Added test for arrays

These places called PageIndexTupleOverwrite(), with the new tuple
pointing directly to the original page. The PageIndexTupleOverwrite()
call is unnecessary in these cases, as we have already modified the
tuple on the page directly. Moreover, PageIndexTupleOverWrite() will
call memcpy with same src and dst arguments, which is undefined
behavior.

It's OK to modify the pages on disk directly, and we don't need
critical sections, because we either use the generic xlog functions
which create a temporary copy of the page, or we are building a new
index so if we crash the whole index is invisible and will be dropped
anyway.

.github/workflows/build.yml

@@ -8,6 +8,8 @@ jobs:
       fail-fast: false
       matrix:
         include:
+          - postgres: 17
+            os: ubuntu-22.04
           - postgres: 16
             os: ubuntu-22.04
           - postgres: 15
@@ -18,10 +20,8 @@ jobs:
             os: ubuntu-20.04
           - postgres: 12
             os: ubuntu-20.04
-          - postgres: 11
-            os: ubuntu-20.04
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
       - uses: ankane/setup-postgres@v1
         with:
           postgres-version: ${{ matrix.postgres }}
@@ -43,7 +43,7 @@ jobs:
     runs-on: macos-latest
     if: ${{ !startsWith(github.ref_name, 'windows') }}
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
       - uses: ankane/setup-postgres@v1
         with:
           postgres-version: 14
@@ -57,15 +57,15 @@ jobs:
       - run: |
           brew install cpanm
           cpanm --notest IPC::Run
-          wget -q https://github.com/postgres/postgres/archive/refs/tags/REL_14_5.tar.gz
-          tar xf REL_14_5.tar.gz
-      - run: make prove_installcheck PROVE_FLAGS="-I ./postgres-REL_14_5/src/test/perl" PERL5LIB="/Users/runner/perl5/lib/perl5"
-      - run: make clean && /usr/local/opt/llvm@15/bin/scan-build --status-bugs make
+          wget -q https://github.com/postgres/postgres/archive/refs/tags/REL_14_10.tar.gz
+          tar xf REL_14_10.tar.gz
+      - run: make prove_installcheck PROVE_FLAGS="-I ./postgres-REL_14_10/src/test/perl" PERL5LIB="/Users/runner/perl5/lib/perl5"
+      - run: make clean && /usr/local/opt/llvm@15/bin/scan-build --status-bugs make PG_CFLAGS="-DUSE_ASSERT_CHECKING"
   windows:
     runs-on: windows-latest
     if: ${{ !startsWith(github.ref_name, 'mac') }}
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
       - uses: ankane/setup-postgres@v1
         with:
           postgres-version: 14
@@ -81,10 +81,10 @@ 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

CHANGELOG.md

@@ -1,3 +1,23 @@
+## 0.6.1 (unreleased)
+
+- Fixed error with `ANALYZE` and vectors with different dimensions
+
+## 0.6.0 (2024-01-29)
+
+If upgrading with Postgres 12 or Docker, see [these notes](https://github.com/pgvector/pgvector#060).
+
+- 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 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)
 
 - Improved performance of HNSW index builds
@@ -44,7 +64,7 @@
 
 ## 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`
@@ -61,7 +81,7 @@ 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
 

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": "0.6.0",
 	"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": "0.6.0",
 			"abstract": "Open-source vector similarity search for Postgres"
 		}
 	},

Makefile

@@ -1,5 +1,5 @@
 EXTENSION = vector
-EXTVERSION = 0.5.1
+EXTVERSION = 0.6.0
 
 MODULE_big = vector
 DATA = $(wildcard sql/*--*.sql)
@@ -65,13 +65,17 @@ dist:
 	mkdir -p dist
 	git archive --format zip --prefix=$(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) .
+	docker build --build-arg PG_MAJOR=$(PG_MAJOR) -t pgvector/pgvector:$(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 --platform linux/amd64,linux/arm64 -t ankane/pgvector:v$(EXTVERSION) .
+	docker buildx build --push --pull --no-cache --platform linux/amd64,linux/arm64 --build-arg PG_MAJOR=$(PG_MAJOR) -t pgvector/pgvector:pg$(PG_MAJOR) .
+	docker buildx build --push --platform linux/amd64,linux/arm64 --build-arg PG_MAJOR=$(PG_MAJOR) -t pgvector/pgvector:$(EXTVERSION)-pg$(PG_MAJOR) .

Makefile.win

@@ -1,5 +1,5 @@
 EXTENSION = vector
-EXTVERSION = 0.5.1
+EXTVERSION = 0.6.0
 
 OBJS = src\hnsw.obj src\hnswbuild.obj src\hnswinsert.obj src\hnswscan.obj src\hnswutils.obj src\hnswvacuum.obj src\ivfbuild.obj src\ivfflat.obj src\ivfinsert.obj src\ivfkmeans.obj src\ivfscan.obj src\ivfutils.obj src\ivfvacuum.obj src\vector.obj
 HEADERS = src\vector.h
@@ -56,7 +56,7 @@ install:
 	copy $(EXTENSION).control "$(SHAREDIR)\extension"
 	copy sql\$(EXTENSION)--*.sql "$(SHAREDIR)\extension"
 	mkdir "$(INCLUDEDIR_SERVER)\extension\$(EXTENSION)"
-	copy $(HEADERS) "$(INCLUDEDIR_SERVER)\extension\$(EXTENSION)"
+	for %f in ($(HEADERS)) do copy %f "$(INCLUDEDIR_SERVER)\extension\$(EXTENSION)"
 
 installcheck:
 	"$(BINDIR)\pg_regress" --bindir="$(BINDIR)" $(REGRESS_OPTS) $(REGRESS)

README.md

@@ -10,15 +10,17 @@ Store your vectors with the rest of your data. Supports:
 
 Plus [ACID](https://en.wikipedia.org/wiki/ACID) compliance, point-in-time recovery, JOINs, and all of the other [great features](https://www.postgresql.org/about/) of Postgres
 
-[![Build Status](https://github.com/pgvector/pgvector/workflows/build/badge.svg?branch=master)](https://github.com/pgvector/pgvector/actions)
+[![Build Status](https://github.com/pgvector/pgvector/actions/workflows/build.yml/badge.svg)](https://github.com/pgvector/pgvector/actions)
 
 ## 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 v0.6.0 https://github.com/pgvector/pgvector.git
 cd pgvector
 make
 make install # may need sudo
@@ -26,7 +28,29 @@ make install # may need sudo
 
 See the [installation notes](#installation-notes) if you run into issues
 
-You can also install it with [Docker](#docker), [Homebrew](#homebrew), [PGXN](#pgxn), [APT](#apt), [Yum](#yum), or [conda-forge](#conda-forge), and it comes preinstalled with [Postgres.app](#postgresapp) and many [hosted providers](#hosted-postgres)
+You can also install it with [Docker](#docker), [Homebrew](#homebrew), [PGXN](#pgxn), [APT](#apt), [Yum](#yum), or [conda-forge](#conda-forge), and it comes preinstalled with [Postgres.app](#postgresapp) and many [hosted providers](#hosted-postgres). There are also instructions for [GitHub Actions](https://github.com/pgvector/setup-pgvector).
+
+### Windows
+
+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"
+git clone --branch v0.6.0 https://github.com/pgvector/pgvector.git
+cd pgvector
+nmake /F Makefile.win
+nmake /F Makefile.win install
+```
+
+You can also install it with [Docker](#docker) or [conda-forge](#conda-forge).
 
 ## Getting Started
 
@@ -161,8 +185,105 @@ You can add an index to use approximate nearest neighbor search, which trades so
 
 Supported index types are:
 
-- [IVFFlat](#ivfflat)
 - [HNSW](#hnsw) - added in 0.5.0
+- [IVFFlat](#ivfflat)
+
+## HNSW
+
+An HNSW index creates a multilayer graph. It has better query performance than IVFFlat (in terms of speed-recall tradeoff), but has slower build times and uses more memory. Also, an index can be created without any data in the table since there isn’t a training step like IVFFlat.
+
+Add an index for each distance function you want to use.
+
+L2 distance
+
+```sql
+CREATE INDEX ON items USING hnsw (embedding vector_l2_ops);
+```
+
+Inner product
+
+```sql
+CREATE INDEX ON items USING hnsw (embedding vector_ip_ops);
+```
+
+Cosine distance
+
+```sql
+CREATE INDEX ON items USING hnsw (embedding vector_cosine_ops);
+```
+
+Vectors with up to 2,000 dimensions can be indexed.
+
+### Index Options
+
+Specify HNSW parameters
+
+- `m` - the max number of connections per layer (16 by default)
+- `ef_construction` - the size of the dynamic candidate list for constructing the graph (64 by default)
+
+```sql
+CREATE INDEX ON items USING hnsw (embedding vector_l2_ops) WITH (m = 16, ef_construction = 64);
+```
+
+A higher value of `ef_construction` provides better recall at the cost of index build time / insert speed.
+
+### Query Options
+
+Specify the size of the dynamic candidate list for search (40 by default)
+
+```sql
+SET hnsw.ef_search = 100;
+```
+
+A higher value provides better recall at the cost of speed.
+
+Use `SET LOCAL` inside a transaction to set it for a single query
+
+```sql
+BEGIN;
+SET LOCAL hnsw.ef_search = 100;
+SELECT ...
+COMMIT;
+```
+
+### Index Build Time
+
+Indexes build significantly faster when the graph fits into `maintenance_work_mem`
+
+```sql
+SET maintenance_work_mem = '8GB';
+```
+
+A notice is shown when the graph no longer fits
+
+```text
+NOTICE:  hnsw graph no longer fits into maintenance_work_mem after 100000 tuples
+DETAIL:  Building will take significantly more time.
+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
+
+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+
+
+```sql
+SELECT phase, round(100.0 * blocks_done / nullif(blocks_total, 0), 1) AS "%" FROM pg_stat_progress_create_index;
+```
+
+The phases for HNSW are:
+
+1. `initializing`
+2. `loading tuples`
 
 ## IVFFlat
 
@@ -215,78 +336,32 @@ SELECT ...
 COMMIT;
 ```
 
-## HNSW
+### Index Build Time
 
-An HNSW index creates a multilayer graph. It has slower build times and uses more memory than IVFFlat, but has better query performance (in terms of speed-recall tradeoff). There’s no training step like IVFFlat, so the index can be created without any data in the table.
-
-Add an index for each distance function you want to use.
-
-L2 distance
+Speed up index creation on large tables by increasing the number of parallel workers (2 by default)
 
 ```sql
-CREATE INDEX ON items USING hnsw (embedding vector_l2_ops);
+SET max_parallel_maintenance_workers = 7; -- plus leader
 ```
 
-Inner product
+For a large number of workers, you may also need to increase `max_parallel_workers` (8 by default)
 
-```sql
-CREATE INDEX ON items USING hnsw (embedding vector_ip_ops);
-```
-
-Cosine distance
-
-```sql
-CREATE INDEX ON items USING hnsw (embedding vector_cosine_ops);
-```
-
-Vectors with up to 2,000 dimensions can be indexed.
-
-### Index Options
-
-Specify HNSW parameters
-
-- `m` - the max number of connections per layer (16 by default)
-- `ef_construction` - the size of the dynamic candidate list for constructing the graph (64 by default)
-
-```sql
-CREATE INDEX ON items USING hnsw (embedding vector_l2_ops) WITH (m = 16, ef_construction = 64);
-```
-
-### Query Options
-
-Specify the size of the dynamic candidate list for search (40 by default)
-
-```sql
-SET hnsw.ef_search = 100;
-```
-
-A higher value provides better recall at the cost of speed.
-
-Use `SET LOCAL` inside a transaction to set it for a single query
-
-```sql
-BEGIN;
-SET LOCAL hnsw.ef_search = 100;
-SELECT ...
-COMMIT;
-```
-
-## Indexing Progress
+### Indexing Progress
 
 Check [indexing progress](https://www.postgresql.org/docs/current/progress-reporting.html#CREATE-INDEX-PROGRESS-REPORTING) with Postgres 12+
 
 ```sql
-SELECT phase, tuples_done, tuples_total FROM pg_stat_progress_create_index;
+SELECT phase, round(100.0 * tuples_done / nullif(tuples_total, 0), 1) AS "%" FROM pg_stat_progress_create_index;
 ```
 
-The phases are:
+The phases for IVFFlat are:
 
 1. `initializing`
-2. `performing k-means` - IVFFlat only
-3. `assigning tuples` - IVFFlat only
+2. `performing k-means`
+3. `assigning tuples`
 4. `loading tuples`
 
-Note: `tuples_done` and `tuples_total` are only populated during the `loading tuples` phase
+Note: `%` is only populated during the `loading tuples` phase
 
 ## Filtering
 
@@ -305,8 +380,7 @@ CREATE INDEX ON items (category_id);
 Or a [partial index](https://www.postgresql.org/docs/current/indexes-partial.html) on the vector column for approximate search
 
 ```sql
-CREATE INDEX ON items USING ivfflat (embedding vector_l2_ops) WITH (lists = 100)
-    WHERE (category_id = 123);
+CREATE INDEX ON items USING hnsw (embedding vector_l2_ops) WHERE (category_id = 123);
 ```
 
 Use [partitioning](https://www.postgresql.org/docs/current/ddl-partitioning.html) for approximate search on many different values of the `WHERE` columns
@@ -317,13 +391,15 @@ CREATE TABLE items (embedding vector(3), category_id int) PARTITION BY LIST(cate
 
 ## Hybrid Search
 
-Use together with Postgres [full-text search](https://www.postgresql.org/docs/current/textsearch-intro.html) for hybrid search ([Python example](https://github.com/pgvector/pgvector-python/blob/master/examples/hybrid_search.py)).
+Use together with Postgres [full-text search](https://www.postgresql.org/docs/current/textsearch-intro.html) for hybrid search.
 
 ```sql
 SELECT id, content FROM items, plainto_tsquery('hello search') query
     WHERE textsearch @@ query ORDER BY ts_rank_cd(textsearch, query) DESC LIMIT 5;
 ```
 
+You can use [Reciprocal Rank Fusion](https://github.com/pgvector/pgvector-python/blob/master/examples/hybrid_search_rrf.py) or a [cross-encoder](https://github.com/pgvector/pgvector-python/blob/master/examples/hybrid_search.py) to combine results.
+
 ## Performance
 
 Use `EXPLAIN ANALYZE` to debug performance.
@@ -354,23 +430,36 @@ 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;
+```
+
 ## 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.
 
 Language | Libraries / Examples
 --- | ---
+C | [pgvector-c](https://github.com/pgvector/pgvector-c)
 C++ | [pgvector-cpp](https://github.com/pgvector/pgvector-cpp)
-C# | [pgvector-dotnet](https://github.com/pgvector/pgvector-dotnet)
+C#, F#, Visual Basic | [pgvector-dotnet](https://github.com/pgvector/pgvector-dotnet)
 Crystal | [pgvector-crystal](https://github.com/pgvector/pgvector-crystal)
 Dart | [pgvector-dart](https://github.com/pgvector/pgvector-dart)
 Elixir | [pgvector-elixir](https://github.com/pgvector/pgvector-elixir)
 Go | [pgvector-go](https://github.com/pgvector/pgvector-go)
 Haskell | [pgvector-haskell](https://github.com/pgvector/pgvector-haskell)
-Java, Scala | [pgvector-java](https://github.com/pgvector/pgvector-java)
+Java, Kotlin, Groovy, Scala | [pgvector-java](https://github.com/pgvector/pgvector-java)
+JavaScript, TypeScript | [pgvector-node](https://github.com/pgvector/pgvector-node)
 Julia | [pgvector-julia](https://github.com/pgvector/pgvector-julia)
+Lisp | [pgvector-lisp](https://github.com/pgvector/pgvector-lisp)
 Lua | [pgvector-lua](https://github.com/pgvector/pgvector-lua)
-Node.js | [pgvector-node](https://github.com/pgvector/pgvector-node)
+Nim | [pgvector-nim](https://github.com/pgvector/pgvector-nim)
+OCaml | [pgvector-ocaml](https://github.com/pgvector/pgvector-ocaml)
 Perl | [pgvector-perl](https://github.com/pgvector/pgvector-perl)
 PHP | [pgvector-php](https://github.com/pgvector/pgvector-php)
 Python | [pgvector-python](https://github.com/pgvector/pgvector-python)
@@ -378,6 +467,7 @@ R | [pgvector-r](https://github.com/pgvector/pgvector-r)
 Ruby | [pgvector-ruby](https://github.com/pgvector/pgvector-ruby), [Neighbor](https://github.com/ankane/neighbor)
 Rust | [pgvector-rust](https://github.com/pgvector/pgvector-rust)
 Swift | [pgvector-swift](https://github.com/pgvector/pgvector-swift)
+Zig | [pgvector-zig](https://github.com/pgvector/pgvector-zig)
 
 ## Frequently Asked Questions
 
@@ -393,6 +483,63 @@ Yes, pgvector uses the write-ahead log (WAL), which allows for replication and p
 
 You’ll need to use [dimensionality reduction](https://en.wikipedia.org/wiki/Dimensionality_reduction) at the moment.
 
+#### Can I store vectors with different dimensions in the same column?
+
+You can use `vector` as the type (instead of `vector(3)`).
+
+```sql
+CREATE TABLE embeddings (model_id bigint, item_id bigint, embedding vector, PRIMARY KEY (model_id, item_id));
+```
+
+However, you can only create indexes on rows with the same number of dimensions (using [expression](https://www.postgresql.org/docs/current/indexes-expressional.html) and [partial](https://www.postgresql.org/docs/current/indexes-partial.html) indexing):
+
+```sql
+CREATE INDEX ON embeddings USING hnsw ((embedding::vector(3)) vector_l2_ops) WHERE (model_id = 123);
+```
+
+and query with:
+
+```sql
+SELECT * FROM embeddings WHERE model_id = 123 ORDER BY embedding::vector(3) <-> '[3,1,2]' LIMIT 5;
+```
+
+#### Can I store vectors with more precision?
+
+You can use the `double precision[]` or `numeric[]` type to store vectors with more precision.
+
+```sql
+CREATE TABLE items (id bigserial PRIMARY KEY, embedding double precision[]);
+
+-- use {} instead of [] for Postgres arrays
+INSERT INTO items (embedding) VALUES ('{1,2,3}'), ('{4,5,6}');
+```
+
+Optionally, add a [check constraint](https://www.postgresql.org/docs/current/ddl-constraints.html) to ensure data can be converted to the `vector` type and has the expected dimensions.
+
+```sql
+ALTER TABLE items ADD CHECK (vector_dims(embedding::vector) = 3);
+```
+
+Use [expression indexing](https://www.postgresql.org/docs/current/indexes-expressional.html) to index (at a lower precision):
+
+```sql
+CREATE INDEX ON items USING hnsw ((embedding::vector(3)) vector_l2_ops);
+```
+
+and query with:
+
+```sql
+SELECT * FROM items ORDER BY embedding::vector(3) <-> '[3,1,2]' LIMIT 5;
+```
+
+#### Do indexes need to fit into memory?
+
+No, but like other index types, you’ll likely see better performance if they do. You can get the size of an index with:
+
+```sql
+SELECT pg_size_pretty(pg_relation_size('index_name'));
+```
+
 ## Troubleshooting
 
 #### Why isn’t a query using an index?
@@ -406,6 +553,8 @@ SELECT ...
 COMMIT;
 ```
 
+Also, if the table is small, a table scan may be faster.
+
 #### Why isn’t a query using a parallel table scan?
 
 The planner doesn’t consider [out-of-line storage](https://www.postgresql.org/docs/current/storage-toast.html) in cost estimates, which can make a serial scan look cheaper. You can reduce the cost of a parallel scan for a query with:
@@ -474,7 +623,7 @@ sum(vector) → vector | sum | 0.5.0
 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:
@@ -483,6 +632,14 @@ 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.
@@ -490,49 +647,33 @@ If compilation fails with `fatal error: postgres.h: No such file or directory`,
 For Ubuntu and Debian, use:
 
 ```sh
-sudo apt install postgresql-server-dev-15
+sudo apt install postgresql-server-dev-16
 ```
 
-Note: Replace `15` with your Postgres server version
+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:
-
-```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\15"
-git clone --branch v0.5.1 https://github.com/pgvector/pgvector.git
-cd pgvector
-nmake /F Makefile.win
-nmake /F Makefile.win install
-```
+If compilation fails and the output includes `warning: no such sysroot directory` on Mac, reinstall Xcode Command Line Tools.
 
 ## 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 v0.6.0 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
@@ -558,22 +699,22 @@ pgxn install vector
 Debian and Ubuntu packages are available from the [PostgreSQL APT Repository](https://wiki.postgresql.org/wiki/Apt). Follow the [setup instructions](https://wiki.postgresql.org/wiki/Apt#Quickstart) and run:
 
 ```sh
-sudo apt install postgresql-15-pgvector
+sudo apt install postgresql-16-pgvector
 ```
 
-Note: Replace `15` with your Postgres server version
+Note: Replace `16` with your Postgres server version
 
 ### Yum
 
 RPM packages are available from the [PostgreSQL Yum Repository](https://yum.postgresql.org/). Follow the [setup instructions](https://www.postgresql.org/download/linux/redhat/) for your distribution and run:
 
 ```sh
-sudo yum install pgvector_15
+sudo yum install pgvector_16
 # or
-sudo dnf install pgvector_15
+sudo dnf install pgvector_16
 ```
 
-Note: Replace `15` with your Postgres server version
+Note: Replace `16` with your Postgres server version
 
 ### conda-forge
 
@@ -595,7 +736,7 @@ pgvector is available on [these providers](https://github.com/pgvector/pgvector/
 
 ## Upgrading
 
-Install the latest version. Then in each database you want to upgrade, run:
+[Install](#installation) the latest version (use the same method as the original installation). Then in each database you want to upgrade, run:
 
 ```sql
 ALTER EXTENSION vector UPDATE;
@@ -609,28 +750,32 @@ 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
--- Postgres 12+
-REINDEX INDEX CONCURRENTLY index_name;
+```sh
+docker pull pgvector/pgvector:pg16
+# or
+docker pull pgvector/pgvector:0.6.0-pg16
+```
 
--- Postgres < 12
-CREATE INDEX CONCURRENTLY temp_name ON table USING ivfflat (column opclass);
-DROP INDEX CONCURRENTLY index_name;
-ALTER INDEX temp_name RENAME TO index_name;
+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.
+
+```sh
+docker run --shm-size=1g ...
 ```
 
 ## Thanks
@@ -676,14 +821,32 @@ make prove_installcheck  # TAP tests
 To run single tests:
 
 ```sh
-make installcheck REGRESS=functions                    # regression test
-make prove_installcheck PROVE_TESTS=test/t/001_wal.pl  # TAP test
+make installcheck REGRESS=functions                            # regression test
+make prove_installcheck PROVE_TESTS=test/t/001_ivfflat_wal.pl  # TAP test
 ```
 
 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 enable assertions:
+
+```sh
+make clean && PG_CFLAGS="-DUSE_ASSERT_CHECKING" 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.sql

@@ -26,7 +26,7 @@ CREATE TYPE vector (
 	TYPMOD_IN = vector_typmod_in,
 	RECEIVE   = vector_recv,
 	SEND      = vector_send,
-	STORAGE   = extended
+	STORAGE   = external
 );
 
 -- functions

src/hnsw.c

@@ -4,24 +4,57 @@
 #include <math.h>
 
 #include "access/amapi.h"
+#include "access/reloptions.h"
+#include "commands/progress.h"
 #include "commands/vacuum.h"
 #include "hnsw.h"
 #include "utils/guc.h"
 #include "utils/selfuncs.h"
 
-#if PG_VERSION_NUM >= 120000
-#include "commands/progress.h"
+#if PG_VERSION_NUM < 150000
+#define MarkGUCPrefixReserved(x) EmitWarningsOnPlaceholders(x)
 #endif
 
 int			hnsw_ef_search;
+int			hnsw_lock_tranche_id;
 static relopt_kind hnsw_relopt_kind;
 
+/*
+ * Assign a tranche ID for our LWLocks. This only needs to be done by one
+ * backend, as the tranche ID is remembered in shared memory.
+ *
+ * This shared memory area is very small, so we just allocate it from the
+ * "slop" that PostgreSQL reserves for small allocations like this. If
+ * this grows bigger, we should use a shmem_request_hook and
+ * RequestAddinShmemSpace() to pre-reserve space for this.
+ */
+static void
+HnswInitLockTranche(void)
+{
+	int		   *tranche_ids;
+	bool		found;
+
+	LWLockAcquire(AddinShmemInitLock, LW_EXCLUSIVE);
+	tranche_ids = ShmemInitStruct("hnsw LWLock ids",
+								  sizeof(int) * 1,
+								  &found);
+	if (!found)
+		tranche_ids[0] = LWLockNewTrancheId();
+	hnsw_lock_tranche_id = tranche_ids[0];
+	LWLockRelease(AddinShmemInitLock);
+
+	/* Per-backend registration of the tranche ID */
+	LWLockRegisterTranche(hnsw_lock_tranche_id, "HnswBuild");
+}
+
 /*
  * Initialize index options and variables
  */
 void
 HnswInit(void)
 {
+	HnswInitLockTranche();
+
 	hnsw_relopt_kind = add_reloption_kind();
 	add_int_reloption(hnsw_relopt_kind, "m", "Max number of connections",
 					  HNSW_DEFAULT_M, HNSW_MIN_M, HNSW_MAX_M
@@ -39,12 +72,13 @@ 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)
 {
@@ -58,7 +92,6 @@ hnswbuildphasename(int64 phasenum)
 			return NULL;
 	}
 }
-#endif
 
 /*
  * Estimate the cost of an index scan
@@ -73,9 +106,6 @@ 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)
@@ -101,12 +131,7 @@ 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;
@@ -200,9 +225,7 @@ 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

@@ -3,15 +3,17 @@
 
 #include "postgres.h"
 
-#include "access/generic_xlog.h"
-#include "access/reloptions.h"
+#include "access/genam.h"
+#include "access/parallel.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+"
+#if PG_VERSION_NUM < 120000
+#error "Requires PostgreSQL 12+"
 #endif
 
 #define HNSW_MAX_DIM 2000
@@ -58,17 +60,22 @@
 #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(_dim)	MAXALIGN(offsetof(HnswElementTupleData, vec) + VECTOR_SIZE(_dim))
+#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))
 
 #if PG_VERSION_NUM >= 150000
 #define RandomDouble() pg_prng_double(&pg_global_prng_state)
+#define SeedRandom(seed) pg_prng_seed(&pg_global_prng_state, seed)
 #else
 #define RandomDouble() (((double) random()) / MAX_RANDOM_VALUE)
+#define SeedRandom(seed) srandom(seed)
 #endif
 
 #if PG_VERSION_NUM < 130000
@@ -86,31 +93,64 @@
 #define HnswGetMl(m) (1 / log(m))
 
 /* Ensure fits on page and in uint8 */
-#define HnswGetMaxLevel(m) Min(((BLCKSZ - MAXALIGN(SizeOfPageHeaderData) - MAXALIGN(sizeof(HnswPageOpaqueData)) - offsetof(HnswNeighborTupleData, indextids) - sizeof(ItemIdData)) / (sizeof(ItemPointerData)) / m) - 2, 255)
+#define HnswGetMaxLevel(m) Min(((BLCKSZ - MAXALIGN(SizeOfPageHeaderData) - MAXALIGN(sizeof(HnswPageOpaqueData)) - offsetof(HnswNeighborTupleData, indextids) - sizeof(ItemIdData)) / (sizeof(ItemPointerData)) / (m)) - 2, 255)
+
+#define HnswGetValue(base, element) PointerGetDatum(HnswPtrAccess(base, (element)->value))
+
+#if PG_VERSION_NUM < 140005
+#define relptr_offset(rp) ((rp).relptr_off - 1)
+#endif
+
+/* Pointer macros */
+#define HnswPtrAccess(base, hp) ((base) == NULL ? (hp).ptr : relptr_access(base, (hp).relptr))
+#define HnswPtrStore(base, hp, value) ((base) == NULL ? (void) ((hp).ptr = (value)) : (void) relptr_store(base, (hp).relptr, value))
+#define HnswPtrIsNull(base, hp) ((base) == NULL ? (hp).ptr == NULL : relptr_is_null((hp).relptr))
+#define HnswPtrEqual(base, hp1, hp2) ((base) == NULL ? (hp1).ptr == (hp2).ptr : relptr_offset((hp1).relptr) == relptr_offset((hp2).relptr))
+
+/* For code paths dedicated to each type */
+#define HnswPtrPointer(hp) (hp).ptr
+#define HnswPtrOffset(hp) relptr_offset((hp).relptr)
 
 /* Variables */
 extern int	hnsw_ef_search;
+extern int	hnsw_lock_tranche_id;
 
+typedef struct HnswElementData HnswElementData;
 typedef struct HnswNeighborArray HnswNeighborArray;
 
+#define HnswPtrDeclare(type, relptrtype, ptrtype) \
+	relptr_declare(type, relptrtype); \
+	typedef union { type *ptr; relptrtype relptr; } ptrtype;
+
+/* Pointers that can be absolute or relative */
+/* Use char for DatumPtr so works with Pointer */
+HnswPtrDeclare(HnswElementData, HnswElementRelptr, HnswElementPtr);
+HnswPtrDeclare(HnswNeighborArray, HnswNeighborArrayRelptr, HnswNeighborArrayPtr);
+HnswPtrDeclare(HnswNeighborArrayPtr, HnswNeighborsRelptr, HnswNeighborsPtr);
+HnswPtrDeclare(char, DatumRelptr, DatumPtr);
+
 typedef struct HnswElementData
 {
-	List	   *heaptids;
+	HnswElementPtr next;
+	ItemPointerData heaptids[HNSW_HEAPTIDS];
+	uint8		heaptidsLength;
 	uint8		level;
 	uint8		deleted;
-	HnswNeighborArray *neighbors;
+	uint32		hash;
+	HnswNeighborsPtr neighbors;
 	BlockNumber blkno;
 	OffsetNumber offno;
 	OffsetNumber neighborOffno;
 	BlockNumber neighborPage;
-	Vector	   *vec;
+	DatumPtr	value;
+	LWLock		lock;
 }			HnswElementData;
 
 typedef HnswElementData * HnswElement;
 
 typedef struct HnswCandidate
 {
-	HnswElement element;
+	HnswElementPtr element;
 	float		distance;
 	bool		closer;
 }			HnswCandidate;
@@ -119,7 +159,7 @@ typedef struct HnswNeighborArray
 {
 	int			length;
 	bool		closerSet;
-	HnswCandidate *items;
+	HnswCandidate items[FLEXIBLE_ARRAY_MEMBER];
 }			HnswNeighborArray;
 
 typedef struct HnswPairingHeapNode
@@ -136,6 +176,64 @@ typedef struct HnswOptions
 	int			efConstruction; /* size of dynamic candidate list */
 }			HnswOptions;
 
+typedef struct HnswGraph
+{
+	/* Graph state */
+	slock_t		lock;
+	HnswElementPtr head;
+	double		indtuples;
+
+	/* Entry state */
+	LWLock		entryLock;
+	HnswElementPtr entryPoint;
+
+	/* Allocations state */
+	LWLock		allocatorLock;
+	long		memoryUsed;
+	long		memoryTotal;
+
+	/* Flushed state */
+	LWLock		flushLock;
+	bool		flushed;
+}			HnswGraph;
+
+typedef struct HnswShared
+{
+	/* Immutable state */
+	Oid			heaprelid;
+	Oid			indexrelid;
+	bool		isconcurrent;
+
+	/* Worker progress */
+	ConditionVariable workersdonecv;
+
+	/* Mutex for mutable state */
+	slock_t		mutex;
+
+	/* Mutable state */
+	int			nparticipantsdone;
+	double		reltuples;
+	HnswGraph	graphData;
+}			HnswShared;
+
+#define ParallelTableScanFromHnswShared(shared) \
+	(ParallelTableScanDesc) ((char *) (shared) + BUFFERALIGN(sizeof(HnswShared)))
+
+typedef struct HnswLeader
+{
+	ParallelContext *pcxt;
+	int			nparticipanttuplesorts;
+	HnswShared *hnswshared;
+	Snapshot	snapshot;
+	char	   *hnswarea;
+}			HnswLeader;
+
+typedef struct HnswAllocator
+{
+	void	   *(*alloc) (Size size, void *state);
+	void	   *state;
+}			HnswAllocator;
+
 typedef struct HnswBuildState
 {
 	/* Info */
@@ -159,16 +257,21 @@ typedef struct HnswBuildState
 	Oid			collation;
 
 	/* Variables */
-	List	   *elements;
-	HnswElement entryPoint;
+	HnswGraph	graphData;
+	HnswGraph  *graph;
 	double		ml;
 	int			maxLevel;
-	double		maxInMemoryElements;
-	bool		flushed;
 	Vector	   *normvec;
 
 	/* Memory */
+	MemoryContext graphCtx;
 	MemoryContext tmpCtx;
+	HnswAllocator allocator;
+
+	/* Parallel builds */
+	HnswLeader *hnswleader;
+	HnswShared *hnswshared;
+	char	   *hnswarea;
 }			HnswBuildState;
 
 typedef struct HnswMetaPageData
@@ -204,7 +307,7 @@ typedef struct HnswElementTupleData
 	ItemPointerData heaptids[HNSW_HEAPTIDS];
 	ItemPointerData neighbortid;
 	uint16		unused2;
-	Vector		vec;
+	Vector		data;
 }			HnswElementTupleData;
 
 typedef HnswElementTupleData * HnswElementTuple;
@@ -250,7 +353,7 @@ typedef struct HnswVacuumState
 	Oid			collation;
 
 	/* Variables */
-	HTAB	   *deleted;
+	struct tidhash_hash *deleted;
 	BufferAccessStrategy bas;
 	HnswNeighborTuple ntup;
 	HnswElementData highestPoint;
@@ -264,31 +367,29 @@ int			HnswGetM(Relation index);
 int			HnswGetEfConstruction(Relation index);
 FmgrInfo   *HnswOptionalProcInfo(Relation index, uint16 procnum);
 bool		HnswNormValue(FmgrInfo *procinfo, Oid collation, Datum *value, Vector * result);
-void		HnswCommitBuffer(Buffer buf, GenericXLogState *state);
 Buffer		HnswNewBuffer(Relation index, ForkNumber forkNum);
 void		HnswInitPage(Buffer buf, Page page);
-void		HnswInitRegisterPage(Relation index, Buffer *buf, Page *page, GenericXLogState **state);
 void		HnswInit(void);
-List	   *HnswSearchLayer(Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool inserting, HnswElement skipElement);
+List	   *HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool inserting, HnswElement skipElement);
 HnswElement HnswGetEntryPoint(Relation index);
 void		HnswGetMetaPageInfo(Relation index, int *m, HnswElement * entryPoint);
-HnswElement HnswInitElement(ItemPointer tid, int m, double ml, int maxLevel);
-void		HnswFreeElement(HnswElement element);
+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(HnswElement element, HnswElement entryPoint, Relation index, FmgrInfo *procinfo, Oid collation, int m, int efConstruction, bool existing);
-HnswElement HnswFindDuplicate(HnswElement e);
-HnswCandidate *HnswEntryCandidate(HnswElement em, Datum q, Relation rel, FmgrInfo *procinfo, Oid collation, bool loadVec);
-void		HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, BlockNumber insertPage, ForkNumber forkNum);
-void		HnswSetNeighborTuple(HnswNeighborTuple ntup, HnswElement e, int m);
+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(HnswElement element, int m);
-bool		HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid, Relation heapRel);
-void		HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement e, int m, bool checkExisting);
+void		HnswInitNeighbors(char *base, HnswElement element, int m, HnswAllocator * alloc);
+bool		HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull, ItemPointer heap_tid, bool building);
+void		HnswUpdateNeighborsOnDisk(Relation index, 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(HnswElementTuple etup, HnswElement element);
-void		HnswUpdateConnection(HnswElement element, HnswCandidate * hc, int m, int lc, int *updateIdx, Relation index, FmgrInfo *procinfo, Oid collation);
+void		HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element);
+void		HnswUpdateConnection(char *base, HnswElement element, HnswCandidate * hc, int lm, int lc, int *updateIdx, Relation index, FmgrInfo *procinfo, Oid collation);
 void		HnswLoadNeighbors(HnswElement element, Relation index, int m);
+PGDLLEXPORT void HnswParallelBuildMain(dsm_segment *seg, shm_toc *toc);
 
 /* Index access methods */
 IndexBuildResult *hnswbuild(Relation heap, Relation index, IndexInfo *indexInfo);
@@ -306,4 +407,54 @@ void		hnswrescan(IndexScanDesc scan, ScanKey keys, int nkeys, ScanKey orderbys,
 bool		hnswgettuple(IndexScanDesc scan, ScanDirection dir);
 void		hnswendscan(IndexScanDesc scan);
 
+static inline HnswNeighborArray *
+HnswGetNeighbors(char *base, HnswElement element, int lc)
+{
+	HnswNeighborArrayPtr *neighborList = HnswPtrAccess(base, element->neighbors);
+
+	Assert(element->level >= lc);
+
+	return HnswPtrAccess(base, neighborList[lc]);
+}
+
+/* Hash tables */
+typedef struct TidHashEntry
+{
+	ItemPointerData tid;
+	char		status;
+}			TidHashEntry;
+
+#define SH_PREFIX tidhash
+#define SH_ELEMENT_TYPE TidHashEntry
+#define SH_KEY_TYPE ItemPointerData
+#define SH_SCOPE extern
+#define SH_DECLARE
+#include "lib/simplehash.h"
+
+typedef struct PointerHashEntry
+{
+	uintptr_t	ptr;
+	char		status;
+}			PointerHashEntry;
+
+#define SH_PREFIX pointerhash
+#define SH_ELEMENT_TYPE PointerHashEntry
+#define SH_KEY_TYPE uintptr_t
+#define SH_SCOPE extern
+#define SH_DECLARE
+#include "lib/simplehash.h"
+
+typedef struct OffsetHashEntry
+{
+	Size		offset;
+	char		status;
+}			OffsetHashEntry;
+
+#define SH_PREFIX offsethash
+#define SH_ELEMENT_TYPE OffsetHashEntry
+#define SH_KEY_TYPE Size
+#define SH_SCOPE extern
+#define SH_DECLARE
+#include "lib/simplehash.h"
+
 #endif

src/hnswinsert.c

@@ -2,9 +2,11 @@
 
 #include <math.h>
 
+#include "access/generic_xlog.h"
 #include "hnsw.h"
 #include "storage/bufmgr.h"
 #include "storage/lmgr.h"
+#include "utils/datum.h"
 #include "utils/memutils.h"
 
 /*
@@ -92,7 +94,7 @@ HnswFreeOffset(Relation index, Buffer buf, Page page, HnswElement element, Size
  * Add a new page
  */
 static void
-HnswInsertAppendPage(Relation index, Buffer *nbuf, Page *npage, GenericXLogState *state, Page page)
+HnswInsertAppendPage(Relation index, Buffer *nbuf, Page *npage, GenericXLogState *state, Page page, bool building)
 {
 	/* Add a new page */
 	LockRelationForExtension(index, ExclusiveLock);
@@ -100,7 +102,11 @@ HnswInsertAppendPage(Relation index, Buffer *nbuf, Page *npage, GenericXLogState
 	UnlockRelationForExtension(index, ExclusiveLock);
 
 	/* Init new page */
-	*npage = GenericXLogRegisterBuffer(state, *nbuf, GENERIC_XLOG_FULL_IMAGE);
+	if (building)
+		*npage = BufferGetPage(*nbuf);
+	else
+		*npage = GenericXLogRegisterBuffer(state, *nbuf, GENERIC_XLOG_FULL_IMAGE);
+
 	HnswInitPage(*nbuf, *npage);
 
 	/* Update previous buffer */
@@ -111,7 +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)
+AddElementOnDisk(Relation index, HnswElement e, int m, BlockNumber insertPage, BlockNumber *updatedInsertPage, bool building)
 {
 	Buffer		buf;
 	Page		page;
@@ -123,16 +129,16 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
 	Size		minCombinedSize;
 	HnswElementTuple etup;
 	BlockNumber currentPage = insertPage;
-	int			dimensions = e->vec->dim;
 	HnswNeighborTuple ntup;
 	Buffer		nbuf;
 	Page		npage;
 	OffsetNumber freeOffno = InvalidOffsetNumber;
 	OffsetNumber freeNeighborOffno = InvalidOffsetNumber;
 	BlockNumber newInsertPage = InvalidBlockNumber;
+	char	   *base = NULL;
 
 	/* Calculate sizes */
-	etupSize = HNSW_ELEMENT_TUPLE_SIZE(dimensions);
+	etupSize = HNSW_ELEMENT_TUPLE_SIZE(VARSIZE_ANY(HnswPtrAccess(base, e->value)));
 	ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(e->level, m);
 	combinedSize = etupSize + ntupSize + sizeof(ItemIdData);
 	maxSize = HNSW_MAX_SIZE;
@@ -140,11 +146,11 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
 
 	/* Prepare element tuple */
 	etup = palloc0(etupSize);
-	HnswSetElementTuple(etup, e);
+	HnswSetElementTuple(base, etup, e);
 
 	/* Prepare neighbor tuple */
 	ntup = palloc0(ntupSize);
-	HnswSetNeighborTuple(ntup, e, m);
+	HnswSetNeighborTuple(base, ntup, e, m);
 
 	/* Find a page (or two if needed) to insert the tuples */
 	for (;;)
@@ -152,8 +158,16 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
 		buf = ReadBuffer(index, currentPage);
 		LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
 
-		state = GenericXLogStart(index);
-		page = GenericXLogRegisterBuffer(state, buf, 0);
+		if (building)
+		{
+			state = NULL;
+			page = BufferGetPage(buf);
+		}
+		else
+		{
+			state = GenericXLogStart(index);
+			page = GenericXLogRegisterBuffer(state, buf, 0);
+		}
 
 		/* Keep track of first page where element at level 0 can fit */
 		if (!BlockNumberIsValid(newInsertPage) && PageGetFreeSpace(page) >= minCombinedSize)
@@ -173,7 +187,12 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
 		if (HnswFreeOffset(index, buf, page, e, ntupSize, &nbuf, &npage, &freeOffno, &freeNeighborOffno, &newInsertPage))
 		{
 			if (nbuf != buf)
-				npage = GenericXLogRegisterBuffer(state, nbuf, 0);
+			{
+				if (building)
+					npage = BufferGetPage(nbuf);
+				else
+					npage = GenericXLogRegisterBuffer(state, nbuf, 0);
+			}
 
 			break;
 		}
@@ -182,7 +201,7 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
 		/* Skip if both tuples can fit on the same page */
 		if (combinedSize > maxSize && PageGetFreeSpace(page) >= etupSize && !BlockNumberIsValid(HnswPageGetOpaque(page)->nextblkno))
 		{
-			HnswInsertAppendPage(index, &nbuf, &npage, state, page);
+			HnswInsertAppendPage(index, &nbuf, &npage, state, page, building);
 			break;
 		}
 
@@ -191,7 +210,8 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
 		if (BlockNumberIsValid(currentPage))
 		{
 			/* Move to next page */
-			GenericXLogAbort(state);
+			if (!building)
+				GenericXLogAbort(state);
 			UnlockReleaseBuffer(buf);
 		}
 		else
@@ -199,22 +219,33 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
 			Buffer		newbuf;
 			Page		newpage;
 
-			HnswInsertAppendPage(index, &newbuf, &newpage, state, page);
+			HnswInsertAppendPage(index, &newbuf, &newpage, state, page, building);
 
 			/* Commit */
-			GenericXLogFinish(state);
+			if (building)
+				MarkBufferDirty(buf);
+			else
+				GenericXLogFinish(state);
 
 			/* Unlock previous buffer */
 			UnlockReleaseBuffer(buf);
 
 			/* Prepare new buffer */
-			state = GenericXLogStart(index);
 			buf = newbuf;
-			page = GenericXLogRegisterBuffer(state, buf, 0);
+			if (building)
+			{
+				state = NULL;
+				page = BufferGetPage(buf);
+			}
+			else
+			{
+				state = GenericXLogStart(index);
+				page = GenericXLogRegisterBuffer(state, buf, 0);
+			}
 
 			/* Create new page for neighbors if needed */
 			if (PageGetFreeSpace(page) < combinedSize)
-				HnswInsertAppendPage(index, &nbuf, &npage, state, page);
+				HnswInsertAppendPage(index, &nbuf, &npage, state, page, building);
 			else
 			{
 				nbuf = buf;
@@ -268,7 +299,14 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
 	}
 
 	/* Commit */
-	GenericXLogFinish(state);
+	if (building)
+	{
+		MarkBufferDirty(buf);
+		if (nbuf != buf)
+			MarkBufferDirty(nbuf);
+	}
+	else
+		GenericXLogFinish(state);
 	UnlockReleaseBuffer(buf);
 	if (nbuf != buf)
 		UnlockReleaseBuffer(nbuf);
@@ -302,12 +340,14 @@ 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)
+HnswUpdateNeighborsOnDisk(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement e, int m, bool checkExisting, bool building)
 {
+	char	   *base = NULL;
+
 	for (int lc = e->level; lc >= 0; lc--)
 	{
 		int			lm = HnswGetLayerM(m, lc);
-		HnswNeighborArray *neighbors = &e->neighbors[lc];
+		HnswNeighborArray *neighbors = HnswGetNeighbors(base, e, lc);
 
 		for (int i = 0; i < neighbors->length; i++)
 		{
@@ -315,16 +355,15 @@ 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;
-			OffsetNumber offno = hc->element->neighborOffno;
+			HnswElement neighborElement = HnswPtrAccess(base, hc->element);
+			OffsetNumber offno = neighborElement->neighborOffno;
 
 			/* Get latest neighbors since they may have changed */
 			/* Do not lock yet since selecting neighbors can take time */
-			HnswLoadNeighbors(hc->element, index, m);
+			HnswLoadNeighbors(neighborElement, index, m);
 
 			/*
 			 * Could improve performance for vacuuming by checking neighbors
@@ -334,25 +373,31 @@ HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswE
 			 */
 
 			/* Select neighbors */
-			HnswUpdateConnection(e, hc, lm, lc, &idx, index, procinfo, collation);
+			HnswUpdateConnection(NULL, e, hc, lm, lc, &idx, index, procinfo, collation);
 
 			/* New element was not selected as a neighbor */
 			if (idx == -1)
 				continue;
 
 			/* Register page */
-			buf = ReadBuffer(index, hc->element->neighborPage);
+			buf = ReadBuffer(index, neighborElement->neighborPage);
 			LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
-			state = GenericXLogStart(index);
-			page = GenericXLogRegisterBuffer(state, buf, 0);
+			if (building)
+			{
+				state = NULL;
+				page = BufferGetPage(buf);
+			}
+			else
+			{
+				state = GenericXLogStart(index);
+				page = GenericXLogRegisterBuffer(state, buf, 0);
+			}
 
 			/* Get tuple */
-			itemid = PageGetItemId(page, offno);
-			ntup = (HnswNeighborTuple) PageGetItem(page, itemid);
-			ntupSize = ItemIdGetLength(itemid);
+			ntup = (HnswNeighborTuple) PageGetItem(page, PageGetItemId(page, offno));
 
 			/* Calculate index for update */
-			startIdx = (hc->element->level - lc) * m;
+			startIdx = (neighborElement->level - lc) * m;
 
 			/* Check for existing connection */
 			if (checkExisting && ConnectionExists(e, ntup, startIdx, lm))
@@ -378,17 +423,16 @@ 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 */
-				GenericXLogFinish(state);
+				if (building)
+					MarkBufferDirty(buf);
+				else
+					GenericXLogFinish(state);
 			}
-			else
+			else if (!building)
 				GenericXLogAbort(state);
 
 			UnlockReleaseBuffer(buf);
@@ -400,20 +444,27 @@ 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)
+AddDuplicateOnDisk(Relation index, HnswElement element, HnswElement dup, bool building)
 {
 	Buffer		buf;
 	Page		page;
 	GenericXLogState *state;
-	Size		etupSize = HNSW_ELEMENT_TUPLE_SIZE(dup->vec->dim);
 	HnswElementTuple etup;
 	int			i;
 
 	/* Read page */
 	buf = ReadBuffer(index, dup->blkno);
 	LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
-	state = GenericXLogStart(index);
-	page = GenericXLogRegisterBuffer(state, buf, 0);
+	if (building)
+	{
+		state = NULL;
+		page = BufferGetPage(buf);
+	}
+	else
+	{
+		state = GenericXLogStart(index);
+		page = GenericXLogRegisterBuffer(state, buf, 0);
+	}
 
 	/* Find space */
 	etup = (HnswElementTuple) PageGetItem(page, PageGetItemId(page, dup->offno));
@@ -426,82 +477,93 @@ HnswAddDuplicate(Relation index, HnswElement element, HnswElement dup)
 	/* Either being deleted or we lost our chance to another backend */
 	if (i == 0 || i == HNSW_HEAPTIDS)
 	{
-		GenericXLogAbort(state);
+		if (!building)
+			GenericXLogAbort(state);
 		UnlockReleaseBuffer(buf);
 		return false;
 	}
 
-	/* Add heap TID */
-	etup->heaptids[i] = *((ItemPointer) linitial(element->heaptids));
-
-	/* Overwrite tuple */
-	if (!PageIndexTupleOverwrite(page, dup->offno, (Item) etup, etupSize))
-		elog(ERROR, "failed to add index item to \"%s\"", RelationGetRelationName(index));
+	/* Add heap TID, modifying the tuple on the page directly */
+	etup->heaptids[i] = element->heaptids[0];
 
 	/* Commit */
-	GenericXLogFinish(state);
+	if (building)
+		MarkBufferDirty(buf);
+	else
+		GenericXLogFinish(state);
 	UnlockReleaseBuffer(buf);
 
 	return true;
 }
 
 /*
- * Write changes to disk
+ * Find duplicate element
+ */
+static bool
+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		neighborValue = HnswGetValue(base, neighborElement);
+
+		/* Exit early since ordered by distance */
+		if (!datumIsEqual(value, neighborValue, false, -1))
+			return false;
+
+		if (AddDuplicateOnDisk(index, element, neighborElement, building))
+			return true;
+	}
+
+	return false;
+}
+
+/*
+ * Update graph on disk
  */
 static void
-WriteElement(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement element, int m, int efConstruction, HnswElement dup, HnswElement entryPoint)
+UpdateGraphOnDisk(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement element, int m, int efConstruction, HnswElement entryPoint, bool building)
 {
 	BlockNumber newInsertPage = InvalidBlockNumber;
 
-	/* Try to add to existing page */
-	if (dup != NULL)
-	{
-		if (HnswAddDuplicate(index, element, dup))
-			return;
-	}
+	/* Look for duplicate */
+	if (FindDuplicateOnDisk(index, element, building))
+		return;
 
-	/* Write element and neighbor tuples */
-	WriteNewElementPages(index, element, m, GetInsertPage(index), &newInsertPage);
+	/* Add element */
+	AddElementOnDisk(index, element, m, GetInsertPage(index), &newInsertPage, building);
 
 	/* Update insert page if needed */
 	if (BlockNumberIsValid(newInsertPage))
-		HnswUpdateMetaPage(index, 0, NULL, newInsertPage, MAIN_FORKNUM);
+		HnswUpdateMetaPage(index, 0, NULL, newInsertPage, MAIN_FORKNUM, building);
 
 	/* Update neighbors */
-	HnswUpdateNeighborPages(index, procinfo, collation, element, m, false);
+	HnswUpdateNeighborsOnDisk(index, procinfo, collation, element, m, false, building);
 
-	/* Update metapage if needed */
+	/* Update entry point if needed */
 	if (entryPoint == NULL || element->level > entryPoint->level)
-		HnswUpdateMetaPage(index, HNSW_UPDATE_ENTRY_GREATER, element, InvalidBlockNumber, MAIN_FORKNUM);
+		HnswUpdateMetaPage(index, HNSW_UPDATE_ENTRY_GREATER, element, InvalidBlockNumber, MAIN_FORKNUM, building);
 }
 
 /*
  * Insert a tuple into the index
  */
 bool
-HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid, Relation heapRel)
+HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull, ItemPointer heap_tid, bool building)
 {
-	Datum		value;
-	FmgrInfo   *normprocinfo;
 	HnswElement entryPoint;
 	HnswElement element;
 	int			m;
 	int			efConstruction = HnswGetEfConstruction(index);
 	FmgrInfo   *procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
 	Oid			collation = index->rd_indcollation[0];
-	HnswElement dup;
 	LOCKMODE	lockmode = ShareLock;
-
-	/* Detoast once for all calls */
-	value = PointerGetDatum(PG_DETOAST_DATUM(values[0]));
-
-	/* Normalize if needed */
-	normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
-	if (normprocinfo != NULL)
-	{
-		if (!HnswNormValue(normprocinfo, collation, &value, NULL))
-			return false;
-	}
+	char	   *base = NULL;
 
 	/*
 	 * Get a shared lock. This allows vacuum to ensure no in-flight inserts
@@ -514,8 +576,8 @@ HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_ti
 	HnswGetMetaPageInfo(index, &m, &entryPoint);
 
 	/* Create an element */
-	element = HnswInitElement(heap_tid, m, HnswGetMl(m), HnswGetMaxLevel(m));
-	element->vec = DatumGetVector(value);
+	element = HnswInitElement(base, heap_tid, m, HnswGetMl(m), HnswGetMaxLevel(m), NULL);
+	HnswPtrStore(base, element->value, DatumGetPointer(value));
 
 	/* Prevent concurrent inserts when likely updating entry point */
 	if (entryPoint == NULL || element->level > entryPoint->level)
@@ -531,14 +593,11 @@ HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_ti
 		entryPoint = HnswGetEntryPoint(index);
 	}
 
-	/* Insert element in graph */
-	HnswInsertElement(element, entryPoint, index, procinfo, collation, m, efConstruction, false);
+	/* Find neighbors for element */
+	HnswFindElementNeighbors(base, element, entryPoint, index, procinfo, collation, m, efConstruction, false);
 
-	/* Look for duplicate */
-	dup = HnswFindDuplicate(element);
-
-	/* Write to disk */
-	WriteElement(index, procinfo, collation, element, m, efConstruction, dup, entryPoint);
+	/* Update graph on disk */
+	UpdateGraphOnDisk(index, procinfo, collation, element, m, efConstruction, entryPoint, building);
 
 	/* Release lock */
 	UnlockPage(index, HNSW_UPDATE_LOCK, lockmode);
@@ -546,6 +605,30 @@ HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_ti
 	return true;
 }
 
+/*
+ * Insert a tuple into the index
+ */
+static void
+HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid)
+{
+	Datum		value;
+	FmgrInfo   *normprocinfo;
+	Oid			collation = index->rd_indcollation[0];
+
+	/* Detoast once for all calls */
+	value = PointerGetDatum(PG_DETOAST_DATUM(values[0]));
+
+	/* Normalize if needed */
+	normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
+	if (normprocinfo != NULL)
+	{
+		if (!HnswNormValue(normprocinfo, collation, &value, NULL))
+			return;
+	}
+
+	HnswInsertTupleOnDisk(index, value, values, isnull, heap_tid, false);
+}
+
 /*
  * Insert a tuple into the index
  */
@@ -572,7 +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

@@ -21,6 +21,7 @@ GetScanItems(IndexScanDesc scan, Datum q)
 	List	   *w;
 	int			m;
 	HnswElement entryPoint;
+	char	   *base = NULL;
 
 	/* Get m and entry point */
 	HnswGetMetaPageInfo(index, &m, &entryPoint);
@@ -28,15 +29,15 @@ GetScanItems(IndexScanDesc scan, Datum q)
 	if (entryPoint == NULL)
 		return NIL;
 
-	ep = list_make1(HnswEntryCandidate(entryPoint, q, index, procinfo, collation, false));
+	ep = list_make1(HnswEntryCandidate(base, entryPoint, q, index, procinfo, collation, false));
 
 	for (int lc = entryPoint->level; lc >= 1; lc--)
 	{
-		w = HnswSearchLayer(q, ep, 1, lc, index, procinfo, collation, m, false, NULL);
+		w = HnswSearchLayer(base, q, ep, 1, lc, index, procinfo, collation, m, false, NULL);
 		ep = w;
 	}
 
-	return HnswSearchLayer(q, ep, hnsw_ef_search, 0, index, procinfo, collation, m, false, NULL);
+	return HnswSearchLayer(base, q, ep, hnsw_ef_search, 0, index, procinfo, collation, m, false, NULL);
 }
 
 /*
@@ -184,28 +185,24 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
 
 	while (list_length(so->w) > 0)
 	{
+		char	   *base = NULL;
 		HnswCandidate *hc = llast(so->w);
+		HnswElement element = HnswPtrAccess(base, hc->element);
 		ItemPointer heaptid;
 
 		/* Move to next element if no valid heap TIDs */
-		if (list_length(hc->element->heaptids) == 0)
+		if (element->heaptidsLength == 0)
 		{
 			so->w = list_delete_last(so->w);
 			continue;
 		}
 
-		heaptid = llast(hc->element->heaptids);
-
-		hc->element->heaptids = list_delete_last(hc->element->heaptids);
+		heaptid = &element->heaptids[--element->heaptidsLength];
 
 		MemoryContextSwitchTo(oldCtx);
 
-#if PG_VERSION_NUM >= 120000
 		scan->xs_heaptid = *heaptid;
-#else
-		scan->xs_ctup.t_self = *heaptid;
-#endif
-
+		scan->xs_recheck = false;
 		scan->xs_recheckorderby = false;
 		return true;
 	}

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"
@@ -12,12 +13,9 @@
  * Check if deleted list contains an index TID
  */
 static bool
-DeletedContains(HTAB *deleted, ItemPointer indextid)
+DeletedContains(tidhash_hash * deleted, ItemPointer indextid)
 {
-	bool		found;
-
-	hash_search(deleted, indextid, HASH_FIND, &found);
-	return found;
+	return tidhash_lookup(deleted, *indextid) != NULL;
 }
 
 /*
@@ -93,15 +91,10 @@ RemoveHeapTids(HnswVacuumState * vacuumstate)
 
 				if (itemUpdated)
 				{
-					Size		etupSize = HNSW_ELEMENT_TUPLE_SIZE(etup->vec.dim);
-
 					/* 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;
 				}
 			}
@@ -109,11 +102,13 @@ RemoveHeapTids(HnswVacuumState * vacuumstate)
 			if (!ItemPointerIsValid(&etup->heaptids[0]))
 			{
 				ItemPointerData ip;
+				bool		found;
 
 				/* Add to deleted list */
 				ItemPointerSet(&ip, blkno, offno);
 
-				(void) hash_search(vacuumstate->deleted, &ip, HASH_ENTER, NULL);
+				tidhash_insert(vacuumstate->deleted, ip, &found);
+				Assert(!found);
 			}
 			else if (etup->level > highestLevel && !(entryPoint != NULL && blkno == entryPoint->blkno && offno == entryPoint->offno))
 			{
@@ -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(element, m);
-	element->heaptids = NIL;
+	HnswInitNeighbors(base, element, m, NULL);
+	element->heaptidsLength = 0;
 
-	/* Add element to graph, skipping itself */
-	HnswInsertElement(element, entryPoint, index, procinfo, collation, m, efConstruction, true);
+	/* Find neighbors for element, skipping itself */
+	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(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);
+	HnswUpdateNeighborsOnDisk(index, procinfo, collation, element, m, true, false);
 }
 
 /*
@@ -286,7 +285,7 @@ RepairGraphEntryPoint(HnswVacuumState * vacuumstate)
 			 * point is outdated and empty, the entry point will be empty
 			 * until an element is repaired.
 			 */
-			HnswUpdateMetaPage(index, HNSW_UPDATE_ENTRY_ALWAYS, highestPoint, InvalidBlockNumber, MAIN_FORKNUM);
+			HnswUpdateMetaPage(index, HNSW_UPDATE_ENTRY_ALWAYS, highestPoint, InvalidBlockNumber, MAIN_FORKNUM, false);
 		}
 		else
 		{
@@ -301,7 +300,7 @@ RepairGraphEntryPoint(HnswVacuumState * vacuumstate)
 			{
 				/* Reset neighbors from previous update */
 				if (highestPoint != NULL)
-					highestPoint->neighbors = NULL;
+					HnswPtrStore((char *) NULL, highestPoint->neighbors, (HnswNeighborArrayPtr *) NULL);
 
 				RepairGraphElement(vacuumstate, entryPoint, highestPoint);
 			}
@@ -419,7 +418,7 @@ RepairGraph(HnswVacuumState * vacuumstate)
 			 * was replaced and highest point was outdated.
 			 */
 			if (entryPoint == NULL || element->level > entryPoint->level)
-				HnswUpdateMetaPage(index, HNSW_UPDATE_ENTRY_GREATER, element, InvalidBlockNumber, MAIN_FORKNUM);
+				HnswUpdateMetaPage(index, HNSW_UPDATE_ENTRY_GREATER, element, InvalidBlockNumber, MAIN_FORKNUM, false);
 
 			/* Release lock */
 			UnlockPage(index, HNSW_UPDATE_LOCK, lockmode);
@@ -479,8 +478,6 @@ MarkDeleted(HnswVacuumState * vacuumstate)
 		{
 			HnswElementTuple etup = (HnswElementTuple) PageGetItem(page, PageGetItemId(page, offno));
 			HnswNeighborTuple ntup;
-			Size		etupSize;
-			Size		ntupSize;
 			Buffer		nbuf;
 			Page		npage;
 			BlockNumber neighborPage;
@@ -504,10 +501,6 @@ MarkDeleted(HnswVacuumState * vacuumstate)
 			if (ItemPointerIsValid(&etup->heaptids[0]))
 				continue;
 
-			/* Calculate sizes */
-			etupSize = HNSW_ELEMENT_TUPLE_SIZE(etup->vec.dim);
-			ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(etup->level, vacuumstate->m);
-
 			/* Get neighbor page */
 			neighborPage = ItemPointerGetBlockNumber(&etup->neighbortid);
 			neighborOffno = ItemPointerGetOffsetNumber(&etup->neighbortid);
@@ -528,19 +521,16 @@ MarkDeleted(HnswVacuumState * vacuumstate)
 
 			/* Overwrite element */
 			etup->deleted = 1;
-			MemSet(&etup->vec.x, 0, etup->vec.dim * sizeof(float));
+			MemSet(&etup->data, 0, VARSIZE_ANY(&etup->data));
 
 			/* Overwrite neighbors */
 			for (int i = 0; i < ntup->count; i++)
 				ItemPointerSetInvalid(&ntup->indextids[i]);
 
-			/* Overwrite element tuple */
-			if (!PageIndexTupleOverwrite(page, offno, (Item) etup, etupSize))
-				elog(ERROR, "failed to add index item to \"%s\"", RelationGetRelationName(index));
-
-			/* Overwrite neighbor tuple */
-			if (!PageIndexTupleOverwrite(npage, neighborOffno, (Item) ntup, ntupSize))
-				elog(ERROR, "failed to add index item to \"%s\"", RelationGetRelationName(index));
+			/*
+			 * We modified the tuples in place, no need to call
+			 * PageIndexTupleOverwrite
+			 */
 
 			/* Commit */
 			GenericXLogFinish(state);
@@ -563,7 +553,7 @@ MarkDeleted(HnswVacuumState * vacuumstate)
 	}
 
 	/* Update insert page last, after everything has been marked as deleted */
-	HnswUpdateMetaPage(index, 0, NULL, insertPage, MAIN_FORKNUM);
+	HnswUpdateMetaPage(index, 0, NULL, insertPage, MAIN_FORKNUM, false);
 }
 
 /*
@@ -573,7 +563,6 @@ static void
 InitVacuumState(HnswVacuumState * vacuumstate, IndexVacuumInfo *info, IndexBulkDeleteResult *stats, IndexBulkDeleteCallback callback, void *callback_state)
 {
 	Relation	index = info->index;
-	HASHCTL		hash_ctl;
 
 	if (stats == NULL)
 		stats = (IndexBulkDeleteResult *) palloc0(sizeof(IndexBulkDeleteResult));
@@ -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);
@@ -595,10 +584,7 @@ InitVacuumState(HnswVacuumState * vacuumstate, IndexVacuumInfo *info, IndexBulkD
 	HnswGetMetaPageInfo(index, &vacuumstate->m, NULL);
 
 	/* Create hash table */
-	hash_ctl.keysize = sizeof(ItemPointerData);
-	hash_ctl.entrysize = sizeof(ItemPointerData);
-	hash_ctl.hcxt = CurrentMemoryContext;
-	vacuumstate->deleted = hash_create("hnswbulkdelete indextids", 256, &hash_ctl, HASH_ELEM | HASH_BLOBS | HASH_CONTEXT);
+	vacuumstate->deleted = tidhash_create(CurrentMemoryContext, 256, NULL);
 }
 
 /*
@@ -607,7 +593,7 @@ InitVacuumState(HnswVacuumState * vacuumstate, IndexVacuumInfo *info, IndexBulkD
 static void
 FreeVacuumState(HnswVacuumState * vacuumstate)
 {
-	hash_destroy(vacuumstate->deleted);
+	tidhash_destroy(vacuumstate->deleted);
 	FreeAccessStrategy(vacuumstate->bas);
 	pfree(vacuumstate->ntup);
 	MemoryContextDelete(vacuumstate->tmpCtx);

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
-#define PROGRESS_CREATEIDX_TUPLES_TOTAL 0
-#define PROGRESS_CREATEIDX_TUPLES_DONE 0
+#include "pgstat.h"
 #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);
@@ -543,10 +506,10 @@ CreateListPages(Relation index, VectorArray centers, int dimensions,
 	pfree(list);
 }
 
+#ifdef IVFFLAT_KMEANS_DEBUG
 /*
  * Print k-means metrics
  */
-#ifdef IVFFLAT_KMEANS_DEBUG
 static void
 PrintKmeansMetrics(IvfflatBuildState * buildstate)
 {
@@ -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
-#include "commands/progress.h"
+#if PG_VERSION_NUM < 150000
+#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/ivfkmeans.c

@@ -6,6 +6,10 @@
 #include "ivfflat.h"
 #include "miscadmin.h"
 
+#ifdef IVFFLAT_MEMORY
+#include "utils/memutils.h"
+#endif
+
 /*
  * Initialize with kmeans++
  *
@@ -151,6 +155,23 @@ QuickCenters(Relation index, VectorArray samples, VectorArray centers)
 	}
 }
 
+#ifdef IVFFLAT_MEMORY
+/*
+ * Show memory usage
+ */
+static void
+ShowMemoryUsage(Size estimatedSize)
+{
+#if PG_VERSION_NUM >= 130000
+	elog(INFO, "total memory: %zu MB",
+		 MemoryContextMemAllocated(CurrentMemoryContext, true) / (1024 * 1024));
+#else
+	MemoryContextStats(CurrentMemoryContext);
+#endif
+	elog(INFO, "estimated memory: %zu MB", estimatedSize / (1024 * 1024));
+}
+#endif
+
 /*
  * Use Elkan for performance. This requires distance function to satisfy triangle inequality.
  *
@@ -231,6 +252,10 @@ ElkanKmeans(Relation index, VectorArray samples, VectorArray centers)
 		vec->dim = dimensions;
 	}
 
+#ifdef IVFFLAT_MEMORY
+	ShowMemoryUsage(totalSize);
+#endif
+
 	/* Pick initial centers */
 	InitCenters(index, samples, centers, lowerBound);
 

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_ctup.t_self = *heaptid;
-#endif
-
+		scan->xs_recheck = false;
 		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'
@@ -89,7 +84,7 @@ CheckDim(int dim)
 }
 
 /*
- * Ensure finite elements
+ * Ensure finite element
  */
 static inline void
 CheckElement(float value)
@@ -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 = ']';
@@ -437,17 +420,18 @@ vector_send(PG_FUNCTION_ARGS)
 
 /*
  * Convert vector to vector
+ * This is needed to check the type modifier
  */
 PGDLLEXPORT PG_FUNCTION_INFO_V1(vector);
 Datum
 vector(PG_FUNCTION_ARGS)
 {
-	Vector	   *arg = PG_GETARG_VECTOR_P(0);
+	Vector	   *vec = PG_GETARG_VECTOR_P(0);
 	int32		typmod = PG_GETARG_INT32(1);
 
-	CheckExpectedDim(typmod, arg->dim);
+	CheckExpectedDim(typmod, vec->dim);
 
-	PG_RETURN_POINTER(arg);
+	PG_RETURN_POINTER(vec);
 }
 
 /*
@@ -464,7 +448,6 @@ array_to_vector(PG_FUNCTION_ARGS)
 	bool		typbyval;
 	char		typalign;
 	Datum	   *elemsp;
-	bool	   *nullsp;
 	int			nelemsp;
 
 	if (ARR_NDIM(array) > 1)
@@ -478,7 +461,7 @@ array_to_vector(PG_FUNCTION_ARGS)
 				 errmsg("array must not contain nulls")));
 
 	get_typlenbyvalalign(ARR_ELEMTYPE(array), &typlen, &typbyval, &typalign);
-	deconstruct_array(array, ARR_ELEMTYPE(array), typlen, typbyval, typalign, &elemsp, &nullsp, &nelemsp);
+	deconstruct_array(array, ARR_ELEMTYPE(array), typlen, typbyval, typalign, &elemsp, NULL, &nelemsp);
 
 	CheckDim(nelemsp);
 	CheckExpectedDim(typmod, nelemsp);
@@ -512,6 +495,12 @@ array_to_vector(PG_FUNCTION_ARGS)
 				 errmsg("unsupported array type")));
 	}
 
+	/*
+	 * Free allocation from deconstruct_array. Do not free individual elements
+	 * when pass-by-reference since they point to original array.
+	 */
+	pfree(elemsp);
+
 	/* Check elements */
 	for (int i = 0; i < result->dim; i++)
 		CheckElement(result->x[i]);
@@ -718,7 +707,7 @@ vector_spherical_distance(PG_FUNCTION_ARGS)
 }
 
 /*
- * Get the L1 distance between vectors
+ * Get the L1 distance between two vectors
  */
 PGDLLEXPORT PG_FUNCTION_INFO_V1(l1_distance);
 Datum
@@ -877,9 +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;
@@ -887,6 +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;
 }
 
@@ -897,8 +894,11 @@ PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_lt);
 Datum
 vector_lt(PG_FUNCTION_ARGS)
 {
-	Vector	   *a = (Vector *) PG_GETARG_VECTOR_P(0);
-	Vector	   *b = (Vector *) PG_GETARG_VECTOR_P(1);
+	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);
 }
@@ -910,8 +910,11 @@ PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_le);
 Datum
 vector_le(PG_FUNCTION_ARGS)
 {
-	Vector	   *a = (Vector *) PG_GETARG_VECTOR_P(0);
-	Vector	   *b = (Vector *) PG_GETARG_VECTOR_P(1);
+	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);
 }
@@ -923,8 +926,11 @@ PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_eq);
 Datum
 vector_eq(PG_FUNCTION_ARGS)
 {
-	Vector	   *a = (Vector *) PG_GETARG_VECTOR_P(0);
-	Vector	   *b = (Vector *) PG_GETARG_VECTOR_P(1);
+	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);
 }
@@ -936,8 +942,11 @@ PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_ne);
 Datum
 vector_ne(PG_FUNCTION_ARGS)
 {
-	Vector	   *a = (Vector *) PG_GETARG_VECTOR_P(0);
-	Vector	   *b = (Vector *) PG_GETARG_VECTOR_P(1);
+	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);
 }
@@ -949,8 +958,11 @@ PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_ge);
 Datum
 vector_ge(PG_FUNCTION_ARGS)
 {
-	Vector	   *a = (Vector *) PG_GETARG_VECTOR_P(0);
-	Vector	   *b = (Vector *) PG_GETARG_VECTOR_P(1);
+	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);
 }
@@ -962,8 +974,11 @@ PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_gt);
 Datum
 vector_gt(PG_FUNCTION_ARGS)
 {
-	Vector	   *a = (Vector *) PG_GETARG_VECTOR_P(0);
-	Vector	   *b = (Vector *) PG_GETARG_VECTOR_P(1);
+	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);
 }
@@ -975,8 +990,8 @@ PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_cmp);
 Datum
 vector_cmp(PG_FUNCTION_ARGS)
 {
-	Vector	   *a = (Vector *) PG_GETARG_VECTOR_P(0);
-	Vector	   *b = (Vector *) PG_GETARG_VECTOR_P(1);
+	Vector	   *a = PG_GETARG_VECTOR_P(0);
+	Vector	   *b = PG_GETARG_VECTOR_P(1);
 
 	PG_RETURN_INT32(vector_cmp_internal(a, b));
 }

test/expected/functions.out

@@ -24,6 +24,56 @@ 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 = '[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 +6,17 @@ SELECT '[1,2,3]'::vector * '[4,5,6]';
 SELECT '[1e37]'::vector * '[1e37]';
 SELECT '[1e-37]'::vector * '[1e-37]';
 
+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/012_hnsw_build_recall.pl

@@ -83,11 +83,46 @@ for my $i (0 .. $#operators)
 		push(@expected, $res);
 	}
 
-	# Add index
-	$node->safe_psql("postgres", "CREATE INDEX ON tst USING hnsw (v $opclass);");
+	# Build index serially
+	$node->safe_psql("postgres", qq(
+		SET max_parallel_maintenance_workers = 0;
+		CREATE INDEX idx ON tst USING hnsw (v $opclass);
+	));
 
+	# Test approximate results
 	my $min = $operator eq "<#>" ? 0.80 : 0.99;
 	test_recall($min, $operator);
+
+	$node->safe_psql("postgres", "DROP INDEX idx;");
+
+	# Build index in parallel in memory
+	my ($ret, $stdout, $stderr) = $node->psql("postgres", qq(
+		SET client_min_messages = DEBUG;
+		SET min_parallel_table_scan_size = 1;
+		CREATE INDEX idx ON tst USING hnsw (v $opclass);
+	));
+	is($ret, 0, $stderr);
+	like($stderr, qr/using \d+ parallel workers/);
+
+	# Test approximate results
+	test_recall($min, $operator);
+
+	$node->safe_psql("postgres", "DROP INDEX idx;");
+
+	# Build index in parallel on disk
+	# Set parallel_workers on table to use workers with low maintenance_work_mem
+	($ret, $stdout, $stderr) = $node->psql("postgres", qq(
+		ALTER TABLE tst SET (parallel_workers = 2);
+		SET client_min_messages = DEBUG;
+		SET maintenance_work_mem = '4MB';
+		CREATE INDEX idx ON tst USING hnsw (v $opclass);
+		ALTER TABLE tst RESET (parallel_workers);
+	));
+	is($ret, 0, $stderr);
+	like($stderr, qr/using \d+ parallel workers/);
+	like($stderr, qr/hnsw graph no longer fits into maintenance_work_mem/);
+
+	$node->safe_psql("postgres", "DROP INDEX idx;");
 }
 
 done_testing();

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();

test/t/020_hnsw_array.pl

@@ -0,0 +1,113 @@
+use strict;
+use warnings;
+use PostgresNode;
+use TestLib;
+use Test::More;
+
+my $node;
+my @queries = ();
+my @expected;
+my $limit = 20;
+
+sub test_recall
+{
+	my ($min, $operator) = @_;
+	my $correct = 0;
+	my $total = 0;
+
+	my $explain = $node->safe_psql("postgres", qq(
+		SET enable_seqscan = off;
+		EXPLAIN ANALYZE SELECT i FROM tst ORDER BY v $operator '$queries[0]' LIMIT $limit;
+	));
+	like($explain, qr/Index Scan/);
+
+	for my $i (0 .. $#queries)
+	{
+		my $actual = $node->safe_psql("postgres", qq(
+			SET enable_seqscan = off;
+			SELECT i FROM tst ORDER BY v $operator '$queries[$i]' LIMIT $limit;
+		));
+		my @actual_ids = split("\n", $actual);
+		my %actual_set = map { $_ => 1 } @actual_ids;
+
+		my @expected_ids = split("\n", $expected[$i]);
+
+		foreach (@expected_ids)
+		{
+			if (exists($actual_set{$_}))
+			{
+				$correct++;
+			}
+			$total++;
+		}
+	}
+
+	cmp_ok($correct / $total, ">=", $min, $operator);
+}
+
+# Initialize node
+$node = get_new_node('node');
+$node->init;
+$node->start;
+
+# Create table
+$node->safe_psql("postgres", "CREATE EXTENSION vector;");
+$node->safe_psql("postgres", "CREATE TABLE tst (i int4, v float4[3]);");
+$node->safe_psql("postgres",
+	"INSERT INTO tst SELECT i, ARRAY[random(), random(), random()] FROM generate_series(1, 10000) i;"
+);
+
+$node->safe_psql("postgres", qq(
+	CREATE FUNCTION float4_l2_distance(float4[], float4[]) RETURNS float8
+		AS 'BEGIN RETURN l2_distance(\$1::vector, \$2::vector); END;'
+		LANGUAGE plpgsql IMMUTABLE STRICT PARALLEL SAFE;
+
+	CREATE FUNCTION float4_l2_squared_distance(float4[], float4[]) RETURNS float8
+		AS 'BEGIN RETURN vector_l2_squared_distance(\$1::vector, \$2::vector); END;'
+		LANGUAGE plpgsql IMMUTABLE STRICT PARALLEL SAFE;
+
+	CREATE OPERATOR <-> (
+		LEFTARG = float4[], RIGHTARG = float4[], PROCEDURE = float4_l2_distance,
+		COMMUTATOR = '<->'
+	);
+
+	CREATE OPERATOR CLASS float4_l2_ops
+		FOR TYPE float4[] USING hnsw AS
+		OPERATOR 1 <-> (float4[], float4[]) FOR ORDER BY float_ops,
+		FUNCTION 1 float4_l2_squared_distance(float4[], float4[]);
+));
+
+# Generate queries
+for (1 .. 20)
+{
+	my $r1 = rand();
+	my $r2 = rand();
+	my $r3 = rand();
+	push(@queries, "{$r1,$r2,$r3}");
+}
+
+# Check each index type
+my @operators = ("<->");
+my @opclasses = ("float4_l2_ops");
+
+for my $i (0 .. $#operators)
+{
+	my $operator = $operators[$i];
+	my $opclass = $opclasses[$i];
+
+	# Get exact results
+	@expected = ();
+	foreach (@queries)
+	{
+		my $res = $node->safe_psql("postgres", "SELECT i FROM tst ORDER BY v $operator '$_' LIMIT $limit;");
+		push(@expected, $res);
+	}
+
+	# Add index
+	$node->safe_psql("postgres", "CREATE INDEX ON tst USING hnsw (v $opclass);");
+
+	my $min = $operator eq "<#>" ? 0.80 : 0.99;
+	test_recall($min, $operator);
+}
+
+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 = '0.6.0'
 module_pathname = '$libdir/vector'
 relocatable = true