = dsa_allocate_extended(dsa, esthnswarea, DSA_ALLOC_HUGE | DSA_ALLOC_NO_OOM);
-
-	/* If not enough shared memory, back out (do serial build) */
-	if (!DsaPointerIsValid(hnswshared->dsaptr))
-	{
-		if (IsMVCCSnapshot(snapshot))
-			UnregisterSnapshot(snapshot);
-		DestroyParallelContext(pcxt);
-		ExitParallelMode();
-		return;
-	}
-
-	hnswarea = dsa_get_address(dsa, hnswshared->dsaptr);
 	/* 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, dsaspace);
+	shm_toc_insert(pcxt->toc, PARALLEL_KEY_HNSW_AREA, hnswarea);
 
 	/* Store query string for workers */
 	if (debug_query_string)
@@ -1068,7 +1066,7 @@ BuildGraph(HnswBuildState * buildstate, ForkNumber forkNum)
 {
 	int			parallel_workers = 0;
 
-	UpdateProgress(PROGRESS_CREATEIDX_SUBPHASE, PROGRESS_HNSW_PHASE_LOAD);
+	pgstat_progress_update_param(PROGRESS_CREATEIDX_SUBPHASE, PROGRESS_HNSW_PHASE_LOAD);
 
 	/* Calculate parallel workers */
 	if (buildstate->heap != NULL)
@@ -1084,15 +1082,8 @@ BuildGraph(HnswBuildState * buildstate, ForkNumber forkNum)
 		if (buildstate->hnswleader)
 			buildstate->reltuples = ParallelHeapScan(buildstate);
 		else
-		{
-#if PG_VERSION_NUM >= 120000
 			buildstate->reltuples = table_index_build_scan(buildstate->heap, buildstate->index, buildstate->indexInfo,
 														   true, true, BuildCallback, (void *) buildstate, NULL);
-#else
-			buildstate->reltuples = IndexBuildHeapScan(buildstate->heap, buildstate->index, buildstate->indexInfo,
-													   true, BuildCallback, (void *) buildstate, NULL);
-#endif
-		}
 
 		buildstate->indtuples = buildstate->graph->indtuples;
 	}
@@ -1106,22 +1097,6 @@ BuildGraph(HnswBuildState * buildstate, ForkNumber forkNum)
 		HnswEndParallel(buildstate->hnswleader);
 }
 
-#if PG_VERSION_NUM < 110008
-void
-log_newpage_range(Relation rel, ForkNumber forkNum, BlockNumber startblk, BlockNumber endblk, bool page_std)
-{
-	for (BlockNumber blkno = startblk; blkno < endblk; blkno++)
-	{
-		Buffer		buf = ReadBufferExtended(rel, forkNum, blkno, RBM_NORMAL, NULL);
-
-		LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
-		MarkBufferDirty(buf);
-		log_newpage_buffer(buf, page_std);
-		UnlockReleaseBuffer(buf);
-	}
-}
-#endif
-
 /*
  * Build the index
  */

src/hnswinsert.c

@@ -2,6 +2,7 @@
 
 #include <math.h>
 
+#include "access/generic_xlog.h"
 #include "hnsw.h"
 #include "storage/bufmgr.h"
 #include "storage/lmgr.h"
@@ -116,7 +117,7 @@ HnswInsertAppendPage(Relation index, Buffer *nbuf, Page *npage, GenericXLogState
  * Add to element and neighbor pages
  */
 static void
-WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPage, BlockNumber *updatedInsertPage, bool building)
+AddElementOnDisk(Relation index, HnswElement e, int m, BlockNumber insertPage, BlockNumber *updatedInsertPage, bool building)
 {
 	Buffer		buf;
 	Page		page;
@@ -339,7 +340,7 @@ ConnectionExists(HnswElement e, HnswNeighborTuple ntup, int startIdx, int lm)
  * Update neighbors
  */
 void
-HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, 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;
 
@@ -354,9 +355,7 @@ HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswE
 			Buffer		buf;
 			Page		page;
 			GenericXLogState *state;
-			ItemId		itemid;
 			HnswNeighborTuple ntup;
-			Size		ntupSize;
 			int			idx = -1;
 			int			startIdx;
 			HnswElement neighborElement = HnswPtrAccess(base, hc->element);
@@ -395,9 +394,7 @@ HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswE
 			}
 
 			/* Get tuple */
-			itemid = PageGetItemId(page, offno);
+			ntup = (HnswNeighborTuple) PageGetItem(page, PageGetItemId(page, offno));
-			ntup = (HnswNeighborTuple) PageGetItem(page, itemid);
-			ntupSize = ItemIdGetLength(itemid);
 
 			/* Calculate index for update */
 			startIdx = (neighborElement->level - lc) * m;
@@ -426,13 +423,9 @@ HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswE
 			{
 				ItemPointer indextid = &ntup->indextids[idx];
 
-				/* Update neighbor */
+				/* Update neighbor on the buffer */
 				ItemPointerSet(indextid, e->blkno, e->offno);
 
-				/* Overwrite tuple */
-				if (!PageIndexTupleOverwrite(page, offno, (Item) ntup, ntupSize))
-					elog(ERROR, "failed to add index item to \"%s\"", RelationGetRelationName(index));
-
 				/* Commit */
 				if (building)
 					MarkBufferDirty(buf);
@@ -451,14 +444,12 @@ HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswE
  * Add a heap TID to an existing element
  */
 static bool
-HnswAddDuplicate(Relation index, HnswElement element, HnswElement dup, bool building)
+AddDuplicateOnDisk(Relation index, HnswElement element, HnswElement dup, bool building)
 {
 	Buffer		buf;
 	Page		page;
 	GenericXLogState *state;
-	ItemId		itemid;
 	HnswElementTuple etup;
-	Size		etupSize;
 	int			i;
 
 	/* Read page */
@@ -476,9 +467,7 @@ HnswAddDuplicate(Relation index, HnswElement element, HnswElement dup, bool buil
 	}
 
 	/* Find space */
-	itemid = PageGetItemId(page, dup->offno);
+	etup = (HnswElementTuple) PageGetItem(page, PageGetItemId(page, dup->offno));
-	etup = (HnswElementTuple) PageGetItem(page, itemid);
-	etupSize = ItemIdGetLength(itemid);
 	for (i = 0; i < HNSW_HEAPTIDS; i++)
 	{
 		if (!ItemPointerIsValid(&etup->heaptids[i]))
@@ -494,13 +483,9 @@ HnswAddDuplicate(Relation index, HnswElement element, HnswElement dup, bool buil
 		return false;
 	}
 
-	/* Add heap TID */
+	/* Add heap TID, modifying the tuple on the page directly */
 	etup->heaptids[i] = element->heaptids[0];
 
-	/* Overwrite tuple */
-	if (!PageIndexTupleOverwrite(page, dup->offno, (Item) etup, etupSize))
-		elog(ERROR, "failed to add index item to \"%s\"", RelationGetRelationName(index));
-
 	/* Commit */
 	if (building)
 		MarkBufferDirty(buf);
@@ -515,23 +500,23 @@ HnswAddDuplicate(Relation index, HnswElement element, HnswElement dup, bool buil
  * Find duplicate element
  */
 static bool
-HnswFindDuplicate(Relation index, HnswElement element, bool building)
+FindDuplicateOnDisk(Relation index, HnswElement element, bool building)
 {
 	char	   *base = NULL;
 	HnswNeighborArray *neighbors = HnswGetNeighbors(base, element, 0);
+	Datum		value = HnswGetValue(base, element);
 
 	for (int i = 0; i < neighbors->length; i++)
 	{
 		HnswCandidate *neighbor = &neighbors->items[i];
 		HnswElement neighborElement = HnswPtrAccess(base, neighbor->element);
-		Datum		value = HnswGetValue(base, element);
 		Datum		neighborValue = HnswGetValue(base, neighborElement);
 
 		/* Exit early since ordered by distance */
 		if (!datumIsEqual(value, neighborValue, false, -1))
 			return false;
 
-		if (HnswAddDuplicate(index, element, neighborElement, building))
+		if (AddDuplicateOnDisk(index, element, neighborElement, building))
 			return true;
 	}
 
@@ -539,26 +524,26 @@ HnswFindDuplicate(Relation index, HnswElement element, bool building)
 }
 
 /*
- * Write changes to disk
+ * Update graph on disk
  */
 static void
-WriteElement(Relation index, FmgrInfo *procinfo, Oid collation, 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;
 
 	/* Look for duplicate */
-	if (HnswFindDuplicate(index, element, building))
+	if (FindDuplicateOnDisk(index, element, building))
 		return;
 
-	/* Write element and neighbor tuples */
+	/* Add element */
-	WriteNewElementPages(index, element, m, GetInsertPage(index), &newInsertPage, building);
+	AddElementOnDisk(index, element, m, GetInsertPage(index), &newInsertPage, building);
 
 	/* Update insert page if needed */
 	if (BlockNumberIsValid(newInsertPage))
 		HnswUpdateMetaPage(index, 0, NULL, newInsertPage, MAIN_FORKNUM, building);
 
 	/* Update neighbors */
-	HnswUpdateNeighborPages(index, procinfo, collation, element, m, false, building);
+	HnswUpdateNeighborsOnDisk(index, procinfo, collation, element, m, false, building);
 
 	/* Update entry point if needed */
 	if (entryPoint == NULL || element->level > entryPoint->level)
@@ -569,7 +554,7 @@ WriteElement(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement elem
  * Insert a tuple into the index
  */
 bool
-HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull, ItemPointer heap_tid, Relation heapRel, bool building)
+HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull, ItemPointer heap_tid, bool building)
 {
 	HnswElement entryPoint;
 	HnswElement element;
@@ -608,11 +593,11 @@ HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull,
 		entryPoint = HnswGetEntryPoint(index);
 	}
 
-	/* Insert element in graph */
+	/* Find neighbors for element */
-	HnswInsertElement(base, element, entryPoint, index, procinfo, collation, m, efConstruction, false);
+	HnswFindElementNeighbors(base, element, entryPoint, index, procinfo, collation, m, efConstruction, false);
 
-	/* Write to disk */
+	/* Update graph on disk */
-	WriteElement(index, procinfo, collation, element, m, efConstruction, entryPoint, building);
+	UpdateGraphOnDisk(index, procinfo, collation, element, m, efConstruction, entryPoint, building);
 
 	/* Release lock */
 	UnlockPage(index, HNSW_UPDATE_LOCK, lockmode);
@@ -624,7 +609,7 @@ HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull,
  * Insert a tuple into the index
  */
 static void
-HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid, Relation heapRel)
+HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid)
 {
 	Datum		value;
 	FmgrInfo   *normprocinfo;
@@ -641,7 +626,7 @@ HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_ti
 			return;
 	}
 
-	HnswInsertTupleOnDisk(index, value, values, isnull, heap_tid, heapRel, false);
+	HnswInsertTupleOnDisk(index, value, values, isnull, heap_tid, false);
 }
 
 /*
@@ -670,7 +655,7 @@ hnswinsert(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid,
 	oldCtx = MemoryContextSwitchTo(insertCtx);
 
 	/* Insert tuple */
-	HnswInsertTuple(index, values, isnull, heap_tid, heap);
+	HnswInsertTuple(index, values, isnull, heap_tid);
 
 	/* Delete memory context */
 	MemoryContextSwitchTo(oldCtx);

src/hnswscan.c

@@ -201,12 +201,8 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
 
 		MemoryContextSwitchTo(oldCtx);
 
-#if PG_VERSION_NUM >= 120000
 		scan->xs_heaptid = *heaptid;
-#else
+		scan->xs_recheck = false;
-		scan->xs_ctup.t_self = *heaptid;
-#endif
-
 		scan->xs_recheckorderby = false;
 		return true;
 	}

src/hnswutils.c

@@ -2,9 +2,13 @@
 
 #include <math.h>
 
+#include "access/generic_xlog.h"
 #include "hnsw.h"
+#include "lib/pairingheap.h"
 #include "storage/bufmgr.h"
 #include "utils/datum.h"
+#include "utils/memdebug.h"
+#include "utils/rel.h"
 #include "vector.h"
 
 #if PG_VERSION_NUM >= 130000
@@ -56,13 +60,6 @@ hash_tid(ItemPointerData tid)
 #define SH_DEFINE
 #include "lib/simplehash.h"
 
-/* Needed to include simplehash.h twice */
-#if PG_VERSION_NUM < 120000
-#undef SH_EQUAL
-#define sh_log2 pointerhash_sh_log2
-#define sh_pow2 pointerhash_sh_pow2
-#endif
-
 /* Pointer hash table */
 static uint32
 hash_pointer(uintptr_t ptr)
@@ -84,15 +81,6 @@ hash_pointer(uintptr_t ptr)
 #define SH_DEFINE
 #include "lib/simplehash.h"
 
-/* Needed to include simplehash.h again */
-#if PG_VERSION_NUM < 120000
-#undef SH_EQUAL
-#undef sh_log2
-#undef sh_pow2
-#define sh_log2 offsethash_sh_log2
-#define sh_pow2 offsethash_sh_pow2
-#endif
-
 /* Offset hash table */
 static uint32
 hash_offset(Size offset)
@@ -215,6 +203,19 @@ HnswInitPage(Buffer buf, Page page)
 	HnswPageGetOpaque(page)->page_id = HNSW_PAGE_ID;
 }
 
+/*
+ * Allocate a neighbor array
+ */
+static HnswNeighborArray *
+HnswInitNeighborArray(int lm, HnswAllocator * allocator)
+{
+	HnswNeighborArray *a = HnswAlloc(allocator, HNSW_NEIGHBOR_ARRAY_SIZE(lm));
+
+	a->length = 0;
+	a->closerSet = false;
+	return a;
+}
+
 /*
  * Allocate neighbors
  */
@@ -222,22 +223,12 @@ void
 HnswInitNeighbors(char *base, HnswElement element, int m, HnswAllocator * allocator)
 {
 	int			level = element->level;
-
 	HnswNeighborArrayPtr *neighborList = (HnswNeighborArrayPtr *) HnswAlloc(allocator, sizeof(HnswNeighborArrayPtr) * (level + 1));
 
 	HnswPtrStore(base, element->neighbors, neighborList);
 
 	for (int lc = 0; lc <= level; lc++)
-	{
+		HnswPtrStore(base, neighborList[lc], HnswInitNeighborArray(HnswGetLayerM(m, lc), allocator));
-		HnswNeighborArray *a;
-		int			lm = HnswGetLayerM(m, lc);
-
-		HnswPtrStore(base, neighborList[lc], (HnswNeighborArray *) HnswAlloc(allocator, offsetof(HnswNeighborArray, items) + sizeof(HnswCandidate) * lm));
-
-		a = HnswGetNeighbors(base, element, lc);
-		a->length = 0;
-		a->closerSet = false;
-	}
 }
 
 /*
@@ -325,7 +316,10 @@ HnswGetMetaPageInfo(Relation index, int *m, HnswElement * entryPoint)
 	if (entryPoint != NULL)
 	{
 		if (BlockNumberIsValid(metap->entryBlkno))
+		{
 			*entryPoint = HnswInitElementFromBlock(metap->entryBlkno, metap->entryOffno);
+			(*entryPoint)->level = metap->entryLevel;
+		}
 		else
 			*entryPoint = NULL;
 	}
@@ -656,11 +650,25 @@ CreatePairingHeapNode(HnswCandidate * c)
 	return node;
 }
 
+/*
+ * Init visited
+ */
+static inline void
+InitVisited(char *base, visited_hash * v, Relation index, int ef, int m)
+{
+	if (index != NULL)
+		v->tids = tidhash_create(CurrentMemoryContext, ef * m * 2, NULL);
+	else if (base != NULL)
+		v->offsets = offsethash_create(CurrentMemoryContext, ef * m * 2, NULL);
+	else
+		v->pointers = pointerhash_create(CurrentMemoryContext, ef * m * 2, NULL);
+}
+
 /*
  * Add to visited
  */
 static inline void
-AddToVisited(char *base, visited_hash v, HnswCandidate * hc, Relation index, bool *found)
+AddToVisited(char *base, visited_hash * v, HnswCandidate * hc, Relation index, bool *found)
 {
 	if (index != NULL)
 	{
@@ -668,16 +676,16 @@ AddToVisited(char *base, visited_hash v, HnswCandidate * hc, Relation index, boo
 		ItemPointerData indextid;
 
 		ItemPointerSet(&indextid, element->blkno, element->offno);
-		tidhash_insert(v.tids, indextid, found);
+		tidhash_insert(v->tids, indextid, found);
 	}
 	else if (base != NULL)
 	{
 #if PG_VERSION_NUM >= 130000
 		HnswElement element = HnswPtrAccess(base, hc->element);
 
-		offsethash_insert_hash(v.offsets, HnswPtrOffset(hc->element), element->hash, found);
+		offsethash_insert_hash(v->offsets, HnswPtrOffset(hc->element), element->hash, found);
 #else
-		offsethash_insert(v.offsets, HnswPtrOffset(hc->element), found);
+		offsethash_insert(v->offsets, HnswPtrOffset(hc->element), found);
 #endif
 	}
 	else
@@ -685,9 +693,9 @@ AddToVisited(char *base, visited_hash v, HnswCandidate * hc, Relation index, boo
 #if PG_VERSION_NUM >= 130000
 		HnswElement element = HnswPtrAccess(base, hc->element);
 
-		pointerhash_insert_hash(v.pointers, (uintptr_t) HnswPtrPointer(hc->element), element->hash, found);
+		pointerhash_insert_hash(v->pointers, (uintptr_t) HnswPtrPointer(hc->element), element->hash, found);
 #else
-		pointerhash_insert(v.pointers, (uintptr_t) HnswPtrPointer(hc->element), found);
+		pointerhash_insert(v->pointers, (uintptr_t) HnswPtrPointer(hc->element), found);
 #endif
 	}
 }
@@ -725,18 +733,12 @@ HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, F
 	HnswNeighborArray *neighborhoodData = NULL;
 	Size		neighborhoodSize;
 
-	/* Create hash table */
+	InitVisited(base, &v, index, ef, m);
-	if (index != NULL)
-		v.tids = tidhash_create(CurrentMemoryContext, ef * m * 2, NULL);
-	else if (base != NULL)
-		v.offsets = offsethash_create(CurrentMemoryContext, ef * m * 2, NULL);
-	else
-		v.pointers = pointerhash_create(CurrentMemoryContext, ef * m * 2, NULL);
 
 	/* Create local memory for neighborhood if needed */
 	if (index == NULL)
 	{
-		neighborhoodSize = offsetof(HnswNeighborArray, items) + sizeof(HnswCandidate) * HnswGetLayerM(m, lc);
+		neighborhoodSize = HNSW_NEIGHBOR_ARRAY_SIZE(HnswGetLayerM(m, lc));
 		neighborhoodData = palloc(neighborhoodSize);
 	}
 
@@ -746,7 +748,7 @@ HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, F
 		HnswCandidate *hc = (HnswCandidate *) lfirst(lc2);
 		bool		found;
 
-		AddToVisited(base, v, hc, index, &found);
+		AddToVisited(base, &v, hc, index, &found);
 
 		pairingheap_add(C, &(CreatePairingHeapNode(hc)->ph_node));
 		pairingheap_add(W, &(CreatePairingHeapNode(hc)->ph_node));
@@ -781,7 +783,7 @@ HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, F
 		/* Copy neighborhood to local memory if needed */
 		if (index == NULL)
 		{
-			LWLockAcquire(&cElement->lock, LW_EXCLUSIVE);
+			LWLockAcquire(&cElement->lock, LW_SHARED);
 			memcpy(neighborhoodData, neighborhood, neighborhoodSize);
 			LWLockRelease(&cElement->lock);
 			neighborhood = neighborhoodData;
@@ -792,7 +794,7 @@ HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, F
 			HnswCandidate *e = &neighborhood->items[i];
 			bool		visited;
 
-			AddToVisited(base, v, e, index, &visited);
+			AddToVisited(base, &v, e, index, &visited);
 
 			if (!visited)
 			{
@@ -858,12 +860,15 @@ HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, F
 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 *hca = lfirst(*(ListCell **) a);
-	HnswCandidate *hcb = lfirst((ListCell *) b);
+	HnswCandidate *hcb = lfirst(*(ListCell **) b);
+#endif
 
 	if (hca->distance < hcb->distance)
 		return 1;
@@ -886,12 +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 *hca = lfirst(*(ListCell **) a);
-	HnswCandidate *hcb = lfirst((ListCell *) b);
+	HnswCandidate *hcb = lfirst(*(ListCell **) b);
+#endif
 
 	if (hca->distance < hcb->distance)
 		return 1;
@@ -912,40 +920,10 @@ CompareCandidateDistancesOffset(const void *a, const void *b)
  * Calculate the distance between elements
  */
 static float
-HnswGetDistance(char *base, HnswElement a, HnswElement b, int lc, FmgrInfo *procinfo, Oid collation)
+HnswGetDistance(char *base, HnswElement a, HnswElement b, FmgrInfo *procinfo, Oid collation)
 {
-	Datum		aValue;
+	Datum		aValue = HnswGetValue(base, a);
-	Datum		bValue;
+	Datum		bValue = HnswGetValue(base, b);
-
-	/* Look for cached distance */
-	if (!HnswPtrIsNull(base, a->neighbors))
-	{
-		HnswNeighborArray *neighbors = HnswGetNeighbors(base, a, lc);
-
-		for (int i = 0; i < neighbors->length; i++)
-		{
-			HnswElement element = HnswPtrAccess(base, neighbors->items[i].element);
-
-			if (element == b)
-				return neighbors->items[i].distance;
-		}
-	}
-
-	if (!HnswPtrIsNull(base, b->neighbors))
-	{
-		HnswNeighborArray *neighbors = HnswGetNeighbors(base, b, lc);
-
-		for (int i = 0; i < neighbors->length; i++)
-		{
-			HnswElement element = HnswPtrAccess(base, neighbors->items[i].element);
-
-			if (element == a)
-				return neighbors->items[i].distance;
-		}
-	}
-
-	aValue = HnswGetValue(base, a);
-	bValue = HnswGetValue(base, b);
 
 	return DatumGetFloat8(FunctionCall2Coll(procinfo, collation, aValue, bValue));
 }
@@ -954,7 +932,7 @@ HnswGetDistance(char *base, HnswElement a, HnswElement b, int lc, FmgrInfo *proc
  * Check if an element is closer to q than any element from R
  */
 static bool
-CheckElementCloser(char *base, HnswCandidate * e, List *r, int lc, FmgrInfo *procinfo, Oid collation)
+CheckElementCloser(char *base, HnswCandidate * e, List *r, FmgrInfo *procinfo, Oid collation)
 {
 	HnswElement eElement = HnswPtrAccess(base, e->element);
 	ListCell   *lc2;
@@ -963,8 +941,7 @@ CheckElementCloser(char *base, HnswCandidate * e, List *r, int lc, FmgrInfo *pro
 	{
 		HnswCandidate *ri = lfirst(lc2);
 		HnswElement riElement = HnswPtrAccess(base, ri->element);
-
+		float		distance = HnswGetDistance(base, eElement, riElement, procinfo, collation);
-		float		distance = HnswGetDistance(base, eElement, riElement, lc, procinfo, collation);
 
 		if (distance <= e->distance)
 			return false;
@@ -977,20 +954,22 @@ CheckElementCloser(char *base, HnswCandidate * e, List *r, int lc, FmgrInfo *pro
  * Algorithm 4 from paper
  */
 static List *
-SelectNeighbors(char *base, List *c, int m, int lc, FmgrInfo *procinfo, Oid collation, 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;
 	bool		removedAny = false;
 
-	if (list_length(w) <= m)
+	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)
@@ -1001,7 +980,7 @@ SelectNeighbors(char *base, List *c, int m, int lc, FmgrInfo *procinfo, Oid coll
 			list_sort(w, CompareCandidateDistancesOffset);
 	}
 
-	while (list_length(w) > 0 && list_length(r) < m)
+	while (list_length(w) > 0 && list_length(r) < lm)
 	{
 		/* Assumes w is already ordered desc */
 		HnswCandidate *e = llast(w);
@@ -1010,16 +989,20 @@ SelectNeighbors(char *base, List *c, int m, int lc, FmgrInfo *procinfo, Oid coll
 
 		/* Use previous state of r and wd to skip work when possible */
 		if (mustCalculate)
-			e->closer = CheckElementCloser(base, e, r, lc, procinfo, collation);
+			e->closer = CheckElementCloser(base, e, r, procinfo, collation);
 		else if (list_length(added) > 0)
 		{
+			/* Keep Valgrind happy for in-memory, parallel builds */
+			if (base != NULL)
+				VALGRIND_MAKE_MEM_DEFINED(&e->closer, 1);
+
 			/*
 			 * If the current candidate was closer, we only need to compare it
 			 * with the other candidates that we have added.
 			 */
 			if (e->closer)
 			{
-				e->closer = CheckElementCloser(base, e, added, lc, procinfo, collation);
+				e->closer = CheckElementCloser(base, e, added, procinfo, collation);
 
 				if (!e->closer)
 					removedAny = true;
@@ -1032,7 +1015,7 @@ SelectNeighbors(char *base, List *c, int m, int lc, FmgrInfo *procinfo, Oid coll
 				 */
 				if (removedAny)
 				{
-					e->closer = CheckElementCloser(base, e, r, lc, procinfo, collation);
+					e->closer = CheckElementCloser(base, e, r, procinfo, collation);
 					if (e->closer)
 						added = lappend(added, e);
 				}
@@ -1040,29 +1023,33 @@ SelectNeighbors(char *base, List *c, int m, int lc, FmgrInfo *procinfo, Oid coll
 		}
 		else if (e == newCandidate)
 		{
-			e->closer = CheckElementCloser(base, e, r, lc, procinfo, collation);
+			e->closer = CheckElementCloser(base, e, r, procinfo, collation);
 			if (e->closer)
 				added = lappend(added, e);
 		}
 
+		/* Keep Valgrind happy for in-memory, parallel builds */
+		if (base != NULL)
+			VALGRIND_MAKE_MEM_DEFINED(&e->closer, 1);
+
 		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) < m)
+	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 */
 	if (pruned != NULL)
 	{
-		if (!pairingheap_is_empty(wd))
+		if (wdoff < wdlen)
-			*pruned = ((HnswPairingHeapNode *) pairingheap_first(wd))->inner;
+			*pruned = wd[wdoff];
 		else
 			*pruned = linitial(w);
 	}
@@ -1074,7 +1061,7 @@ SelectNeighbors(char *base, List *c, int m, int lc, FmgrInfo *procinfo, Oid coll
  * Add connections
  */
 static void
-AddConnections(char *base, HnswElement element, List *neighbors, int m, int lc)
+AddConnections(char *base, HnswElement element, List *neighbors, int lc)
 {
 	ListCell   *lc2;
 	HnswNeighborArray *a = HnswGetNeighbors(base, element, lc);
@@ -1087,7 +1074,7 @@ AddConnections(char *base, HnswElement element, List *neighbors, int m, int lc)
  * Update connections
  */
 void
-HnswUpdateConnection(char *base, HnswElement element, HnswCandidate * hc, int m, int lc, int *updateIdx, Relation index, FmgrInfo *procinfo, Oid collation)
+HnswUpdateConnection(char *base, HnswElement element, HnswCandidate * hc, int lm, int lc, int *updateIdx, Relation index, FmgrInfo *procinfo, Oid collation)
 {
 	HnswElement hce = HnswPtrAccess(base, hc->element);
 	HnswNeighborArray *currentNeighbors = HnswGetNeighbors(base, hce, lc);
@@ -1096,7 +1083,7 @@ HnswUpdateConnection(char *base, HnswElement element, HnswCandidate * hc, int m,
 	HnswPtrStore(base, hc2.element, element);
 	hc2.distance = hc->distance;
 
-	if (currentNeighbors->length < m)
+	if (currentNeighbors->length < lm)
 	{
 		currentNeighbors->items[currentNeighbors->length++] = hc2;
 
@@ -1142,7 +1129,7 @@ HnswUpdateConnection(char *base, HnswElement element, HnswCandidate * hc, int m,
 				c = lappend(c, &currentNeighbors->items[i]);
 			c = lappend(c, &hc2);
 
-			SelectNeighbors(base, c, m, lc, procinfo, collation, hce, &hc2, &pruned, true);
+			SelectNeighbors(base, c, lm, lc, procinfo, collation, hce, &hc2, &pruned, true);
 
 			/* Should not happen */
 			if (pruned == NULL)
@@ -1216,7 +1203,7 @@ PrecomputeHash(char *base, HnswElement element)
  * Algorithm 1 from paper
  */
 void
-HnswInsertElement(char *base, HnswElement element, HnswElement entryPoint, Relation index, FmgrInfo *procinfo, Oid collation, int m, int efConstruction, bool existing)
+HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, FmgrInfo *procinfo, Oid collation, int m, int efConstruction, bool existing)
 {
 	List	   *ep;
 	List	   *w;
@@ -1276,7 +1263,7 @@ HnswInsertElement(char *base, HnswElement element, HnswElement entryPoint, Relat
 		 */
 		neighbors = SelectNeighbors(base, lw, lm, lc, procinfo, collation, element, NULL, NULL, false);
 
-		AddConnections(base, element, neighbors, lm, lc);
+		AddConnections(base, element, neighbors, lc);
 
 		ep = w;
 	}

src/hnswvacuum.c

@@ -2,6 +2,7 @@
 
 #include <math.h>
 
+#include "access/generic_xlog.h"
 #include "commands/vacuum.h"
 #include "hnsw.h"
 #include "storage/bufmgr.h"
@@ -59,8 +60,7 @@ RemoveHeapTids(HnswVacuumState * vacuumstate)
 		/* Iterate over nodes */
 		for (offno = FirstOffsetNumber; offno <= maxoffno; offno = OffsetNumberNext(offno))
 		{
-			ItemId		itemid = PageGetItemId(page, offno);
+			HnswElementTuple etup = (HnswElementTuple) PageGetItem(page, PageGetItemId(page, offno));
-			HnswElementTuple etup = (HnswElementTuple) PageGetItem(page, itemid);
 			int			idx = 0;
 			bool		itemUpdated = false;
 
@@ -91,15 +91,10 @@ RemoveHeapTids(HnswVacuumState * vacuumstate)
 
 				if (itemUpdated)
 				{
-					Size		etupSize = ItemIdGetLength(itemid);
-
 					/* Mark rest as invalid */
 					for (int i = idx; i < HNSW_HEAPTIDS; i++)
 						ItemPointerSetInvalid(&etup->heaptids[i]);
 
-					if (!PageIndexTupleOverwrite(page, offno, (Item) etup, etupSize))
-						elog(ERROR, "failed to add index item to \"%s\"", RelationGetRelationName(index));
-
 					updated = true;
 				}
 			}
@@ -199,21 +194,25 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
 	BufferAccessStrategy bas = vacuumstate->bas;
 	HnswNeighborTuple ntup = vacuumstate->ntup;
 	Size		ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(element->level, m);
+	char	   *base = NULL;
 
 	/* Skip if element is entry point */
 	if (entryPoint != NULL && element->blkno == entryPoint->blkno && element->offno == entryPoint->offno)
 		return;
 
 	/* Init fields */
-	HnswInitNeighbors(NULL, element, m, NULL);
+	HnswInitNeighbors(base, element, m, NULL);
 	element->heaptidsLength = 0;
 
-	/* Add element to graph, skipping itself */
+	/* Find neighbors for element, skipping itself */
-	HnswInsertElement(NULL, element, entryPoint, index, procinfo, collation, 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);
 
 	/* Update neighbor tuple */
 	/* Do this before getting page to minimize locking */
-	HnswSetNeighborTuple(NULL, ntup, element, m);
+	HnswSetNeighborTuple(base, ntup, element, m);
 
 	/* Get neighbor page */
 	buf = ReadBufferExtended(index, MAIN_FORKNUM, element->neighborPage, RBM_NORMAL, bas);
@@ -230,7 +229,7 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
 	UnlockReleaseBuffer(buf);
 
 	/* Update neighbors */
-	HnswUpdateNeighborPages(index, procinfo, collation, element, m, true, false);
+	HnswUpdateNeighborsOnDisk(index, procinfo, collation, element, m, true, false);
 }
 
 /*
@@ -477,11 +476,8 @@ MarkDeleted(HnswVacuumState * vacuumstate)
 		/* Update element and neighbors together */
 		for (offno = FirstOffsetNumber; offno <= maxoffno; offno = OffsetNumberNext(offno))
 		{
-			ItemId		itemid = PageGetItemId(page, offno);
+			HnswElementTuple etup = (HnswElementTuple) PageGetItem(page, PageGetItemId(page, offno));
-			HnswElementTuple etup = (HnswElementTuple) PageGetItem(page, itemid);
 			HnswNeighborTuple ntup;
-			Size		etupSize;
-			Size		ntupSize;
 			Buffer		nbuf;
 			Page		npage;
 			BlockNumber neighborPage;
@@ -505,10 +501,6 @@ MarkDeleted(HnswVacuumState * vacuumstate)
 			if (ItemPointerIsValid(&etup->heaptids[0]))
 				continue;
 
-			/* Calculate sizes */
-			etupSize = ItemIdGetLength(itemid);
-			ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(etup->level, vacuumstate->m);
-
 			/* Get neighbor page */
 			neighborPage = ItemPointerGetBlockNumber(&etup->neighbortid);
 			neighborOffno = ItemPointerGetOffsetNumber(&etup->neighbortid);
@@ -535,13 +527,10 @@ MarkDeleted(HnswVacuumState * vacuumstate)
 			for (int i = 0; i < ntup->count; i++)
 				ItemPointerSetInvalid(&ntup->indextids[i]);
 
-			/* Overwrite element tuple */
+			/*
-			if (!PageIndexTupleOverwrite(page, offno, (Item) etup, etupSize))
+			 * We modified the tuples in place, no need to call
-				elog(ERROR, "failed to add index item to \"%s\"", RelationGetRelationName(index));
+			 * PageIndexTupleOverwrite
-
+			 */
-			/* Overwrite neighbor tuple */
-			if (!PageIndexTupleOverwrite(npage, neighborOffno, (Item) ntup, ntupSize))
-				elog(ERROR, "failed to add index item to \"%s\"", RelationGetRelationName(index));
 
 			/* Commit */
 			GenericXLogFinish(state);
@@ -586,7 +575,7 @@ InitVacuumState(HnswVacuumState * vacuumstate, IndexVacuumInfo *info, IndexBulkD
 	vacuumstate->bas = GetAccessStrategy(BAS_BULKREAD);
 	vacuumstate->procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
 	vacuumstate->collation = index->rd_indcollation[0];
-	vacuumstate->ntup = palloc0(BLCKSZ);
+	vacuumstate->ntup = palloc0(HNSW_TUPLE_ALLOC_SIZE);
 	vacuumstate->tmpCtx = AllocSetContextCreate(CurrentMemoryContext,
 												"Hnsw vacuum temporary context",
 												ALLOCSET_DEFAULT_SIZES);

src/ivfbuild.c

@@ -2,30 +2,25 @@
 
 #include <float.h>
 
+#include "access/table.h"
+#include "access/tableam.h"
 #include "access/parallel.h"
 #include "access/xact.h"
 #include "catalog/index.h"
 #include "catalog/pg_operator_d.h"
 #include "catalog/pg_type_d.h"
+#include "commands/progress.h"
 #include "ivfflat.h"
 #include "miscadmin.h"
+#include "optimizer/optimizer.h"
 #include "storage/bufmgr.h"
 #include "tcop/tcopprot.h"
 #include "utils/memutils.h"
 
 #if PG_VERSION_NUM >= 140000
 #include "utils/backend_progress.h"
-#elif PG_VERSION_NUM >= 120000
-#include "pgstat.h"
-#endif
-
-#if PG_VERSION_NUM >= 120000
-#include "access/tableam.h"
-#include "commands/progress.h"
 #else
-#define PROGRESS_CREATEIDX_SUBPHASE 0
+#include "pgstat.h"
-#define PROGRESS_CREATEIDX_TUPLES_TOTAL 0
-#define PROGRESS_CREATEIDX_TUPLES_DONE 0
 #endif
 
 #if PG_VERSION_NUM >= 130000
@@ -34,26 +29,11 @@
 #define CALLBACK_ITEM_POINTER HeapTuple hup
 #endif
 
-#if PG_VERSION_NUM >= 120000
-#define UpdateProgress(index, val) pgstat_progress_update_param(index, val)
-#else
-#define UpdateProgress(index, val) ((void)val)
-#endif
-
 #if PG_VERSION_NUM >= 140000
 #include "utils/backend_status.h"
 #include "utils/wait_event.h"
 #endif
 
-#if PG_VERSION_NUM >= 120000
-#include "access/table.h"
-#include "optimizer/optimizer.h"
-#else
-#include "access/heapam.h"
-#include "optimizer/planner.h"
-#include "pgstat.h"
-#endif
-
 #define PARALLEL_KEY_IVFFLAT_SHARED		UINT64CONST(0xA000000000000001)
 #define PARALLEL_KEY_TUPLESORT			UINT64CONST(0xA000000000000002)
 #define PARALLEL_KEY_IVFFLAT_CENTERS	UINT64CONST(0xA000000000000003)
@@ -150,13 +130,8 @@ SampleRows(IvfflatBuildState * buildstate)
 	{
 		BlockNumber targblock = BlockSampler_Next(&buildstate->bs);
 
-#if PG_VERSION_NUM >= 120000
 		table_index_build_range_scan(buildstate->heap, buildstate->index, buildstate->indexInfo,
 									 false, true, false, targblock, 1, SampleCallback, (void *) buildstate, NULL);
-#else
-		IndexBuildHeapRangeScan(buildstate->heap, buildstate->index, buildstate->indexInfo,
-								false, true, targblock, 1, SampleCallback, (void *) buildstate, NULL);
-#endif
 	}
 }
 
@@ -282,16 +257,12 @@ InsertTuples(Relation index, IvfflatBuildState * buildstate, ForkNumber forkNum)
 	IndexTuple	itup = NULL;	/* silence compiler warning */
 	int64		inserted = 0;
 
-#if PG_VERSION_NUM >= 120000
 	TupleTableSlot *slot = MakeSingleTupleTableSlot(buildstate->tupdesc, &TTSOpsMinimalTuple);
-#else
-	TupleTableSlot *slot = MakeSingleTupleTableSlot(buildstate->tupdesc);
-#endif
 	TupleDesc	tupdesc = RelationGetDescr(index);
 
-	UpdateProgress(PROGRESS_CREATEIDX_SUBPHASE, PROGRESS_IVFFLAT_PHASE_LOAD);
+	pgstat_progress_update_param(PROGRESS_CREATEIDX_SUBPHASE, PROGRESS_IVFFLAT_PHASE_LOAD);
 
-	UpdateProgress(PROGRESS_CREATEIDX_TUPLES_TOTAL, buildstate->indtuples);
+	pgstat_progress_update_param(PROGRESS_CREATEIDX_TUPLES_TOTAL, buildstate->indtuples);
 
 	GetNextTuple(buildstate->sortstate, tupdesc, slot, &itup, &list);
 
@@ -327,7 +298,7 @@ InsertTuples(Relation index, IvfflatBuildState * buildstate, ForkNumber forkNum)
 
 			pfree(itup);
 
-			UpdateProgress(PROGRESS_CREATEIDX_TUPLES_DONE, ++inserted);
+			pgstat_progress_update_param(PROGRESS_CREATEIDX_TUPLES_DONE, ++inserted);
 
 			GetNextTuple(buildstate->sortstate, tupdesc, slot, &itup, &list);
 		}
@@ -375,20 +346,12 @@ InitBuildState(IvfflatBuildState * buildstate, Relation heap, Relation index, In
 		elog(ERROR, "dimensions must be greater than one for this opclass");
 
 	/* Create tuple description for sorting */
-#if PG_VERSION_NUM >= 120000
 	buildstate->tupdesc = CreateTemplateTupleDesc(3);
-#else
-	buildstate->tupdesc = CreateTemplateTupleDesc(3, false);
-#endif
 	TupleDescInitEntry(buildstate->tupdesc, (AttrNumber) 1, "list", INT4OID, -1, 0);
 	TupleDescInitEntry(buildstate->tupdesc, (AttrNumber) 2, "tid", TIDOID, -1, 0);
 	TupleDescInitEntry(buildstate->tupdesc, (AttrNumber) 3, "vector", RelationGetDescr(index)->attrs[0].atttypid, -1, 0);
 
-#if PG_VERSION_NUM >= 120000
 	buildstate->slot = MakeSingleTupleTableSlot(buildstate->tupdesc, &TTSOpsVirtual);
-#else
-	buildstate->slot = MakeSingleTupleTableSlot(buildstate->tupdesc);
-#endif
 
 	buildstate->centers = VectorArrayInit(buildstate->lists, buildstate->dimensions);
 	buildstate->listInfo = palloc(sizeof(ListInfo) * buildstate->lists);
@@ -435,7 +398,7 @@ ComputeCenters(IvfflatBuildState * buildstate)
 {
 	int			numSamples;
 
-	UpdateProgress(PROGRESS_CREATEIDX_SUBPHASE, PROGRESS_IVFFLAT_PHASE_KMEANS);
+	pgstat_progress_update_param(PROGRESS_CREATEIDX_SUBPHASE, PROGRESS_IVFFLAT_PHASE_KMEANS);
 
 	/* Target 50 samples per list, with at least 10000 samples */
 	/* The number of samples has a large effect on index build time */
@@ -510,7 +473,7 @@ CreateListPages(Relation index, VectorArray centers, int dimensions,
 	IvfflatList list;
 
 	listSize = MAXALIGN(IVFFLAT_LIST_SIZE(dimensions));
-	list = palloc(listSize);
+	list = palloc0(listSize);
 
 	buf = IvfflatNewBuffer(index, forkNum);
 	IvfflatInitRegisterPage(index, &buf, &page, &state);
@@ -631,11 +594,7 @@ IvfflatParallelScanAndSort(IvfflatSpool * ivfspool, IvfflatShared * ivfshared, S
 {
 	SortCoordinate coordinate;
 	IvfflatBuildState buildstate;
-#if PG_VERSION_NUM >= 120000
 	TableScanDesc scan;
-#else
-	HeapScanDesc scan;
-#endif
 	double		reltuples;
 	IndexInfo  *indexInfo;
 
@@ -659,18 +618,11 @@ IvfflatParallelScanAndSort(IvfflatSpool * ivfspool, IvfflatShared * ivfshared, S
 	buildstate.centers->length = buildstate.centers->maxlen;
 	ivfspool->sortstate = tuplesort_begin_heap(buildstate.tupdesc, 1, attNums, sortOperators, sortCollations, nullsFirstFlags, sortmem, coordinate, false);
 	buildstate.sortstate = ivfspool->sortstate;
-#if PG_VERSION_NUM >= 120000
 	scan = table_beginscan_parallel(ivfspool->heap,
 									ParallelTableScanFromIvfflatShared(ivfshared));
 	reltuples = table_index_build_scan(ivfspool->heap, ivfspool->index, indexInfo,
 									   true, progress, BuildCallback,
 									   (void *) &buildstate, scan);
-#else
-	scan = heap_beginscan_parallel(ivfspool->heap, &ivfshared->heapdesc);
-	reltuples = IndexBuildHeapScan(ivfspool->heap, ivfspool->index, indexInfo,
-								   true, BuildCallback,
-								   (void *) &buildstate, scan);
-#endif
 
 	/* Execute this worker's part of the sort */
 	tuplesort_performsort(ivfspool->sortstate);
@@ -740,11 +692,7 @@ IvfflatParallelBuildMain(dsm_segment *seg, shm_toc *toc)
 	}
 
 	/* Open relations within worker */
-#if PG_VERSION_NUM >= 120000
 	heapRel = table_open(ivfshared->heaprelid, heapLockmode);
-#else
-	heapRel = heap_open(ivfshared->heaprelid, heapLockmode);
-#endif
 	indexRel = index_open(ivfshared->indexrelid, indexLockmode);
 
 	/* Initialize worker's own spool */
@@ -764,11 +712,7 @@ IvfflatParallelBuildMain(dsm_segment *seg, shm_toc *toc)
 
 	/* Close relations within worker */
 	index_close(indexRel, indexLockmode);
-#if PG_VERSION_NUM >= 120000
 	table_close(heapRel, heapLockmode);
-#else
-	heap_close(heapRel, heapLockmode);
-#endif
 }
 
 /*
@@ -793,19 +737,7 @@ IvfflatEndParallel(IvfflatLeader * ivfleader)
 static Size
 ParallelEstimateShared(Relation heap, Snapshot snapshot)
 {
-#if PG_VERSION_NUM >= 120000
 	return add_size(BUFFERALIGN(sizeof(IvfflatShared)), table_parallelscan_estimate(heap, snapshot));
-#else
-	if (!IsMVCCSnapshot(snapshot))
-	{
-		Assert(snapshot == SnapshotAny);
-		return sizeof(IvfflatShared);
-	}
-
-	return add_size(offsetof(IvfflatShared, heapdesc) +
-					offsetof(ParallelHeapScanDescData, phs_snapshot_data),
-					EstimateSnapshotSpace(snapshot));
-#endif
 }
 
 /*
@@ -856,11 +788,7 @@ IvfflatBeginParallel(IvfflatBuildState * buildstate, bool isconcurrent, int requ
 	/* Enter parallel mode and create context */
 	EnterParallelMode();
 	Assert(request > 0);
-#if PG_VERSION_NUM >= 120000
 	pcxt = CreateParallelContext("vector", "IvfflatParallelBuildMain", request);
-#else
-	pcxt = CreateParallelContext("vector", "IvfflatParallelBuildMain", request, true);
-#endif
 
 	scantuplesortstates = leaderparticipates ? request + 1 : request;
 
@@ -918,13 +846,9 @@ IvfflatBeginParallel(IvfflatBuildState * buildstate, bool isconcurrent, int requ
 #ifdef IVFFLAT_KMEANS_DEBUG
 	ivfshared->inertia = 0;
 #endif
-#if PG_VERSION_NUM >= 120000
 	table_parallelscan_initialize(buildstate->heap,
 								  ParallelTableScanFromIvfflatShared(ivfshared),
 								  snapshot);
-#else
-	heap_parallelscan_initialize(&ivfshared->heapdesc, buildstate->heap, snapshot);
-#endif
 
 	/* Store shared tuplesort-private state, for which we reserved space */
 	sharedsort = (Sharedsort *) shm_toc_allocate(pcxt->toc, estsort);
@@ -995,7 +919,7 @@ AssignTuples(IvfflatBuildState * buildstate)
 	Oid			sortCollations[] = {InvalidOid};
 	bool		nullsFirstFlags[] = {false};
 
-	UpdateProgress(PROGRESS_CREATEIDX_SUBPHASE, PROGRESS_IVFFLAT_PHASE_ASSIGN);
+	pgstat_progress_update_param(PROGRESS_CREATEIDX_SUBPHASE, PROGRESS_IVFFLAT_PHASE_ASSIGN);
 
 	/* Calculate parallel workers */
 	if (buildstate->heap != NULL)
@@ -1023,15 +947,8 @@ AssignTuples(IvfflatBuildState * buildstate)
 		if (buildstate->ivfleader)
 			buildstate->reltuples = ParallelHeapScan(buildstate);
 		else
-		{
-#if PG_VERSION_NUM >= 120000
 			buildstate->reltuples = table_index_build_scan(buildstate->heap, buildstate->index, buildstate->indexInfo,
 														   true, true, BuildCallback, (void *) buildstate, NULL);
-#else
-			buildstate->reltuples = IndexBuildHeapScan(buildstate->heap, buildstate->index, buildstate->indexInfo,
-													   true, BuildCallback, (void *) buildstate, NULL);
-#endif
-		}
 
 #ifdef IVFFLAT_KMEANS_DEBUG
 		PrintKmeansMetrics(buildstate);

src/ivfflat.c

@@ -3,14 +3,16 @@
 #include <float.h>
 
 #include "access/amapi.h"
+#include "access/reloptions.h"
+#include "commands/progress.h"
 #include "commands/vacuum.h"
 #include "ivfflat.h"
 #include "utils/guc.h"
 #include "utils/selfuncs.h"
 #include "utils/spccache.h"
 
-#if PG_VERSION_NUM >= 120000
+#if PG_VERSION_NUM < 150000
-#include "commands/progress.h"
+#define MarkGUCPrefixReserved(x) EmitWarningsOnPlaceholders(x)
 #endif
 
 int			ivfflat_probes;
@@ -33,12 +35,13 @@ IvfflatInit(void)
 	DefineCustomIntVariable("ivfflat.probes", "Sets the number of probes",
 							"Valid range is 1..lists.", &ivfflat_probes,
 							IVFFLAT_DEFAULT_PROBES, IVFFLAT_MIN_LISTS, IVFFLAT_MAX_LISTS, PGC_USERSET, 0, NULL, NULL, NULL);
+
+	MarkGUCPrefixReserved("ivfflat");
 }
 
 /*
  * Get the name of index build phase
  */
-#if PG_VERSION_NUM >= 120000
 static char *
 ivfflatbuildphasename(int64 phasenum)
 {
@@ -56,7 +59,6 @@ ivfflatbuildphasename(int64 phasenum)
 			return NULL;
 	}
 }
-#endif
 
 /*
  * Estimate the cost of an index scan
@@ -72,9 +74,6 @@ ivfflatcostestimate(PlannerInfo *root, IndexPath *path, double loop_count,
 	double		ratio;
 	double		spc_seq_page_cost;
 	Relation	index;
-#if PG_VERSION_NUM < 120000
-	List	   *qinfos;
-#endif
 
 	/* Never use index without order */
 	if (path->indexorderbys == NULL)
@@ -105,12 +104,7 @@ ivfflatcostestimate(PlannerInfo *root, IndexPath *path, double loop_count,
 	 */
 	costs.numIndexTuples = path->indexinfo->tuples * ratio;
 
-#if PG_VERSION_NUM >= 120000
 	genericcostestimate(root, path, loop_count, &costs);
-#else
-	qinfos = deconstruct_indexquals(path);
-	genericcostestimate(root, path, loop_count, qinfos, &costs);
-#endif
 
 	get_tablespace_page_costs(path->indexinfo->reltablespace, NULL, &spc_seq_page_cost);
 
@@ -227,9 +221,7 @@ ivfflathandler(PG_FUNCTION_ARGS)
 	amroutine->amcostestimate = ivfflatcostestimate;
 	amroutine->amoptions = ivfflatoptions;
 	amroutine->amproperty = NULL;	/* TODO AMPROP_DISTANCE_ORDERABLE */
-#if PG_VERSION_NUM >= 120000
 	amroutine->ambuildphasename = ivfflatbuildphasename;
-#endif
 	amroutine->amvalidate = ivfflatvalidate;
 #if PG_VERSION_NUM >= 140000
 	amroutine->amadjustmembers = NULL;

src/ivfflat.h

@@ -3,9 +3,10 @@
 
 #include "postgres.h"
 
+#include "access/genam.h"
 #include "access/generic_xlog.h"
 #include "access/parallel.h"
-#include "access/reloptions.h"
+#include "lib/pairingheap.h"
 #include "nodes/execnodes.h"
 #include "port.h"				/* for random() */
 #include "utils/sampling.h"
@@ -16,10 +17,6 @@
 #include "common/pg_prng.h"
 #endif
 
-#if PG_VERSION_NUM < 120000
-#include "access/relscan.h"
-#endif
-
 #ifdef IVFFLAT_BENCH
 #include "portability/instr_time.h"
 #endif
@@ -135,16 +132,10 @@ typedef struct IvfflatShared
 #ifdef IVFFLAT_KMEANS_DEBUG
 	double		inertia;
 #endif
-
-#if PG_VERSION_NUM < 120000
-	ParallelHeapScanDescData heapdesc;	/* must come last */
-#endif
 }			IvfflatShared;
 
-#if PG_VERSION_NUM >= 120000
 #define ParallelTableScanFromIvfflatShared(shared) \
 	(ParallelTableScanDesc) ((char *) (shared) + BUFFERALIGN(sizeof(IvfflatShared)))
-#endif
 
 typedef struct IvfflatLeader
 {

src/ivfinsert.c

@@ -2,6 +2,7 @@
 
 #include <float.h>
 
+#include "access/generic_xlog.h"
 #include "ivfflat.h"
 #include "storage/bufmgr.h"
 #include "storage/lmgr.h"

src/ivfscan.c

@@ -5,6 +5,7 @@
 #include "access/relscan.h"
 #include "catalog/pg_operator_d.h"
 #include "catalog/pg_type_d.h"
+#include "lib/pairingheap.h"
 #include "ivfflat.h"
 #include "miscadmin.h"
 #include "pgstat.h"
@@ -105,12 +106,7 @@ GetScanItems(IndexScanDesc scan, Datum value)
 	IvfflatScanOpaque so = (IvfflatScanOpaque) scan->opaque;
 	TupleDesc	tupdesc = RelationGetDescr(scan->indexRelation);
 	double		tuples = 0;
-
-#if PG_VERSION_NUM >= 120000
 	TupleTableSlot *slot = MakeSingleTupleTableSlot(so->tupdesc, &TTSOpsVirtual);
-#else
-	TupleTableSlot *slot = MakeSingleTupleTableSlot(so->tupdesc);
-#endif
 
 	/*
 	 * Reuse same set of shared buffers for scan
@@ -216,22 +212,14 @@ ivfflatbeginscan(Relation index, int nkeys, int norderbys)
 	so->collation = index->rd_indcollation[0];
 
 	/* Create tuple description for sorting */
-#if PG_VERSION_NUM >= 120000
 	so->tupdesc = CreateTemplateTupleDesc(2);
-#else
-	so->tupdesc = CreateTemplateTupleDesc(2, false);
-#endif
 	TupleDescInitEntry(so->tupdesc, (AttrNumber) 1, "distance", FLOAT8OID, -1, 0);
 	TupleDescInitEntry(so->tupdesc, (AttrNumber) 2, "heaptid", TIDOID, -1, 0);
 
 	/* Prep sort */
 	so->sortstate = tuplesort_begin_heap(so->tupdesc, 1, attNums, sortOperators, sortCollations, nullsFirstFlags, work_mem, NULL, false);
 
-#if PG_VERSION_NUM >= 120000
 	so->slot = MakeSingleTupleTableSlot(so->tupdesc, &TTSOpsMinimalTuple);
-#else
-	so->slot = MakeSingleTupleTableSlot(so->tupdesc);
-#endif
 
 	so->listQueue = pairingheap_allocate(CompareLists, scan);
 
@@ -321,12 +309,8 @@ ivfflatgettuple(IndexScanDesc scan, ScanDirection dir)
 	{
 		ItemPointer heaptid = (ItemPointer) DatumGetPointer(slot_getattr(so->slot, 2, &so->isnull));
 
-#if PG_VERSION_NUM >= 120000
 		scan->xs_heaptid = *heaptid;
-#else
+		scan->xs_recheck = false;
-		scan->xs_ctup.t_self = *heaptid;
-#endif
-
 		scan->xs_recheckorderby = false;
 		return true;
 	}

src/ivfutils.c

@@ -1,5 +1,6 @@
 #include "postgres.h"
 
+#include "access/generic_xlog.h"
 #include "ivfflat.h"
 #include "storage/bufmgr.h"
 #include "vector.h"

src/ivfvacuum.c

@@ -1,5 +1,6 @@
 #include "postgres.h"
 
+#include "access/generic_xlog.h"
 #include "commands/vacuum.h"
 #include "ivfflat.h"
 #include "storage/bufmgr.h"

src/vector.c

@@ -3,6 +3,7 @@
 #include <math.h>
 
 #include "catalog/pg_type.h"
+#include "common/shortest_dec.h"
 #include "fmgr.h"
 #include "hnsw.h"
 #include "ivfflat.h"
@@ -11,6 +12,7 @@
 #include "port.h"				/* for strtof() */
 #include "utils/array.h"
 #include "utils/builtins.h"
+#include "utils/float.h"
 #include "utils/lsyscache.h"
 #include "utils/numeric.h"
 #include "vector.h"
@@ -19,13 +21,6 @@
 #include "varatt.h"
 #endif
 
-#if PG_VERSION_NUM >= 120000
-#include "common/shortest_dec.h"
-#include "utils/float.h"
-#else
-#include <float.h>
-#endif
-
 #if PG_VERSION_NUM < 130000
 #define TYPALIGN_DOUBLE 'd'
 #define TYPALIGN_INT 'i'
@@ -177,14 +172,15 @@ PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_in);
 Datum
 vector_in(PG_FUNCTION_ARGS)
 {
-	char	   *str = PG_GETARG_CSTRING(0);
+	char	   *lit = PG_GETARG_CSTRING(0);
 	int32		typmod = PG_GETARG_INT32(2);
 	float		x[VECTOR_MAX_DIM];
 	int			dim = 0;
 	char	   *pt;
 	char	   *stringEnd;
 	Vector	   *result;
-	char	   *lit = pstrdup(str);
+	char	   *litcopy = pstrdup(lit);
+	char	   *str = litcopy;
 
 	while (vector_isspace(*str))
 		str++;
@@ -268,7 +264,7 @@ vector_in(PG_FUNCTION_ARGS)
 				(errcode(ERRCODE_DATA_EXCEPTION),
 				 errmsg("vector must have at least 1 dimension")));
 
-	pfree(lit);
+	pfree(litcopy);
 
 	CheckExpectedDim(typmod, dim);
 
@@ -292,15 +288,6 @@ vector_out(PG_FUNCTION_ARGS)
 	char	   *ptr;
 	int			n;
 
-#if PG_VERSION_NUM < 120000
-	int			ndig = FLT_DIG + extra_float_digits;
-
-	if (ndig < 1)
-		ndig = 1;
-
-#define FLOAT_SHORTEST_DECIMAL_LEN (ndig + 10)
-#endif
-
 	/*
 	 * Need:
 	 *
@@ -324,11 +311,7 @@ vector_out(PG_FUNCTION_ARGS)
 			ptr++;
 		}
 
-#if PG_VERSION_NUM >= 120000
 		n = float_to_shortest_decimal_bufn(vector->x[i], ptr);
-#else
-		n = sprintf(ptr, "%.*g", ndig, vector->x[i]);
-#endif
 		ptr += n;
 	}
 	*ptr = ']';
@@ -883,9 +866,10 @@ vector_mul(PG_FUNCTION_ARGS)
 int
 vector_cmp_internal(Vector * a, Vector * b)
 {
-	CheckDims(a, b);
+	int			dim = Min(a->dim, b->dim);
 
-	for (int i = 0; i < a->dim; i++)
+	/* Check values before dimensions to be consistent with Postgres arrays */
+	for (int i = 0; i < dim; i++)
 	{
 		if (a->x[i] < b->x[i])
 			return -1;
@@ -893,6 +877,13 @@ vector_cmp_internal(Vector * a, Vector * b)
 		if (a->x[i] > b->x[i])
 			return 1;
 	}
+
+	if (a->dim < b->dim)
+		return -1;
+
+	if (a->dim > b->dim)
+		return 1;
+
 	return 0;
 }
 
@@ -906,6 +897,9 @@ vector_lt(PG_FUNCTION_ARGS)
 	Vector	   *a = PG_GETARG_VECTOR_P(0);
 	Vector	   *b = PG_GETARG_VECTOR_P(1);
 
+	/* TODO Remove in 0.7.0 */
+	CheckDims(a, b);
+
 	PG_RETURN_BOOL(vector_cmp_internal(a, b) < 0);
 }
 
@@ -919,6 +913,9 @@ vector_le(PG_FUNCTION_ARGS)
 	Vector	   *a = PG_GETARG_VECTOR_P(0);
 	Vector	   *b = PG_GETARG_VECTOR_P(1);
 
+	/* TODO Remove in 0.7.0 */
+	CheckDims(a, b);
+
 	PG_RETURN_BOOL(vector_cmp_internal(a, b) <= 0);
 }
 
@@ -932,6 +929,9 @@ vector_eq(PG_FUNCTION_ARGS)
 	Vector	   *a = PG_GETARG_VECTOR_P(0);
 	Vector	   *b = PG_GETARG_VECTOR_P(1);
 
+	/* TODO Remove in 0.7.0 */
+	CheckDims(a, b);
+
 	PG_RETURN_BOOL(vector_cmp_internal(a, b) == 0);
 }
 
@@ -945,6 +945,9 @@ vector_ne(PG_FUNCTION_ARGS)
 	Vector	   *a = PG_GETARG_VECTOR_P(0);
 	Vector	   *b = PG_GETARG_VECTOR_P(1);
 
+	/* TODO Remove in 0.7.0 */
+	CheckDims(a, b);
+
 	PG_RETURN_BOOL(vector_cmp_internal(a, b) != 0);
 }
 
@@ -958,6 +961,9 @@ vector_ge(PG_FUNCTION_ARGS)
 	Vector	   *a = PG_GETARG_VECTOR_P(0);
 	Vector	   *b = PG_GETARG_VECTOR_P(1);
 
+	/* TODO Remove in 0.7.0 */
+	CheckDims(a, b);
+
 	PG_RETURN_BOOL(vector_cmp_internal(a, b) >= 0);
 }
 
@@ -971,6 +977,9 @@ vector_gt(PG_FUNCTION_ARGS)
 	Vector	   *a = PG_GETARG_VECTOR_P(0);
 	Vector	   *b = PG_GETARG_VECTOR_P(1);
 
+	/* TODO Remove in 0.7.0 */
+	CheckDims(a, b);
+
 	PG_RETURN_BOOL(vector_cmp_internal(a, b) > 0);
 }
 
@@ -1151,3 +1160,28 @@ vector_avg(PG_FUNCTION_ARGS)
 
 	PG_RETURN_POINTER(result);
 }
+
+/*
+ * Concat vectors
+ */
+PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_concat);
+Datum
+vector_concat(PG_FUNCTION_ARGS)
+{
+	Vector	   *a = PG_GETARG_VECTOR_P(0);
+	Vector	   *b = PG_GETARG_VECTOR_P(1);
+	Vector	   *result;
+	int			dim = a->dim + b->dim;
+
+	CheckDim(dim);
+
+	result = InitVector(dim);
+
+	for (int i = 0; i < a->dim; i++)
+		result->x[i] = a->x[i];
+
+	for (int i = 0; i < b->dim; i++)
+		result->x[i + a->dim] = b->x[i];
+
+	PG_RETURN_POINTER(result);
+}

test/expected/functions.out

@@ -24,6 +24,64 @@ SELECT '[1e37]'::vector * '[1e37]';
 ERROR:  value out of range: overflow
 SELECT '[1e-37]'::vector * '[1e-37]';
 ERROR:  value out of range: underflow
+SELECT '[1,2,3]'::vector || '[4,5]'::vector;
+  ?column?   
+-------------
+ [1,2,3,4,5]
+(1 row)
+
+SELECT array_fill(0, ARRAY[16000])::vector || '[1]'::vector;
+ERROR:  vector cannot have more than 16000 dimensions
+SELECT '[1,2,3]'::vector = '[1,2,3]';
+ ?column? 
+----------
+ t
+(1 row)
+
+SELECT '[1,2,3]'::vector = '[1,2]';
+ERROR:  different vector dimensions 3 and 2
+SELECT vector_cmp('[1,2,3]', '[1,2,3]');
+ vector_cmp 
+------------
+          0
+(1 row)
+
+SELECT vector_cmp('[1,2,3]', '[0,0,0]');
+ vector_cmp 
+------------
+          1
+(1 row)
+
+SELECT vector_cmp('[0,0,0]', '[1,2,3]');
+ vector_cmp 
+------------
+         -1
+(1 row)
+
+SELECT vector_cmp('[1,2]', '[1,2,3]');
+ vector_cmp 
+------------
+         -1
+(1 row)
+
+SELECT vector_cmp('[1,2,3]', '[1,2]');
+ vector_cmp 
+------------
+          1
+(1 row)
+
+SELECT vector_cmp('[1,2]', '[2,3,4]');
+ vector_cmp 
+------------
+         -1
+(1 row)
+
+SELECT vector_cmp('[2,3]', '[1,2,3]');
+ vector_cmp 
+------------
+          1
+(1 row)
+
 SELECT vector_dims('[1,2,3]');
  vector_dims 
 -------------

test/sql/functions.sql

@@ -6,6 +6,20 @@ SELECT '[1,2,3]'::vector * '[4,5,6]';
 SELECT '[1e37]'::vector * '[1e37]';
 SELECT '[1e-37]'::vector * '[1e-37]';
 
+SELECT '[1,2,3]'::vector || '[4,5]'::vector;
+SELECT array_fill(0, ARRAY[16000])::vector || '[1]'::vector;
+
+SELECT '[1,2,3]'::vector = '[1,2,3]';
+SELECT '[1,2,3]'::vector = '[1,2]';
+
+SELECT vector_cmp('[1,2,3]', '[1,2,3]');
+SELECT vector_cmp('[1,2,3]', '[0,0,0]');
+SELECT vector_cmp('[0,0,0]', '[1,2,3]');
+SELECT vector_cmp('[1,2]', '[1,2,3]');
+SELECT vector_cmp('[1,2,3]', '[1,2]');
+SELECT vector_cmp('[1,2]', '[2,3,4]');
+SELECT vector_cmp('[2,3]', '[1,2,3]');
+
 SELECT vector_dims('[1,2,3]');
 
 SELECT round(vector_norm('[1,1]')::numeric, 5);

test/t/018_hnsw_filtering.pl

@@ -0,0 +1,114 @@
+use strict;
+use warnings;
+use PostgresNode;
+use TestLib;
+use Test::More;
+
+my $dim = 3;
+my $nc = 50;
+my $limit = 20;
+
+my $array_sql = join(",", ('random()') x $dim);
+
+# Initialize node
+my $node = get_new_node('node');
+$node->init;
+$node->start;
+
+# Create table and index
+$node->safe_psql("postgres", "CREATE EXTENSION vector;");
+$node->safe_psql("postgres", "CREATE TABLE tst (i int4, v vector($dim), c int4, t text);");
+$node->safe_psql("postgres",
+	"INSERT INTO tst SELECT i, ARRAY[$array_sql], i % $nc, 'test ' || i FROM generate_series(1, 10000) i;"
+);
+$node->safe_psql("postgres", "CREATE INDEX idx ON tst USING hnsw (v vector_l2_ops);");
+$node->safe_psql("postgres", "ANALYZE tst;");
+
+# Generate query
+my @r = ();
+for (1 .. $dim)
+{
+	push(@r, rand());
+}
+my $query = "[" . join(",", @r) . "]";
+my $c = int(rand() * $nc);
+
+# Test attribute filtering
+my $explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE c = $c ORDER BY v <-> '$query' LIMIT $limit;
+));
+# TODO Do not use index
+like($explain, qr/Index Scan using idx/);
+
+# Test attribute filtering with few rows removed
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE c != $c ORDER BY v <-> '$query' LIMIT $limit;
+));
+like($explain, qr/Index Scan using idx/);
+
+# Test attribute filtering with few rows removed comparison
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE c >= 1 ORDER BY v <-> '$query' LIMIT $limit;
+));
+like($explain, qr/Index Scan using idx/);
+
+# Test attribute filtering with many rows removed comparison
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE c < 1 ORDER BY v <-> '$query' LIMIT $limit;
+));
+# TODO Do not use index
+like($explain, qr/Index Scan using idx/);
+
+# Test attribute filtering with few rows removed like
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE t LIKE '%%test%%' ORDER BY v <-> '$query' LIMIT $limit;
+));
+like($explain, qr/Index Scan using idx/);
+
+# Test attribute filtering with many rows removed like
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE t LIKE '%%other%%' ORDER BY v <-> '$query' LIMIT $limit;
+));
+like($explain, qr/Seq Scan/);
+
+# Test distance filtering
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE v <-> '$query' < 1 ORDER BY v <-> '$query' LIMIT $limit;
+));
+like($explain, qr/Index Scan using idx/);
+
+# Test distance filtering greater than distance
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE v <-> '$query' > 1 ORDER BY v <-> '$query' LIMIT $limit;
+));
+# TODO Do not use index
+like($explain, qr/Index Scan using idx/);
+
+# Test distance filtering without order
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE v <-> '$query' < 1;
+));
+like($explain, qr/Seq Scan/);
+
+# Test distance filtering without limit
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE v <-> '$query' < 1 ORDER BY v <-> '$query';
+));
+like($explain, qr/Seq Scan/);
+
+# Test attribute index
+$node->safe_psql("postgres", "CREATE INDEX attribute_idx ON tst (c);");
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE c = $c ORDER BY v <-> '$query' LIMIT $limit;
+));
+# TODO Use attribute index
+like($explain, qr/Index Scan using idx/);
+
+# Test partial index
+$node->safe_psql("postgres", "CREATE INDEX partial_idx ON tst USING hnsw (v vector_l2_ops) WHERE (c = $c);");
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE c = $c ORDER BY v <-> '$query' LIMIT $limit;
+));
+like($explain, qr/Index Scan using partial_idx/);
+
+done_testing();

test/t/018_ivfflat_deletes.pl

@@ -1,43 +0,0 @@
-use strict;
-use warnings;
-use PostgresNode;
-use TestLib;
-use Test::More;
-
-my $dim = 3;
-
-my $array_sql = join(",", ('random()') x $dim);
-
-# Initialize node
-my $node = get_new_node('node');
-$node->init;
-$node->start;
-
-# Create table and index
-$node->safe_psql("postgres", "CREATE EXTENSION vector;");
-$node->safe_psql("postgres", "CREATE TABLE tst (i serial, v vector($dim));");
-$node->safe_psql("postgres",
-	"INSERT INTO tst (v) SELECT ARRAY[$array_sql] FROM generate_series(1, 10000) i;"
-);
-$node->safe_psql("postgres", "CREATE INDEX ON tst USING ivfflat (v vector_l2_ops);");
-
-# Delete data
-$node->safe_psql("postgres", "DELETE FROM tst WHERE i % 100 != 0;");
-
-my $exp = $node->safe_psql("postgres", qq(
-	SET enable_indexscan = off;
-	SELECT i FROM tst ORDER BY v <-> '[0,0,0]';
-));
-
-# Run twice to make sure correct tuples marked as dead
-for (1 .. 2)
-{
-	my $res = $node->safe_psql("postgres", qq(
-		SET enable_seqscan = off;
-		SET ivfflat.probes = 100;
-		SELECT i FROM tst ORDER BY v <-> '[0,0,0]';
-	));
-	is($res, $exp);
-}
-
-done_testing();

test/t/019_ivfflat_filtering.pl

@@ -0,0 +1,116 @@
+use strict;
+use warnings;
+use PostgresNode;
+use TestLib;
+use Test::More;
+
+my $dim = 3;
+my $nc = 50;
+my $limit = 20;
+
+my $array_sql = join(",", ('random()') x $dim);
+
+# Initialize node
+my $node = get_new_node('node');
+$node->init;
+$node->start;
+
+# Create table and index
+$node->safe_psql("postgres", "CREATE EXTENSION vector;");
+$node->safe_psql("postgres", "CREATE TABLE tst (i int4, v vector($dim), c int4, t text);");
+$node->safe_psql("postgres",
+	"INSERT INTO tst SELECT i, ARRAY[$array_sql], i % $nc, 'test ' || i FROM generate_series(1, 10000) i;"
+);
+$node->safe_psql("postgres", "CREATE INDEX idx ON tst USING ivfflat (v vector_l2_ops) WITH (lists = 100);");
+$node->safe_psql("postgres", "ANALYZE tst;");
+
+# Generate query
+my @r = ();
+for (1 .. $dim)
+{
+	push(@r, rand());
+}
+my $query = "[" . join(",", @r) . "]";
+my $c = int(rand() * $nc);
+
+# Test attribute filtering
+my $explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE c = $c ORDER BY v <-> '$query' LIMIT $limit;
+));
+# TODO Do not use index
+like($explain, qr/Index Scan using idx/);
+
+# Test attribute filtering with few rows removed
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE c != $c ORDER BY v <-> '$query' LIMIT $limit;
+));
+like($explain, qr/Index Scan using idx/);
+
+# Test attribute filtering with few rows removed comparison
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE c >= 1 ORDER BY v <-> '$query' LIMIT $limit;
+));
+like($explain, qr/Index Scan using idx/);
+
+# Test attribute filtering with many rows removed comparison
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE c < 1 ORDER BY v <-> '$query' LIMIT $limit;
+));
+# TODO Do not use index
+like($explain, qr/Index Scan using idx/);
+
+# Test attribute filtering with few rows removed like
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE t LIKE '%%test%%' ORDER BY v <-> '$query' LIMIT $limit;
+));
+like($explain, qr/Index Scan using idx/);
+
+# Test attribute filtering with many rows removed like
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE t LIKE '%%other%%' ORDER BY v <-> '$query' LIMIT $limit;
+));
+like($explain, qr/Seq Scan/);
+
+# Test distance filtering
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE v <-> '$query' < 1 ORDER BY v <-> '$query' LIMIT $limit;
+));
+like($explain, qr/Index Scan using idx/);
+
+# Test distance filtering greater than distance
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE v <-> '$query' > 1 ORDER BY v <-> '$query' LIMIT $limit;
+));
+# TODO Do not use index
+like($explain, qr/Index Scan using idx/);
+
+# Test distance filtering without order
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE v <-> '$query' < 1;
+));
+like($explain, qr/Seq Scan/);
+
+# Test distance filtering without limit
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE v <-> '$query' < 1 ORDER BY v <-> '$query';
+));
+# TODO Do not use index
+like($explain, qr/Index Scan using idx/);
+
+# Test attribute index
+$node->safe_psql("postgres", "CREATE INDEX attribute_idx ON tst (c);");
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE c = $c ORDER BY v <-> '$query' LIMIT $limit;
+));
+# TODO Use attribute index
+like($explain, qr/Index Scan using idx/);
+
+# Test partial index
+$node->safe_psql("postgres", "CREATE INDEX partial_idx ON tst USING ivfflat (v vector_l2_ops) WITH (lists = 5) WHERE (c = $c);");
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE c = $c ORDER BY v <-> '$query' LIMIT $limit;
+));
+# TODO Use partial index
+like($explain, qr/Index Scan using idx/);
+
+done_testing();

vector.control

@@ -1,4 +1,4 @@
 comment = 'vector data type and ivfflat and hnsw access methods'
-default_version = '0.5.1'
+default_version = '0.6.1'
 module_pathname = '$libdir/vector'
 relocatable = true