Fixed Windows build [skip ci]

.github/workflows/build.yml

@@ -8,8 +8,6 @@ jobs:
       fail-fast: false
       matrix:
         include:
-          - postgres: 17
-            os: ubuntu-22.04
           - postgres: 16
             os: ubuntu-22.04
           - postgres: 15
@@ -23,7 +21,7 @@ jobs:
           - postgres: 11
             os: ubuntu-20.04
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
       - uses: ankane/setup-postgres@v1
         with:
           postgres-version: ${{ matrix.postgres }}
@@ -45,7 +43,7 @@ jobs:
     runs-on: macos-latest
     if: ${{ !startsWith(github.ref_name, 'windows') }}
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
       - uses: ankane/setup-postgres@v1
         with:
           postgres-version: 14
@@ -67,7 +65,7 @@ jobs:
     runs-on: windows-latest
     if: ${{ !startsWith(github.ref_name, 'mac') }}
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
       - uses: ankane/setup-postgres@v1
         with:
           postgres-version: 14

CHANGELOG.md

@@ -1,14 +1,7 @@
-## 0.5.2 (unreleased)
+## 0.5.1 (unreleased)
 
-- Improved performance of HNSW
+- Added check for MVCC-compliant snapshot for HNSW index scans
-- Added support for on-disk parallel index builds for HNSW
+- Improved performance of index scans for IVFFlat after updates and deletes
-- Reduced WAL generation for HNSW index builds
-- Fixed `invalid memory alloc request size` error with HNSW index build
-
-## 0.5.1 (2023-10-10)
-
-- Improved performance of HNSW index builds
-- Added check for MVCC-compliant snapshot for index scans
 
 ## 0.5.0 (2023-08-28)
 

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": "0.5.0",
 	"maintainer": [
 		"Andrew Kane <andrew@ankane.org>"
 	],
@@ -20,7 +20,7 @@
 		"vector": {
 			"file": "sql/vector.sql",
 			"docfile": "README.md",
-			"version": "0.5.1",
+			"version": "0.5.0",
 			"abstract": "Open-source vector similarity search for Postgres"
 		}
 	},

Makefile

@@ -1,10 +1,10 @@
 EXTENSION = vector
-EXTVERSION = 0.5.1
+EXTVERSION = 0.5.0
 
 MODULE_big = vector
 DATA = $(wildcard sql/*--*.sql)
-OBJS = src/hnsw.o src/hnswbuild.o src/hnswinsert.o src/hnswscan.o src/hnswutils.o src/hnswvacuum.o src/ivfbuild.o src/ivfflat.o src/ivfinsert.o src/ivfkmeans.o src/ivfscan.o src/ivfutils.o src/ivfvacuum.o src/vector.o
+OBJS = src/hnsw.o src/hnswbuild.o src/hnswinsert.o src/hnswscan.o src/hnswutils.o src/hnswvacuum.o src/ivfbuild.o src/ivfflat.o src/ivfinsert.o src/ivfkmeans.o src/ivfscan.o src/ivfutils.o src/ivfvacuum.o src/tinyint.o src/vector.o
-HEADERS = src/vector.h
+HEADERS = src/tinyint.h src/vector.h
 
 TESTS = $(wildcard test/sql/*.sql)
 REGRESS = $(patsubst test/sql/%.sql,%,$(TESTS))

Makefile.win

@@ -1,8 +1,8 @@
 EXTENSION = vector
-EXTVERSION = 0.5.1
+EXTVERSION = 0.5.0
 
-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
+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\tinyint.obj src\vector.obj
-HEADERS = src\vector.h
+HEADERS = src\tinyint.h src\vector.h
 
 REGRESS = btree cast copy functions input ivfflat_cosine ivfflat_ip ivfflat_l2 ivfflat_options ivfflat_unlogged
 REGRESS_OPTS = --inputdir=test --load-extension=$(EXTENSION)

README.md

@@ -10,7 +10,7 @@ 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/actions/workflows/build.yml/badge.svg)](https://github.com/pgvector/pgvector/actions)
+[![Build Status](https://github.com/pgvector/pgvector/workflows/build/badge.svg?branch=master)](https://github.com/pgvector/pgvector/actions)
 
 ## Installation
 
@@ -18,7 +18,7 @@ Compile and install the extension (supports Postgres 11+)
 
 ```sh
 cd /tmp
-git clone --branch v0.5.1 https://github.com/pgvector/pgvector.git
+git clone --branch v0.5.0 https://github.com/pgvector/pgvector.git
 cd pgvector
 make
 make install # may need sudo
@@ -26,7 +26,7 @@ make install # may need sudo
 
 See the [installation notes](#installation-notes) if you run into issues
 
-You can also install it with [Docker](#docker), [Homebrew](#homebrew), [PGXN](#pgxn), [APT](#apt), [Yum](#yum), or [conda-forge](#conda-forge), and it comes preinstalled with [Postgres.app](#postgresapp) and many [hosted providers](#hosted-postgres). There are also instructions for [GitHub Actions](https://github.com/pgvector/setup-pgvector).
+You can also install it with [Docker](#docker), [Homebrew](#homebrew), [PGXN](#pgxn), [APT](#apt), [Yum](#yum), or [conda-forge](#conda-forge), and it comes preinstalled with [Postgres.app](#postgresapp) and many [hosted providers](#hosted-postgres)
 
 ## Getting Started
 
@@ -215,23 +215,6 @@ SELECT ...
 COMMIT;
 ```
 
-### 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 * tuples_done / nullif(tuples_total, 0), 1) AS "%" FROM pg_stat_progress_create_index;
-```
-
-The phases for IVFFlat are:
-
-1. `initializing`
-2. `performing k-means`
-3. `assigning tuples`
-4. `loading tuples`
-
-Note: `%` is only populated during the `loading tuples` phase
-
 ## HNSW
 
 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.
@@ -269,8 +252,6 @@ Specify HNSW parameters
 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)
@@ -290,18 +271,22 @@ 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, round(100.0 * blocks_done / nullif(blocks_total, 0), 1) AS "%" FROM pg_stat_progress_create_index;
+SELECT phase, tuples_done, tuples_total FROM pg_stat_progress_create_index;
 ```
 
-The phases for HNSW are:
+The phases are:
 
 1. `initializing`
-2. `loading tuples`
+2. `performing k-means` - IVFFlat only
+3. `assigning tuples` - IVFFlat only
+4. `loading tuples`
+
+Note: `tuples_done` and `tuples_total` are only populated during the `loading tuples` phase
 
 ## Filtering
 
@@ -332,15 +317,13 @@ 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.
+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)).
 
 ```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.
@@ -377,21 +360,17 @@ Use pgvector from any language with a Postgres client. You can even generate and
 
 Language | Libraries / Examples
 --- | ---
-C | [pgvector-c](https://github.com/pgvector/pgvector-c)
 C++ | [pgvector-cpp](https://github.com/pgvector/pgvector-cpp)
-C#, F#, Visual Basic | [pgvector-dotnet](https://github.com/pgvector/pgvector-dotnet)
+C# | [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, Kotlin, Groovy, Scala | [pgvector-java](https://github.com/pgvector/pgvector-java)
+Java, 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)
-Nim | [pgvector-nim](https://github.com/pgvector/pgvector-nim)
+Node.js | [pgvector-node](https://github.com/pgvector/pgvector-node)
-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)
@@ -399,7 +378,6 @@ 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
 
@@ -415,63 +393,6 @@ 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?
@@ -485,8 +406,6 @@ 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:
@@ -590,7 +509,7 @@ 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
+git clone --branch v0.5.0 https://github.com/pgvector/pgvector.git
 cd pgvector
 nmake /F Makefile.win
 nmake /F Makefile.win install
@@ -611,7 +530,7 @@ This adds pgvector to the [Postgres image](https://hub.docker.com/_/postgres) (r
 You can also build the image manually:
 
 ```sh
-git clone --branch v0.5.1 https://github.com/pgvector/pgvector.git
+git clone --branch v0.5.0 https://github.com/pgvector/pgvector.git
 cd pgvector
 docker build --build-arg PG_MAJOR=15 -t myuser/pgvector .
 ```
@@ -676,7 +595,7 @@ pgvector is available on [these providers](https://github.com/pgvector/pgvector/
 
 ## Upgrading
 
-[Install](#installation) the latest version (use the same method as the original installation). Then in each database you want to upgrade, run:
+Install the latest version. Then in each database you want to upgrade, run:
 
 ```sql
 ALTER EXTENSION vector UPDATE;

sql/vector--0.5.0--0.5.1.sql

@@ -1,2 +1,67 @@
 -- complain if script is sourced in psql, rather than via CREATE EXTENSION
 \echo Use "ALTER EXTENSION vector UPDATE TO '0.5.1'" to load this file. \quit
+
+-- tinyint
+
+CREATE TYPE tinyint;
+
+CREATE FUNCTION tinyint_in(cstring, oid, integer) RETURNS tinyint
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE FUNCTION tinyint_out(tinyint) RETURNS cstring
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE FUNCTION tinyint_recv(internal, oid, integer) RETURNS tinyint
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE FUNCTION tinyint_send(tinyint) RETURNS bytea
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE TYPE tinyint (
+	INPUT     = tinyint_in,
+	OUTPUT    = tinyint_out,
+	RECEIVE   = tinyint_recv,
+	SEND      = tinyint_send,
+	INTERNALLENGTH = 1,
+	PASSEDBYVALUE,
+	ALIGNMENT = char
+);
+
+CREATE FUNCTION integer_to_tinyint(integer, integer, boolean) RETURNS tinyint
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE FUNCTION numeric_to_tinyint(numeric, integer, boolean) RETURNS tinyint
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE CAST (integer AS tinyint)
+	WITH FUNCTION integer_to_tinyint(integer, integer, boolean) AS IMPLICIT;
+
+CREATE CAST (numeric AS tinyint)
+	WITH FUNCTION numeric_to_tinyint(numeric, integer, boolean) AS IMPLICIT;
+
+CREATE FUNCTION l2_distance(tinyint[], tinyint[]) RETURNS float8
+	AS 'MODULE_PATHNAME', 'tinyint_l2_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE FUNCTION inner_product(tinyint[], tinyint[]) RETURNS float8
+	AS 'MODULE_PATHNAME', 'tinyint_inner_product' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE FUNCTION cosine_distance(tinyint[], tinyint[]) RETURNS float8
+	AS 'MODULE_PATHNAME', 'tinyint_cosine_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE FUNCTION tinyint_negative_inner_product(tinyint[], tinyint[]) RETURNS float8
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE OPERATOR <-> (
+	LEFTARG = tinyint[], RIGHTARG = tinyint[], PROCEDURE = l2_distance,
+	COMMUTATOR = '<->'
+);
+
+CREATE OPERATOR <#> (
+	LEFTARG = tinyint[], RIGHTARG = tinyint[], PROCEDURE = tinyint_negative_inner_product,
+	COMMUTATOR = '<#>'
+);
+
+CREATE OPERATOR <=> (
+	LEFTARG = tinyint[], RIGHTARG = tinyint[], PROCEDURE = cosine_distance,
+	COMMUTATOR = '<=>'
+);

sql/vector.sql

@@ -290,3 +290,68 @@ CREATE OPERATOR CLASS vector_cosine_ops
 	OPERATOR 1 <=> (vector, vector) FOR ORDER BY float_ops,
 	FUNCTION 1 vector_negative_inner_product(vector, vector),
 	FUNCTION 2 vector_norm(vector);
+
+-- tinyint
+
+CREATE TYPE tinyint;
+
+CREATE FUNCTION tinyint_in(cstring, oid, integer) RETURNS tinyint
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE FUNCTION tinyint_out(tinyint) RETURNS cstring
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE FUNCTION tinyint_recv(internal, oid, integer) RETURNS tinyint
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE FUNCTION tinyint_send(tinyint) RETURNS bytea
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE TYPE tinyint (
+	INPUT     = tinyint_in,
+	OUTPUT    = tinyint_out,
+	RECEIVE   = tinyint_recv,
+	SEND      = tinyint_send,
+	INTERNALLENGTH = 1,
+	PASSEDBYVALUE,
+	ALIGNMENT = char
+);
+
+CREATE FUNCTION integer_to_tinyint(integer, integer, boolean) RETURNS tinyint
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE FUNCTION numeric_to_tinyint(numeric, integer, boolean) RETURNS tinyint
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE CAST (integer AS tinyint)
+	WITH FUNCTION integer_to_tinyint(integer, integer, boolean) AS IMPLICIT;
+
+CREATE CAST (numeric AS tinyint)
+	WITH FUNCTION numeric_to_tinyint(numeric, integer, boolean) AS IMPLICIT;
+
+CREATE FUNCTION l2_distance(tinyint[], tinyint[]) RETURNS float8
+	AS 'MODULE_PATHNAME', 'tinyint_l2_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE FUNCTION inner_product(tinyint[], tinyint[]) RETURNS float8
+	AS 'MODULE_PATHNAME', 'tinyint_inner_product' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE FUNCTION cosine_distance(tinyint[], tinyint[]) RETURNS float8
+	AS 'MODULE_PATHNAME', 'tinyint_cosine_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE FUNCTION tinyint_negative_inner_product(tinyint[], tinyint[]) RETURNS float8
+	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
+
+CREATE OPERATOR <-> (
+	LEFTARG = tinyint[], RIGHTARG = tinyint[], PROCEDURE = l2_distance,
+	COMMUTATOR = '<->'
+);
+
+CREATE OPERATOR <#> (
+	LEFTARG = tinyint[], RIGHTARG = tinyint[], PROCEDURE = tinyint_negative_inner_product,
+	COMMUTATOR = '<#>'
+);
+
+CREATE OPERATOR <=> (
+	LEFTARG = tinyint[], RIGHTARG = tinyint[], PROCEDURE = cosine_distance,
+	COMMUTATOR = '<=>'
+);

src/hnsw.c

@@ -14,7 +14,6 @@
 #endif
 
 int			hnsw_ef_search;
-bool		hnsw_enable_parallel_build;
 static relopt_kind hnsw_relopt_kind;
 
 /*
@@ -40,11 +39,6 @@ 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);
-
-	/* Behind a variable for now since can be slower than building in memory */
-	DefineCustomBoolVariable("hnsw.enable_parallel_build", "Enables or disables building indexes in parallel",
-							 NULL, &hnsw_enable_parallel_build,
-							 false, PGC_USERSET, 0, NULL, NULL, NULL);
 }
 
 /*

src/hnsw.h

@@ -4,7 +4,6 @@
 #include "postgres.h"
 
 #include "access/generic_xlog.h"
-#include "access/parallel.h"
 #include "access/reloptions.h"
 #include "nodes/execnodes.h"
 #include "port.h"				/* for random() */
@@ -15,10 +14,6 @@
 #error "Requires PostgreSQL 11+"
 #endif
 
-#if PG_VERSION_NUM < 120000
-#include "access/relscan.h"
-#endif
-
 #define HNSW_MAX_DIM 2000
 
 /* Support functions */
@@ -64,7 +59,7 @@
 
 #define HNSW_MAX_SIZE (BLCKSZ - MAXALIGN(SizeOfPageHeaderData) - MAXALIGN(sizeof(HnswPageOpaqueData)) - sizeof(ItemIdData))
 
-#define HNSW_ELEMENT_TUPLE_SIZE(size)	MAXALIGN(offsetof(HnswElementTupleData, data) + (size))
+#define HNSW_ELEMENT_TUPLE_SIZE(_dim)	MAXALIGN(offsetof(HnswElementTupleData, vec) + VECTOR_SIZE(_dim))
 #define HNSW_NEIGHBOR_TUPLE_SIZE(level, m)	MAXALIGN(offsetof(HnswNeighborTupleData, indextids) + ((level) + 2) * (m) * sizeof(ItemPointerData))
 
 #define HnswPageGetOpaque(page)	((HnswPageOpaque) PageGetSpecialPointer(page))
@@ -95,7 +90,6 @@
 
 /* Variables */
 extern int	hnsw_ef_search;
-extern bool hnsw_enable_parallel_build;
 
 typedef struct HnswNeighborArray HnswNeighborArray;
 
@@ -104,13 +98,12 @@ typedef struct HnswElementData
 	List	   *heaptids;
 	uint8		level;
 	uint8		deleted;
-	uint32		hash;
 	HnswNeighborArray *neighbors;
 	BlockNumber blkno;
 	OffsetNumber offno;
 	OffsetNumber neighborOffno;
 	BlockNumber neighborPage;
-	Datum		value;
+	Vector	   *vec;
 }			HnswElementData;
 
 typedef HnswElementData * HnswElement;
@@ -119,13 +112,11 @@ typedef struct HnswCandidate
 {
 	HnswElement element;
 	float		distance;
-	bool		closer;
 }			HnswCandidate;
 
 typedef struct HnswNeighborArray
 {
 	int			length;
-	bool		closerSet;
 	HnswCandidate *items;
 }			HnswNeighborArray;
 
@@ -143,49 +134,6 @@ typedef struct HnswOptions
 	int			efConstruction; /* size of dynamic candidate list */
 }			HnswOptions;
 
-typedef struct HnswSpool
-{
-	Relation	heap;
-	Relation	index;
-}			HnswSpool;
-
-typedef struct HnswShared
-{
-	/* Immutable state */
-	Oid			heaprelid;
-	Oid			indexrelid;
-	bool		isconcurrent;
-	int			scantuplesortstates;
-
-	/* Worker progress */
-	ConditionVariable workersdonecv;
-
-	/* Mutex for mutable state */
-	slock_t		mutex;
-
-	/* Mutable state */
-	int			nparticipantsdone;
-	double		reltuples;
-	double		indtuples;
-
-#if PG_VERSION_NUM < 120000
-	ParallelHeapScanDescData heapdesc;	/* must come last */
-#endif
-}			HnswShared;
-
-#if PG_VERSION_NUM >= 120000
-#define ParallelTableScanFromHnswShared(shared) \
-	(ParallelTableScanDesc) ((char *) (shared) + BUFFERALIGN(sizeof(HnswShared)))
-#endif
-
-typedef struct HnswLeader
-{
-	ParallelContext *pcxt;
-	int			nparticipanttuplesorts;
-	HnswShared *hnswshared;
-	Snapshot	snapshot;
-}			HnswLeader;
-
 typedef struct HnswBuildState
 {
 	/* Info */
@@ -213,16 +161,12 @@ typedef struct HnswBuildState
 	HnswElement entryPoint;
 	double		ml;
 	int			maxLevel;
-	long		memoryLeft;
+	double		maxInMemoryElements;
 	bool		flushed;
 	Vector	   *normvec;
 
 	/* Memory */
 	MemoryContext tmpCtx;
-
-	/* Parallel builds */
-	HnswLeader *hnswleader;
-	HnswShared *hnswshared;
 }			HnswBuildState;
 
 typedef struct HnswMetaPageData
@@ -258,7 +202,7 @@ typedef struct HnswElementTupleData
 	ItemPointerData heaptids[HNSW_HEAPTIDS];
 	ItemPointerData neighbortid;
 	uint16		unused2;
-	Vector		data;
+	Vector		vec;
 }			HnswElementTupleData;
 
 typedef HnswElementTupleData * HnswElementTuple;
@@ -304,7 +248,7 @@ typedef struct HnswVacuumState
 	Oid			collation;
 
 	/* Variables */
-	struct tidhash_hash *deleted;
+	HTAB	   *deleted;
 	BufferAccessStrategy bas;
 	HnswNeighborTuple ntup;
 	HnswElementData highestPoint;
@@ -318,8 +262,10 @@ 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);
 HnswElement HnswGetEntryPoint(Relation index);
@@ -330,18 +276,17 @@ 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, bool building);
+void		HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, BlockNumber insertPage, ForkNumber forkNum);
 void		HnswSetNeighborTuple(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, bool building);
+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, bool building);
+void		HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement e, int m, bool checkExisting);
 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		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);
@@ -359,31 +304,4 @@ void		hnswrescan(IndexScanDesc scan, ScanKey keys, int nkeys, ScanKey orderbys,
 bool		hnswgettuple(IndexScanDesc scan, ScanDirection dir);
 void		hnswendscan(IndexScanDesc scan);
 
-/* 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"
-
 #endif

src/hnswbuild.c

@@ -2,16 +2,12 @@
 
 #include <math.h>
 
-#include "access/parallel.h"
-#include "access/xact.h"
 #include "catalog/index.h"
 #include "hnsw.h"
 #include "miscadmin.h"
 #include "lib/pairingheap.h"
 #include "nodes/pg_list.h"
 #include "storage/bufmgr.h"
-#include "tcop/tcopprot.h"
-#include "utils/datum.h"
 #include "utils/memutils.h"
 
 #if PG_VERSION_NUM >= 140000
@@ -39,25 +35,6 @@
 #define UpdateProgress(index, val) ((void)val)
 #endif
 
-#if PG_VERSION_NUM >= 140000
-#include "utils/backend_status.h"
-#include "utils/wait_event.h"
-#endif
-
-#if PG_VERSION_NUM >= 120000
-#include "access/table.h"
-#include "optimizer/optimizer.h"
-#else
-#include "access/heapam.h"
-#include "optimizer/planner.h"
-#include "pgstat.h"
-#endif
-
-#define PARALLEL_KEY_HNSW_SHARED		UINT64CONST(0xA000000000000001)
-#define PARALLEL_KEY_QUERY_TEXT			UINT64CONST(0xA000000000000002)
-
-#define LIST_MAX_LENGTH ((1 << 26) - 1)
-
 /*
  * Create the metapage
  */
@@ -68,11 +45,11 @@ CreateMetaPage(HnswBuildState * buildstate)
 	ForkNumber	forkNum = buildstate->forkNum;
 	Buffer		buf;
 	Page		page;
+	GenericXLogState *state;
 	HnswMetaPage metap;
 
 	buf = HnswNewBuffer(index, forkNum);
-	page = BufferGetPage(buf);
+	HnswInitRegisterPage(index, &buf, &page, &state);
-	HnswInitPage(buf, page);
 
 	/* Set metapage data */
 	metap = HnswPageGetMeta(page);
@@ -88,14 +65,14 @@ CreateMetaPage(HnswBuildState * buildstate)
 	((PageHeader) page)->pd_lower =
 		((char *) metap + sizeof(HnswMetaPageData)) - (char *) page;
 
-	UnlockReleaseBuffer(buf);
+	HnswCommitBuffer(buf, state);
 }
 
 /*
  * Add a new page
  */
 static void
-HnswBuildAppendPage(Relation index, Buffer *buf, Page *page, ForkNumber forkNum)
+HnswBuildAppendPage(Relation index, Buffer *buf, Page *page, GenericXLogState **state, ForkNumber forkNum)
 {
 	/* Add a new page */
 	Buffer		newbuf = HnswNewBuffer(index, forkNum);
@@ -104,6 +81,7 @@ HnswBuildAppendPage(Relation index, Buffer *buf, Page *page, ForkNumber forkNum)
 	HnswPageGetOpaque(*page)->nextblkno = BufferGetBlockNumber(newbuf);
 
 	/* Commit */
+	GenericXLogFinish(*state);
 	UnlockReleaseBuffer(*buf);
 
 	/* Can take a while, so ensure we can interrupt */
@@ -114,7 +92,8 @@ HnswBuildAppendPage(Relation index, Buffer *buf, Page *page, ForkNumber forkNum)
 
 	/* Prepare new page */
 	*buf = newbuf;
-	*page = BufferGetPage(*buf);
+	*state = GenericXLogStart(index);
+	*page = GenericXLogRegisterBuffer(*state, *buf, GENERIC_XLOG_FULL_IMAGE);
 	HnswInitPage(*buf, *page);
 }
 
@@ -126,52 +105,46 @@ CreateElementPages(HnswBuildState * buildstate)
 {
 	Relation	index = buildstate->index;
 	ForkNumber	forkNum = buildstate->forkNum;
-	Size		etupAllocSize;
+	int			dimensions = buildstate->dimensions;
+	Size		etupSize;
 	Size		maxSize;
 	HnswElementTuple etup;
 	HnswNeighborTuple ntup;
 	BlockNumber insertPage;
 	Buffer		buf;
 	Page		page;
+	GenericXLogState *state;
 	ListCell   *lc;
 
 	/* Calculate sizes */
-	etupAllocSize = BLCKSZ;
 	maxSize = HNSW_MAX_SIZE;
+	etupSize = HNSW_ELEMENT_TUPLE_SIZE(dimensions);
 
 	/* Allocate once */
-	etup = palloc0(etupAllocSize);
+	etup = palloc0(etupSize);
 	ntup = palloc0(BLCKSZ);
 
 	/* Prepare first page */
 	buf = HnswNewBuffer(index, forkNum);
-	page = BufferGetPage(buf);
+	state = GenericXLogStart(index);
+	page = GenericXLogRegisterBuffer(state, buf, GENERIC_XLOG_FULL_IMAGE);
 	HnswInitPage(buf, page);
 
 	foreach(lc, buildstate->elements)
 	{
 		HnswElement element = lfirst(lc);
-		Size		etupSize;
 		Size		ntupSize;
 		Size		combinedSize;
 
-		/* Zero memory for each element */
+		HnswSetElementTuple(etup, element);
-		MemSet(etup, 0, etupAllocSize);
 
 		/* Calculate sizes */
-		etupSize = HNSW_ELEMENT_TUPLE_SIZE(VARSIZE_ANY(DatumGetPointer(element->value)));
 		ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(element->level, buildstate->m);
 		combinedSize = etupSize + ntupSize + sizeof(ItemIdData);
 
-		/* Initial size check */
-		if (etupSize > etupAllocSize)
-			elog(ERROR, "index tuple too large");
-
-		HnswSetElementTuple(etup, element);
-
 		/* Keep element and neighbors on the same page if possible */
 		if (PageGetFreeSpace(page) < etupSize || (combinedSize <= maxSize && PageGetFreeSpace(page) < combinedSize))
-			HnswBuildAppendPage(index, &buf, &page, forkNum);
+			HnswBuildAppendPage(index, &buf, &page, &state, forkNum);
 
 		/* Calculate offsets */
 		element->blkno = BufferGetBlockNumber(buf);
@@ -195,7 +168,7 @@ CreateElementPages(HnswBuildState * buildstate)
 
 		/* Add new page if needed */
 		if (PageGetFreeSpace(page) < ntupSize)
-			HnswBuildAppendPage(index, &buf, &page, forkNum);
+			HnswBuildAppendPage(index, &buf, &page, &state, forkNum);
 
 		/* Add placeholder for neighbors */
 		if (PageAddItem(page, (Item) ntup, ntupSize, InvalidOffsetNumber, false, false) != element->neighborOffno)
@@ -205,9 +178,10 @@ CreateElementPages(HnswBuildState * buildstate)
 	insertPage = BufferGetBlockNumber(buf);
 
 	/* Commit */
+	GenericXLogFinish(state);
 	UnlockReleaseBuffer(buf);
 
-	HnswUpdateMetaPage(index, HNSW_UPDATE_ENTRY_ALWAYS, buildstate->entryPoint, insertPage, forkNum, true);
+	HnswUpdateMetaPage(index, HNSW_UPDATE_ENTRY_ALWAYS, buildstate->entryPoint, insertPage, forkNum);
 
 	pfree(etup);
 	pfree(ntup);
@@ -233,6 +207,7 @@ CreateNeighborPages(HnswBuildState * buildstate)
 		HnswElement e = lfirst(lc);
 		Buffer		buf;
 		Page		page;
+		GenericXLogState *state;
 		Size		ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(e->level, m);
 
 		/* Can take a while, so ensure we can interrupt */
@@ -241,7 +216,8 @@ CreateNeighborPages(HnswBuildState * buildstate)
 
 		buf = ReadBufferExtended(index, forkNum, e->neighborPage, RBM_NORMAL, NULL);
 		LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
-		page = BufferGetPage(buf);
+		state = GenericXLogStart(index);
+		page = GenericXLogRegisterBuffer(state, buf, 0);
 
 		HnswSetNeighborTuple(ntup, e, m);
 
@@ -249,6 +225,7 @@ CreateNeighborPages(HnswBuildState * buildstate)
 			elog(ERROR, "failed to add index item to \"%s\"", RelationGetRelationName(index));
 
 		/* Commit */
+		GenericXLogFinish(state);
 		UnlockReleaseBuffer(buf);
 	}
 
@@ -287,14 +264,13 @@ FlushPages(HnswBuildState * buildstate)
  * Insert tuple
  */
 static bool
-InsertTuple(Relation index, Datum *values, HnswElement element, HnswBuildState * buildstate, HnswElement * dup, MemoryContext outerCtx)
+InsertTuple(Relation index, Datum *values, HnswElement element, HnswBuildState * buildstate, HnswElement * dup)
 {
 	FmgrInfo   *procinfo = buildstate->procinfo;
 	Oid			collation = buildstate->collation;
 	HnswElement entryPoint = buildstate->entryPoint;
 	int			efConstruction = buildstate->efConstruction;
 	int			m = buildstate->m;
-	MemoryContext oldCtx;
 
 	/* Detoast once for all calls */
 	Datum		value = PointerGetDatum(PG_DETOAST_DATUM(values[0]));
@@ -307,9 +283,7 @@ InsertTuple(Relation index, Datum *values, HnswElement element, HnswBuildState *
 	}
 
 	/* Copy value to element so accessible outside of memory context */
-	oldCtx = MemoryContextSwitchTo(outerCtx);
+	memcpy(element->vec, DatumGetVector(value), VECTOR_SIZE(buildstate->dimensions));
-	element->value = datumCopy(value, false, -1);
-	MemoryContextSwitchTo(oldCtx);
 
 	/* Insert element in graph */
 	HnswInsertElement(element, entryPoint, NULL, procinfo, collation, m, efConstruction, false);
@@ -339,21 +313,6 @@ InsertTuple(Relation index, Datum *values, HnswElement element, HnswBuildState *
 	return *dup == NULL;
 }
 
-/*
- * Get the memory used by an element
- */
-static long
-HnswElementMemory(HnswElement e, int m)
-{
-	long		elementSize = sizeof(HnswElementData);
-
-	elementSize += sizeof(HnswNeighborArray) * (e->level + 1);
-	elementSize += sizeof(HnswCandidate) * (m * (e->level + 2));
-	elementSize += sizeof(ItemPointerData);
-	elementSize += VARSIZE_ANY(DatumGetPointer(e->value));
-	return elementSize;
-}
-
 /*
  * Callback for table_index_build_scan
  */
@@ -375,11 +334,10 @@ BuildCallback(Relation index, CALLBACK_ITEM_POINTER, Datum *values,
 	if (isnull[0])
 		return;
 
-	if (buildstate->flushed || buildstate->memoryLeft <= 0 || list_length(buildstate->elements) == LIST_MAX_LENGTH)
+	if (buildstate->indtuples >= buildstate->maxInMemoryElements)
 	{
 		if (!buildstate->flushed)
 		{
-			if (buildstate->memoryLeft <= 0)
 			ereport(NOTICE,
 					(errmsg("hnsw graph no longer fits into maintenance_work_mem after " INT64_FORMAT " tuples", (int64) buildstate->indtuples),
 					 errdetail("Building will take significantly more time."),
@@ -390,19 +348,8 @@ BuildCallback(Relation index, CALLBACK_ITEM_POINTER, Datum *values,
 
 		oldCtx = MemoryContextSwitchTo(buildstate->tmpCtx);
 
-		if (HnswInsertTuple(buildstate->index, values, isnull, tid, buildstate->heap, true))
+		if (HnswInsertTuple(buildstate->index, values, isnull, tid, buildstate->heap))
-		{
-			if (buildstate->hnswshared)
-			{
-				HnswShared *hnswshared = buildstate->hnswshared;
-
-				SpinLockAcquire(&hnswshared->mutex);
-				UpdateProgress(PROGRESS_CREATEIDX_TUPLES_DONE, ++hnswshared->indtuples);
-				SpinLockRelease(&hnswshared->mutex);
-			}
-			else
 			UpdateProgress(PROGRESS_CREATEIDX_TUPLES_DONE, ++buildstate->indtuples);
-		}
 
 		/* Reset memory context */
 		MemoryContextSwitchTo(oldCtx);
@@ -413,12 +360,13 @@ BuildCallback(Relation index, CALLBACK_ITEM_POINTER, Datum *values,
 
 	/* Allocate necessary memory outside of memory context */
 	element = HnswInitElement(tid, buildstate->m, buildstate->ml, buildstate->maxLevel);
+	element->vec = palloc(VECTOR_SIZE(buildstate->dimensions));
 
 	/* Use memory context since detoast can allocate */
 	oldCtx = MemoryContextSwitchTo(buildstate->tmpCtx);
 
 	/* Insert tuple */
-	inserted = InsertTuple(index, values, element, buildstate, &dup, oldCtx);
+	inserted = InsertTuple(index, values, element, buildstate, &dup);
 
 	/* Reset memory context */
 	MemoryContextSwitchTo(oldCtx);
@@ -426,21 +374,31 @@ BuildCallback(Relation index, CALLBACK_ITEM_POINTER, Datum *values,
 
 	/* Add outside memory context */
 	if (dup != NULL)
-	{
 		HnswAddHeapTid(dup, tid);
-		buildstate->memoryLeft -= sizeof(ItemPointerData);
-	}
 
 	/* Add to buildstate or free */
 	if (inserted)
-	{
 		buildstate->elements = lappend(buildstate->elements, element);
-		buildstate->memoryLeft -= HnswElementMemory(element, buildstate->m);
-	}
 	else
 		HnswFreeElement(element);
 }
 
+/*
+ * Get the max number of elements that fit into maintenance_work_mem
+ */
+static double
+HnswGetMaxInMemoryElements(int m, double ml, int dimensions)
+{
+	Size		elementSize = sizeof(HnswElementData);
+	double		avgLevel = -log(0.5) * ml;
+
+	elementSize += sizeof(HnswNeighborArray) * (avgLevel + 1);
+	elementSize += sizeof(HnswCandidate) * (m * (avgLevel + 2));
+	elementSize += sizeof(ItemPointerData);
+	elementSize += VECTOR_SIZE(dimensions);
+	return (maintenance_work_mem * 1024L) / elementSize;
+}
+
 /*
  * Initialize the build state
  */
@@ -478,7 +436,7 @@ InitBuildState(HnswBuildState * buildstate, Relation heap, Relation index, Index
 	buildstate->entryPoint = NULL;
 	buildstate->ml = HnswGetMl(buildstate->m);
 	buildstate->maxLevel = HnswGetMaxLevel(buildstate->m);
-	buildstate->memoryLeft = maintenance_work_mem * 1024L;
+	buildstate->maxInMemoryElements = HnswGetMaxInMemoryElements(buildstate->m, buildstate->ml, buildstate->dimensions);
 	buildstate->flushed = false;
 
 	/* Reuse for each tuple */
@@ -487,9 +445,6 @@ InitBuildState(HnswBuildState * buildstate, Relation heap, Relation index, Index
 	buildstate->tmpCtx = AllocSetContextCreate(CurrentMemoryContext,
 											   "Hnsw build temporary context",
 											   ALLOCSET_DEFAULT_SIZES);
-
-	buildstate->hnswleader = NULL;
-	buildstate->hnswshared = NULL;
 }
 
 /*
@@ -502,362 +457,14 @@ FreeBuildState(HnswBuildState * buildstate)
 	MemoryContextDelete(buildstate->tmpCtx);
 }
 
-/*
- * Within leader, wait for end of heap scan
- */
-static double
-ParallelHeapScan(HnswBuildState * buildstate)
-{
-	HnswShared *hnswshared = buildstate->hnswleader->hnswshared;
-	int			nparticipanttuplesorts;
-	double		reltuples;
-
-	nparticipanttuplesorts = buildstate->hnswleader->nparticipanttuplesorts;
-	for (;;)
-	{
-		SpinLockAcquire(&hnswshared->mutex);
-		if (hnswshared->nparticipantsdone == nparticipanttuplesorts)
-		{
-			buildstate->indtuples = hnswshared->indtuples;
-			reltuples = hnswshared->reltuples;
-			SpinLockRelease(&hnswshared->mutex);
-			break;
-		}
-		SpinLockRelease(&hnswshared->mutex);
-
-		ConditionVariableSleep(&hnswshared->workersdonecv,
-							   WAIT_EVENT_PARALLEL_CREATE_INDEX_SCAN);
-	}
-
-	ConditionVariableCancelSleep();
-
-	return reltuples;
-}
-
-/*
- * Perform a worker's portion of a parallel insert
- */
-static void
-HnswParallelScanAndInsert(HnswSpool * hnswspool, HnswShared * hnswshared, bool progress)
-{
-	HnswBuildState buildstate;
-#if PG_VERSION_NUM >= 120000
-	TableScanDesc scan;
-#else
-	HeapScanDesc scan;
-#endif
-	double		reltuples;
-	IndexInfo  *indexInfo;
-
-	/* Join parallel scan */
-	indexInfo = BuildIndexInfo(hnswspool->index);
-	indexInfo->ii_Concurrent = hnswshared->isconcurrent;
-	InitBuildState(&buildstate, hnswspool->heap, hnswspool->index, indexInfo, MAIN_FORKNUM);
-	/* TODO Support in-memory builds */
-	buildstate.memoryLeft = 0;
-	buildstate.flushed = true;
-	buildstate.hnswshared = hnswshared;
-#if PG_VERSION_NUM >= 120000
-	scan = table_beginscan_parallel(hnswspool->heap,
-									ParallelTableScanFromHnswShared(hnswshared));
-	reltuples = table_index_build_scan(hnswspool->heap, hnswspool->index, indexInfo,
-									   true, progress, BuildCallback,
-									   (void *) &buildstate, scan);
-#else
-	scan = heap_beginscan_parallel(hnswspool->heap, &hnswshared->heapdesc);
-	reltuples = IndexBuildHeapScan(hnswspool->heap, hnswspool->index, indexInfo,
-								   true, BuildCallback,
-								   (void *) &buildstate, scan);
-#endif
-
-	/* Record statistics */
-	SpinLockAcquire(&hnswshared->mutex);
-	hnswshared->nparticipantsdone++;
-	hnswshared->reltuples += reltuples;
-	SpinLockRelease(&hnswshared->mutex);
-
-	/* Log statistics */
-	if (progress)
-		ereport(DEBUG1, (errmsg("leader processed " INT64_FORMAT " tuples", (int64) reltuples)));
-	else
-		ereport(DEBUG1, (errmsg("worker processed " INT64_FORMAT " tuples", (int64) reltuples)));
-
-	/* Notify leader */
-	ConditionVariableSignal(&hnswshared->workersdonecv);
-
-	FreeBuildState(&buildstate);
-}
-
-/*
- * Perform work within a launched parallel process
- */
-void
-HnswParallelBuildMain(dsm_segment *seg, shm_toc *toc)
-{
-	char	   *sharedquery;
-	HnswSpool  *hnswspool;
-	HnswShared *hnswshared;
-	Relation	heapRel;
-	Relation	indexRel;
-	LOCKMODE	heapLockmode;
-	LOCKMODE	indexLockmode;
-
-	/* Set debug_query_string for individual workers first */
-	sharedquery = shm_toc_lookup(toc, PARALLEL_KEY_QUERY_TEXT, true);
-	debug_query_string = sharedquery;
-
-	/* Report the query string from leader */
-	pgstat_report_activity(STATE_RUNNING, debug_query_string);
-
-	/* Look up shared state */
-	hnswshared = shm_toc_lookup(toc, PARALLEL_KEY_HNSW_SHARED, false);
-
-	/* Open relations using lock modes known to be obtained by index.c */
-	if (!hnswshared->isconcurrent)
-	{
-		heapLockmode = ShareLock;
-		indexLockmode = AccessExclusiveLock;
-	}
-	else
-	{
-		heapLockmode = ShareUpdateExclusiveLock;
-		indexLockmode = RowExclusiveLock;
-	}
-
-	/* Open relations within worker */
-#if PG_VERSION_NUM >= 120000
-	heapRel = table_open(hnswshared->heaprelid, heapLockmode);
-#else
-	heapRel = heap_open(hnswshared->heaprelid, heapLockmode);
-#endif
-	indexRel = index_open(hnswshared->indexrelid, indexLockmode);
-
-	/* Initialize worker's own spool */
-	hnswspool = (HnswSpool *) palloc0(sizeof(HnswSpool));
-	hnswspool->heap = heapRel;
-	hnswspool->index = indexRel;
-
-	/* Perform inserts */
-	HnswParallelScanAndInsert(hnswspool, hnswshared, false);
-
-	/* Close relations within worker */
-	index_close(indexRel, indexLockmode);
-#if PG_VERSION_NUM >= 120000
-	table_close(heapRel, heapLockmode);
-#else
-	heap_close(heapRel, heapLockmode);
-#endif
-}
-
-/*
- * End parallel build
- */
-static void
-HnswEndParallel(HnswLeader * hnswleader)
-{
-	/* Shutdown worker processes */
-	WaitForParallelWorkersToFinish(hnswleader->pcxt);
-
-	/* Free last reference to MVCC snapshot, if one was used */
-	if (IsMVCCSnapshot(hnswleader->snapshot))
-		UnregisterSnapshot(hnswleader->snapshot);
-	DestroyParallelContext(hnswleader->pcxt);
-	ExitParallelMode();
-}
-
-/*
- * Return size of shared memory required for parallel index build
- */
-static Size
-ParallelEstimateShared(Relation heap, Snapshot snapshot)
-{
-#if PG_VERSION_NUM >= 120000
-	return add_size(BUFFERALIGN(sizeof(HnswShared)), table_parallelscan_estimate(heap, snapshot));
-#else
-	if (!IsMVCCSnapshot(snapshot))
-	{
-		Assert(snapshot == SnapshotAny);
-		return sizeof(HnswShared);
-	}
-
-	return add_size(offsetof(HnswShared, heapdesc) +
-					offsetof(ParallelHeapScanDescData, phs_snapshot_data),
-					EstimateSnapshotSpace(snapshot));
-#endif
-}
-
-/*
- * Within leader, participate as a parallel worker
- */
-static void
-HnswLeaderParticipateAsWorker(HnswBuildState * buildstate)
-{
-	HnswLeader *hnswleader = buildstate->hnswleader;
-	HnswSpool  *leaderworker;
-
-	/* Allocate memory and initialize private spool */
-	leaderworker = (HnswSpool *) palloc0(sizeof(HnswSpool));
-	leaderworker->heap = buildstate->heap;
-	leaderworker->index = buildstate->index;
-
-	/* Perform work common to all participants */
-	HnswParallelScanAndInsert(leaderworker, hnswleader->hnswshared, true);
-}
-
-/*
- * Begin parallel build
- */
-static void
-HnswBeginParallel(HnswBuildState * buildstate, bool isconcurrent, int request)
-{
-	ParallelContext *pcxt;
-	int			scantuplesortstates;
-	Snapshot	snapshot;
-	Size		esthnswshared;
-	HnswShared *hnswshared;
-	HnswLeader *hnswleader = (HnswLeader *) palloc0(sizeof(HnswLeader));
-	bool		leaderparticipates = true;
-	int			querylen;
-
-#ifdef DISABLE_LEADER_PARTICIPATION
-	leaderparticipates = false;
-#endif
-
-	/* Enter parallel mode and create context */
-	EnterParallelMode();
-	Assert(request > 0);
-#if PG_VERSION_NUM >= 120000
-	pcxt = CreateParallelContext("vector", "HnswParallelBuildMain", request);
-#else
-	pcxt = CreateParallelContext("vector", "HnswParallelBuildMain", request, true);
-#endif
-
-	scantuplesortstates = leaderparticipates ? request + 1 : request;
-
-	/* Get snapshot for table scan */
-	if (!isconcurrent)
-		snapshot = SnapshotAny;
-	else
-		snapshot = RegisterSnapshot(GetTransactionSnapshot());
-
-	/* Estimate size of workspaces */
-	esthnswshared = ParallelEstimateShared(buildstate->heap, snapshot);
-	shm_toc_estimate_chunk(&pcxt->estimator, esthnswshared);
-	shm_toc_estimate_keys(&pcxt->estimator, 1);
-
-	/* Finally, estimate PARALLEL_KEY_QUERY_TEXT space */
-	if (debug_query_string)
-	{
-		querylen = strlen(debug_query_string);
-		shm_toc_estimate_chunk(&pcxt->estimator, querylen + 1);
-		shm_toc_estimate_keys(&pcxt->estimator, 1);
-	}
-	else
-		querylen = 0;			/* keep compiler quiet */
-
-	/* Everyone's had a chance to ask for space, so now create the DSM */
-	InitializeParallelDSM(pcxt);
-
-	/* If no DSM segment was available, back out (do serial build) */
-	if (pcxt->seg == NULL)
-	{
-		if (IsMVCCSnapshot(snapshot))
-			UnregisterSnapshot(snapshot);
-		DestroyParallelContext(pcxt);
-		ExitParallelMode();
-		return;
-	}
-
-	/* Store shared build state, for which we reserved space */
-	hnswshared = (HnswShared *) shm_toc_allocate(pcxt->toc, esthnswshared);
-	/* Initialize immutable state */
-	hnswshared->heaprelid = RelationGetRelid(buildstate->heap);
-	hnswshared->indexrelid = RelationGetRelid(buildstate->index);
-	hnswshared->isconcurrent = isconcurrent;
-	hnswshared->scantuplesortstates = scantuplesortstates;
-	ConditionVariableInit(&hnswshared->workersdonecv);
-	SpinLockInit(&hnswshared->mutex);
-	/* Initialize mutable state */
-	hnswshared->nparticipantsdone = 0;
-	hnswshared->reltuples = 0;
-	hnswshared->indtuples = 0;
-#if PG_VERSION_NUM >= 120000
-	table_parallelscan_initialize(buildstate->heap,
-								  ParallelTableScanFromHnswShared(hnswshared),
-								  snapshot);
-#else
-	heap_parallelscan_initialize(&hnswshared->heapdesc, buildstate->heap, snapshot);
-#endif
-
-	shm_toc_insert(pcxt->toc, PARALLEL_KEY_HNSW_SHARED, hnswshared);
-
-	/* Store query string for workers */
-	if (debug_query_string)
-	{
-		char	   *sharedquery;
-
-		sharedquery = (char *) shm_toc_allocate(pcxt->toc, querylen + 1);
-		memcpy(sharedquery, debug_query_string, querylen + 1);
-		shm_toc_insert(pcxt->toc, PARALLEL_KEY_QUERY_TEXT, sharedquery);
-	}
-
-	/* Launch workers, saving status for leader/caller */
-	LaunchParallelWorkers(pcxt);
-	hnswleader->pcxt = pcxt;
-	hnswleader->nparticipanttuplesorts = pcxt->nworkers_launched;
-	if (leaderparticipates)
-		hnswleader->nparticipanttuplesorts++;
-	hnswleader->hnswshared = hnswshared;
-	hnswleader->snapshot = snapshot;
-
-	/* If no workers were successfully launched, back out (do serial build) */
-	if (pcxt->nworkers_launched == 0)
-	{
-		HnswEndParallel(hnswleader);
-		return;
-	}
-
-	/* Log participants */
-	ereport(DEBUG1, (errmsg("using %d parallel workers", pcxt->nworkers_launched)));
-
-	/* Save leader state now that it's clear build will be parallel */
-	buildstate->hnswleader = hnswleader;
-
-	/* Join heap scan ourselves */
-	if (leaderparticipates)
-		HnswLeaderParticipateAsWorker(buildstate);
-
-	/* Wait for all launched workers */
-	WaitForParallelWorkersToAttach(pcxt);
-}
-
 /*
  * Build graph
  */
 static void
 BuildGraph(HnswBuildState * buildstate, ForkNumber forkNum)
 {
-	int			parallel_workers = 0;
-
 	UpdateProgress(PROGRESS_CREATEIDX_SUBPHASE, PROGRESS_HNSW_PHASE_LOAD);
 
-	/* Calculate parallel workers */
-	if (hnsw_enable_parallel_build)
-		parallel_workers = plan_create_index_workers(RelationGetRelid(buildstate->heap), RelationGetRelid(buildstate->index));
-
-	/* Attempt to launch parallel worker scan when required */
-	if (parallel_workers > 0)
-	{
-		/* TODO Support in-memory builds */
-		FlushPages(buildstate);
-		HnswBeginParallel(buildstate, buildstate->indexInfo->ii_Concurrent, parallel_workers);
-	}
-
-	/* Add tuples to sort */
-	if (buildstate->hnswleader)
-		buildstate->reltuples = ParallelHeapScan(buildstate);
-	else
-	{
 #if PG_VERSION_NUM >= 120000
 	buildstate->reltuples = table_index_build_scan(buildstate->heap, buildstate->index, buildstate->indexInfo,
 												   true, true, BuildCallback, (void *) buildstate, NULL);
@@ -867,27 +474,6 @@ BuildGraph(HnswBuildState * buildstate, ForkNumber forkNum)
 #endif
 }
 
-	/* End parallel build */
-	if (buildstate->hnswleader)
-		HnswEndParallel(buildstate->hnswleader);
-}
-
-#if PG_VERSION_NUM < 110008
-void
-log_newpage_range(Relation rel, ForkNumber forkNum, BlockNumber startblk, BlockNumber endblk, bool page_std)
-{
-	for (BlockNumber blkno = startblk; blkno < endblk; blkno++)
-	{
-		Buffer		buf = ReadBufferExtended(rel, forkNum, blkno, RBM_NORMAL, NULL);
-
-		LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
-		MarkBufferDirty(buf);
-		log_newpage_buffer(buf, page_std);
-		UnlockReleaseBuffer(buf);
-	}
-}
-#endif
-
 /*
  * Build the index
  */
@@ -903,9 +489,6 @@ BuildIndex(Relation heap, Relation index, IndexInfo *indexInfo,
 	if (!buildstate->flushed)
 		FlushPages(buildstate);
 
-	if (RelationNeedsWAL(index))
-		log_newpage_range(index, forkNum, 0, RelationGetNumberOfBlocks(index), true);
-
 	FreeBuildState(buildstate);
 }
 

src/hnswinsert.c

@@ -92,7 +92,7 @@ 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, bool building)
+HnswInsertAppendPage(Relation index, Buffer *nbuf, Page *npage, GenericXLogState *state, Page page)
 {
 	/* Add a new page */
 	LockRelationForExtension(index, ExclusiveLock);
@@ -100,11 +100,7 @@ HnswInsertAppendPage(Relation index, Buffer *nbuf, Page *npage, GenericXLogState
 	UnlockRelationForExtension(index, ExclusiveLock);
 
 	/* Init new page */
-	if (building)
-		*npage = BufferGetPage(*nbuf);
-	else
 	*npage = GenericXLogRegisterBuffer(state, *nbuf, GENERIC_XLOG_FULL_IMAGE);
-
 	HnswInitPage(*nbuf, *npage);
 
 	/* Update previous buffer */
@@ -115,7 +111,7 @@ HnswInsertAppendPage(Relation index, Buffer *nbuf, Page *npage, GenericXLogState
  * Add to element and neighbor pages
  */
 static void
-WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPage, BlockNumber *updatedInsertPage, bool building)
+WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPage, BlockNumber *updatedInsertPage)
 {
 	Buffer		buf;
 	Page		page;
@@ -127,6 +123,7 @@ 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;
@@ -135,7 +132,7 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
 	BlockNumber newInsertPage = InvalidBlockNumber;
 
 	/* Calculate sizes */
-	etupSize = HNSW_ELEMENT_TUPLE_SIZE(VARSIZE_ANY(DatumGetPointer(e->value)));
+	etupSize = HNSW_ELEMENT_TUPLE_SIZE(dimensions);
 	ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(e->level, m);
 	combinedSize = etupSize + ntupSize + sizeof(ItemIdData);
 	maxSize = HNSW_MAX_SIZE;
@@ -155,16 +152,8 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
 		buf = ReadBuffer(index, currentPage);
 		LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
 
-		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)
@@ -184,12 +173,7 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
 		if (HnswFreeOffset(index, buf, page, e, ntupSize, &nbuf, &npage, &freeOffno, &freeNeighborOffno, &newInsertPage))
 		{
 			if (nbuf != buf)
-			{
-				if (building)
-					npage = BufferGetPage(nbuf);
-				else
 				npage = GenericXLogRegisterBuffer(state, nbuf, 0);
-			}
 
 			break;
 		}
@@ -198,7 +182,7 @@ 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, building);
+			HnswInsertAppendPage(index, &nbuf, &npage, state, page);
 			break;
 		}
 
@@ -207,7 +191,6 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
 		if (BlockNumberIsValid(currentPage))
 		{
 			/* Move to next page */
-			if (!building)
 			GenericXLogAbort(state);
 			UnlockReleaseBuffer(buf);
 		}
@@ -216,31 +199,22 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
 			Buffer		newbuf;
 			Page		newpage;
 
-			HnswInsertAppendPage(index, &newbuf, &newpage, state, page, building);
+			HnswInsertAppendPage(index, &newbuf, &newpage, state, page);
 
 			/* Commit */
-			if (!building)
 			GenericXLogFinish(state);
 
 			/* Unlock previous buffer */
 			UnlockReleaseBuffer(buf);
 
 			/* Prepare new buffer */
-			buf = newbuf;
-			if (building)
-			{
-				state = NULL;
-				page = BufferGetPage(buf);
-			}
-			else
-			{
 			state = GenericXLogStart(index);
+			buf = newbuf;
 			page = GenericXLogRegisterBuffer(state, buf, 0);
-			}
 
 			/* Create new page for neighbors if needed */
 			if (PageGetFreeSpace(page) < combinedSize)
-				HnswInsertAppendPage(index, &nbuf, &npage, state, page, building);
+				HnswInsertAppendPage(index, &nbuf, &npage, state, page);
 			else
 			{
 				nbuf = buf;
@@ -294,7 +268,6 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
 	}
 
 	/* Commit */
-	if (!building)
 	GenericXLogFinish(state);
 	UnlockReleaseBuffer(buf);
 	if (nbuf != buf)
@@ -329,7 +302,7 @@ ConnectionExists(HnswElement e, HnswNeighborTuple ntup, int startIdx, int lm)
  * Update neighbors
  */
 void
-HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement e, int m, bool checkExisting, bool building)
+HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement e, int m, bool checkExisting)
 {
 	for (int lc = e->level; lc >= 0; lc--)
 	{
@@ -370,16 +343,8 @@ HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswE
 			/* Register page */
 			buf = ReadBuffer(index, hc->element->neighborPage);
 			LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
-			if (building)
-			{
-				state = NULL;
-				page = BufferGetPage(buf);
-			}
-			else
-			{
 			state = GenericXLogStart(index);
 			page = GenericXLogRegisterBuffer(state, buf, 0);
-			}
 
 			/* Get tuple */
 			itemid = PageGetItemId(page, offno);
@@ -421,10 +386,9 @@ HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswE
 					elog(ERROR, "failed to add index item to \"%s\"", RelationGetRelationName(index));
 
 				/* Commit */
-				if (!building)
 				GenericXLogFinish(state);
 			}
-			else if (!building)
+			else
 				GenericXLogAbort(state);
 
 			UnlockReleaseBuffer(buf);
@@ -436,34 +400,23 @@ HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswE
  * Add a heap TID to an existing element
  */
 static bool
-HnswAddDuplicate(Relation index, HnswElement element, HnswElement dup, bool building)
+HnswAddDuplicate(Relation index, HnswElement element, HnswElement dup)
 {
 	Buffer		buf;
 	Page		page;
 	GenericXLogState *state;
-	ItemId		itemid;
+	Size		etupSize = HNSW_ELEMENT_TUPLE_SIZE(dup->vec->dim);
 	HnswElementTuple etup;
-	Size		etupSize;
 	int			i;
 
 	/* Read page */
 	buf = ReadBuffer(index, dup->blkno);
 	LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
-	if (building)
-	{
-		state = NULL;
-		page = BufferGetPage(buf);
-	}
-	else
-	{
 	state = GenericXLogStart(index);
 	page = GenericXLogRegisterBuffer(state, buf, 0);
-	}
 
 	/* Find space */
-	itemid = PageGetItemId(page, dup->offno);
+	etup = (HnswElementTuple) PageGetItem(page, PageGetItemId(page, dup->offno));
-	etup = (HnswElementTuple) PageGetItem(page, itemid);
-	etupSize = ItemIdGetLength(itemid);
 	for (i = 0; i < HNSW_HEAPTIDS; i++)
 	{
 		if (!ItemPointerIsValid(&etup->heaptids[i]))
@@ -473,7 +426,6 @@ HnswAddDuplicate(Relation index, HnswElement element, HnswElement dup, bool buil
 	/* Either being deleted or we lost our chance to another backend */
 	if (i == 0 || i == HNSW_HEAPTIDS)
 	{
-		if (!building)
 		GenericXLogAbort(state);
 		UnlockReleaseBuffer(buf);
 		return false;
@@ -487,7 +439,6 @@ HnswAddDuplicate(Relation index, HnswElement element, HnswElement dup, bool buil
 		elog(ERROR, "failed to add index item to \"%s\"", RelationGetRelationName(index));
 
 	/* Commit */
-	if (!building)
 	GenericXLogFinish(state);
 	UnlockReleaseBuffer(buf);
 
@@ -498,37 +449,37 @@ HnswAddDuplicate(Relation index, HnswElement element, HnswElement dup, bool buil
  * Write changes to disk
  */
 static void
-WriteElement(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement element, int m, int efConstruction, HnswElement dup, HnswElement entryPoint, bool building)
+WriteElement(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement element, int m, int efConstruction, HnswElement dup, HnswElement entryPoint)
 {
 	BlockNumber newInsertPage = InvalidBlockNumber;
 
 	/* Try to add to existing page */
 	if (dup != NULL)
 	{
-		if (HnswAddDuplicate(index, element, dup, building))
+		if (HnswAddDuplicate(index, element, dup))
 			return;
 	}
 
 	/* Write element and neighbor tuples */
-	WriteNewElementPages(index, element, m, GetInsertPage(index), &newInsertPage, building);
+	WriteNewElementPages(index, element, m, GetInsertPage(index), &newInsertPage);
 
 	/* Update insert page if needed */
 	if (BlockNumberIsValid(newInsertPage))
-		HnswUpdateMetaPage(index, 0, NULL, newInsertPage, MAIN_FORKNUM, building);
+		HnswUpdateMetaPage(index, 0, NULL, newInsertPage, MAIN_FORKNUM);
 
 	/* Update neighbors */
-	HnswUpdateNeighborPages(index, procinfo, collation, element, m, false, building);
+	HnswUpdateNeighborPages(index, procinfo, collation, element, m, false);
 
 	/* Update metapage if needed */
 	if (entryPoint == NULL || element->level > entryPoint->level)
-		HnswUpdateMetaPage(index, HNSW_UPDATE_ENTRY_GREATER, element, InvalidBlockNumber, MAIN_FORKNUM, building);
+		HnswUpdateMetaPage(index, HNSW_UPDATE_ENTRY_GREATER, element, InvalidBlockNumber, MAIN_FORKNUM);
 }
 
 /*
  * Insert a tuple into the index
  */
 bool
-HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid, Relation heapRel, bool building)
+HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid, Relation heapRel)
 {
 	Datum		value;
 	FmgrInfo   *normprocinfo;
@@ -564,7 +515,7 @@ HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_ti
 
 	/* Create an element */
 	element = HnswInitElement(heap_tid, m, HnswGetMl(m), HnswGetMaxLevel(m));
-	element->value = value;
+	element->vec = DatumGetVector(value);
 
 	/* Prevent concurrent inserts when likely updating entry point */
 	if (entryPoint == NULL || element->level > entryPoint->level)
@@ -587,7 +538,7 @@ HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_ti
 	dup = HnswFindDuplicate(element);
 
 	/* Write to disk */
-	WriteElement(index, procinfo, collation, element, m, efConstruction, dup, entryPoint, building);
+	WriteElement(index, procinfo, collation, element, m, efConstruction, dup, entryPoint);
 
 	/* Release lock */
 	UnlockPage(index, HNSW_UPDATE_LOCK, lockmode);
@@ -621,7 +572,7 @@ hnswinsert(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid,
 	oldCtx = MemoryContextSwitchTo(insertCtx);
 
 	/* Insert tuple */
-	HnswInsertTuple(index, values, isnull, heap_tid, heap, false);
+	HnswInsertTuple(index, values, isnull, heap_tid, heap);
 
 	/* Delete memory context */
 	MemoryContextSwitchTo(oldCtx);

src/hnswutils.c

@@ -4,92 +4,8 @@
 
 #include "hnsw.h"
 #include "storage/bufmgr.h"
-#include "utils/datum.h"
 #include "vector.h"
 
-#if PG_VERSION_NUM >= 130000
-#include "common/hashfn.h"
-#else
-#include "utils/hashutils.h"
-#endif
-
-#if PG_VERSION_NUM < 170000
-static inline uint64
-murmurhash64(uint64 data)
-{
-	uint64		h = data;
-
-	h ^= h >> 33;
-	h *= 0xff51afd7ed558ccd;
-	h ^= h >> 33;
-	h *= 0xc4ceb9fe1a85ec53;
-	h ^= h >> 33;
-
-	return h;
-}
-#endif
-
-/* TID hash table */
-static uint32
-hash_tid(ItemPointerData tid)
-{
-	union
-	{
-		uint64		i;
-		ItemPointerData tid;
-	}			x;
-
-	/* Initialize unused bytes */
-	x.i = 0;
-	x.tid = tid;
-
-	return murmurhash64(x.i);
-}
-
-#define SH_PREFIX		tidhash
-#define SH_ELEMENT_TYPE	TidHashEntry
-#define SH_KEY_TYPE		ItemPointerData
-#define	SH_KEY			tid
-#define SH_HASH_KEY(tb, key)	hash_tid(key)
-#define SH_EQUAL(tb, a, b)		ItemPointerEquals(&a, &b)
-#define	SH_SCOPE		extern
-#define SH_DEFINE
-#include "lib/simplehash.h"
-
-/* Needed to include simplehash.h twice */
-#if PG_VERSION_NUM < 120000
-#undef SH_EQUAL
-#define sh_log2 pointerhash_sh_log2
-#define sh_pow2 pointerhash_sh_pow2
-#endif
-
-/* Pointer hash table */
-static uint32
-hash_pointer(uintptr_t ptr)
-{
-#if SIZEOF_VOID_P == 8
-	return murmurhash64((uint64) ptr);
-#else
-	return murmurhash32((uint32) ptr);
-#endif
-}
-
-#define SH_PREFIX		pointerhash
-#define SH_ELEMENT_TYPE	PointerHashEntry
-#define SH_KEY_TYPE		uintptr_t
-#define	SH_KEY			ptr
-#define SH_HASH_KEY(tb, key)	hash_pointer(key)
-#define SH_EQUAL(tb, a, b)		(a == b)
-#define	SH_SCOPE		extern
-#define SH_DEFINE
-#include "lib/simplehash.h"
-
-typedef union
-{
-	pointerhash_hash *pointers;
-	tidhash_hash *tids;
-}			visited_hash;
-
 /*
  * Get the max number of connections in an upper layer for each element in the index
  */
@@ -184,6 +100,27 @@ HnswInitPage(Buffer buf, Page page)
 	HnswPageGetOpaque(page)->page_id = HNSW_PAGE_ID;
 }
 
+/*
+ * Init and register page
+ */
+void
+HnswInitRegisterPage(Relation index, Buffer *buf, Page *page, GenericXLogState **state)
+{
+	*state = GenericXLogStart(index);
+	*page = GenericXLogRegisterBuffer(*state, *buf, GENERIC_XLOG_FULL_IMAGE);
+	HnswInitPage(*buf, *page);
+}
+
+/*
+ * Commit buffer
+ */
+void
+HnswCommitBuffer(Buffer buf, GenericXLogState *state)
+{
+	GenericXLogFinish(state);
+	UnlockReleaseBuffer(buf);
+}
+
 /*
  * Allocate neighbors
  */
@@ -202,7 +139,6 @@ HnswInitNeighbors(HnswElement element, int m)
 		a = &element->neighbors[lc];
 		a->length = 0;
 		a->items = palloc(sizeof(HnswCandidate) * lm);
-		a->closerSet = false;
 	}
 }
 
@@ -239,8 +175,6 @@ HnswInitElement(ItemPointer heaptid, int m, double ml, int maxLevel)
 
 	HnswInitNeighbors(element, m);
 
-	element->value = PointerGetDatum(NULL);
-
 	return element;
 }
 
@@ -252,8 +186,7 @@ HnswFreeElement(HnswElement element)
 {
 	HnswFreeNeighbors(element);
 	list_free_deep(element->heaptids);
-	if (DatumGetPointer(element->value))
+	pfree(element->vec);
-		pfree(DatumGetPointer(element->value));
 	pfree(element);
 }
 
@@ -280,7 +213,7 @@ HnswInitElementFromBlock(BlockNumber blkno, OffsetNumber offno)
 	element->blkno = blkno;
 	element->offno = offno;
 	element->neighbors = NULL;
-	element->value = PointerGetDatum(NULL);
+	element->vec = NULL;
 	return element;
 }
 
@@ -358,7 +291,7 @@ HnswUpdateMetaPageInfo(Page page, int updateEntry, HnswElement entryPoint, Block
  * Update the metapage
  */
 void
-HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, BlockNumber insertPage, ForkNumber forkNum, bool building)
+HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, BlockNumber insertPage, ForkNumber forkNum)
 {
 	Buffer		buf;
 	Page		page;
@@ -366,22 +299,12 @@ HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, Bloc
 
 	buf = ReadBufferExtended(index, forkNum, HNSW_METAPAGE_BLKNO, RBM_NORMAL, NULL);
 	LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
-	if (building)
-	{
-		state = NULL;
-		page = BufferGetPage(buf);
-	}
-	else
-	{
 	state = GenericXLogStart(index);
 	page = GenericXLogRegisterBuffer(state, buf, 0);
-	}
 
 	HnswUpdateMetaPageInfo(page, updateEntry, entryPoint, insertPage);
 
-	if (!building)
+	HnswCommitBuffer(buf, state);
-		GenericXLogFinish(state);
-	UnlockReleaseBuffer(buf);
 }
 
 /*
@@ -400,7 +323,7 @@ HnswSetElementTuple(HnswElementTuple etup, HnswElement element)
 		else
 			ItemPointerSetInvalid(&etup->heaptids[i]);
 	}
-	memcpy(&etup->data, DatumGetPointer(element->value), VARSIZE_ANY(DatumGetPointer(element->value)));
+	memcpy(&etup->vec, element->vec, VECTOR_SIZE(element->vec->dim));
 }
 
 /*
@@ -522,7 +445,10 @@ HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHe
 	}
 
 	if (loadVec)
-		element->value = datumCopy(PointerGetDatum(&etup->data), false, -1);
+	{
+		element->vec = palloc(VECTOR_SIZE(etup->vec.dim));
+		memcpy(element->vec, &etup->vec, VECTOR_SIZE(etup->vec.dim));
+	}
 }
 
 /*
@@ -549,7 +475,7 @@ HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation index,
 
 	/* Calculate distance */
 	if (distance != NULL)
-		*distance = (float) DatumGetFloat8(FunctionCall2Coll(procinfo, collation, *q, PointerGetDatum(&etup->data)));
+		*distance = (float) DatumGetFloat8(FunctionCall2Coll(procinfo, collation, *q, PointerGetDatum(&etup->vec)));
 
 	UnlockReleaseBuffer(buf);
 }
@@ -560,7 +486,7 @@ HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation index,
 static float
 GetCandidateDistance(HnswCandidate * hc, Datum q, FmgrInfo *procinfo, Oid collation)
 {
-	return DatumGetFloat8(FunctionCall2Coll(procinfo, collation, q, hc->element->value));
+	return DatumGetFloat8(FunctionCall2Coll(procinfo, collation, q, PointerGetDatum(hc->element->vec)));
 }
 
 /*
@@ -625,22 +551,16 @@ CreatePairingHeapNode(HnswCandidate * c)
  * Add to visited
  */
 static inline void
-AddToVisited(visited_hash v, HnswCandidate * hc, Relation index, bool *found)
+AddToVisited(HTAB *v, HnswCandidate * hc, Relation index, bool *found)
 {
 	if (index == NULL)
-	{
+		hash_search(v, &hc->element, HASH_ENTER, found);
-#if PG_VERSION_NUM >= 130000
-		pointerhash_insert_hash(v.pointers, (uintptr_t) hc->element, hc->element->hash, found);
-#else
-		pointerhash_insert(v.pointers, (uintptr_t) hc->element, found);
-#endif
-	}
 	else
 	{
 		ItemPointerData indextid;
 
 		ItemPointerSet(&indextid, hc->element->blkno, hc->element->offno);
-		tidhash_insert(v.tids, indextid, found);
+		hash_search(v, &indextid, HASH_ENTER, found);
 	}
 }
 
@@ -656,21 +576,30 @@ HnswSearchLayer(Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *pro
 	pairingheap *C = pairingheap_allocate(CompareNearestCandidates, NULL);
 	pairingheap *W = pairingheap_allocate(CompareFurthestCandidates, NULL);
 	int			wlen = 0;
-	visited_hash v;
+	HASHCTL		hash_ctl;
+	HTAB	   *v;
 
 	/* Create hash table */
 	if (index == NULL)
-		v.pointers = pointerhash_create(CurrentMemoryContext, ef * m * 2, NULL);
+	{
+		hash_ctl.keysize = sizeof(HnswElement *);
+		hash_ctl.entrysize = sizeof(HnswElement *);
+	}
 	else
-		v.tids = tidhash_create(CurrentMemoryContext, ef * m * 2, NULL);
+	{
+		hash_ctl.keysize = sizeof(ItemPointerData);
+		hash_ctl.entrysize = sizeof(ItemPointerData);
+	}
+
+	hash_ctl.hcxt = CurrentMemoryContext;
+	v = hash_create("hnsw visited", 256, &hash_ctl, HASH_ELEM | HASH_BLOBS | HASH_CONTEXT);
 
 	/* Add entry points to v, C, and W */
 	foreach(lc2, ep)
 	{
 		HnswCandidate *hc = (HnswCandidate *) lfirst(lc2);
-		bool		found;
 
-		AddToVisited(v, hc, index, &found);
+		AddToVisited(v, hc, index, NULL);
 
 		pairingheap_add(C, &(CreatePairingHeapNode(hc)->ph_node));
 		pairingheap_add(W, &(CreatePairingHeapNode(hc)->ph_node));
@@ -763,34 +692,6 @@ HnswSearchLayer(Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *pro
 	return w;
 }
 
-/*
- * Compare candidate distances
- */
-static int
-#if PG_VERSION_NUM >= 130000
-CompareCandidateDistances(const ListCell *a, const ListCell *b)
-#else
-CompareCandidateDistances(const void *a, const void *b)
-#endif
-{
-	HnswCandidate *hca = lfirst((ListCell *) a);
-	HnswCandidate *hcb = lfirst((ListCell *) b);
-
-	if (hca->distance < hcb->distance)
-		return 1;
-
-	if (hca->distance > hcb->distance)
-		return -1;
-
-	if (hca->element < hcb->element)
-		return 1;
-
-	if (hca->element > hcb->element)
-		return -1;
-
-	return 0;
-}
-
 /*
  * Calculate the distance between elements
  */
@@ -820,7 +721,7 @@ HnswGetDistance(HnswElement a, HnswElement b, int lc, FmgrInfo *procinfo, Oid co
 		}
 	}
 
-	return DatumGetFloat8(FunctionCall2Coll(procinfo, collation, a->value, b->value));
+	return DatumGetFloat8(FunctionCall2Coll(procinfo, collation, PointerGetDatum(a->vec), PointerGetDatum(b->vec)));
 }
 
 /*
@@ -847,77 +748,33 @@ CheckElementCloser(HnswCandidate * e, List *r, int lc, FmgrInfo *procinfo, Oid c
  * Algorithm 4 from paper
  */
 static List *
-SelectNeighbors(List *c, int m, int lc, FmgrInfo *procinfo, Oid collation, HnswElement e2, HnswCandidate * newCandidate, HnswCandidate * *pruned, bool sortCandidates)
+SelectNeighbors(List *c, int m, int lc, FmgrInfo *procinfo, Oid collation, HnswCandidate * *pruned)
 {
 	List	   *r = NIL;
 	List	   *w = list_copy(c);
 	pairingheap *wd;
-	bool		mustCalculate = !e2->neighbors[lc].closerSet;
-	List	   *added = NIL;
-	bool		removedAny = false;
 
 	if (list_length(w) <= m)
 		return w;
 
 	wd = pairingheap_allocate(CompareNearestCandidates, NULL);
 
-	/* Ensure order of candidates is deterministic for closer caching */
-	if (sortCandidates)
-		list_sort(w, CompareCandidateDistances);
-
 	while (list_length(w) > 0 && list_length(r) < m)
 	{
 		/* Assumes w is already ordered desc */
 		HnswCandidate *e = llast(w);
+		bool		closer;
 
 		w = list_delete_last(w);
 
-		/* Use previous state of r and wd to skip work when possible */
+		closer = CheckElementCloser(e, r, lc, procinfo, collation);
-		if (mustCalculate)
-			e->closer = CheckElementCloser(e, r, lc, procinfo, collation);
-		else if (list_length(added) > 0)
-		{
-			/*
-			 * If the current candidate was closer, we only need to compare it
-			 * with the other candidates that we have added.
-			 */
-			if (e->closer)
-			{
-				e->closer = CheckElementCloser(e, added, lc, procinfo, collation);
 
-				if (!e->closer)
+		if (closer)
-					removedAny = true;
-			}
-			else
-			{
-				/*
-				 * If we have removed any candidates from closer, a candidate
-				 * that was not closer earlier might now be.
-				 */
-				if (removedAny)
-				{
-					e->closer = CheckElementCloser(e, r, lc, procinfo, collation);
-					if (e->closer)
-						added = lappend(added, e);
-				}
-			}
-		}
-		else if (e == newCandidate)
-		{
-			e->closer = CheckElementCloser(e, r, lc, procinfo, collation);
-			if (e->closer)
-				added = lappend(added, e);
-		}
-
-		if (e->closer)
 			r = lappend(r, e);
 		else
 			pairingheap_add(wd, &(CreatePairingHeapNode(e)->ph_node));
 	}
 
-	/* Cached value can only be used in future if sorted deterministically */
-	e2->neighbors[lc].closerSet = sortCandidates;
-
 	/* Keep pruned connections */
 	while (!pairingheap_is_empty(wd) && list_length(r) < m)
 		r = lappend(r, ((HnswPairingHeapNode *) pairingheap_remove_first(wd))->inner);
@@ -947,7 +804,7 @@ HnswFindDuplicate(HnswElement e)
 		HnswCandidate *neighbor = &neighbors->items[i];
 
 		/* Exit early since ordered by distance */
-		if (!datumIsEqual(e->value, neighbor->element->value, false, -1))
+		if (vector_cmp_internal(e->vec, neighbor->element->vec) != 0)
 			break;
 
 		/* Check for space */
@@ -971,6 +828,28 @@ AddConnections(HnswElement element, List *neighbors, int m, int lc)
 		a->items[a->length++] = *((HnswCandidate *) lfirst(lc2));
 }
 
+/*
+ * Compare candidate distances
+ */
+static int
+#if PG_VERSION_NUM >= 130000
+CompareCandidateDistances(const ListCell *a, const ListCell *b)
+#else
+CompareCandidateDistances(const void *a, const void *b)
+#endif
+{
+	HnswCandidate *hca = lfirst((ListCell *) a);
+	HnswCandidate *hcb = lfirst((ListCell *) b);
+
+	if (hca->distance < hcb->distance)
+		return 1;
+
+	if (hca->distance > hcb->distance)
+		return -1;
+
+	return 0;
+}
+
 /*
  * Update connections
  */
@@ -1000,13 +879,13 @@ HnswUpdateConnection(HnswElement element, HnswCandidate * hc, int m, int lc, int
 		/* Load elements on insert */
 		if (index != NULL)
 		{
-			Datum		q = hc->element->value;
+			Datum		q = PointerGetDatum(hc->element->vec);
 
 			for (int i = 0; i < currentNeighbors->length; i++)
 			{
 				HnswCandidate *hc3 = &currentNeighbors->items[i];
 
-				if (DatumGetPointer(hc3->element->value) == NULL)
+				if (hc3->element->vec == NULL)
 					HnswLoadElement(hc3->element, &hc3->distance, &q, index, procinfo, collation, true);
 				else
 					hc3->distance = GetCandidateDistance(hc3, q, procinfo, collation);
@@ -1024,12 +903,13 @@ HnswUpdateConnection(HnswElement element, HnswCandidate * hc, int m, int lc, int
 		{
 			List	   *c = NIL;
 
-			/* Add candidates */
+			/* Add and sort candidates */
 			for (int i = 0; i < currentNeighbors->length; i++)
 				c = lappend(c, &currentNeighbors->items[i]);
 			c = lappend(c, &hc2);
+			list_sort(c, CompareCandidateDistances);
 
-			SelectNeighbors(c, m, lc, procinfo, collation, hc->element, &hc2, &pruned, true);
+			SelectNeighbors(c, m, lc, procinfo, collation, &pruned);
 
 			/* Should not happen */
 			if (pruned == NULL)
@@ -1087,15 +967,9 @@ HnswInsertElement(HnswElement element, HnswElement entryPoint, Relation index, F
 	List	   *w;
 	int			level = element->level;
 	int			entryLevel;
-	Datum		q = element->value;
+	Datum		q = PointerGetDatum(element->vec);
 	HnswElement skipElement = existing ? element : NULL;
 
-#if PG_VERSION_NUM >= 130000
-	/* Precompute hash */
-	if (index == NULL)
-		element->hash = hash_pointer((uintptr_t) element);
-#endif
-
 	/* No neighbors if no entry point */
 	if (entryPoint == NULL)
 		return;
@@ -1134,12 +1008,7 @@ HnswInsertElement(HnswElement element, HnswElement entryPoint, Relation index, F
 		else
 			lw = w;
 
-		/*
+		neighbors = SelectNeighbors(lw, lm, lc, procinfo, collation, NULL);
-		 * Candidates are sorted, but not deterministically. Could set
-		 * sortCandidates to true for in-memory builds to enable closer
-		 * caching, but there does not seem to be a difference in performance.
-		 */
-		neighbors = SelectNeighbors(lw, lm, lc, procinfo, collation, element, NULL, NULL, false);
 
 		AddConnections(element, neighbors, lm, lc);
 

src/hnswvacuum.c

@@ -12,9 +12,12 @@
  * Check if deleted list contains an index TID
  */
 static bool
-DeletedContains(tidhash_hash * deleted, ItemPointer indextid)
+DeletedContains(HTAB *deleted, ItemPointer indextid)
 {
-	return tidhash_lookup(deleted, *indextid) != NULL;
+	bool		found;
+
+	hash_search(deleted, indextid, HASH_FIND, &found);
+	return found;
 }
 
 /*
@@ -59,8 +62,7 @@ RemoveHeapTids(HnswVacuumState * vacuumstate)
 		/* Iterate over nodes */
 		for (offno = FirstOffsetNumber; offno <= maxoffno; offno = OffsetNumberNext(offno))
 		{
-			ItemId		itemid = PageGetItemId(page, offno);
+			HnswElementTuple etup = (HnswElementTuple) PageGetItem(page, PageGetItemId(page, offno));
-			HnswElementTuple etup = (HnswElementTuple) PageGetItem(page, itemid);
 			int			idx = 0;
 			bool		itemUpdated = false;
 
@@ -91,7 +93,7 @@ RemoveHeapTids(HnswVacuumState * vacuumstate)
 
 				if (itemUpdated)
 				{
-					Size		etupSize = ItemIdGetLength(itemid);
+					Size		etupSize = HNSW_ELEMENT_TUPLE_SIZE(etup->vec.dim);
 
 					/* Mark rest as invalid */
 					for (int i = idx; i < HNSW_HEAPTIDS; i++)
@@ -107,13 +109,11 @@ RemoveHeapTids(HnswVacuumState * vacuumstate)
 			if (!ItemPointerIsValid(&etup->heaptids[0]))
 			{
 				ItemPointerData ip;
-				bool		found;
 
 				/* Add to deleted list */
 				ItemPointerSet(&ip, blkno, offno);
 
-				tidhash_insert(vacuumstate->deleted, ip, &found);
+				(void) hash_search(vacuumstate->deleted, &ip, HASH_ENTER, NULL);
-				Assert(!found);
 			}
 			else if (etup->level > highestLevel && !(entryPoint != NULL && blkno == entryPoint->blkno && offno == entryPoint->offno))
 			{
@@ -230,7 +230,7 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
 	UnlockReleaseBuffer(buf);
 
 	/* Update neighbors */
-	HnswUpdateNeighborPages(index, procinfo, collation, element, m, true, false);
+	HnswUpdateNeighborPages(index, procinfo, collation, element, m, true);
 }
 
 /*
@@ -286,7 +286,7 @@ 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, false);
+			HnswUpdateMetaPage(index, HNSW_UPDATE_ENTRY_ALWAYS, highestPoint, InvalidBlockNumber, MAIN_FORKNUM);
 		}
 		else
 		{
@@ -419,7 +419,7 @@ 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, false);
+				HnswUpdateMetaPage(index, HNSW_UPDATE_ENTRY_GREATER, element, InvalidBlockNumber, MAIN_FORKNUM);
 
 			/* Release lock */
 			UnlockPage(index, HNSW_UPDATE_LOCK, lockmode);
@@ -477,8 +477,7 @@ MarkDeleted(HnswVacuumState * vacuumstate)
 		/* Update element and neighbors together */
 		for (offno = FirstOffsetNumber; offno <= maxoffno; offno = OffsetNumberNext(offno))
 		{
-			ItemId		itemid = PageGetItemId(page, offno);
+			HnswElementTuple etup = (HnswElementTuple) PageGetItem(page, PageGetItemId(page, offno));
-			HnswElementTuple etup = (HnswElementTuple) PageGetItem(page, itemid);
 			HnswNeighborTuple ntup;
 			Size		etupSize;
 			Size		ntupSize;
@@ -506,7 +505,7 @@ MarkDeleted(HnswVacuumState * vacuumstate)
 				continue;
 
 			/* Calculate sizes */
-			etupSize = ItemIdGetLength(itemid);
+			etupSize = HNSW_ELEMENT_TUPLE_SIZE(etup->vec.dim);
 			ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(etup->level, vacuumstate->m);
 
 			/* Get neighbor page */
@@ -529,7 +528,7 @@ MarkDeleted(HnswVacuumState * vacuumstate)
 
 			/* Overwrite element */
 			etup->deleted = 1;
-			MemSet(&etup->data, 0, VARSIZE_ANY(&etup->data));
+			MemSet(&etup->vec.x, 0, etup->vec.dim * sizeof(float));
 
 			/* Overwrite neighbors */
 			for (int i = 0; i < ntup->count; i++)
@@ -564,7 +563,7 @@ MarkDeleted(HnswVacuumState * vacuumstate)
 	}
 
 	/* Update insert page last, after everything has been marked as deleted */
-	HnswUpdateMetaPage(index, 0, NULL, insertPage, MAIN_FORKNUM, false);
+	HnswUpdateMetaPage(index, 0, NULL, insertPage, MAIN_FORKNUM);
 }
 
 /*
@@ -574,6 +573,7 @@ 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));
@@ -595,7 +595,10 @@ InitVacuumState(HnswVacuumState * vacuumstate, IndexVacuumInfo *info, IndexBulkD
 	HnswGetMetaPageInfo(index, &vacuumstate->m, NULL);
 
 	/* Create hash table */
-	vacuumstate->deleted = tidhash_create(CurrentMemoryContext, 256, NULL);
+	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);
 }
 
 /*
@@ -604,7 +607,7 @@ InitVacuumState(HnswVacuumState * vacuumstate, IndexVacuumInfo *info, IndexBulkD
 static void
 FreeVacuumState(HnswVacuumState * vacuumstate)
 {
-	tidhash_destroy(vacuumstate->deleted);
+	hash_destroy(vacuumstate->deleted);
 	FreeAccessStrategy(vacuumstate->bas);
 	pfree(vacuumstate->ntup);
 	MemoryContextDelete(vacuumstate->tmpCtx);

src/ivfflat.h

@@ -246,6 +246,8 @@ typedef struct IvfflatScanOpaqueData
 	int			probes;
 	int			dimensions;
 	bool		first;
+	Buffer		buf;
+	ItemPointerData heaptid;
 
 	/* Sorting */
 	Tuplesortstate *sortstate;

src/ivfscan.c

@@ -143,6 +143,10 @@ GetScanItems(IndexScanDesc scan, Datum value)
 				bool		isnull;
 				ItemId		itemid = PageGetItemId(page, offno);
 
+				/* Skip dead tuples */
+				if (scan->ignore_killed_tuples && ItemIdIsDead(itemid))
+					continue;
+
 				itup = (IndexTuple) PageGetItem(page, itemid);
 				datum = index_getattr(itup, 1, tupdesc, &isnull);
 
@@ -157,6 +161,8 @@ GetScanItems(IndexScanDesc scan, Datum value)
 				slot->tts_isnull[0] = false;
 				slot->tts_values[1] = PointerGetDatum(&itup->t_tid);
 				slot->tts_isnull[1] = false;
+				slot->tts_values[2] = Int32GetDatum((int) searchPage);
+				slot->tts_isnull[2] = false;
 				ExecStoreVirtualTuple(slot);
 
 				tuplesort_puttupleslot(so->sortstate, slot);
@@ -181,6 +187,55 @@ GetScanItems(IndexScanDesc scan, Datum value)
 	tuplesort_performsort(so->sortstate);
 }
 
+/*
+ * Mark prior tuple as dead
+ */
+static void
+MarkPriorTupleDead(IndexScanDesc scan)
+{
+	IvfflatScanOpaque so = (IvfflatScanOpaque) scan->opaque;
+	Buffer		buf = so->buf;
+	Page		page;
+	OffsetNumber maxoffno;
+
+	/* Safety check */
+	if (!BufferIsValid(so->buf) || !ItemPointerIsValid(&so->heaptid))
+		return;
+
+	/* Only a shared locked is needed for ItemIdMarkDead */
+	LockBuffer(buf, BUFFER_LOCK_SHARE);
+	page = BufferGetPage(buf);
+	maxoffno = PageGetMaxOffsetNumber(page);
+
+	for (OffsetNumber offno = FirstOffsetNumber; offno <= maxoffno; offno = OffsetNumberNext(offno))
+	{
+		ItemId		itemid = PageGetItemId(page, offno);
+		IndexTuple	itup = (IndexTuple) PageGetItem(page, itemid);
+
+		/*
+		 * Find tuple. Since buffer has been pinned, tuple cannot have been
+		 * vacuumed (and heap TID reused).
+		 */
+		if (ItemPointerEquals(&itup->t_tid, &so->heaptid))
+		{
+			/*
+			 * Make sure tuple has not already been marked dead to avoid extra
+			 * WAL if wal_log_hints or data checksums enabled
+			 */
+			if (!ItemIdIsDead(itemid))
+			{
+				ItemIdMarkDead(itemid);
+				MarkBufferDirtyHint(buf, true);
+			}
+
+			break;
+		}
+	}
+
+	/* Unlock buffer */
+	LockBuffer(buf, BUFFER_LOCK_UNLOCK);
+}
+
 /*
  * Prepare for an index scan
  */
@@ -206,7 +261,9 @@ ivfflatbeginscan(Relation index, int nkeys, int norderbys)
 		probes = lists;
 
 	so = (IvfflatScanOpaque) palloc(offsetof(IvfflatScanOpaqueData, lists) + probes * sizeof(IvfflatScanList));
+	so->buf = InvalidBuffer;
 	so->first = true;
+	ItemPointerSetInvalid(&so->heaptid);
 	so->probes = probes;
 	so->dimensions = dimensions;
 
@@ -217,12 +274,13 @@ ivfflatbeginscan(Relation index, int nkeys, int norderbys)
 
 	/* Create tuple description for sorting */
 #if PG_VERSION_NUM >= 120000
-	so->tupdesc = CreateTemplateTupleDesc(2);
+	so->tupdesc = CreateTemplateTupleDesc(3);
 #else
-	so->tupdesc = CreateTemplateTupleDesc(2, false);
+	so->tupdesc = CreateTemplateTupleDesc(3, false);
 #endif
 	TupleDescInitEntry(so->tupdesc, (AttrNumber) 1, "distance", FLOAT8OID, -1, 0);
 	TupleDescInitEntry(so->tupdesc, (AttrNumber) 2, "heaptid", TIDOID, -1, 0);
+	TupleDescInitEntry(so->tupdesc, (AttrNumber) 3, "indexblkno", INT4OID, -1, 0);
 
 	/* Prep sort */
 	so->sortstate = tuplesort_begin_heap(so->tupdesc, 1, attNums, sortOperators, sortCollations, nullsFirstFlags, work_mem, NULL, false);
@@ -254,6 +312,7 @@ ivfflatrescan(IndexScanDesc scan, ScanKey keys, int nkeys, ScanKey orderbys, int
 #endif
 
 	so->first = true;
+	ItemPointerSetInvalid(&so->heaptid);
 	pairingheap_reset(so->listQueue);
 
 	if (keys && scan->numberOfKeys > 0)
@@ -288,11 +347,6 @@ ivfflatgettuple(IndexScanDesc scan, ScanDirection dir)
 		if (scan->orderByData == NULL)
 			elog(ERROR, "cannot scan ivfflat index without order");
 
-		/* Requires MVCC-compliant snapshot as not able to pin during sorting */
-		/* https://www.postgresql.org/docs/current/index-locking.html */
-		if (!IsMVCCSnapshot(scan->xs_snapshot))
-			elog(ERROR, "non-MVCC snapshots are not supported with ivfflat");
-
 		if (scan->orderByData->sk_flags & SK_ISNULL)
 			value = PointerGetDatum(InitVector(so->dimensions));
 		else
@@ -316,10 +370,17 @@ ivfflatgettuple(IndexScanDesc scan, ScanDirection dir)
 		if (value != scan->orderByData->sk_argument)
 			pfree(DatumGetPointer(value));
 	}
+	else
+	{
+		/* Mark prior tuple as dead */
+		if (scan->kill_prior_tuple)
+			MarkPriorTupleDead(scan);
+	}
 
 	if (tuplesort_gettupleslot(so->sortstate, true, false, so->slot, NULL))
 	{
 		ItemPointer heaptid = (ItemPointer) DatumGetPointer(slot_getattr(so->slot, 2, &so->isnull));
+		BlockNumber indexblkno = DatumGetInt32(slot_getattr(so->slot, 3, &so->isnull));
 
 #if PG_VERSION_NUM >= 120000
 		scan->xs_heaptid = *heaptid;
@@ -327,6 +388,21 @@ ivfflatgettuple(IndexScanDesc scan, ScanDirection dir)
 		scan->xs_ctup.t_self = *heaptid;
 #endif
 
+		/* Keep track of info needed to mark tuple as dead */
+		so->heaptid = *heaptid;
+
+		/* Unpin buffer */
+		if (BufferIsValid(so->buf))
+			ReleaseBuffer(so->buf);
+
+		/*
+		 * An index scan must maintain a pin on the index page holding the
+		 * item last returned by amgettuple
+		 *
+		 * https://www.postgresql.org/docs/current/index-locking.html
+		 */
+		so->buf = ReadBuffer(scan->indexRelation, indexblkno);
+
 		scan->xs_recheckorderby = false;
 		return true;
 	}
@@ -342,6 +418,10 @@ ivfflatendscan(IndexScanDesc scan)
 {
 	IvfflatScanOpaque so = (IvfflatScanOpaque) scan->opaque;
 
+	/* Release pin */
+	if (BufferIsValid(so->buf))
+		ReleaseBuffer(so->buf);
+
 	pairingheap_free(so->listQueue);
 	tuplesort_end(so->sortstate);
 

src/tinyint.c

@@ -0,0 +1,294 @@
+#include "postgres.h"
+
+#include <math.h>
+#include <stdint.h>
+
+#include "fmgr.h"
+#include "lib/stringinfo.h"
+#include "libpq/pqformat.h"
+#include "tinyint.h"
+#include "utils/array.h"
+#include "utils/builtins.h"
+#include "utils/numeric.h"
+
+/*
+ * Check if array is a vector
+ */
+static bool
+ArrayIsVector(ArrayType *a)
+{
+	return ARR_NDIM(a) == 1 && !array_contains_nulls(a);
+}
+
+/*
+ * Check if dimensions are the same
+ */
+static int
+CheckDims(ArrayType *a, ArrayType *b)
+{
+	int			dima;
+	int			dimb;
+
+	if (!ArrayIsVector(a) || !ArrayIsVector(b))
+		return 0;
+
+	dima = ARR_DIMS(a)[0];
+	dimb = ARR_DIMS(b)[0];
+
+	if (dima != dimb)
+		return 0;
+
+	return dima;
+}
+
+/*
+ * Check range
+ */
+static void
+CheckRange(long i)
+{
+	if (i < INT8_MIN || i > INT8_MAX)
+		ereport(ERROR,
+				(errcode(ERRCODE_NUMERIC_VALUE_OUT_OF_RANGE),
+				 errmsg("value \"%ld\" is out of range for type tinyint", i)));
+}
+
+/*
+ * Convert textual representation to internal representation
+ */
+PGDLLEXPORT PG_FUNCTION_INFO_V1(tinyint_in);
+Datum
+tinyint_in(PG_FUNCTION_ARGS)
+{
+	char	   *s = PG_GETARG_CSTRING(0);
+	const char *ptr = s;
+	long		i;
+	char	   *end;
+
+	/* skip leading spaces */
+	while (*ptr != '\0' && isspace((unsigned char) *ptr))
+		ptr++;
+
+	if (*ptr == '\0')
+		ereport(ERROR,
+				(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
+				 errmsg("invalid input syntax for type tinyint: \"%s\"", s)));
+
+	i = strtol(ptr, &end, 10);
+	ptr = end;
+
+	if (i < INT8_MIN || i > INT8_MAX)
+		ereport(ERROR,
+				(errcode(ERRCODE_NUMERIC_VALUE_OUT_OF_RANGE),
+				 errmsg("value \"%s\" is out of range for type tinyint", s)));
+
+	/* allow trailing whitespace, but not other trailing chars */
+	while (*ptr != '\0' && isspace((unsigned char) *ptr))
+		ptr++;
+
+	if (*ptr != '\0')
+		ereport(ERROR,
+				(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
+				 errmsg("invalid input syntax for type tinyint: \"%s\"", s)));
+
+	PG_RETURN_INT8(i);
+}
+
+/*
+ * Convert internal representation to textual representation
+ */
+PGDLLEXPORT PG_FUNCTION_INFO_V1(tinyint_out);
+Datum
+tinyint_out(PG_FUNCTION_ARGS)
+{
+	int8		num = PG_GETARG_INT8(0);
+	char	   *result = (char *) palloc(5);	/* sign, 3 digits, '\0' */
+
+	pg_ltoa((int32) num, result);
+	PG_RETURN_CSTRING(result);
+}
+
+/*
+ * Convert external binary representation to internal representation
+ */
+PGDLLEXPORT PG_FUNCTION_INFO_V1(tinyint_recv);
+Datum
+tinyint_recv(PG_FUNCTION_ARGS)
+{
+	StringInfo	buf = (StringInfo) PG_GETARG_POINTER(0);
+
+	PG_RETURN_INT8((int8) pq_getmsgint(buf, sizeof(int8)));
+}
+
+/*
+ * Convert internal representation to the external binary representation
+ */
+PGDLLEXPORT PG_FUNCTION_INFO_V1(tinyint_send);
+Datum
+tinyint_send(PG_FUNCTION_ARGS)
+{
+	int8		arg1 = PG_GETARG_INT8(0);
+	StringInfoData buf;
+
+	pq_begintypsend(&buf);
+	pq_sendint8(&buf, arg1);
+	PG_RETURN_BYTEA_P(pq_endtypsend(&buf));
+}
+
+/*
+ * Convert integer to tinyint
+ */
+PGDLLEXPORT PG_FUNCTION_INFO_V1(integer_to_tinyint);
+Datum
+integer_to_tinyint(PG_FUNCTION_ARGS)
+{
+	int32		i = PG_GETARG_INT32(0);
+
+	CheckRange(i);
+
+	PG_RETURN_INT8(i);
+}
+
+/*
+ * Convert numeric to tinyint
+ */
+PGDLLEXPORT PG_FUNCTION_INFO_V1(numeric_to_tinyint);
+Datum
+numeric_to_tinyint(PG_FUNCTION_ARGS)
+{
+	Numeric		num = PG_GETARG_NUMERIC(0);
+	int32		i = numeric_int4_opt_error(num, NULL);
+
+	CheckRange(i);
+
+	PG_RETURN_INT8(i);
+}
+
+/*
+ * Get the L2 distance between tinyint arrays
+ */
+PGDLLEXPORT PG_FUNCTION_INFO_V1(tinyint_l2_distance);
+Datum
+tinyint_l2_distance(PG_FUNCTION_ARGS)
+{
+	ArrayType  *a = PG_GETARG_ARRAYTYPE_P(0);
+	ArrayType  *b = PG_GETARG_ARRAYTYPE_P(1);
+	int8    *ax = (int8 *) ARR_DATA_PTR(a);
+	int8    *bx = (int8 *) ARR_DATA_PTR(b);
+	double		distance = 0.0;
+	int			dim = CheckDims(a, b);
+
+	/* TODO Decide on error or NULL */
+	if (!dim)
+		PG_RETURN_NULL();
+
+	/* Auto-vectorized */
+	for (int i = 0; i < dim; i++)
+	{
+		double		diff = ax[i] - bx[i];
+
+		distance += diff * diff;
+	}
+
+	PG_RETURN_FLOAT8(sqrt(distance));
+}
+
+/*
+ * Get the inner product of two tinyint arrays
+ */
+PGDLLEXPORT PG_FUNCTION_INFO_V1(tinyint_inner_product);
+Datum
+tinyint_inner_product(PG_FUNCTION_ARGS)
+{
+	ArrayType  *a = PG_GETARG_ARRAYTYPE_P(0);
+	ArrayType  *b = PG_GETARG_ARRAYTYPE_P(1);
+	int8	   *ax = (int8 *) ARR_DATA_PTR(a);
+	int8	   *bx = (int8 *) ARR_DATA_PTR(b);
+	double		distance = 0.0;
+	int			dim = CheckDims(a, b);
+
+	/* TODO Decide on error or NULL */
+	if (!dim)
+		PG_RETURN_NULL();
+
+	/* Auto-vectorized */
+	for (int i = 0; i < dim; i++)
+		distance += ax[i] * bx[i];
+
+	PG_RETURN_FLOAT8(distance);
+}
+
+/*
+ * Get the negative inner product of two tinyint arrays
+ */
+PGDLLEXPORT PG_FUNCTION_INFO_V1(tinyint_negative_inner_product);
+Datum
+tinyint_negative_inner_product(PG_FUNCTION_ARGS)
+{
+	ArrayType  *a = PG_GETARG_ARRAYTYPE_P(0);
+	ArrayType  *b = PG_GETARG_ARRAYTYPE_P(1);
+	int8	   *ax = (int8 *) ARR_DATA_PTR(a);
+	int8	   *bx = (int8 *) ARR_DATA_PTR(b);
+	double		distance = 0.0;
+	int			dim = CheckDims(a, b);
+
+	/* TODO Decide on error or NULL */
+	if (!dim)
+		PG_RETURN_NULL();
+
+	/* Auto-vectorized */
+	for (int i = 0; i < dim; i++)
+		distance += ax[i] * bx[i];
+
+	PG_RETURN_FLOAT8(distance * -1);
+}
+
+/*
+ * Get the cosine distance between two float2 arrays
+ */
+PGDLLEXPORT PG_FUNCTION_INFO_V1(tinyint_cosine_distance);
+Datum
+tinyint_cosine_distance(PG_FUNCTION_ARGS)
+{
+	ArrayType  *a = PG_GETARG_ARRAYTYPE_P(0);
+	ArrayType  *b = PG_GETARG_ARRAYTYPE_P(1);
+	int8   *ax = (int8 *) ARR_DATA_PTR(a);
+	int8   *bx = (int8 *) ARR_DATA_PTR(b);
+	double		distance = 0.0;
+	double		norma = 0.0;
+	double		normb = 0.0;
+	double		similarity;
+	int			dim = CheckDims(a, b);
+
+	/* TODO Decide on error or NULL */
+	if (!dim)
+		PG_RETURN_NULL();
+
+	/* Auto-vectorized */
+	for (int i = 0; i < dim; i++)
+	{
+		float		axi = ax[i];
+		float		bxi = bx[i];
+
+		distance += axi * bxi;
+		norma += axi * axi;
+		normb += bxi * bxi;
+	}
+
+	/* Use sqrt(a * b) over sqrt(a) * sqrt(b) */
+	similarity = distance / sqrt(norma * normb);
+
+#ifdef _MSC_VER
+	/* /fp:fast may not propagate NaN */
+	if (isnan(similarity))
+		PG_RETURN_FLOAT8(NAN);
+#endif
+
+	/* Keep in range */
+	if (similarity > 1)
+		similarity = 1;
+	else if (similarity < -1)
+		similarity = -1;
+
+	PG_RETURN_FLOAT8(1 - similarity);
+}

src/tinyint.h

@@ -0,0 +1,8 @@
+#ifndef TINYINT_H
+#define TINYINT_H
+
+#define DatumGetInt8(X) ((int8) (X))
+#define PG_GETARG_INT8(n)	 DatumGetInt8(PG_GETARG_DATUM(n))
+#define PG_RETURN_INT8(x)	 return Int8GetDatum(x)
+
+#endif

src/vector.c

@@ -89,7 +89,7 @@ CheckDim(int dim)
 }
 
 /*
- * Ensure finite element
+ * Ensure finite elements
  */
 static inline void
 CheckElement(float value)
@@ -437,18 +437,17 @@ 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	   *vec = PG_GETARG_VECTOR_P(0);
+	Vector	   *arg = PG_GETARG_VECTOR_P(0);
 	int32		typmod = PG_GETARG_INT32(1);
 
-	CheckExpectedDim(typmod, vec->dim);
+	CheckExpectedDim(typmod, arg->dim);
 
-	PG_RETURN_POINTER(vec);
+	PG_RETURN_POINTER(arg);
 }
 
 /*
@@ -465,6 +464,7 @@ array_to_vector(PG_FUNCTION_ARGS)
 	bool		typbyval;
 	char		typalign;
 	Datum	   *elemsp;
+	bool	   *nullsp;
 	int			nelemsp;
 
 	if (ARR_NDIM(array) > 1)
@@ -478,7 +478,7 @@ 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, NULL, &nelemsp);
+	deconstruct_array(array, ARR_ELEMTYPE(array), typlen, typbyval, typalign, &elemsp, &nullsp, &nelemsp);
 
 	CheckDim(nelemsp);
 	CheckExpectedDim(typmod, nelemsp);
@@ -512,12 +512,6 @@ 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]);
@@ -724,7 +718,7 @@ vector_spherical_distance(PG_FUNCTION_ARGS)
 }
 
 /*
- * Get the L1 distance between two vectors
+ * Get the L1 distance between vectors
  */
 PGDLLEXPORT PG_FUNCTION_INFO_V1(l1_distance);
 Datum
@@ -903,8 +897,8 @@ PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_lt);
 Datum
 vector_lt(PG_FUNCTION_ARGS)
 {
-	Vector	   *a = PG_GETARG_VECTOR_P(0);
+	Vector	   *a = (Vector *) PG_GETARG_VECTOR_P(0);
-	Vector	   *b = PG_GETARG_VECTOR_P(1);
+	Vector	   *b = (Vector *) PG_GETARG_VECTOR_P(1);
 
 	PG_RETURN_BOOL(vector_cmp_internal(a, b) < 0);
 }
@@ -916,8 +910,8 @@ PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_le);
 Datum
 vector_le(PG_FUNCTION_ARGS)
 {
-	Vector	   *a = PG_GETARG_VECTOR_P(0);
+	Vector	   *a = (Vector *) PG_GETARG_VECTOR_P(0);
-	Vector	   *b = PG_GETARG_VECTOR_P(1);
+	Vector	   *b = (Vector *) PG_GETARG_VECTOR_P(1);
 
 	PG_RETURN_BOOL(vector_cmp_internal(a, b) <= 0);
 }
@@ -929,8 +923,8 @@ PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_eq);
 Datum
 vector_eq(PG_FUNCTION_ARGS)
 {
-	Vector	   *a = PG_GETARG_VECTOR_P(0);
+	Vector	   *a = (Vector *) PG_GETARG_VECTOR_P(0);
-	Vector	   *b = PG_GETARG_VECTOR_P(1);
+	Vector	   *b = (Vector *) PG_GETARG_VECTOR_P(1);
 
 	PG_RETURN_BOOL(vector_cmp_internal(a, b) == 0);
 }
@@ -942,8 +936,8 @@ PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_ne);
 Datum
 vector_ne(PG_FUNCTION_ARGS)
 {
-	Vector	   *a = PG_GETARG_VECTOR_P(0);
+	Vector	   *a = (Vector *) PG_GETARG_VECTOR_P(0);
-	Vector	   *b = PG_GETARG_VECTOR_P(1);
+	Vector	   *b = (Vector *) PG_GETARG_VECTOR_P(1);
 
 	PG_RETURN_BOOL(vector_cmp_internal(a, b) != 0);
 }
@@ -955,8 +949,8 @@ PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_ge);
 Datum
 vector_ge(PG_FUNCTION_ARGS)
 {
-	Vector	   *a = PG_GETARG_VECTOR_P(0);
+	Vector	   *a = (Vector *) PG_GETARG_VECTOR_P(0);
-	Vector	   *b = PG_GETARG_VECTOR_P(1);
+	Vector	   *b = (Vector *) PG_GETARG_VECTOR_P(1);
 
 	PG_RETURN_BOOL(vector_cmp_internal(a, b) >= 0);
 }
@@ -968,8 +962,8 @@ PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_gt);
 Datum
 vector_gt(PG_FUNCTION_ARGS)
 {
-	Vector	   *a = PG_GETARG_VECTOR_P(0);
+	Vector	   *a = (Vector *) PG_GETARG_VECTOR_P(0);
-	Vector	   *b = PG_GETARG_VECTOR_P(1);
+	Vector	   *b = (Vector *) PG_GETARG_VECTOR_P(1);
 
 	PG_RETURN_BOOL(vector_cmp_internal(a, b) > 0);
 }
@@ -981,8 +975,8 @@ PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_cmp);
 Datum
 vector_cmp(PG_FUNCTION_ARGS)
 {
-	Vector	   *a = PG_GETARG_VECTOR_P(0);
+	Vector	   *a = (Vector *) PG_GETARG_VECTOR_P(0);
-	Vector	   *b = PG_GETARG_VECTOR_P(1);
+	Vector	   *b = (Vector *) PG_GETARG_VECTOR_P(1);
 
 	PG_RETURN_INT32(vector_cmp_internal(a, b));
 }

test/expected/functions.out

@@ -54,85 +54,85 @@ SELECT vector_norm('[3e37,4e37]')::real;
        5e+37
 (1 row)
 
-SELECT l2_distance('[0,0]', '[3,4]');
+SELECT l2_distance('[0,0]'::vector, '[3,4]');
  l2_distance 
 -------------
            5
 (1 row)
 
-SELECT l2_distance('[0,0]', '[0,1]');
+SELECT l2_distance('[0,0]'::vector, '[0,1]');
  l2_distance 
 -------------
            1
 (1 row)
 
-SELECT l2_distance('[1,2]', '[3]');
+SELECT l2_distance('[1,2]'::vector, '[3]');
 ERROR:  different vector dimensions 2 and 1
-SELECT l2_distance('[3e38]', '[-3e38]');
+SELECT l2_distance('[3e38]'::vector, '[-3e38]');
  l2_distance 
 -------------
     Infinity
 (1 row)
 
-SELECT inner_product('[1,2]', '[3,4]');
+SELECT inner_product('[1,2]'::vector, '[3,4]');
  inner_product 
 ---------------
             11
 (1 row)
 
-SELECT inner_product('[1,2]', '[3]');
+SELECT inner_product('[1,2]'::vector, '[3]');
 ERROR:  different vector dimensions 2 and 1
-SELECT inner_product('[3e38]', '[3e38]');
+SELECT inner_product('[3e38]'::vector, '[3e38]');
  inner_product 
 ---------------
       Infinity
 (1 row)
 
-SELECT cosine_distance('[1,2]', '[2,4]');
+SELECT cosine_distance('[1,2]'::vector, '[2,4]');
  cosine_distance 
 -----------------
                0
 (1 row)
 
-SELECT cosine_distance('[1,2]', '[0,0]');
+SELECT cosine_distance('[1,2]'::vector, '[0,0]');
  cosine_distance 
 -----------------
              NaN
 (1 row)
 
-SELECT cosine_distance('[1,1]', '[1,1]');
+SELECT cosine_distance('[1,1]'::vector, '[1,1]');
  cosine_distance 
 -----------------
                0
 (1 row)
 
-SELECT cosine_distance('[1,0]', '[0,2]');
+SELECT cosine_distance('[1,0]'::vector, '[0,2]');
  cosine_distance 
 -----------------
                1
 (1 row)
 
-SELECT cosine_distance('[1,1]', '[-1,-1]');
+SELECT cosine_distance('[1,1]'::vector, '[-1,-1]');
  cosine_distance 
 -----------------
                2
 (1 row)
 
-SELECT cosine_distance('[1,2]', '[3]');
+SELECT cosine_distance('[1,2]'::vector, '[3]');
 ERROR:  different vector dimensions 2 and 1
-SELECT cosine_distance('[1,1]', '[1.1,1.1]');
+SELECT cosine_distance('[1,1]'::vector, '[1.1,1.1]');
  cosine_distance 
 -----------------
                0
 (1 row)
 
-SELECT cosine_distance('[1,1]', '[-1.1,-1.1]');
+SELECT cosine_distance('[1,1]'::vector, '[-1.1,-1.1]');
  cosine_distance 
 -----------------
                2
 (1 row)
 
-SELECT cosine_distance('[3e38]', '[3e38]');
+SELECT cosine_distance('[3e38]'::vector, '[3e38]');
  cosine_distance 
 -----------------
              NaN

test/expected/tinyint.out

@@ -0,0 +1,148 @@
+SELECT '127'::tinyint;
+ tinyint 
+---------
+ 127
+(1 row)
+
+SELECT '128'::tinyint;
+ERROR:  value "128" is out of range for type tinyint
+LINE 1: SELECT '128'::tinyint;
+               ^
+SELECT '-128'::tinyint;
+ tinyint 
+---------
+ -128
+(1 row)
+
+SELECT '-129'::tinyint;
+ERROR:  value "-129" is out of range for type tinyint
+LINE 1: SELECT '-129'::tinyint;
+               ^
+SELECT ''::tinyint;
+ERROR:  invalid input syntax for type tinyint: ""
+LINE 1: SELECT ''::tinyint;
+               ^
+SELECT ' 1'::tinyint;
+ tinyint 
+---------
+ 1
+(1 row)
+
+SELECT '1 '::tinyint;
+ tinyint 
+---------
+ 1
+(1 row)
+
+SELECT '1a'::tinyint;
+ERROR:  invalid input syntax for type tinyint: "1a"
+LINE 1: SELECT '1a'::tinyint;
+               ^
+SELECT '{1,2,3}'::tinyint[];
+ tinyint 
+---------
+ {1,2,3}
+(1 row)
+
+SELECT '128'::numeric::tinyint;
+ERROR:  value "128" is out of range for type tinyint
+SELECT 'NaN'::numeric::tinyint;
+ERROR:  cannot convert NaN to integer
+SELECT l2_distance('{0,0}'::tinyint[], '{3,4}'::tinyint[]);
+ l2_distance 
+-------------
+           5
+(1 row)
+
+SELECT l2_distance('{0,0}'::tinyint[], '{0,1}'::tinyint[]);
+ l2_distance 
+-------------
+           1
+(1 row)
+
+SELECT l2_distance('{1,2}'::tinyint[], '{3}'::tinyint[]);
+ l2_distance 
+-------------
+            
+(1 row)
+
+SELECT l2_distance('{3e38}'::tinyint[], '{-3e38}'::tinyint[]);
+ERROR:  invalid input syntax for type tinyint: "3e38"
+LINE 1: SELECT l2_distance('{3e38}'::tinyint[], '{-3e38}'::tinyint[]...
+                           ^
+SELECT '{0,0}'::tinyint[] <-> '{3,4}'::tinyint[];
+ ?column? 
+----------
+        5
+(1 row)
+
+SELECT inner_product('{1,2}'::tinyint[], '{3,4}'::tinyint[]);
+ inner_product 
+---------------
+            11
+(1 row)
+
+SELECT inner_product('{1,2}'::tinyint[], '{3}'::tinyint[]);
+ inner_product 
+---------------
+              
+(1 row)
+
+SELECT inner_product('{127}'::tinyint[], '{127}'::tinyint[]);
+ inner_product 
+---------------
+         16129
+(1 row)
+
+SELECT '{1,2}'::tinyint[] <#> '{3,4}'::tinyint[];
+ ?column? 
+----------
+      -11
+(1 row)
+
+SELECT cosine_distance('{1,2}'::tinyint[], '{2,4}'::tinyint[]);
+ cosine_distance 
+-----------------
+               0
+(1 row)
+
+SELECT cosine_distance('{1,2}'::tinyint[], '{0,0}'::tinyint[]);
+ cosine_distance 
+-----------------
+             NaN
+(1 row)
+
+SELECT cosine_distance('{1,1}'::tinyint[], '{1,1}'::tinyint[]);
+ cosine_distance 
+-----------------
+               0
+(1 row)
+
+SELECT cosine_distance('{1,0}'::tinyint[], '{0,2}'::tinyint[]);
+ cosine_distance 
+-----------------
+               1
+(1 row)
+
+SELECT cosine_distance('{1,1}'::tinyint[], '{-1,-1}'::tinyint[]);
+ cosine_distance 
+-----------------
+               2
+(1 row)
+
+SELECT cosine_distance('{1,2}'::tinyint[], '{3}'::tinyint[]);
+ cosine_distance 
+-----------------
+                
+(1 row)
+
+SELECT cosine_distance('{3e38}'::tinyint[], '{3e38}'::tinyint[]);
+ERROR:  invalid input syntax for type tinyint: "3e38"
+LINE 1: SELECT cosine_distance('{3e38}'::tinyint[], '{3e38}'::tinyin...
+                               ^
+SELECT '{1,2}'::tinyint[] <=> '{2,4}'::tinyint[];
+ ?column? 
+----------
+        0
+(1 row)
+

test/sql/functions.sql

@@ -13,24 +13,24 @@ SELECT vector_norm('[3,4]');
 SELECT vector_norm('[0,1]');
 SELECT vector_norm('[3e37,4e37]')::real;
 
-SELECT l2_distance('[0,0]', '[3,4]');
+SELECT l2_distance('[0,0]'::vector, '[3,4]');
-SELECT l2_distance('[0,0]', '[0,1]');
+SELECT l2_distance('[0,0]'::vector, '[0,1]');
-SELECT l2_distance('[1,2]', '[3]');
+SELECT l2_distance('[1,2]'::vector, '[3]');
-SELECT l2_distance('[3e38]', '[-3e38]');
+SELECT l2_distance('[3e38]'::vector, '[-3e38]');
 
-SELECT inner_product('[1,2]', '[3,4]');
+SELECT inner_product('[1,2]'::vector, '[3,4]');
-SELECT inner_product('[1,2]', '[3]');
+SELECT inner_product('[1,2]'::vector, '[3]');
-SELECT inner_product('[3e38]', '[3e38]');
+SELECT inner_product('[3e38]'::vector, '[3e38]');
 
-SELECT cosine_distance('[1,2]', '[2,4]');
+SELECT cosine_distance('[1,2]'::vector, '[2,4]');
-SELECT cosine_distance('[1,2]', '[0,0]');
+SELECT cosine_distance('[1,2]'::vector, '[0,0]');
-SELECT cosine_distance('[1,1]', '[1,1]');
+SELECT cosine_distance('[1,1]'::vector, '[1,1]');
-SELECT cosine_distance('[1,0]', '[0,2]');
+SELECT cosine_distance('[1,0]'::vector, '[0,2]');
-SELECT cosine_distance('[1,1]', '[-1,-1]');
+SELECT cosine_distance('[1,1]'::vector, '[-1,-1]');
-SELECT cosine_distance('[1,2]', '[3]');
+SELECT cosine_distance('[1,2]'::vector, '[3]');
-SELECT cosine_distance('[1,1]', '[1.1,1.1]');
+SELECT cosine_distance('[1,1]'::vector, '[1.1,1.1]');
-SELECT cosine_distance('[1,1]', '[-1.1,-1.1]');
+SELECT cosine_distance('[1,1]'::vector, '[-1.1,-1.1]');
-SELECT cosine_distance('[3e38]', '[3e38]');
+SELECT cosine_distance('[3e38]'::vector, '[3e38]');
 
 SELECT l1_distance('[0,0]', '[3,4]');
 SELECT l1_distance('[0,0]', '[0,1]');

test/sql/tinyint.sql

@@ -0,0 +1,34 @@
+SELECT '127'::tinyint;
+SELECT '128'::tinyint;
+SELECT '-128'::tinyint;
+SELECT '-129'::tinyint;
+
+SELECT ''::tinyint;
+SELECT ' 1'::tinyint;
+SELECT '1 '::tinyint;
+SELECT '1a'::tinyint;
+
+SELECT '{1,2,3}'::tinyint[];
+
+SELECT '128'::numeric::tinyint;
+SELECT 'NaN'::numeric::tinyint;
+
+SELECT l2_distance('{0,0}'::tinyint[], '{3,4}'::tinyint[]);
+SELECT l2_distance('{0,0}'::tinyint[], '{0,1}'::tinyint[]);
+SELECT l2_distance('{1,2}'::tinyint[], '{3}'::tinyint[]);
+SELECT l2_distance('{3e38}'::tinyint[], '{-3e38}'::tinyint[]);
+SELECT '{0,0}'::tinyint[] <-> '{3,4}'::tinyint[];
+
+SELECT inner_product('{1,2}'::tinyint[], '{3,4}'::tinyint[]);
+SELECT inner_product('{1,2}'::tinyint[], '{3}'::tinyint[]);
+SELECT inner_product('{127}'::tinyint[], '{127}'::tinyint[]);
+SELECT '{1,2}'::tinyint[] <#> '{3,4}'::tinyint[];
+
+SELECT cosine_distance('{1,2}'::tinyint[], '{2,4}'::tinyint[]);
+SELECT cosine_distance('{1,2}'::tinyint[], '{0,0}'::tinyint[]);
+SELECT cosine_distance('{1,1}'::tinyint[], '{1,1}'::tinyint[]);
+SELECT cosine_distance('{1,0}'::tinyint[], '{0,2}'::tinyint[]);
+SELECT cosine_distance('{1,1}'::tinyint[], '{-1,-1}'::tinyint[]);
+SELECT cosine_distance('{1,2}'::tinyint[], '{3}'::tinyint[]);
+SELECT cosine_distance('{3e38}'::tinyint[], '{3e38}'::tinyint[]);
+SELECT '{1,2}'::tinyint[] <=> '{2,4}'::tinyint[];

test/t/012_hnsw_build_recall.pl

@@ -83,32 +83,11 @@ for my $i (0 .. $#operators)
 		push(@expected, $res);
 	}
 
-	# Build index serially
+	# Add index
-	$node->safe_psql("postgres", qq(
+	$node->safe_psql("postgres", "CREATE INDEX ON tst USING hnsw (v $opclass);");
-		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);
-
-	$node->safe_psql("postgres", "DROP INDEX idx;");
-
-	# Build index in parallel
-	my ($ret, $stdout, $stderr) = $node->psql("postgres", qq(
-		SET client_min_messages = DEBUG;
-		SET min_parallel_table_scan_size = 1;
-		SET hnsw.enable_parallel_build = on;
-		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;");
 }
 
 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 = '0.5.0'
 module_pathname = '$libdir/vector'
 relocatable = true