Use DSA

Spinlocks should be held only for a few instructions, for multiple
reasons:

- You have to be very careful not to elog() out while holding a
  spinlock, because there is no mechanism to release the spinlock on
  error.

- Waiters can waste a lot of cycles spinning if the lock is
  contended. I you wait on a spinlock for too long, the PostgreSQL
  implementation will actually PANIC, see s_lock_stuck().

The flushLock is particularly problematic. It is held in exclusive
mode, which means it holds a spinlock, over the call to
FlushPages(). FlushPages() performs lots of I/O so it can take a very
long time (>= minutes), and can also easily error out for various
reasons.

allocatorLock would perhaps be OK as a spinlocks, but even that feels
a bit heavy, so I converted that to an LWLock, too.

entryLock is usually held for a very short time, in shared mode, so
that would be fine as a spinlock. However, in the rare case that the
entry point is updated, it's held for a very long time. An LWLock used
in shared mode is about as fast a spinlock, that path is pretty
heavily optimized.

I think we have some problems with the per-element spinlocks too. In
HnswUpdateNeighborPagesInMemory(), it's held over a call to
HnswUpdateConnection(), but HnswUpdateConnection() can error out at
least in case of an out-of-memory error (it uses lappend(), which
calls palloc()). It also calls the distance function, and I don't
think they are guaranteed to be ereport-free either. However, I didn't
address that in this PR, it needs a bit more thinking.

.github/workflows/build.yml

@@ -20,6 +20,8 @@ jobs:
             os: ubuntu-20.04
           - postgres: 12
             os: ubuntu-20.04
+          - postgres: 11
+            os: ubuntu-20.04
     steps:
       - uses: actions/checkout@v4
       - uses: ankane/setup-postgres@v1
@@ -60,7 +62,7 @@ jobs:
           wget -q https://github.com/postgres/postgres/archive/refs/tags/REL_14_5.tar.gz
           tar xf REL_14_5.tar.gz
       - run: make prove_installcheck PROVE_FLAGS="-I ./postgres-REL_14_5/src/test/perl" PERL5LIB="/Users/runner/perl5/lib/perl5"
-      - run: make clean && /usr/local/opt/llvm@15/bin/scan-build --status-bugs make
+      - run: make clean && /usr/local/opt/llvm@15/bin/scan-build --status-bugs make PG_CFLAGS="-DUSE_ASSERT_CHECKING"
   windows:
     runs-on: windows-latest
     if: ${{ !startsWith(github.ref_name, 'mac') }}

CHANGELOG.md

@@ -1,6 +1,10 @@
 ## 0.5.2 (unreleased)
 
-- Added support for on-disk parallel index builds for HNSW
+- Improved performance of HNSW
+- Added support for parallel index builds for HNSW
+- Reduced memory usage for HNSW index builds
+- Reduced WAL generation for HNSW index builds
+- Fixed `invalid memory alloc request size` error with HNSW index build
 
 ## 0.5.1 (2023-10-10)
 

Makefile

@@ -3,8 +3,8 @@ EXTVERSION = 0.5.1
 
 MODULE_big = vector
 DATA = $(wildcard sql/*--*.sql)
-OBJS = src/half.o 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
-HEADERS = src/half.h src/vector.h
+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
+HEADERS = 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
 
-OBJS = src\half.obj src\hnsw.obj src\hnswbuild.obj src\hnswinsert.obj src\hnswscan.obj src\hnswutils.obj src\hnswvacuum.obj src\ivfbuild.obj src\ivfflat.obj src\ivfinsert.obj src\ivfkmeans.obj src\ivfscan.obj src\ivfutils.obj src\ivfvacuum.obj src\vector.obj
-HEADERS = src\half.h src\vector.h
+OBJS = src\hnsw.obj src\hnswbuild.obj src\hnswinsert.obj src\hnswscan.obj src\hnswutils.obj src\hnswvacuum.obj src\ivfbuild.obj src\ivfflat.obj src\ivfinsert.obj src\ivfkmeans.obj src\ivfscan.obj src\ivfutils.obj src\ivfvacuum.obj src\vector.obj
+HEADERS = src\vector.h
 
 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

@@ -161,8 +161,97 @@ You can add an index to use approximate nearest neighbor search, which trades so
 
 Supported index types are:
 
-- [IVFFlat](#ivfflat)
 - [HNSW](#hnsw) - added in 0.5.0
+- [IVFFlat](#ivfflat)
+
+## HNSW
+
+An HNSW index creates a multilayer graph. It has better query performance than IVFFlat (in terms of speed-recall tradeoff), but has slower build times and uses more memory. Also, an index can be created without any data in the table since there isn’t a training step like IVFFlat.
+
+Add an index for each distance function you want to use.
+
+L2 distance
+
+```sql
+CREATE INDEX ON items USING hnsw (embedding vector_l2_ops);
+```
+
+Inner product
+
+```sql
+CREATE INDEX ON items USING hnsw (embedding vector_ip_ops);
+```
+
+Cosine distance
+
+```sql
+CREATE INDEX ON items USING hnsw (embedding vector_cosine_ops);
+```
+
+Vectors with up to 2,000 dimensions can be indexed.
+
+### Index Options
+
+Specify HNSW parameters
+
+- `m` - the max number of connections per layer (16 by default)
+- `ef_construction` - the size of the dynamic candidate list for constructing the graph (64 by default)
+
+```sql
+CREATE INDEX ON items USING hnsw (embedding vector_l2_ops) WITH (m = 16, ef_construction = 64);
+```
+
+A higher value of `ef_construction` provides better recall at the cost of index build time / insert speed.
+
+### Query Options
+
+Specify the size of the dynamic candidate list for search (40 by default)
+
+```sql
+SET hnsw.ef_search = 100;
+```
+
+A higher value provides better recall at the cost of speed.
+
+Use `SET LOCAL` inside a transaction to set it for a single query
+
+```sql
+BEGIN;
+SET LOCAL hnsw.ef_search = 100;
+SELECT ...
+COMMIT;
+```
+
+### Index Build Time
+
+Indexes build significantly faster when the graph fits into `maintenance_work_mem`
+
+```sql
+SET maintenance_work_mem = '8GB';
+```
+
+A notice is shown when the graph no longer fits
+
+```text
+NOTICE:  hnsw graph no longer fits into maintenance_work_mem after 100000 tuples
+DETAIL:  Building will take significantly more time.
+HINT:  Increase maintenance_work_mem to speed up builds.
+```
+
+Note: Do not set `maintenance_work_mem` so high that it exhausts the memory on the server
+
+### Indexing Progress
+
+Check [indexing progress](https://www.postgresql.org/docs/current/progress-reporting.html#CREATE-INDEX-PROGRESS-REPORTING) with Postgres 12+
+
+```sql
+SELECT phase, round(100.0 * blocks_done / nullif(blocks_total, 0), 1) AS "%" FROM pg_stat_progress_create_index;
+```
+
+The phases for HNSW are:
+
+1. `initializing`
+2. `loading tuples`
 
 ## IVFFlat
 
@@ -232,77 +321,6 @@ The phases for IVFFlat are:
 
 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.
-
-Add an index for each distance function you want to use.
-
-L2 distance
-
-```sql
-CREATE INDEX ON items USING hnsw (embedding vector_l2_ops);
-```
-
-Inner product
-
-```sql
-CREATE INDEX ON items USING hnsw (embedding vector_ip_ops);
-```
-
-Cosine distance
-
-```sql
-CREATE INDEX ON items USING hnsw (embedding vector_cosine_ops);
-```
-
-Vectors with up to 2,000 dimensions can be indexed.
-
-### Index Options
-
-Specify HNSW parameters
-
-- `m` - the max number of connections per layer (16 by default)
-- `ef_construction` - the size of the dynamic candidate list for constructing the graph (64 by default)
-
-```sql
-CREATE INDEX ON items USING hnsw (embedding vector_l2_ops) WITH (m = 16, ef_construction = 64);
-```
-
-A higher value of `ef_construction` provides better recall at the cost of index build time / insert speed.
-
-### Query Options
-
-Specify the size of the dynamic candidate list for search (40 by default)
-
-```sql
-SET hnsw.ef_search = 100;
-```
-
-A higher value provides better recall at the cost of speed.
-
-Use `SET LOCAL` inside a transaction to set it for a single query
-
-```sql
-BEGIN;
-SET LOCAL hnsw.ef_search = 100;
-SELECT ...
-COMMIT;
-```
-
-### Indexing Progress
-
-Check [indexing progress](https://www.postgresql.org/docs/current/progress-reporting.html#CREATE-INDEX-PROGRESS-REPORTING) with Postgres 12+
-
-```sql
-SELECT phase, round(100.0 * blocks_done / nullif(blocks_total, 0), 1) AS "%" FROM pg_stat_progress_create_index;
-```
-
-The phases for HNSW are:
-
-1. `initializing`
-2. `loading tuples`
-
 ## Filtering
 
 There are a few ways to index nearest neighbor queries with a `WHERE` clause
@@ -320,8 +338,7 @@ CREATE INDEX ON items (category_id);
 Or a [partial index](https://www.postgresql.org/docs/current/indexes-partial.html) on the vector column for approximate search
 
 ```sql
-CREATE INDEX ON items USING ivfflat (embedding vector_l2_ops) WITH (lists = 100)
-    WHERE (category_id = 123);
+CREATE INDEX ON items USING hnsw (embedding vector_l2_ops) WHERE (category_id = 123);
 ```
 
 Use [partitioning](https://www.postgresql.org/docs/current/ddl-partitioning.html) for approximate search on many different values of the `WHERE` columns
@@ -571,10 +588,10 @@ If compilation fails with `fatal error: postgres.h: No such file or directory`,
 For Ubuntu and Debian, use:
 
 ```sh
-sudo apt install postgresql-server-dev-15
+sudo apt install postgresql-server-dev-16
 ```
 
-Note: Replace `15` with your Postgres server version
+Note: Replace `16` with your Postgres server version
 
 ### Windows
 
@@ -589,7 +606,7 @@ Note: The exact path will vary depending on your Visual Studio version and editi
 Then use `nmake` to build:
 
 ```cmd
-set "PGROOT=C:\Program Files\PostgreSQL\15"
+set "PGROOT=C:\Program Files\PostgreSQL\16"
 git clone --branch v0.5.1 https://github.com/pgvector/pgvector.git
 cd pgvector
 nmake /F Makefile.win
@@ -639,22 +656,22 @@ pgxn install vector
 Debian and Ubuntu packages are available from the [PostgreSQL APT Repository](https://wiki.postgresql.org/wiki/Apt). Follow the [setup instructions](https://wiki.postgresql.org/wiki/Apt#Quickstart) and run:
 
 ```sh
-sudo apt install postgresql-15-pgvector
+sudo apt install postgresql-16-pgvector
 ```
 
-Note: Replace `15` with your Postgres server version
+Note: Replace `16` with your Postgres server version
 
 ### Yum
 
 RPM packages are available from the [PostgreSQL Yum Repository](https://yum.postgresql.org/). Follow the [setup instructions](https://www.postgresql.org/download/linux/redhat/) for your distribution and run:
 
 ```sh
-sudo yum install pgvector_15
+sudo yum install pgvector_16
 # or
-sudo dnf install pgvector_15
+sudo dnf install pgvector_16
 ```
 
-Note: Replace `15` with your Postgres server version
+Note: Replace `16` with your Postgres server version
 
 ### conda-forge
 

sql/vector--0.5.1--0.6.0.sql

@@ -1,101 +0,0 @@
--- complain if script is sourced in psql, rather than via CREATE EXTENSION
-\echo Use "ALTER EXTENSION vector UPDATE TO '0.6.0'" to load this file. \quit
-
-CREATE TYPE half;
-
-CREATE FUNCTION half_in(cstring, oid, integer) RETURNS half
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION half_out(half) RETURNS cstring
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION half_recv(internal, oid, integer) RETURNS half
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION half_send(half) RETURNS bytea
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE TYPE half (
-	INPUT     = half_in,
-	OUTPUT    = half_out,
-	RECEIVE   = half_recv,
-	SEND      = half_send,
-	INTERNALLENGTH = 2,
-	PASSEDBYVALUE,
-	ALIGNMENT = int2
-);
-
-CREATE FUNCTION l2_distance(half[], half[]) RETURNS float8
-	AS 'MODULE_PATHNAME', 'half_l2_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION inner_product(half[], half[]) RETURNS float8
-	AS 'MODULE_PATHNAME', 'half_inner_product' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION cosine_distance(half[], half[]) RETURNS float8
-	AS 'MODULE_PATHNAME', 'half_cosine_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION l1_distance(half[], half[]) RETURNS float8
-	AS 'MODULE_PATHNAME', 'half_l1_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION half_l2_squared_distance(half[], half[]) RETURNS float8
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION half_negative_inner_product(half[], half[]) RETURNS float8
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION float4_to_half(real, integer, boolean) RETURNS half
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION half_to_float4(half, integer, boolean) RETURNS real
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION float8_to_half(float8, integer, boolean) RETURNS half
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION half_to_float8(half, integer, boolean) RETURNS float8
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION integer_to_half(integer, integer, boolean) RETURNS half
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION numeric_to_half(numeric, integer, boolean) RETURNS half
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION half_to_numeric(half, integer, boolean) RETURNS numeric
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE CAST (real AS half)
-	WITH FUNCTION float4_to_half(real, integer, boolean) AS IMPLICIT;
-
-CREATE CAST (half AS real)
-	WITH FUNCTION half_to_float4(half, integer, boolean) AS IMPLICIT;
-
-CREATE CAST (float8 AS half)
-	WITH FUNCTION float8_to_half(float8, integer, boolean) AS IMPLICIT;
-
-CREATE CAST (half AS float8)
-	WITH FUNCTION half_to_float8(half, integer, boolean) AS IMPLICIT;
-
-CREATE CAST (integer AS half)
-	WITH FUNCTION integer_to_half(integer, integer, boolean) AS IMPLICIT;
-
-CREATE CAST (numeric AS half)
-	WITH FUNCTION numeric_to_half(numeric, integer, boolean) AS IMPLICIT;
-
-CREATE CAST (half AS numeric)
-	WITH FUNCTION half_to_numeric(half, integer, boolean) AS IMPLICIT;
-
-CREATE OPERATOR <-> (
-	LEFTARG = half[], RIGHTARG = half[], PROCEDURE = l2_distance,
-	COMMUTATOR = '<->'
-);
-
-CREATE OPERATOR <#> (
-	LEFTARG = half[], RIGHTARG = half[], PROCEDURE = half_negative_inner_product,
-	COMMUTATOR = '<#>'
-);
-
-CREATE OPERATOR <=> (
-	LEFTARG = half[], RIGHTARG = half[], PROCEDURE = cosine_distance,
-	COMMUTATOR = '<=>'
-);

sql/vector.sql

@@ -290,114 +290,3 @@ 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);
-
--- half type
-
-CREATE TYPE half;
-
-CREATE FUNCTION half_in(cstring, oid, integer) RETURNS half
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION half_out(half) RETURNS cstring
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION half_recv(internal, oid, integer) RETURNS half
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION half_send(half) RETURNS bytea
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE TYPE half (
-	INPUT     = half_in,
-	OUTPUT    = half_out,
-	RECEIVE   = half_recv,
-	SEND      = half_send,
-	INTERNALLENGTH = 2,
-	PASSEDBYVALUE,
-	ALIGNMENT = int2
-);
-
--- half functions
-
-CREATE FUNCTION l2_distance(half[], half[]) RETURNS float8
-	AS 'MODULE_PATHNAME', 'half_l2_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION inner_product(half[], half[]) RETURNS float8
-	AS 'MODULE_PATHNAME', 'half_inner_product' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION cosine_distance(half[], half[]) RETURNS float8
-	AS 'MODULE_PATHNAME', 'half_cosine_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION l1_distance(half[], half[]) RETURNS float8
-	AS 'MODULE_PATHNAME', 'half_l1_distance' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
--- half private functions
-
-CREATE FUNCTION half_l2_squared_distance(half[], half[]) RETURNS float8
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION half_negative_inner_product(half[], half[]) RETURNS float8
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
--- half cast functions
-
-CREATE FUNCTION float4_to_half(real, integer, boolean) RETURNS half
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION half_to_float4(half, integer, boolean) RETURNS real
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION float8_to_half(float8, integer, boolean) RETURNS half
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION half_to_float8(half, integer, boolean) RETURNS float8
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION integer_to_half(integer, integer, boolean) RETURNS half
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION numeric_to_half(numeric, integer, boolean) RETURNS half
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
-CREATE FUNCTION half_to_numeric(half, integer, boolean) RETURNS numeric
-	AS 'MODULE_PATHNAME' LANGUAGE C IMMUTABLE STRICT PARALLEL SAFE;
-
--- half casts
-
-CREATE CAST (real AS half)
-	WITH FUNCTION float4_to_half(real, integer, boolean) AS IMPLICIT;
-
-CREATE CAST (half AS real)
-	WITH FUNCTION half_to_float4(half, integer, boolean) AS IMPLICIT;
-
-CREATE CAST (float8 AS half)
-	WITH FUNCTION float8_to_half(float8, integer, boolean) AS IMPLICIT;
-
-CREATE CAST (half AS float8)
-	WITH FUNCTION half_to_float8(half, integer, boolean) AS IMPLICIT;
-
-CREATE CAST (integer AS half)
-	WITH FUNCTION integer_to_half(integer, integer, boolean) AS IMPLICIT;
-
-CREATE CAST (numeric AS half)
-	WITH FUNCTION numeric_to_half(numeric, integer, boolean) AS IMPLICIT;
-
-CREATE CAST (half AS numeric)
-	WITH FUNCTION half_to_numeric(half, integer, boolean) AS IMPLICIT;
-
--- half operators
-
-CREATE OPERATOR <-> (
-	LEFTARG = half[], RIGHTARG = half[], PROCEDURE = l2_distance,
-	COMMUTATOR = '<->'
-);
-
-CREATE OPERATOR <#> (
-	LEFTARG = half[], RIGHTARG = half[], PROCEDURE = half_negative_inner_product,
-	COMMUTATOR = '<#>'
-);
-
-CREATE OPERATOR <=> (
-	LEFTARG = half[], RIGHTARG = half[], PROCEDURE = cosine_distance,
-	COMMUTATOR = '<=>'
-);

src/half.c

@@ -1,694 +0,0 @@
-#include "postgres.h"
-
-#include <math.h>
-
-#include "common/shortest_dec.h"
-#include "fmgr.h"
-#include "half.h"
-#include "lib/stringinfo.h"
-#include "libpq/pqformat.h"
-#include "utils/array.h"
-#include "utils/builtins.h"
-#include "utils/float.h"
-#include "utils/numeric.h"
-
-#if PG_VERSION_NUM < 120003
-static pg_noinline void
-float_overflow_error(void)
-{
-	ereport(ERROR,
-			(errcode(ERRCODE_NUMERIC_VALUE_OUT_OF_RANGE),
-			 errmsg("value out of range: overflow")));
-}
-
-static pg_noinline void
-float_underflow_error(void)
-{
-	ereport(ERROR,
-			(errcode(ERRCODE_NUMERIC_VALUE_OUT_OF_RANGE),
-			 errmsg("value out of range: underflow")));
-}
-#endif
-
-/*
- * Check if array is a vector
- */
-static void
-CheckArrayIsVector(ArrayType *array)
-{
-	if (ARR_NDIM(array) > 1)
-		ereport(ERROR,
-				(errcode(ERRCODE_DATA_EXCEPTION),
-				 errmsg("array must be 1-D")));
-
-	if (ARR_HASNULL(array) && array_contains_nulls(array))
-		ereport(ERROR,
-				(errcode(ERRCODE_NULL_VALUE_NOT_ALLOWED),
-				 errmsg("array must not contain nulls")));
-}
-
-/*
- * Check if dimensions are the same
- */
-static int
-CheckDims(ArrayType *a, ArrayType *b)
-{
-	int			dima;
-	int			dimb;
-
-	CheckArrayIsVector(a);
-	CheckArrayIsVector(b);
-
-	dima = ARR_DIMS(a)[0];
-	dimb = ARR_DIMS(b)[0];
-
-	if (dima != dimb)
-		ereport(ERROR,
-				(errcode(ERRCODE_DATA_EXCEPTION),
-				 errmsg("different dimensions %d and %d", dima, dimb)));
-
-	return dima;
-}
-
-/*
- * Return the datum representation for a half
- */
-static inline Datum
-HalfGetDatum(half X)
-{
-	union
-	{
-		half		value;
-		int16		retval;
-	}			myunion;
-
-	myunion.value = X;
-	return Int16GetDatum(myunion.retval);
-}
-
-/*
- * Return the half value of a datum
- */
-static inline half
-DatumGetHalf(Datum X)
-{
-	union
-	{
-		int16		value;
-		half		retval;
-	}			myunion;
-
-	myunion.value = DatumGetInt16(X);
-	return myunion.retval;
-}
-
-/*
- * Get a half from a message buffer
- */
-static half
-pq_getmsghalf(StringInfo msg)
-{
-	union
-	{
-		half		h;
-		uint16		i;
-	}			swap;
-
-	swap.i = pq_getmsgint(msg, 2);
-	return swap.h;
-}
-
-/*
- * Append a half to a StringInfo buffer
- */
-static void
-pq_sendhalf(StringInfo buf, half h)
-{
-	union
-	{
-		half		h;
-		uint16		i;
-	}			swap;
-
-	swap.h = h;
-	pq_sendint16(buf, swap.i);
-}
-
-/*
- * Convert a half to a float4
- */
-static float
-HalfToFloat4(half num)
-{
-#ifdef FLT16_SUPPORT
-	return (float) num;
-#else
-	/* TODO Improve performance */
-	/* TODO Check endianness */
-	uint16		bin = *((uint16 *) &num);
-	uint32		exponent = (bin & 0x7C00) >> 10;
-	uint32		mantissa = bin & 0x03FF;
-
-	/* Sign */
-	uint32		result = (bin & 0x8000) << 16;
-
-	if (exponent == 31)
-	{
-		if (mantissa == 0)
-		{
-			/* Infinite */
-			result |= 0x7F800000;
-		}
-		else
-		{
-			/* NaN */
-			result |= 0x7FC00000;
-			result |= mantissa << 13;
-		}
-	}
-	else if (exponent == 0)
-	{
-		/* Subnormal */
-		if (mantissa != 0)
-		{
-			exponent = -14;
-
-			for (int i = 0; i < 10; i++)
-			{
-				mantissa <<= 1;
-				exponent -= 1;
-
-				if ((mantissa >> 10) % 2 == 1)
-				{
-					mantissa &= 0x03ff;
-					break;
-				}
-			}
-
-			result |= (exponent + 127) << 23;
-			result |= mantissa << 13;
-		}
-	}
-	else
-	{
-		/* Normal */
-		result |= (exponent - 15 + 127) << 23;
-		result |= mantissa << 13;
-	}
-
-	return *((float *) &result);
-#endif
-}
-
-/*
- * Convert a float4 to a half
- */
-static half
-Float4ToHalfUnchecked(float num)
-{
-#ifdef FLT16_SUPPORT
-	return (_Float16) num;
-#else
-	/* TODO Improve performance */
-	/* TODO Check endianness */
-	uint32		bin = *((uint32 *) &num);
-	int			exponent = (bin & 0x7F800000) >> 23;
-	int			mantissa = bin & 0x007FFFFF;
-
-	/* Sign */
-	uint16		result = (bin & 0x80000000) >> 16;
-
-	if (isinf(num))
-	{
-		/* Infinite */
-		result |= 0x7C00;
-	}
-	else if (isnan(num))
-	{
-		/* NaN */
-		result |= 0x7E00;
-		result |= mantissa >> 13;
-	}
-	else if (exponent > 98)
-	{
-		int			m;
-		int			gr;
-		int			s;
-
-		exponent -= 127;
-		s = mantissa & 0x00000FFF;
-
-		/* Subnormal */
-		if (exponent < -14)
-		{
-			int			diff = -exponent - 14;
-
-			mantissa >>= diff;
-			mantissa += 1 << (23 - diff);
-			s |= mantissa & 0x00000FFF;
-		}
-
-		m = mantissa >> 13;
-
-		/* Round */
-		gr = (mantissa >> 12) % 4;
-		if (gr == 3 || (gr == 1 && s != 0))
-			m += 1;
-
-		if (m == 1024)
-		{
-			m = 0;
-			exponent += 1;
-		}
-
-		if (exponent > 15)
-		{
-			/* Infinite */
-			result |= 0x7C00;
-		}
-		else
-		{
-			if (exponent >= -14)
-				result |= (exponent + 15) << 10;
-
-			result |= m;
-		}
-	}
-
-	return *((half *) & result);
-#endif
-}
-
-/*
- * Check if half is infinite
- */
-static inline bool
-HalfIsInf(half num)
-{
-#ifdef FLT16_SUPPORT
-	return isinf(num);
-#else
-	return (num << 1) == 0xF800;
-#endif
-}
-
-/*
- * Check if half is zero
- */
-static inline bool
-HalfIsZero(half num)
-{
-#ifdef FLT16_SUPPORT
-	return num == 0;
-#else
-	return (num << 1) == 0x0000;
-#endif
-}
-
-/*
- * Convert a float4 to a half
- */
-static half
-Float4ToHalf(float num)
-{
-	half		result = Float4ToHalfUnchecked(num);
-
-	if (unlikely(HalfIsInf(result)) && !isinf(num))
-		float_overflow_error();
-	if (unlikely(HalfIsZero(result)) && num != 0.0)
-		float_underflow_error();
-
-	return result;
-}
-
-/*
- * Convert a float8 to a half
- */
-static half
-Float8ToHalf(double num)
-{
-	/* TODO Convert directly for greater accuracy */
-	half		result = Float4ToHalfUnchecked((float) num);
-
-	if (unlikely(HalfIsInf(result)) && !isinf(num))
-		float_overflow_error();
-	if (unlikely(HalfIsZero(result)) && num != 0.0)
-		float_underflow_error();
-
-	return result;
-}
-
-/*
- * Convert textual representation to internal representation
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(half_in);
-Datum
-half_in(PG_FUNCTION_ARGS)
-{
-	char	   *num = PG_GETARG_CSTRING(0);
-	char	   *orig_num;
-	float		val;
-	char	   *endptr;
-
-	orig_num = num;
-
-	/* Skip leading whitespace */
-	while (*num != '\0' && isspace((unsigned char) *num))
-		num++;
-
-	/*
-	 * Check for an empty-string input to begin with, to avoid the vagaries of
-	 * strtof() on different platforms.
-	 */
-	if (*num == '\0')
-		ereport(ERROR,
-				(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
-				 errmsg("invalid input syntax for type %s: \"%s\"",
-						"half", orig_num)));
-
-	val = strtof(num, &endptr);
-
-	if (val < -HALF_MAX || val > HALF_MAX)
-		ereport(ERROR,
-				(errcode(ERRCODE_NUMERIC_VALUE_OUT_OF_RANGE),
-				 errmsg("\"%s\" is out of range for type %s",
-						orig_num, "half")));
-
-	/* Skip trailing whitespace */
-	while (*endptr != '\0' && isspace((unsigned char) *endptr))
-		endptr++;
-
-	/* If there is any junk left at the end of the string, bail out */
-	if (*endptr != '\0')
-		ereport(ERROR,
-				(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
-				 errmsg("invalid input syntax for type %s: \"%s\"",
-						"half", orig_num)));
-
-	PG_RETURN_HALF(Float4ToHalf(val));
-}
-
-/*
- * Convert internal representation to textual representation
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(half_out);
-Datum
-half_out(PG_FUNCTION_ARGS)
-{
-	float		num = HalfToFloat4(PG_GETARG_HALF(0));
-	char	   *ascii = (char *) palloc(32);
-	int			ndig = FLT_DIG + extra_float_digits;
-
-	if (extra_float_digits > 0)
-	{
-		float_to_shortest_decimal_buf(num, ascii);
-		PG_RETURN_CSTRING(ascii);
-	}
-
-	(void) pg_strfromd(ascii, 32, ndig, num);
-	PG_RETURN_CSTRING(ascii);
-}
-
-/*
- * Convert external binary representation to internal representation
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(half_recv);
-Datum
-half_recv(PG_FUNCTION_ARGS)
-{
-	StringInfo	buf = (StringInfo) PG_GETARG_POINTER(0);
-
-	PG_RETURN_HALF(pq_getmsghalf(buf));
-}
-
-/*
- * Convert internal representation to the external binary representation
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(half_send);
-Datum
-half_send(PG_FUNCTION_ARGS)
-{
-	half		arg1 = PG_GETARG_HALF(0);
-	StringInfoData buf;
-
-	pq_begintypsend(&buf);
-	pq_sendhalf(&buf, arg1);
-	PG_RETURN_BYTEA_P(pq_endtypsend(&buf));
-}
-
-/*
- * Convert integer to half
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(integer_to_half);
-Datum
-integer_to_half(PG_FUNCTION_ARGS)
-{
-	int32		i = PG_GETARG_INT32(0);
-
-	/* TODO Figure out correct error */
-	float		f = (float) i;
-	half		h = Float4ToHalf(f);
-
-	PG_RETURN_HALF(h);
-}
-
-/*
- * Convert numeric to half
- *
- * TODO Improve error message if out of range
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(numeric_to_half);
-Datum
-numeric_to_half(PG_FUNCTION_ARGS)
-{
-	Numeric		num = PG_GETARG_NUMERIC(0);
-	float		f = DatumGetFloat4(DirectFunctionCall1(numeric_float4, NumericGetDatum(num)));
-	half		h = Float4ToHalf(f);
-
-	PG_RETURN_HALF(h);
-}
-
-/*
- * Convert half to numeric
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(half_to_numeric);
-Datum
-half_to_numeric(PG_FUNCTION_ARGS)
-{
-	half		h = PG_GETARG_HALF(0);
-	float		f = HalfToFloat4(h);
-	Numeric		num = DatumGetNumeric(DirectFunctionCall1(float4_numeric, Float4GetDatum(f)));
-
-	PG_RETURN_NUMERIC(num);
-}
-
-/*
- * Convert float4 to half
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(float4_to_half);
-Datum
-float4_to_half(PG_FUNCTION_ARGS)
-{
-	float		f = PG_GETARG_FLOAT4(0);
-	half		h = Float4ToHalf(f);
-
-	PG_RETURN_HALF(h);
-}
-
-/*
- * Convert half to float4
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(half_to_float4);
-Datum
-half_to_float4(PG_FUNCTION_ARGS)
-{
-	half		h = PG_GETARG_HALF(0);
-	float		f = HalfToFloat4(h);
-
-	PG_RETURN_FLOAT4(f);
-}
-
-/*
- * Convert float8 to half
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(float8_to_half);
-Datum
-float8_to_half(PG_FUNCTION_ARGS)
-{
-	float8		d = PG_GETARG_FLOAT8(0);
-	half		h = Float8ToHalf(d);
-
-	PG_RETURN_HALF(h);
-}
-
-/*
- * Convert half to float8
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(half_to_float8);
-Datum
-half_to_float8(PG_FUNCTION_ARGS)
-{
-	half		h = PG_GETARG_HALF(0);
-	float		f = HalfToFloat4(h);
-
-	PG_RETURN_FLOAT8((double) f);
-}
-
-/*
- * Get the L2 distance between half arrays
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(half_l2_distance);
-Datum
-half_l2_distance(PG_FUNCTION_ARGS)
-{
-	ArrayType  *a = PG_GETARG_ARRAYTYPE_P(0);
-	ArrayType  *b = PG_GETARG_ARRAYTYPE_P(1);
-	half	   *ax = (half *) ARR_DATA_PTR(a);
-	half	   *bx = (half *) ARR_DATA_PTR(b);
-	float		distance = 0.0;
-	int			dim = CheckDims(a, b);
-
-	/* Auto-vectorized */
-	for (int i = 0; i < dim; i++)
-	{
-		float		diff = HalfToFloat4(ax[i]) - HalfToFloat4(bx[i]);
-
-		distance += diff * diff;
-	}
-
-	PG_RETURN_FLOAT8(sqrt((double) distance));
-}
-
-/*
- * Get the L2 squared distance between half arrays
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(half_l2_squared_distance);
-Datum
-half_l2_squared_distance(PG_FUNCTION_ARGS)
-{
-	ArrayType  *a = PG_GETARG_ARRAYTYPE_P(0);
-	ArrayType  *b = PG_GETARG_ARRAYTYPE_P(1);
-	half	   *ax = (half *) ARR_DATA_PTR(a);
-	half	   *bx = (half *) ARR_DATA_PTR(b);
-	float		distance = 0.0;
-	int			dim = CheckDims(a, b);
-
-	/* Auto-vectorized */
-	for (int i = 0; i < dim; i++)
-	{
-		float		diff = HalfToFloat4(ax[i]) - HalfToFloat4(bx[i]);
-
-		distance += diff * diff;
-	}
-
-	PG_RETURN_FLOAT8((double) distance);
-}
-
-/*
- * Get the inner product of two half arrays
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(half_inner_product);
-Datum
-half_inner_product(PG_FUNCTION_ARGS)
-{
-	ArrayType  *a = PG_GETARG_ARRAYTYPE_P(0);
-	ArrayType  *b = PG_GETARG_ARRAYTYPE_P(1);
-	half	   *ax = (half *) ARR_DATA_PTR(a);
-	half	   *bx = (half *) ARR_DATA_PTR(b);
-	float		distance = 0.0;
-	int			dim = CheckDims(a, b);
-
-	/* Auto-vectorized */
-	for (int i = 0; i < dim; i++)
-		distance += HalfToFloat4(ax[i]) * HalfToFloat4(bx[i]);
-
-	PG_RETURN_FLOAT8((double) distance);
-}
-
-/*
- * Get the negative inner product of two half arrays
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(half_negative_inner_product);
-Datum
-half_negative_inner_product(PG_FUNCTION_ARGS)
-{
-	ArrayType  *a = PG_GETARG_ARRAYTYPE_P(0);
-	ArrayType  *b = PG_GETARG_ARRAYTYPE_P(1);
-	half	   *ax = (half *) ARR_DATA_PTR(a);
-	half	   *bx = (half *) ARR_DATA_PTR(b);
-	float		distance = 0.0;
-	int			dim = CheckDims(a, b);
-
-	/* Auto-vectorized */
-	for (int i = 0; i < dim; i++)
-		distance += HalfToFloat4(ax[i]) * HalfToFloat4(bx[i]);
-
-	PG_RETURN_FLOAT8((double) distance * -1);
-}
-
-/*
- * Get the cosine distance between two half arrays
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(half_cosine_distance);
-Datum
-half_cosine_distance(PG_FUNCTION_ARGS)
-{
-	ArrayType  *a = PG_GETARG_ARRAYTYPE_P(0);
-	ArrayType  *b = PG_GETARG_ARRAYTYPE_P(1);
-	half	   *ax = (half *) ARR_DATA_PTR(a);
-	half	   *bx = (half *) ARR_DATA_PTR(b);
-	float		distance = 0.0;
-	float		norma = 0.0;
-	float		normb = 0.0;
-	double		similarity;
-	int			dim = CheckDims(a, b);
-
-	/* Auto-vectorized */
-	for (int i = 0; i < dim; i++)
-	{
-		float		axi = HalfToFloat4(ax[i]);
-		float		bxi = HalfToFloat4(bx[i]);
-
-		distance += axi * bxi;
-		norma += axi * axi;
-		normb += bxi * bxi;
-	}
-
-	/* Use sqrt(a * b) over sqrt(a) * sqrt(b) */
-	similarity = (double) distance / sqrt((double) norma * (double) 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);
-}
-
-/*
- * Get the L1 distance between two half arrays
- */
-PGDLLEXPORT PG_FUNCTION_INFO_V1(half_l1_distance);
-Datum
-half_l1_distance(PG_FUNCTION_ARGS)
-{
-	ArrayType  *a = PG_GETARG_ARRAYTYPE_P(0);
-	ArrayType  *b = PG_GETARG_ARRAYTYPE_P(1);
-	half	   *ax = (half *) ARR_DATA_PTR(a);
-	half	   *bx = (half *) ARR_DATA_PTR(b);
-	float		distance = 0.0;
-	int			dim = CheckDims(a, b);
-
-	/* Auto-vectorized */
-	for (int i = 0; i < dim; i++)
-		distance += fabsf(HalfToFloat4(ax[i]) - HalfToFloat4(bx[i]));
-
-	PG_RETURN_FLOAT8((double) distance);
-}

src/half.h

@@ -1,23 +0,0 @@
-#ifndef HALF_H
-#define HALF_H
-
-#define __STDC_WANT_IEC_60559_TYPES_EXT__
-
-#include <float.h>
-
-#ifdef __FLT16_MAX__
-#define FLT16_SUPPORT
-#endif
-
-#ifdef FLT16_SUPPORT
-#define half _Float16
-#define HALF_MAX FLT16_MAX
-#else
-#define half uint16
-#define HALF_MAX 65504
-#endif
-
-#define PG_GETARG_HALF(n)  DatumGetHalf(PG_GETARG_DATUM(n))
-#define PG_RETURN_HALF(x)  return HalfGetDatum(x)
-
-#endif

src/hnsw.c

@@ -14,15 +14,45 @@
 #endif
 
 int			hnsw_ef_search;
-bool		hnsw_enable_parallel_build;
+int			hnsw_lock_tranche_id;
 static relopt_kind hnsw_relopt_kind;
 
+/*
+ * Assign a tranche ID for our LWLocks. This only needs to be done by one
+ * backend, as the tranche ID is remembered in shared memory.
+ *
+ * This shared memory area is very small, so we just allocate it from the
+ * "slop" that PostgreSQL reserves for small allocations like this. If
+ * this grows bigger, we should use a shmem_request_hook and
+ * RequestAddinShmemSpace() to pre-reserve space for this.
+ */
+static void
+HnswInitLockTranche(void)
+{
+	int		   *tranche_ids;
+	bool		found;
+
+	LWLockAcquire(AddinShmemInitLock, LW_EXCLUSIVE);
+	tranche_ids = ShmemInitStruct("hnsw LWLock ids",
+								  sizeof(int) * 1,
+								  &found);
+	if (!found)
+		tranche_ids[0] = LWLockNewTrancheId();
+	hnsw_lock_tranche_id = tranche_ids[0];
+	LWLockRelease(AddinShmemInitLock);
+
+	/* Per-backend registration of the tranche ID */
+	LWLockRegisterTranche(hnsw_lock_tranche_id, "HnswBuild");
+}
+
 /*
  * Initialize index options and variables
  */
 void
 HnswInit(void)
 {
+	HnswInitLockTranche();
+
 	hnsw_relopt_kind = add_reloption_kind();
 	add_int_reloption(hnsw_relopt_kind, "m", "Max number of connections",
 					  HNSW_DEFAULT_M, HNSW_MIN_M, HNSW_MAX_M
@@ -40,11 +70,6 @@ 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

@@ -8,6 +8,7 @@
 #include "access/reloptions.h"
 #include "nodes/execnodes.h"
 #include "port.h"				/* for random() */
+#include "utils/relptr.h"
 #include "utils/sampling.h"
 #include "vector.h"
 
@@ -72,8 +73,10 @@
 
 #if PG_VERSION_NUM >= 150000
 #define RandomDouble() pg_prng_double(&pg_global_prng_state)
+#define SeedRandom(seed) pg_prng_seed(&pg_global_prng_state, seed)
 #else
 #define RandomDouble() (((double) random()) / MAX_RANDOM_VALUE)
+#define SeedRandom(seed) srandom(seed)
 #endif
 
 #if PG_VERSION_NUM < 130000
@@ -91,32 +94,66 @@
 #define HnswGetMl(m) (1 / log(m))
 
 /* Ensure fits on page and in uint8 */
-#define HnswGetMaxLevel(m) Min(((BLCKSZ - MAXALIGN(SizeOfPageHeaderData) - MAXALIGN(sizeof(HnswPageOpaqueData)) - offsetof(HnswNeighborTupleData, indextids) - sizeof(ItemIdData)) / (sizeof(ItemPointerData)) / m) - 2, 255)
+#define HnswGetMaxLevel(m) Min(((BLCKSZ - MAXALIGN(SizeOfPageHeaderData) - MAXALIGN(sizeof(HnswPageOpaqueData)) - offsetof(HnswNeighborTupleData, indextids) - sizeof(ItemIdData)) / (sizeof(ItemPointerData)) / (m)) - 2, 255)
+
+#define HnswGetValue(base, element) PointerGetDatum(HnswPtrAccess(base, (element)->value))
+
+#if PG_VERSION_NUM < 140005
+#define relptr_offset(rp) ((rp).relptr_off - 1)
+#endif
+
+/* Pointer macros */
+#define HnswPtrAccess(base, hp) ((base) == NULL ? (hp).ptr : relptr_access(base, (hp).relptr))
+#define HnswPtrStore(base, hp, value) ((base) == NULL ? (void) ((hp).ptr = (value)) : (void) relptr_store(base, (hp).relptr, value))
+#define HnswPtrIsNull(base, hp) ((base) == NULL ? (hp).ptr == NULL : relptr_is_null((hp).relptr))
+#define HnswPtrEqual(base, hp1, hp2) ((base) == NULL ? (hp1).ptr == (hp2).ptr : relptr_offset((hp1).relptr) == relptr_offset((hp2).relptr))
+
+/* For code paths dedicated to each type */
+#define HnswPtrPointer(hp) (hp).ptr
+#define HnswPtrOffset(hp) relptr_offset((hp).relptr)
 
 /* Variables */
 extern int	hnsw_ef_search;
-extern bool hnsw_enable_parallel_build;
 
+/* This is initialized when the module is loaded */
+extern int	hnsw_lock_tranche_id;
+
+typedef struct HnswElementData HnswElementData;
 typedef struct HnswNeighborArray HnswNeighborArray;
 
+#define HnswPtrDeclare(type, relptrtype, ptrtype) \
+	relptr_declare(type, relptrtype); \
+	typedef union { type *ptr; relptrtype relptr; } ptrtype;
+
+/* Pointers that can be absolute or relative */
+/* Use char for DatumPtr so works with Pointer */
+HnswPtrDeclare(HnswElementData, HnswElementRelptr, HnswElementPtr);
+HnswPtrDeclare(HnswNeighborArray, HnswNeighborArrayRelptr, HnswNeighborArrayPtr);
+HnswPtrDeclare(HnswNeighborArrayPtr, HnswNeighborsRelptr, HnswNeighborsPtr);
+HnswPtrDeclare(char, DatumRelptr, DatumPtr);
+
 typedef struct HnswElementData
 {
-	List	   *heaptids;
+	HnswElementPtr next;
+	ItemPointerData heaptids[HNSW_HEAPTIDS];
+	uint8		heaptidsLength;
 	uint8		level;
 	uint8		deleted;
-	HnswNeighborArray *neighbors;
+	uint32		hash;
+	HnswNeighborsPtr neighbors;
 	BlockNumber blkno;
 	OffsetNumber offno;
 	OffsetNumber neighborOffno;
 	BlockNumber neighborPage;
-	Datum		value;
+	DatumPtr	value;
+	LWLock		lock;
 }			HnswElementData;
 
 typedef HnswElementData * HnswElement;
 
 typedef struct HnswCandidate
 {
-	HnswElement element;
+	HnswElementPtr element;
 	float		distance;
 	bool		closer;
 }			HnswCandidate;
@@ -125,7 +162,7 @@ typedef struct HnswNeighborArray
 {
 	int			length;
 	bool		closerSet;
-	HnswCandidate *items;
+	HnswCandidate items[FLEXIBLE_ARRAY_MEMBER];
 }			HnswNeighborArray;
 
 typedef struct HnswPairingHeapNode
@@ -142,6 +179,27 @@ typedef struct HnswOptions
 	int			efConstruction; /* size of dynamic candidate list */
 }			HnswOptions;
 
+typedef struct HnswGraph
+{
+	/* Graph state */
+	slock_t		lock;
+	HnswElementPtr head;
+	double		indtuples;
+
+	/* Entry state */
+	LWLock		entryLock;
+	HnswElementPtr entryPoint;
+
+	/* Allocations state */
+	LWLock		allocatorLock;
+	long		memoryUsed;
+	long		memoryTotal;
+
+	/* Flushed state */
+	LWLock		flushLock;
+	bool		flushed;
+}			HnswGraph;
+
 typedef struct HnswSpool
 {
 	Relation	heap;
@@ -155,6 +213,7 @@ typedef struct HnswShared
 	Oid			indexrelid;
 	bool		isconcurrent;
 	int			scantuplesortstates;
+	dsa_pointer dsaptr;
 
 	/* Worker progress */
 	ConditionVariable workersdonecv;
@@ -165,7 +224,7 @@ typedef struct HnswShared
 	/* Mutable state */
 	int			nparticipantsdone;
 	double		reltuples;
-	double		indtuples;
+	HnswGraph	graphData;
 
 #if PG_VERSION_NUM < 120000
 	ParallelHeapScanDescData heapdesc;	/* must come last */
@@ -183,8 +242,15 @@ typedef struct HnswLeader
 	int			nparticipanttuplesorts;
 	HnswShared *hnswshared;
 	Snapshot	snapshot;
+	char	   *hnswarea;
 }			HnswLeader;
 
+typedef struct HnswAllocator
+{
+	void	   *(*alloc) (Size size, void *state);
+	void	   *state;
+}			HnswAllocator;
+
 typedef struct HnswBuildState
 {
 	/* Info */
@@ -208,20 +274,21 @@ typedef struct HnswBuildState
 	Oid			collation;
 
 	/* Variables */
-	List	   *elements;
-	HnswElement entryPoint;
+	HnswGraph	graphData;
+	HnswGraph  *graph;
 	double		ml;
 	int			maxLevel;
-	long		memoryLeft;
-	bool		flushed;
 	Vector	   *normvec;
 
 	/* Memory */
+	MemoryContext graphCtx;
 	MemoryContext tmpCtx;
+	HnswAllocator allocator;
 
 	/* Parallel builds */
 	HnswLeader *hnswleader;
 	HnswShared *hnswshared;
+	char	   *hnswarea;
 }			HnswBuildState;
 
 typedef struct HnswMetaPageData
@@ -303,7 +370,7 @@ typedef struct HnswVacuumState
 	Oid			collation;
 
 	/* Variables */
-	HTAB	   *deleted;
+	struct tidhash_hash *deleted;
 	BufferAccessStrategy bas;
 	HnswNeighborTuple ntup;
 	HnswElementData highestPoint;
@@ -317,30 +384,27 @@ int			HnswGetM(Relation index);
 int			HnswGetEfConstruction(Relation index);
 FmgrInfo   *HnswOptionalProcInfo(Relation index, uint16 procnum);
 bool		HnswNormValue(FmgrInfo *procinfo, Oid collation, Datum *value, Vector * result);
-void		HnswCommitBuffer(Buffer buf, GenericXLogState *state);
 Buffer		HnswNewBuffer(Relation index, ForkNumber forkNum);
 void		HnswInitPage(Buffer buf, Page page);
-void		HnswInitRegisterPage(Relation index, Buffer *buf, Page *page, GenericXLogState **state);
 void		HnswInit(void);
-List	   *HnswSearchLayer(Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool inserting, HnswElement skipElement);
+List	   *HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool inserting, HnswElement skipElement);
 HnswElement HnswGetEntryPoint(Relation index);
 void		HnswGetMetaPageInfo(Relation index, int *m, HnswElement * entryPoint);
-HnswElement HnswInitElement(ItemPointer tid, int m, double ml, int maxLevel);
-void		HnswFreeElement(HnswElement element);
+void	   *HnswAlloc(HnswAllocator * allocator, Size size);
+HnswElement HnswInitElement(char *base, ItemPointer tid, int m, double ml, int maxLevel, HnswAllocator * alloc);
 HnswElement HnswInitElementFromBlock(BlockNumber blkno, OffsetNumber offno);
-void		HnswInsertElement(HnswElement element, HnswElement entryPoint, Relation index, FmgrInfo *procinfo, Oid collation, int m, int efConstruction, bool existing);
-HnswElement HnswFindDuplicate(HnswElement e);
-HnswCandidate *HnswEntryCandidate(HnswElement em, Datum q, Relation rel, FmgrInfo *procinfo, Oid collation, bool loadVec);
-void		HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, BlockNumber insertPage, ForkNumber forkNum);
-void		HnswSetNeighborTuple(HnswNeighborTuple ntup, HnswElement e, int m);
+void		HnswInsertElement(char *base, HnswElement element, HnswElement entryPoint, Relation index, FmgrInfo *procinfo, Oid collation, int m, int efConstruction, bool existing);
+HnswCandidate *HnswEntryCandidate(char *base, HnswElement em, Datum q, Relation rel, FmgrInfo *procinfo, Oid collation, bool loadVec);
+void		HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, BlockNumber insertPage, ForkNumber forkNum, bool building);
+void		HnswSetNeighborTuple(char *base, HnswNeighborTuple ntup, HnswElement e, int m);
 void		HnswAddHeapTid(HnswElement element, ItemPointer heaptid);
-void		HnswInitNeighbors(HnswElement element, int m);
-bool		HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid, Relation heapRel);
-void		HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement e, int m, bool checkExisting);
+void		HnswInitNeighbors(char *base, HnswElement element, int m, HnswAllocator * alloc);
+bool		HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull, ItemPointer heap_tid, Relation heapRel, bool building);
+void		HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement e, int m, bool checkExisting, bool building);
 void		HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHeaptids, bool loadVec);
 void		HnswLoadElement(HnswElement element, float *distance, Datum *q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec);
-void		HnswSetElementTuple(HnswElementTuple etup, HnswElement element);
-void		HnswUpdateConnection(HnswElement element, HnswCandidate * hc, int m, int lc, int *updateIdx, Relation index, FmgrInfo *procinfo, Oid collation);
+void		HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element);
+void		HnswUpdateConnection(char *base, HnswElement element, HnswCandidate * hc, int 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);
 
@@ -360,4 +424,54 @@ void		hnswrescan(IndexScanDesc scan, ScanKey keys, int nkeys, ScanKey orderbys,
 bool		hnswgettuple(IndexScanDesc scan, ScanDirection dir);
 void		hnswendscan(IndexScanDesc scan);
 
+static inline HnswNeighborArray *
+HnswGetNeighbors(char *base, HnswElement element, int lc)
+{
+	HnswNeighborArrayPtr *neighborList = HnswPtrAccess(base, element->neighbors);
+
+	Assert(element->level >= lc);
+
+	return HnswPtrAccess(base, neighborList[lc]);
+}
+
+/* Hash tables */
+typedef struct TidHashEntry
+{
+	ItemPointerData tid;
+	char		status;
+}			TidHashEntry;
+
+#define SH_PREFIX tidhash
+#define SH_ELEMENT_TYPE TidHashEntry
+#define SH_KEY_TYPE ItemPointerData
+#define SH_SCOPE extern
+#define SH_DECLARE
+#include "lib/simplehash.h"
+
+typedef struct PointerHashEntry
+{
+	uintptr_t	ptr;
+	char		status;
+}			PointerHashEntry;
+
+#define SH_PREFIX pointerhash
+#define SH_ELEMENT_TYPE PointerHashEntry
+#define SH_KEY_TYPE uintptr_t
+#define SH_SCOPE extern
+#define SH_DECLARE
+#include "lib/simplehash.h"
+
+typedef struct OffsetHashEntry
+{
+	Size		offset;
+	char		status;
+}			OffsetHashEntry;
+
+#define SH_PREFIX offsethash
+#define SH_ELEMENT_TYPE OffsetHashEntry
+#define SH_KEY_TYPE Size
+#define SH_SCOPE extern
+#define SH_DECLARE
+#include "lib/simplehash.h"
+
 #endif

src/hnswbuild.c

@@ -54,7 +54,12 @@
 #endif
 
 #define PARALLEL_KEY_HNSW_SHARED		UINT64CONST(0xA000000000000001)
-#define PARALLEL_KEY_QUERY_TEXT			UINT64CONST(0xA000000000000002)
+#define PARALLEL_KEY_HNSW_AREA			UINT64CONST(0xA000000000000002)
+#define PARALLEL_KEY_QUERY_TEXT			UINT64CONST(0xA000000000000003)
+
+#if PG_VERSION_NUM < 130000
+#define GENERATIONCHUNK_RAWSIZE (SIZEOF_SIZE_T + SIZEOF_VOID_P * 2)
+#endif
 
 /*
  * Create the metapage
@@ -66,11 +71,11 @@ CreateMetaPage(HnswBuildState * buildstate)
 	ForkNumber	forkNum = buildstate->forkNum;
 	Buffer		buf;
 	Page		page;
-	GenericXLogState *state;
 	HnswMetaPage metap;
 
 	buf = HnswNewBuffer(index, forkNum);
-	HnswInitRegisterPage(index, &buf, &page, &state);
+	page = BufferGetPage(buf);
+	HnswInitPage(buf, page);
 
 	/* Set metapage data */
 	metap = HnswPageGetMeta(page);
@@ -86,14 +91,15 @@ CreateMetaPage(HnswBuildState * buildstate)
 	((PageHeader) page)->pd_lower =
 		((char *) metap + sizeof(HnswMetaPageData)) - (char *) page;
 
-	HnswCommitBuffer(buf, state);
+	MarkBufferDirty(buf);
+	UnlockReleaseBuffer(buf);
 }
 
 /*
  * Add a new page
  */
 static void
-HnswBuildAppendPage(Relation index, Buffer *buf, Page *page, GenericXLogState **state, ForkNumber forkNum)
+HnswBuildAppendPage(Relation index, Buffer *buf, Page *page, ForkNumber forkNum)
 {
 	/* Add a new page */
 	Buffer		newbuf = HnswNewBuffer(index, forkNum);
@@ -102,7 +108,7 @@ HnswBuildAppendPage(Relation index, Buffer *buf, Page *page, GenericXLogState **
 	HnswPageGetOpaque(*page)->nextblkno = BufferGetBlockNumber(newbuf);
 
 	/* Commit */
-	GenericXLogFinish(*state);
+	MarkBufferDirty(*buf);
 	UnlockReleaseBuffer(*buf);
 
 	/* Can take a while, so ensure we can interrupt */
@@ -113,8 +119,7 @@ HnswBuildAppendPage(Relation index, Buffer *buf, Page *page, GenericXLogState **
 
 	/* Prepare new page */
 	*buf = newbuf;
-	*state = GenericXLogStart(index);
-	*page = GenericXLogRegisterBuffer(*state, *buf, GENERIC_XLOG_FULL_IMAGE);
+	*page = BufferGetPage(*buf);
 	HnswInitPage(*buf, *page);
 }
 
@@ -131,10 +136,11 @@ CreateElementPages(HnswBuildState * buildstate)
 	HnswElementTuple etup;
 	HnswNeighborTuple ntup;
 	BlockNumber insertPage;
+	HnswElement entryPoint;
 	Buffer		buf;
 	Page		page;
-	GenericXLogState *state;
-	ListCell   *lc;
+	HnswElementPtr iter = buildstate->graph->head;
+	char	   *base = buildstate->hnswarea;
 
 	/* Calculate sizes */
 	etupAllocSize = BLCKSZ;
@@ -146,22 +152,25 @@ CreateElementPages(HnswBuildState * buildstate)
 
 	/* Prepare first page */
 	buf = HnswNewBuffer(index, forkNum);
-	state = GenericXLogStart(index);
-	page = GenericXLogRegisterBuffer(state, buf, GENERIC_XLOG_FULL_IMAGE);
+	page = BufferGetPage(buf);
 	HnswInitPage(buf, page);
 
-	foreach(lc, buildstate->elements)
+	while (!HnswPtrIsNull(base, iter))
 	{
-		HnswElement element = lfirst(lc);
+		HnswElement element = HnswPtrAccess(base, iter);
 		Size		etupSize;
 		Size		ntupSize;
 		Size		combinedSize;
+		void	   *valuePtr = HnswPtrAccess(base, element->value);
+
+		/* Update iterator */
+		iter = element->next;
 
 		/* Zero memory for each element */
 		MemSet(etup, 0, etupAllocSize);
 
 		/* Calculate sizes */
-		etupSize = HNSW_ELEMENT_TUPLE_SIZE(VARSIZE_ANY(DatumGetPointer(element->value)));
+		etupSize = HNSW_ELEMENT_TUPLE_SIZE(VARSIZE_ANY(valuePtr));
 		ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(element->level, buildstate->m);
 		combinedSize = etupSize + ntupSize + sizeof(ItemIdData);
 
@@ -169,11 +178,11 @@ CreateElementPages(HnswBuildState * buildstate)
 		if (etupSize > etupAllocSize)
 			elog(ERROR, "index tuple too large");
 
-		HnswSetElementTuple(etup, element);
+		HnswSetElementTuple(base, 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, &state, forkNum);
+			HnswBuildAppendPage(index, &buf, &page, forkNum);
 
 		/* Calculate offsets */
 		element->blkno = BufferGetBlockNumber(buf);
@@ -197,7 +206,7 @@ CreateElementPages(HnswBuildState * buildstate)
 
 		/* Add new page if needed */
 		if (PageGetFreeSpace(page) < ntupSize)
-			HnswBuildAppendPage(index, &buf, &page, &state, forkNum);
+			HnswBuildAppendPage(index, &buf, &page, forkNum);
 
 		/* Add placeholder for neighbors */
 		if (PageAddItem(page, (Item) ntup, ntupSize, InvalidOffsetNumber, false, false) != element->neighborOffno)
@@ -207,10 +216,11 @@ CreateElementPages(HnswBuildState * buildstate)
 	insertPage = BufferGetBlockNumber(buf);
 
 	/* Commit */
-	GenericXLogFinish(state);
+	MarkBufferDirty(buf);
 	UnlockReleaseBuffer(buf);
 
-	HnswUpdateMetaPage(index, HNSW_UPDATE_ENTRY_ALWAYS, buildstate->entryPoint, insertPage, forkNum);
+	entryPoint = HnswPtrAccess(base, buildstate->graph->entryPoint);
+	HnswUpdateMetaPage(index, HNSW_UPDATE_ENTRY_ALWAYS, entryPoint, insertPage, forkNum, true);
 
 	pfree(etup);
 	pfree(ntup);
@@ -225,82 +235,191 @@ CreateNeighborPages(HnswBuildState * buildstate)
 	Relation	index = buildstate->index;
 	ForkNumber	forkNum = buildstate->forkNum;
 	int			m = buildstate->m;
-	ListCell   *lc;
+	HnswElementPtr iter = buildstate->graph->head;
+	char	   *base = buildstate->hnswarea;
 	HnswNeighborTuple ntup;
 
 	/* Allocate once */
 	ntup = palloc0(BLCKSZ);
 
-	foreach(lc, buildstate->elements)
+	while (!HnswPtrIsNull(base, iter))
 	{
-		HnswElement e = lfirst(lc);
+		HnswElement e = HnswPtrAccess(base, iter);
 		Buffer		buf;
 		Page		page;
-		GenericXLogState *state;
 		Size		ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(e->level, m);
 
+		/* Update iterator */
+		iter = e->next;
+
 		/* Can take a while, so ensure we can interrupt */
 		/* Needs to be called when no buffer locks are held */
 		CHECK_FOR_INTERRUPTS();
 
 		buf = ReadBufferExtended(index, forkNum, e->neighborPage, RBM_NORMAL, NULL);
 		LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
-		state = GenericXLogStart(index);
-		page = GenericXLogRegisterBuffer(state, buf, 0);
+		page = BufferGetPage(buf);
 
-		HnswSetNeighborTuple(ntup, e, m);
+		HnswSetNeighborTuple(base, ntup, e, m);
 
 		if (!PageIndexTupleOverwrite(page, e->neighborOffno, (Item) ntup, ntupSize))
 			elog(ERROR, "failed to add index item to \"%s\"", RelationGetRelationName(index));
 
 		/* Commit */
-		GenericXLogFinish(state);
+		MarkBufferDirty(buf);
 		UnlockReleaseBuffer(buf);
 	}
 
 	pfree(ntup);
 }
 
-/*
- * Free elements
- */
-static void
-FreeElements(HnswBuildState * buildstate)
-{
-	ListCell   *lc;
-
-	foreach(lc, buildstate->elements)
-		HnswFreeElement(lfirst(lc));
-
-	list_free(buildstate->elements);
-}
-
 /*
  * Flush pages
  */
 static void
 FlushPages(HnswBuildState * buildstate)
 {
+#ifdef HNSW_MEMORY
+	elog(INFO, "memory: %zu MB", buildstate->graph->memoryUsed / (1024 * 1024));
+#endif
+
 	CreateMetaPage(buildstate);
 	CreateElementPages(buildstate);
 	CreateNeighborPages(buildstate);
 
-	buildstate->flushed = true;
-	FreeElements(buildstate);
+	buildstate->graph->flushed = true;
+	MemoryContextReset(buildstate->graphCtx);
+}
+
+/*
+ * Add a heap TID to an existing element
+ */
+static bool
+HnswAddDuplicateInMemory(HnswElement element, HnswElement dup)
+{
+	LWLockAcquire(&dup->lock, LW_EXCLUSIVE);
+
+	if (dup->heaptidsLength == HNSW_HEAPTIDS)
+	{
+		LWLockRelease(&dup->lock);
+		return false;
+	}
+
+	HnswAddHeapTid(dup, &element->heaptids[0]);
+
+	LWLockRelease(&dup->lock);
+
+	return true;
+}
+
+/*
+ * Find duplicate element
+ */
+static bool
+HnswFindDuplicateInMemory(char *base, HnswElement element)
+{
+	HnswNeighborArray *neighbors = HnswGetNeighbors(base, element, 0);
+
+	for (int i = 0; i < neighbors->length; i++)
+	{
+		HnswCandidate *neighbor = &neighbors->items[i];
+		HnswElement neighborElement = HnswPtrAccess(base, neighbor->element);
+		Datum		value = HnswGetValue(base, element);
+		Datum		neighborValue = HnswGetValue(base, neighborElement);
+
+		/* Exit early since ordered by distance */
+		if (!datumIsEqual(value, neighborValue, false, -1))
+			return false;
+
+		/* Check for space */
+		if (HnswAddDuplicateInMemory(element, neighborElement))
+			return true;
+	}
+
+	return false;
+}
+
+/*
+ * Add to element and neighbor pages
+ */
+static void
+WriteNewElementPagesInMemory(char *base, HnswGraph * graph, HnswElement element)
+{
+	SpinLockAcquire(&graph->lock);
+	element->next = graph->head;
+	HnswPtrStore(base, graph->head, element);
+	SpinLockRelease(&graph->lock);
+}
+
+/*
+ * Update neighbors
+ */
+static void
+HnswUpdateNeighborPagesInMemory(char *base, FmgrInfo *procinfo, Oid collation, HnswElement e, int m)
+{
+	for (int lc = e->level; lc >= 0; lc--)
+	{
+		int			lm = HnswGetLayerM(m, lc);
+		HnswNeighborArray *neighbors = HnswGetNeighbors(base, e, lc);
+
+		for (int i = 0; i < neighbors->length; i++)
+		{
+			HnswCandidate *hc = &neighbors->items[i];
+			HnswElement neighborElement = HnswPtrAccess(base, hc->element);
+
+			/* Keep scan-build happy on Mac x86-64 */
+			Assert(neighborElement);
+
+			/* Use element for lock instead of hc since hc can be replaced */
+			LWLockAcquire(&neighborElement->lock, LW_EXCLUSIVE);
+			HnswUpdateConnection(base, e, hc, lm, lc, NULL, NULL, procinfo, collation);
+			LWLockRelease(&neighborElement->lock);
+		}
+	}
+}
+
+/*
+ * Write changes in memory
+ */
+static void
+WriteElementInMemory(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement element, int m, int efConstruction, HnswElement entryPoint, HnswBuildState * buildstate, HnswGraph * graph, bool updateEntryPoint)
+{
+	char	   *base = buildstate->hnswarea;
+
+	/* Try to add to existing page */
+	if (HnswFindDuplicateInMemory(base, element))
+		return;
+
+	/* Write element and neighbor tuples */
+	WriteNewElementPagesInMemory(base, graph, element);
+
+	/* Update neighbors */
+	HnswUpdateNeighborPagesInMemory(base, procinfo, collation, element, m);
+
+	/* Update entry point if needed (already have lock) */
+	if (updateEntryPoint)
+		HnswPtrStore(base, graph->entryPoint, element);
 }
 
 /*
  * Insert tuple
  */
 static bool
-InsertTuple(Relation index, Datum *values, HnswElement element, HnswBuildState * buildstate, HnswElement * dup, MemoryContext outerCtx)
+InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, HnswBuildState * buildstate)
 {
 	FmgrInfo   *procinfo = buildstate->procinfo;
 	Oid			collation = buildstate->collation;
-	HnswElement entryPoint = buildstate->entryPoint;
+	HnswGraph  *graph = buildstate->graph;
+	HnswElement entryPoint;
 	int			efConstruction = buildstate->efConstruction;
 	int			m = buildstate->m;
-	MemoryContext oldCtx;
+	HnswElement element;
+	HnswAllocator *allocator = &buildstate->allocator;
+	Size		valueSize;
+	Pointer		valuePtr;
+	bool		updateEntryPoint;
+	LWLock	   *flushLock = &graph->flushLock;
+	char	   *base = buildstate->hnswarea;
 
 	/* Detoast once for all calls */
 	Datum		value = PointerGetDatum(PG_DETOAST_DATUM(values[0]));
@@ -312,52 +431,82 @@ InsertTuple(Relation index, Datum *values, HnswElement element, HnswBuildState *
 			return false;
 	}
 
-	/* Copy value to element so accessible outside of memory context */
-	oldCtx = MemoryContextSwitchTo(outerCtx);
-	element->value = datumCopy(value, false, -1);
-	MemoryContextSwitchTo(oldCtx);
+	/* Get datum size */
+	valueSize = VARSIZE_ANY(DatumGetPointer(value));
+
+	/* Ensure graph not flushed when inserting */
+	LWLockAcquire(flushLock, LW_SHARED);
+
+	if (graph->flushed)
+	{
+		LWLockRelease(flushLock);
+
+		return HnswInsertTupleOnDisk(index, value, values, isnull, heaptid, buildstate->heap, true);
+	}
+
+	/* Get lock for allocator */
+	LWLockAcquire(&graph->allocatorLock, LW_EXCLUSIVE);
+
+	/* Flush pages if needed */
+	if (graph->memoryUsed >= graph->memoryTotal)
+	{
+		LWLockRelease(&graph->allocatorLock);
+
+		LWLockRelease(flushLock);
+		LWLockAcquire(flushLock, LW_EXCLUSIVE);
+
+		if (!graph->flushed)
+		{
+			ereport(NOTICE,
+					(errmsg("hnsw graph no longer fits into maintenance_work_mem after " INT64_FORMAT " tuples", (int64) graph->indtuples),
+					 errdetail("Building will take significantly more time."),
+					 errhint("Increase maintenance_work_mem to speed up builds.")));
+
+			FlushPages(buildstate);
+		}
+
+		LWLockRelease(flushLock);
+
+		return HnswInsertTupleOnDisk(index, value, values, isnull, heaptid, buildstate->heap, true);
+	}
+
+	/* Create an element */
+	element = HnswInitElement(base, heaptid, buildstate->m, buildstate->ml, buildstate->maxLevel, allocator);
+	valuePtr = HnswAlloc(allocator, valueSize);
+
+	/* Release allocator lock */
+	LWLockRelease(&graph->allocatorLock);
+
+	/* Copy datum */
+	memcpy(valuePtr, DatumGetPointer(value), valueSize);
+	HnswPtrStore(base, element->value, valuePtr);
+
+	/* Create element lock */
+	LWLockInitialize(&element->lock, hnsw_lock_tranche_id);
+
+	/* Get entry point */
+	LWLockAcquire(&graph->entryLock, LW_EXCLUSIVE);
+	entryPoint = HnswPtrAccess(base, graph->entryPoint);
+	updateEntryPoint = entryPoint == NULL || element->level > entryPoint->level;
+
+	/* Release lock if not updating entry point */
+	if (!updateEntryPoint)
+		LWLockRelease(&graph->entryLock);
 
 	/* Insert element in graph */
-	HnswInsertElement(element, entryPoint, NULL, procinfo, collation, m, efConstruction, false);
+	HnswInsertElement(base, element, entryPoint, NULL, procinfo, collation, m, efConstruction, false);
 
-	/* Look for duplicate */
-	*dup = HnswFindDuplicate(element);
+	/* Write to memory */
+	WriteElementInMemory(index, procinfo, collation, element, m, efConstruction, entryPoint, buildstate, graph, updateEntryPoint);
 
-	/* Update neighbors if needed */
-	if (*dup == NULL)
-	{
-		for (int lc = element->level; lc >= 0; lc--)
-		{
-			int			lm = HnswGetLayerM(m, lc);
-			HnswNeighborArray *neighbors = &element->neighbors[lc];
+	/* Release lock if needed */
+	if (updateEntryPoint)
+		LWLockRelease(&graph->entryLock);
 
-			for (int i = 0; i < neighbors->length; i++)
-				HnswUpdateConnection(element, &neighbors->items[i], lm, lc, NULL, NULL, procinfo, collation);
-		}
-	}
+	/* Release flush lock */
+	LWLockRelease(flushLock);
 
-	/* Update entry point if needed */
-	if (*dup == NULL && (entryPoint == NULL || element->level > entryPoint->level))
-		buildstate->entryPoint = element;
-
-	UpdateProgress(PROGRESS_CREATEIDX_TUPLES_DONE, ++buildstate->indtuples);
-
-	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;
+	return true;
 }
 
 /*
@@ -368,10 +517,8 @@ BuildCallback(Relation index, CALLBACK_ITEM_POINTER, Datum *values,
 			  bool *isnull, bool tupleIsAlive, void *state)
 {
 	HnswBuildState *buildstate = (HnswBuildState *) state;
+	HnswGraph  *graph = buildstate->graph;
 	MemoryContext oldCtx;
-	HnswElement element;
-	HnswElement dup = NULL;
-	bool		inserted;
 
 #if PG_VERSION_NUM < 130000
 	ItemPointer tid = &hup->t_self;
@@ -381,69 +528,80 @@ BuildCallback(Relation index, CALLBACK_ITEM_POINTER, Datum *values,
 	if (isnull[0])
 		return;
 
-	if (buildstate->memoryLeft <= 0)
-	{
-		if (!buildstate->flushed)
-		{
-			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."),
-					 errhint("Increase maintenance_work_mem to speed up builds.")));
-
-			FlushPages(buildstate);
-		}
-
-		oldCtx = MemoryContextSwitchTo(buildstate->tmpCtx);
-
-		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);
-		MemoryContextReset(buildstate->tmpCtx);
-
-		return;
-	}
-
-	/* Allocate necessary memory outside of memory context */
-	element = HnswInitElement(tid, buildstate->m, buildstate->ml, buildstate->maxLevel);
-
-	/* Use memory context since detoast can allocate */
+	/* Use memory context */
 	oldCtx = MemoryContextSwitchTo(buildstate->tmpCtx);
 
 	/* Insert tuple */
-	inserted = InsertTuple(index, values, element, buildstate, &dup, oldCtx);
+	if (InsertTuple(index, values, isnull, tid, buildstate))
+	{
+		/* Update progress */
+		SpinLockAcquire(&graph->lock);
+		UpdateProgress(PROGRESS_CREATEIDX_TUPLES_DONE, ++graph->indtuples);
+		SpinLockRelease(&graph->lock);
+	}
 
 	/* Reset memory context */
 	MemoryContextSwitchTo(oldCtx);
 	MemoryContextReset(buildstate->tmpCtx);
+}
 
-	/* Add outside memory context */
-	if (dup != NULL)
-	{
-		HnswAddHeapTid(dup, tid);
-		buildstate->memoryLeft -= sizeof(ItemPointerData);
-	}
+/*
+ * Initialize the graph
+ */
+static void
+InitGraph(HnswGraph * graph, char *base, long memoryTotal)
+{
+	HnswPtrStore(base, graph->head, (HnswElement) NULL);
+	HnswPtrStore(base, graph->entryPoint, (HnswElement) NULL);
+	graph->memoryUsed = 0;
+	graph->memoryTotal = memoryTotal;
+	graph->flushed = false;
+	graph->indtuples = 0;
+	SpinLockInit(&graph->lock);
+	LWLockInitialize(&graph->entryLock, hnsw_lock_tranche_id);
+	LWLockInitialize(&graph->allocatorLock, hnsw_lock_tranche_id);
+	LWLockInitialize(&graph->flushLock, hnsw_lock_tranche_id);
+}
 
-	/* Add to buildstate or free */
-	if (inserted)
-	{
-		buildstate->elements = lappend(buildstate->elements, element);
-		buildstate->memoryLeft -= HnswElementMemory(element, buildstate->m);
-	}
-	else
-		HnswFreeElement(element);
+/*
+ * Initialize an allocator
+ */
+static void
+InitAllocator(HnswAllocator * allocator, void *(*alloc) (Size size, void *state), void *state)
+{
+	allocator->alloc = alloc;
+	allocator->state = state;
+}
+
+/*
+ * Memory context allocator
+ */
+static void *
+HnswMemoryContextAlloc(Size size, void *state)
+{
+	HnswBuildState *buildstate = (HnswBuildState *) state;
+	void	   *chunk = MemoryContextAlloc(buildstate->graphCtx, size);
+
+#if PG_VERSION_NUM >= 130000
+	buildstate->graphData.memoryUsed = MemoryContextMemAllocated(buildstate->graphCtx, false);
+#else
+	buildstate->graphData.memoryUsed += MAXALIGN(size);
+#endif
+
+	return chunk;
+}
+
+/*
+ * Shared memory allocator
+ */
+static void *
+HnswSharedMemoryAlloc(Size size, void *state)
+{
+	HnswBuildState *buildstate = (HnswBuildState *) state;
+	void	   *chunk = buildstate->hnswarea + buildstate->graph->memoryUsed;
+
+	buildstate->graph->memoryUsed += MAXALIGN(size);
+	return chunk;
 }
 
 /*
@@ -479,22 +637,29 @@ InitBuildState(HnswBuildState * buildstate, Relation heap, Relation index, Index
 	buildstate->normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
 	buildstate->collation = index->rd_indcollation[0];
 
-	buildstate->elements = NIL;
-	buildstate->entryPoint = NULL;
+	InitGraph(&buildstate->graphData, NULL, maintenance_work_mem * 1024L);
+	buildstate->graph = &buildstate->graphData;
 	buildstate->ml = HnswGetMl(buildstate->m);
 	buildstate->maxLevel = HnswGetMaxLevel(buildstate->m);
-	buildstate->memoryLeft = maintenance_work_mem * 1024L;
-	buildstate->flushed = false;
 
 	/* Reuse for each tuple */
 	buildstate->normvec = InitVector(buildstate->dimensions);
 
+	buildstate->graphCtx = GenerationContextCreate(CurrentMemoryContext,
+												   "Hnsw build graph context",
+#if PG_VERSION_NUM >= 150000
+												   1024 * 1024, 1024 * 1024,
+#endif
+												   1024 * 1024);
 	buildstate->tmpCtx = AllocSetContextCreate(CurrentMemoryContext,
 											   "Hnsw build temporary context",
 											   ALLOCSET_DEFAULT_SIZES);
 
+	InitAllocator(&buildstate->allocator, &HnswMemoryContextAlloc, buildstate);
+
 	buildstate->hnswleader = NULL;
 	buildstate->hnswshared = NULL;
+	buildstate->hnswarea = NULL;
 }
 
 /*
@@ -504,6 +669,7 @@ static void
 FreeBuildState(HnswBuildState * buildstate)
 {
 	pfree(buildstate->normvec);
+	MemoryContextDelete(buildstate->graphCtx);
 	MemoryContextDelete(buildstate->tmpCtx);
 }
 
@@ -523,7 +689,8 @@ ParallelHeapScan(HnswBuildState * buildstate)
 		SpinLockAcquire(&hnswshared->mutex);
 		if (hnswshared->nparticipantsdone == nparticipanttuplesorts)
 		{
-			buildstate->indtuples = hnswshared->indtuples;
+			buildstate->graph = &hnswshared->graphData;
+			buildstate->hnswarea = buildstate->hnswleader->hnswarea;
 			reltuples = hnswshared->reltuples;
 			SpinLockRelease(&hnswshared->mutex);
 			break;
@@ -543,7 +710,7 @@ ParallelHeapScan(HnswBuildState * buildstate)
  * Perform a worker's portion of a parallel insert
  */
 static void
-HnswParallelScanAndInsert(HnswSpool * hnswspool, HnswShared * hnswshared, bool progress)
+HnswParallelScanAndInsert(HnswSpool * hnswspool, HnswShared * hnswshared, char *hnswarea, bool progress)
 {
 	HnswBuildState buildstate;
 #if PG_VERSION_NUM >= 120000
@@ -558,10 +725,9 @@ HnswParallelScanAndInsert(HnswSpool * hnswspool, HnswShared * hnswshared, bool p
 	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;
+	buildstate.graph = &hnswshared->graphData;
+	buildstate.hnswarea = hnswarea;
+	InitAllocator(&buildstate.allocator, &HnswSharedMemoryAlloc, &buildstate);
 #if PG_VERSION_NUM >= 120000
 	scan = table_beginscan_parallel(hnswspool->heap,
 									ParallelTableScanFromHnswShared(hnswshared));
@@ -602,6 +768,9 @@ HnswParallelBuildMain(dsm_segment *seg, shm_toc *toc)
 	char	   *sharedquery;
 	HnswSpool  *hnswspool;
 	HnswShared *hnswshared;
+	dsa_area   *dsa;
+	void	   *dsaspace;
+	char	   *hnswarea;
 	Relation	heapRel;
 	Relation	indexRel;
 	LOCKMODE	heapLockmode;
@@ -642,8 +811,12 @@ HnswParallelBuildMain(dsm_segment *seg, shm_toc *toc)
 	hnswspool->heap = heapRel;
 	hnswspool->index = indexRel;
 
+	dsaspace = shm_toc_lookup(toc, PARALLEL_KEY_HNSW_AREA, false);
+	dsa = dsa_attach_in_place(dsaspace, seg);
+	hnswarea = dsa_get_address(dsa, hnswshared->dsaptr);
+
 	/* Perform inserts */
-	HnswParallelScanAndInsert(hnswspool, hnswshared, false);
+	HnswParallelScanAndInsert(hnswspool, hnswshared, hnswarea, false);
 
 	/* Close relations within worker */
 	index_close(indexRel, indexLockmode);
@@ -706,7 +879,7 @@ HnswLeaderParticipateAsWorker(HnswBuildState * buildstate)
 	leaderworker->index = buildstate->index;
 
 	/* Perform work common to all participants */
-	HnswParallelScanAndInsert(leaderworker, hnswleader->hnswshared, true);
+	HnswParallelScanAndInsert(leaderworker, hnswleader->hnswshared, hnswleader->hnswarea, true);
 }
 
 /*
@@ -719,7 +892,12 @@ HnswBeginParallel(HnswBuildState * buildstate, bool isconcurrent, int request)
 	int			scantuplesortstates;
 	Snapshot	snapshot;
 	Size		esthnswshared;
+	Size		esthnswarea;
+	Size		estdsaspace;
 	HnswShared *hnswshared;
+	void	   *dsaspace;
+	dsa_area   *dsa;
+	char	   *hnswarea;
 	HnswLeader *hnswleader = (HnswLeader *) palloc0(sizeof(HnswLeader));
 	bool		leaderparticipates = true;
 	int			querylen;
@@ -748,7 +926,11 @@ HnswBeginParallel(HnswBuildState * buildstate, bool isconcurrent, int request)
 	/* Estimate size of workspaces */
 	esthnswshared = ParallelEstimateShared(buildstate->heap, snapshot);
 	shm_toc_estimate_chunk(&pcxt->estimator, esthnswshared);
-	shm_toc_estimate_keys(&pcxt->estimator, 1);
+
+	/* Start with a minimal DSA so InitializeParallelDSM does not fail */
+	estdsaspace = dsa_minimum_size();
+	shm_toc_estimate_chunk(&pcxt->estimator, estdsaspace);
+	shm_toc_estimate_keys(&pcxt->estimator, 2);
 
 	/* Finally, estimate PARALLEL_KEY_QUERY_TEXT space */
 	if (debug_query_string)
@@ -785,7 +967,6 @@ HnswBeginParallel(HnswBuildState * buildstate, bool isconcurrent, int request)
 	/* Initialize mutable state */
 	hnswshared->nparticipantsdone = 0;
 	hnswshared->reltuples = 0;
-	hnswshared->indtuples = 0;
 #if PG_VERSION_NUM >= 120000
 	table_parallelscan_initialize(buildstate->heap,
 								  ParallelTableScanFromHnswShared(hnswshared),
@@ -794,7 +975,28 @@ HnswBeginParallel(HnswBuildState * buildstate, bool isconcurrent, int request)
 	heap_parallelscan_initialize(&hnswshared->heapdesc, buildstate->heap, snapshot);
 #endif
 
+	dsaspace = shm_toc_allocate(pcxt->toc, estdsaspace);
+	dsa = dsa_create_in_place(dsaspace, estdsaspace, hnsw_lock_tranche_id, pcxt->seg);
+
+	esthnswarea = maintenance_work_mem * 1024L;
+	hnswshared->dsaptr = dsa_allocate_extended(dsa, esthnswarea, DSA_ALLOC_HUGE | DSA_ALLOC_NO_OOM);
+
+	/* If not enough shared memory, back out (do serial build) */
+	if (!DsaPointerIsValid(hnswshared->dsaptr))
+	{
+		if (IsMVCCSnapshot(snapshot))
+			UnregisterSnapshot(snapshot);
+		DestroyParallelContext(pcxt);
+		ExitParallelMode();
+		return;
+	}
+
+	hnswarea = dsa_get_address(dsa, hnswshared->dsaptr);
+	/* Report less than allocated so never fails */
+	InitGraph(&hnswshared->graphData, hnswarea, esthnswarea - 1024 * 1024);
+
 	shm_toc_insert(pcxt->toc, PARALLEL_KEY_HNSW_SHARED, hnswshared);
+	shm_toc_insert(pcxt->toc, PARALLEL_KEY_HNSW_AREA, dsaspace);
 
 	/* Store query string for workers */
 	if (debug_query_string)
@@ -814,6 +1016,7 @@ HnswBeginParallel(HnswBuildState * buildstate, bool isconcurrent, int request)
 		hnswleader->nparticipanttuplesorts++;
 	hnswleader->hnswshared = hnswshared;
 	hnswleader->snapshot = snapshot;
+	hnswleader->hnswarea = hnswarea;
 
 	/* If no workers were successfully launched, back out (do serial build) */
 	if (pcxt->nworkers_launched == 0)
@@ -836,6 +1039,27 @@ HnswBeginParallel(HnswBuildState * buildstate, bool isconcurrent, int request)
 	WaitForParallelWorkersToAttach(pcxt);
 }
 
+/*
+ * Compute parallel workers
+ */
+static int
+ComputeParallelWorkers(Relation heap, Relation index)
+{
+	int			parallel_workers;
+
+	/* Make sure it's safe to use parallel workers */
+	parallel_workers = plan_create_index_workers(RelationGetRelid(heap), RelationGetRelid(index));
+	if (parallel_workers == 0)
+		return 0;
+
+	/* Use parallel_workers storage parameter on table if set */
+	parallel_workers = RelationGetParallelWorkers(heap, -1);
+	if (parallel_workers != -1)
+		return Min(parallel_workers, max_parallel_maintenance_workers);
+
+	return max_parallel_maintenance_workers;
+}
+
 /*
  * Build graph
  */
@@ -847,18 +1071,16 @@ BuildGraph(HnswBuildState * buildstate, ForkNumber forkNum)
 	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));
+	if (buildstate->heap != NULL)
+		parallel_workers = ComputeParallelWorkers(buildstate->heap, 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 */
+	/* Add tuples to graph */
+	if (buildstate->heap != NULL)
+	{
 		if (buildstate->hnswleader)
 			buildstate->reltuples = ParallelHeapScan(buildstate);
 		else
@@ -872,11 +1094,34 @@ BuildGraph(HnswBuildState * buildstate, ForkNumber forkNum)
 #endif
 		}
 
+		buildstate->indtuples = buildstate->graph->indtuples;
+	}
+
+	/* Flush pages */
+	if (!buildstate->graph->flushed)
+		FlushPages(buildstate);
+
 	/* 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
  */
@@ -884,13 +1129,16 @@ static void
 BuildIndex(Relation heap, Relation index, IndexInfo *indexInfo,
 		   HnswBuildState * buildstate, ForkNumber forkNum)
 {
+#ifdef HNSW_MEMORY
+	SeedRandom(42);
+#endif
+
 	InitBuildState(buildstate, heap, index, indexInfo, forkNum);
 
-	if (buildstate->heap != NULL)
 	BuildGraph(buildstate, forkNum);
 
-	if (!buildstate->flushed)
-		FlushPages(buildstate);
+	if (RelationNeedsWAL(index))
+		log_newpage_range(index, forkNum, 0, RelationGetNumberOfBlocks(index), true);
 
 	FreeBuildState(buildstate);
 }

src/hnswinsert.c

@@ -5,6 +5,7 @@
 #include "hnsw.h"
 #include "storage/bufmgr.h"
 #include "storage/lmgr.h"
+#include "utils/datum.h"
 #include "utils/memutils.h"
 
 /*
@@ -92,7 +93,7 @@ HnswFreeOffset(Relation index, Buffer buf, Page page, HnswElement element, Size
  * Add a new page
  */
 static void
-HnswInsertAppendPage(Relation index, Buffer *nbuf, Page *npage, GenericXLogState *state, Page page)
+HnswInsertAppendPage(Relation index, Buffer *nbuf, Page *npage, GenericXLogState *state, Page page, bool building)
 {
 	/* Add a new page */
 	LockRelationForExtension(index, ExclusiveLock);
@@ -100,7 +101,11 @@ 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 */
@@ -111,7 +116,7 @@ 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)
+WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPage, BlockNumber *updatedInsertPage, bool building)
 {
 	Buffer		buf;
 	Page		page;
@@ -129,9 +134,10 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
 	OffsetNumber freeOffno = InvalidOffsetNumber;
 	OffsetNumber freeNeighborOffno = InvalidOffsetNumber;
 	BlockNumber newInsertPage = InvalidBlockNumber;
+	char	   *base = NULL;
 
 	/* Calculate sizes */
-	etupSize = HNSW_ELEMENT_TUPLE_SIZE(VARSIZE_ANY(DatumGetPointer(e->value)));
+	etupSize = HNSW_ELEMENT_TUPLE_SIZE(VARSIZE_ANY(HnswPtrAccess(base, e->value)));
 	ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(e->level, m);
 	combinedSize = etupSize + ntupSize + sizeof(ItemIdData);
 	maxSize = HNSW_MAX_SIZE;
@@ -139,11 +145,11 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
 
 	/* Prepare element tuple */
 	etup = palloc0(etupSize);
-	HnswSetElementTuple(etup, e);
+	HnswSetElementTuple(base, etup, e);
 
 	/* Prepare neighbor tuple */
 	ntup = palloc0(ntupSize);
-	HnswSetNeighborTuple(ntup, e, m);
+	HnswSetNeighborTuple(base, ntup, e, m);
 
 	/* Find a page (or two if needed) to insert the tuples */
 	for (;;)
@@ -151,8 +157,16 @@ 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)
@@ -172,7 +186,12 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
 		if (HnswFreeOffset(index, buf, page, e, ntupSize, &nbuf, &npage, &freeOffno, &freeNeighborOffno, &newInsertPage))
 		{
 			if (nbuf != buf)
+			{
+				if (building)
+					npage = BufferGetPage(nbuf);
+				else
 					npage = GenericXLogRegisterBuffer(state, nbuf, 0);
+			}
 
 			break;
 		}
@@ -181,7 +200,7 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
 		/* Skip if both tuples can fit on the same page */
 		if (combinedSize > maxSize && PageGetFreeSpace(page) >= etupSize && !BlockNumberIsValid(HnswPageGetOpaque(page)->nextblkno))
 		{
-			HnswInsertAppendPage(index, &nbuf, &npage, state, page);
+			HnswInsertAppendPage(index, &nbuf, &npage, state, page, building);
 			break;
 		}
 
@@ -190,6 +209,7 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
 		if (BlockNumberIsValid(currentPage))
 		{
 			/* Move to next page */
+			if (!building)
 				GenericXLogAbort(state);
 			UnlockReleaseBuffer(buf);
 		}
@@ -198,22 +218,33 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
 			Buffer		newbuf;
 			Page		newpage;
 
-			HnswInsertAppendPage(index, &newbuf, &newpage, state, page);
+			HnswInsertAppendPage(index, &newbuf, &newpage, state, page, building);
 
 			/* Commit */
+			if (building)
+				MarkBufferDirty(buf);
+			else
 				GenericXLogFinish(state);
 
 			/* Unlock previous buffer */
 			UnlockReleaseBuffer(buf);
 
 			/* Prepare new buffer */
-			state = GenericXLogStart(index);
 			buf = newbuf;
+			if (building)
+			{
+				state = NULL;
+				page = BufferGetPage(buf);
+			}
+			else
+			{
+				state = GenericXLogStart(index);
 				page = GenericXLogRegisterBuffer(state, buf, 0);
+			}
 
 			/* Create new page for neighbors if needed */
 			if (PageGetFreeSpace(page) < combinedSize)
-				HnswInsertAppendPage(index, &nbuf, &npage, state, page);
+				HnswInsertAppendPage(index, &nbuf, &npage, state, page, building);
 			else
 			{
 				nbuf = buf;
@@ -267,6 +298,13 @@ WriteNewElementPages(Relation index, HnswElement e, int m, BlockNumber insertPag
 	}
 
 	/* Commit */
+	if (building)
+	{
+		MarkBufferDirty(buf);
+		if (nbuf != buf)
+			MarkBufferDirty(nbuf);
+	}
+	else
 		GenericXLogFinish(state);
 	UnlockReleaseBuffer(buf);
 	if (nbuf != buf)
@@ -301,12 +339,14 @@ ConnectionExists(HnswElement e, HnswNeighborTuple ntup, int startIdx, int lm)
  * Update neighbors
  */
 void
-HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement e, int m, bool checkExisting)
+HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement e, int m, bool checkExisting, bool building)
 {
+	char	   *base = NULL;
+
 	for (int lc = e->level; lc >= 0; lc--)
 	{
 		int			lm = HnswGetLayerM(m, lc);
-		HnswNeighborArray *neighbors = &e->neighbors[lc];
+		HnswNeighborArray *neighbors = HnswGetNeighbors(base, e, lc);
 
 		for (int i = 0; i < neighbors->length; i++)
 		{
@@ -319,11 +359,12 @@ HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswE
 			Size		ntupSize;
 			int			idx = -1;
 			int			startIdx;
-			OffsetNumber offno = hc->element->neighborOffno;
+			HnswElement neighborElement = HnswPtrAccess(base, hc->element);
+			OffsetNumber offno = neighborElement->neighborOffno;
 
 			/* Get latest neighbors since they may have changed */
 			/* Do not lock yet since selecting neighbors can take time */
-			HnswLoadNeighbors(hc->element, index, m);
+			HnswLoadNeighbors(neighborElement, index, m);
 
 			/*
 			 * Could improve performance for vacuuming by checking neighbors
@@ -333,17 +374,25 @@ HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswE
 			 */
 
 			/* Select neighbors */
-			HnswUpdateConnection(e, hc, lm, lc, &idx, index, procinfo, collation);
+			HnswUpdateConnection(NULL, e, hc, lm, lc, &idx, index, procinfo, collation);
 
 			/* New element was not selected as a neighbor */
 			if (idx == -1)
 				continue;
 
 			/* Register page */
-			buf = ReadBuffer(index, hc->element->neighborPage);
+			buf = ReadBuffer(index, neighborElement->neighborPage);
 			LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
+			if (building)
+			{
+				state = NULL;
+				page = BufferGetPage(buf);
+			}
+			else
+			{
 				state = GenericXLogStart(index);
 				page = GenericXLogRegisterBuffer(state, buf, 0);
+			}
 
 			/* Get tuple */
 			itemid = PageGetItemId(page, offno);
@@ -351,7 +400,7 @@ HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswE
 			ntupSize = ItemIdGetLength(itemid);
 
 			/* Calculate index for update */
-			startIdx = (hc->element->level - lc) * m;
+			startIdx = (neighborElement->level - lc) * m;
 
 			/* Check for existing connection */
 			if (checkExisting && ConnectionExists(e, ntup, startIdx, lm))
@@ -385,9 +434,12 @@ HnswUpdateNeighborPages(Relation index, FmgrInfo *procinfo, Oid collation, HnswE
 					elog(ERROR, "failed to add index item to \"%s\"", RelationGetRelationName(index));
 
 				/* Commit */
+				if (building)
+					MarkBufferDirty(buf);
+				else
 					GenericXLogFinish(state);
 			}
-			else
+			else if (!building)
 				GenericXLogAbort(state);
 
 			UnlockReleaseBuffer(buf);
@@ -399,7 +451,7 @@ 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)
+HnswAddDuplicate(Relation index, HnswElement element, HnswElement dup, bool building)
 {
 	Buffer		buf;
 	Page		page;
@@ -412,8 +464,16 @@ HnswAddDuplicate(Relation index, HnswElement element, HnswElement dup)
 	/* 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);
@@ -428,82 +488,97 @@ HnswAddDuplicate(Relation index, HnswElement element, HnswElement dup)
 	/* 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;
 	}
 
 	/* Add heap TID */
-	etup->heaptids[i] = *((ItemPointer) linitial(element->heaptids));
+	etup->heaptids[i] = element->heaptids[0];
 
 	/* Overwrite tuple */
 	if (!PageIndexTupleOverwrite(page, dup->offno, (Item) etup, etupSize))
 		elog(ERROR, "failed to add index item to \"%s\"", RelationGetRelationName(index));
 
 	/* Commit */
+	if (building)
+		MarkBufferDirty(buf);
+	else
 		GenericXLogFinish(state);
 	UnlockReleaseBuffer(buf);
 
 	return true;
 }
 
+/*
+ * Find duplicate element
+ */
+static bool
+HnswFindDuplicate(Relation index, HnswElement element, bool building)
+{
+	char	   *base = NULL;
+	HnswNeighborArray *neighbors = HnswGetNeighbors(base, element, 0);
+
+	for (int i = 0; i < neighbors->length; i++)
+	{
+		HnswCandidate *neighbor = &neighbors->items[i];
+		HnswElement neighborElement = HnswPtrAccess(base, neighbor->element);
+		Datum		value = HnswGetValue(base, element);
+		Datum		neighborValue = HnswGetValue(base, neighborElement);
+
+		/* Exit early since ordered by distance */
+		if (!datumIsEqual(value, neighborValue, false, -1))
+			return false;
+
+		if (HnswAddDuplicate(index, element, neighborElement, building))
+			return true;
+	}
+
+	return false;
+}
+
 /*
  * Write changes to disk
  */
 static void
-WriteElement(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement element, int m, int efConstruction, HnswElement dup, HnswElement entryPoint)
+WriteElement(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement element, int m, int efConstruction, HnswElement entryPoint, bool building)
 {
 	BlockNumber newInsertPage = InvalidBlockNumber;
 
-	/* Try to add to existing page */
-	if (dup != NULL)
-	{
-		if (HnswAddDuplicate(index, element, dup))
+	/* Look for duplicate */
+	if (HnswFindDuplicate(index, element, building))
 		return;
-	}
 
 	/* Write element and neighbor tuples */
-	WriteNewElementPages(index, element, m, GetInsertPage(index), &newInsertPage);
+	WriteNewElementPages(index, element, m, GetInsertPage(index), &newInsertPage, building);
 
 	/* Update insert page if needed */
 	if (BlockNumberIsValid(newInsertPage))
-		HnswUpdateMetaPage(index, 0, NULL, newInsertPage, MAIN_FORKNUM);
+		HnswUpdateMetaPage(index, 0, NULL, newInsertPage, MAIN_FORKNUM, building);
 
 	/* Update neighbors */
-	HnswUpdateNeighborPages(index, procinfo, collation, element, m, false);
+	HnswUpdateNeighborPages(index, procinfo, collation, element, m, false, building);
 
-	/* Update metapage if needed */
+	/* Update entry point if needed */
 	if (entryPoint == NULL || element->level > entryPoint->level)
-		HnswUpdateMetaPage(index, HNSW_UPDATE_ENTRY_GREATER, element, InvalidBlockNumber, MAIN_FORKNUM);
+		HnswUpdateMetaPage(index, HNSW_UPDATE_ENTRY_GREATER, element, InvalidBlockNumber, MAIN_FORKNUM, building);
 }
 
 /*
  * Insert a tuple into the index
  */
 bool
-HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid, Relation heapRel)
+HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull, ItemPointer heap_tid, Relation heapRel, bool building)
 {
-	Datum		value;
-	FmgrInfo   *normprocinfo;
 	HnswElement entryPoint;
 	HnswElement element;
 	int			m;
 	int			efConstruction = HnswGetEfConstruction(index);
 	FmgrInfo   *procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
 	Oid			collation = index->rd_indcollation[0];
-	HnswElement dup;
 	LOCKMODE	lockmode = ShareLock;
-
-	/* Detoast once for all calls */
-	value = PointerGetDatum(PG_DETOAST_DATUM(values[0]));
-
-	/* Normalize if needed */
-	normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
-	if (normprocinfo != NULL)
-	{
-		if (!HnswNormValue(normprocinfo, collation, &value, NULL))
-			return false;
-	}
+	char	   *base = NULL;
 
 	/*
 	 * Get a shared lock. This allows vacuum to ensure no in-flight inserts
@@ -516,8 +591,8 @@ HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_ti
 	HnswGetMetaPageInfo(index, &m, &entryPoint);
 
 	/* Create an element */
-	element = HnswInitElement(heap_tid, m, HnswGetMl(m), HnswGetMaxLevel(m));
-	element->value = value;
+	element = HnswInitElement(base, heap_tid, m, HnswGetMl(m), HnswGetMaxLevel(m), NULL);
+	HnswPtrStore(base, element->value, DatumGetPointer(value));
 
 	/* Prevent concurrent inserts when likely updating entry point */
 	if (entryPoint == NULL || element->level > entryPoint->level)
@@ -534,13 +609,10 @@ HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_ti
 	}
 
 	/* Insert element in graph */
-	HnswInsertElement(element, entryPoint, index, procinfo, collation, m, efConstruction, false);
-
-	/* Look for duplicate */
-	dup = HnswFindDuplicate(element);
+	HnswInsertElement(base, element, entryPoint, index, procinfo, collation, m, efConstruction, false);
 
 	/* Write to disk */
-	WriteElement(index, procinfo, collation, element, m, efConstruction, dup, entryPoint);
+	WriteElement(index, procinfo, collation, element, m, efConstruction, entryPoint, building);
 
 	/* Release lock */
 	UnlockPage(index, HNSW_UPDATE_LOCK, lockmode);
@@ -548,6 +620,30 @@ HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_ti
 	return true;
 }
 
+/*
+ * Insert a tuple into the index
+ */
+static void
+HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid, Relation heapRel)
+{
+	Datum		value;
+	FmgrInfo   *normprocinfo;
+	Oid			collation = index->rd_indcollation[0];
+
+	/* Detoast once for all calls */
+	value = PointerGetDatum(PG_DETOAST_DATUM(values[0]));
+
+	/* Normalize if needed */
+	normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
+	if (normprocinfo != NULL)
+	{
+		if (!HnswNormValue(normprocinfo, collation, &value, NULL))
+			return;
+	}
+
+	HnswInsertTupleOnDisk(index, value, values, isnull, heap_tid, heapRel, false);
+}
+
 /*
  * Insert a tuple into the index
  */

src/hnswscan.c

@@ -21,6 +21,7 @@ GetScanItems(IndexScanDesc scan, Datum q)
 	List	   *w;
 	int			m;
 	HnswElement entryPoint;
+	char	   *base = NULL;
 
 	/* Get m and entry point */
 	HnswGetMetaPageInfo(index, &m, &entryPoint);
@@ -28,15 +29,15 @@ GetScanItems(IndexScanDesc scan, Datum q)
 	if (entryPoint == NULL)
 		return NIL;
 
-	ep = list_make1(HnswEntryCandidate(entryPoint, q, index, procinfo, collation, false));
+	ep = list_make1(HnswEntryCandidate(base, entryPoint, q, index, procinfo, collation, false));
 
 	for (int lc = entryPoint->level; lc >= 1; lc--)
 	{
-		w = HnswSearchLayer(q, ep, 1, lc, index, procinfo, collation, m, false, NULL);
+		w = HnswSearchLayer(base, q, ep, 1, lc, index, procinfo, collation, m, false, NULL);
 		ep = w;
 	}
 
-	return HnswSearchLayer(q, ep, hnsw_ef_search, 0, index, procinfo, collation, m, false, NULL);
+	return HnswSearchLayer(base, q, ep, hnsw_ef_search, 0, index, procinfo, collation, m, false, NULL);
 }
 
 /*
@@ -184,19 +185,19 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
 
 	while (list_length(so->w) > 0)
 	{
+		char	   *base = NULL;
 		HnswCandidate *hc = llast(so->w);
+		HnswElement element = HnswPtrAccess(base, hc->element);
 		ItemPointer heaptid;
 
 		/* Move to next element if no valid heap TIDs */
-		if (list_length(hc->element->heaptids) == 0)
+		if (element->heaptidsLength == 0)
 		{
 			so->w = list_delete_last(so->w);
 			continue;
 		}
 
-		heaptid = llast(hc->element->heaptids);
-
-		hc->element->heaptids = list_delete_last(hc->element->heaptids);
+		heaptid = &element->heaptids[--element->heaptidsLength];
 
 		MemoryContextSwitchTo(oldCtx);
 

src/hnswvacuum.c

@@ -12,12 +12,9 @@
  * Check if deleted list contains an index TID
  */
 static bool
-DeletedContains(HTAB *deleted, ItemPointer indextid)
+DeletedContains(tidhash_hash * deleted, ItemPointer indextid)
 {
-	bool		found;
-
-	hash_search(deleted, indextid, HASH_FIND, &found);
-	return found;
+	return tidhash_lookup(deleted, *indextid) != NULL;
 }
 
 /*
@@ -110,11 +107,13 @@ RemoveHeapTids(HnswVacuumState * vacuumstate)
 			if (!ItemPointerIsValid(&etup->heaptids[0]))
 			{
 				ItemPointerData ip;
+				bool		found;
 
 				/* Add to deleted list */
 				ItemPointerSet(&ip, blkno, offno);
 
-				(void) hash_search(vacuumstate->deleted, &ip, HASH_ENTER, NULL);
+				tidhash_insert(vacuumstate->deleted, ip, &found);
+				Assert(!found);
 			}
 			else if (etup->level > highestLevel && !(entryPoint != NULL && blkno == entryPoint->blkno && offno == entryPoint->offno))
 			{
@@ -206,15 +205,15 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
 		return;
 
 	/* Init fields */
-	HnswInitNeighbors(element, m);
-	element->heaptids = NIL;
+	HnswInitNeighbors(NULL, element, m, NULL);
+	element->heaptidsLength = 0;
 
 	/* Add element to graph, skipping itself */
-	HnswInsertElement(element, entryPoint, index, procinfo, collation, m, efConstruction, true);
+	HnswInsertElement(NULL, element, entryPoint, index, procinfo, collation, m, efConstruction, true);
 
 	/* Update neighbor tuple */
 	/* Do this before getting page to minimize locking */
-	HnswSetNeighborTuple(ntup, element, m);
+	HnswSetNeighborTuple(NULL, ntup, element, m);
 
 	/* Get neighbor page */
 	buf = ReadBufferExtended(index, MAIN_FORKNUM, element->neighborPage, RBM_NORMAL, bas);
@@ -231,7 +230,7 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
 	UnlockReleaseBuffer(buf);
 
 	/* Update neighbors */
-	HnswUpdateNeighborPages(index, procinfo, collation, element, m, true);
+	HnswUpdateNeighborPages(index, procinfo, collation, element, m, true, false);
 }
 
 /*
@@ -287,7 +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);
+			HnswUpdateMetaPage(index, HNSW_UPDATE_ENTRY_ALWAYS, highestPoint, InvalidBlockNumber, MAIN_FORKNUM, false);
 		}
 		else
 		{
@@ -302,7 +301,7 @@ RepairGraphEntryPoint(HnswVacuumState * vacuumstate)
 			{
 				/* Reset neighbors from previous update */
 				if (highestPoint != NULL)
-					highestPoint->neighbors = NULL;
+					HnswPtrStore((char *) NULL, highestPoint->neighbors, (HnswNeighborArrayPtr *) NULL);
 
 				RepairGraphElement(vacuumstate, entryPoint, highestPoint);
 			}
@@ -420,7 +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);
+				HnswUpdateMetaPage(index, HNSW_UPDATE_ENTRY_GREATER, element, InvalidBlockNumber, MAIN_FORKNUM, false);
 
 			/* Release lock */
 			UnlockPage(index, HNSW_UPDATE_LOCK, lockmode);
@@ -565,7 +564,7 @@ MarkDeleted(HnswVacuumState * vacuumstate)
 	}
 
 	/* Update insert page last, after everything has been marked as deleted */
-	HnswUpdateMetaPage(index, 0, NULL, insertPage, MAIN_FORKNUM);
+	HnswUpdateMetaPage(index, 0, NULL, insertPage, MAIN_FORKNUM, false);
 }
 
 /*
@@ -575,7 +574,6 @@ static void
 InitVacuumState(HnswVacuumState * vacuumstate, IndexVacuumInfo *info, IndexBulkDeleteResult *stats, IndexBulkDeleteCallback callback, void *callback_state)
 {
 	Relation	index = info->index;
-	HASHCTL		hash_ctl;
 
 	if (stats == NULL)
 		stats = (IndexBulkDeleteResult *) palloc0(sizeof(IndexBulkDeleteResult));
@@ -597,10 +595,7 @@ InitVacuumState(HnswVacuumState * vacuumstate, IndexVacuumInfo *info, IndexBulkD
 	HnswGetMetaPageInfo(index, &vacuumstate->m, NULL);
 
 	/* Create hash table */
-	hash_ctl.keysize = sizeof(ItemPointerData);
-	hash_ctl.entrysize = sizeof(ItemPointerData);
-	hash_ctl.hcxt = CurrentMemoryContext;
-	vacuumstate->deleted = hash_create("hnswbulkdelete indextids", 256, &hash_ctl, HASH_ELEM | HASH_BLOBS | HASH_CONTEXT);
+	vacuumstate->deleted = tidhash_create(CurrentMemoryContext, 256, NULL);
 }
 
 /*
@@ -609,7 +604,7 @@ InitVacuumState(HnswVacuumState * vacuumstate, IndexVacuumInfo *info, IndexBulkD
 static void
 FreeVacuumState(HnswVacuumState * vacuumstate)
 {
-	hash_destroy(vacuumstate->deleted);
+	tidhash_destroy(vacuumstate->deleted);
 	FreeAccessStrategy(vacuumstate->bas);
 	pfree(vacuumstate->ntup);
 	MemoryContextDelete(vacuumstate->tmpCtx);

src/ivfbuild.c

@@ -543,10 +543,10 @@ CreateListPages(Relation index, VectorArray centers, int dimensions,
 	pfree(list);
 }
 
+#ifdef IVFFLAT_KMEANS_DEBUG
 /*
  * Print k-means metrics
  */
-#ifdef IVFFLAT_KMEANS_DEBUG
 static void
 PrintKmeansMetrics(IvfflatBuildState * buildstate)
 {

src/ivfkmeans.c

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

src/vector.c

@@ -724,7 +724,7 @@ vector_spherical_distance(PG_FUNCTION_ARGS)
 }
 
 /*
- * Get the L1 distance between vectors
+ * Get the L1 distance between two vectors
  */
 PGDLLEXPORT PG_FUNCTION_INFO_V1(l1_distance);
 Datum
@@ -903,8 +903,8 @@ PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_lt);
 Datum
 vector_lt(PG_FUNCTION_ARGS)
 {
-	Vector	   *a = (Vector *) PG_GETARG_VECTOR_P(0);
-	Vector	   *b = (Vector *) PG_GETARG_VECTOR_P(1);
+	Vector	   *a = PG_GETARG_VECTOR_P(0);
+	Vector	   *b = PG_GETARG_VECTOR_P(1);
 
 	PG_RETURN_BOOL(vector_cmp_internal(a, b) < 0);
 }
@@ -916,8 +916,8 @@ PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_le);
 Datum
 vector_le(PG_FUNCTION_ARGS)
 {
-	Vector	   *a = (Vector *) PG_GETARG_VECTOR_P(0);
-	Vector	   *b = (Vector *) PG_GETARG_VECTOR_P(1);
+	Vector	   *a = PG_GETARG_VECTOR_P(0);
+	Vector	   *b = PG_GETARG_VECTOR_P(1);
 
 	PG_RETURN_BOOL(vector_cmp_internal(a, b) <= 0);
 }
@@ -929,8 +929,8 @@ PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_eq);
 Datum
 vector_eq(PG_FUNCTION_ARGS)
 {
-	Vector	   *a = (Vector *) PG_GETARG_VECTOR_P(0);
-	Vector	   *b = (Vector *) PG_GETARG_VECTOR_P(1);
+	Vector	   *a = PG_GETARG_VECTOR_P(0);
+	Vector	   *b = PG_GETARG_VECTOR_P(1);
 
 	PG_RETURN_BOOL(vector_cmp_internal(a, b) == 0);
 }
@@ -942,8 +942,8 @@ PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_ne);
 Datum
 vector_ne(PG_FUNCTION_ARGS)
 {
-	Vector	   *a = (Vector *) PG_GETARG_VECTOR_P(0);
-	Vector	   *b = (Vector *) PG_GETARG_VECTOR_P(1);
+	Vector	   *a = PG_GETARG_VECTOR_P(0);
+	Vector	   *b = PG_GETARG_VECTOR_P(1);
 
 	PG_RETURN_BOOL(vector_cmp_internal(a, b) != 0);
 }
@@ -955,8 +955,8 @@ PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_ge);
 Datum
 vector_ge(PG_FUNCTION_ARGS)
 {
-	Vector	   *a = (Vector *) PG_GETARG_VECTOR_P(0);
-	Vector	   *b = (Vector *) PG_GETARG_VECTOR_P(1);
+	Vector	   *a = PG_GETARG_VECTOR_P(0);
+	Vector	   *b = PG_GETARG_VECTOR_P(1);
 
 	PG_RETURN_BOOL(vector_cmp_internal(a, b) >= 0);
 }
@@ -968,8 +968,8 @@ PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_gt);
 Datum
 vector_gt(PG_FUNCTION_ARGS)
 {
-	Vector	   *a = (Vector *) PG_GETARG_VECTOR_P(0);
-	Vector	   *b = (Vector *) PG_GETARG_VECTOR_P(1);
+	Vector	   *a = PG_GETARG_VECTOR_P(0);
+	Vector	   *b = PG_GETARG_VECTOR_P(1);
 
 	PG_RETURN_BOOL(vector_cmp_internal(a, b) > 0);
 }
@@ -981,8 +981,8 @@ PGDLLEXPORT PG_FUNCTION_INFO_V1(vector_cmp);
 Datum
 vector_cmp(PG_FUNCTION_ARGS)
 {
-	Vector	   *a = (Vector *) PG_GETARG_VECTOR_P(0);
-	Vector	   *b = (Vector *) PG_GETARG_VECTOR_P(1);
+	Vector	   *a = PG_GETARG_VECTOR_P(0);
+	Vector	   *b = PG_GETARG_VECTOR_P(1);
 
 	PG_RETURN_INT32(vector_cmp_internal(a, b));
 }

test/expected/copy.out

@@ -1,15 +1,15 @@
-CREATE TABLE t (val vector(3), val2 half[]);
-INSERT INTO t (val, val2) VALUES ('[0,0,0]', '{0,0,0}'), ('[1,2,3]', '{1,2,3}'), ('[1,1,1]', '{1,1,1}'), (NULL, NULL);
-CREATE TABLE t2 (val vector(3), val2 half[]);
+CREATE TABLE t (val vector(3));
+INSERT INTO t (val) VALUES ('[0,0,0]'), ('[1,2,3]'), ('[1,1,1]'), (NULL);
+CREATE TABLE t2 (val vector(3));
 \copy t TO 'results/data.bin' WITH (FORMAT binary)
 \copy t2 FROM 'results/data.bin' WITH (FORMAT binary)
 SELECT * FROM t2 ORDER BY val;
-   val   |  val2   
----------+---------
- [0,0,0] | {0,0,0}
- [1,1,1] | {1,1,1}
- [1,2,3] | {1,2,3}
-         | 
+   val   
+---------
+ [0,0,0]
+ [1,1,1]
+ [1,2,3]
+ 
 (4 rows)
 
 DROP TABLE t;

test/expected/functions.out

@@ -54,105 +54,105 @@ SELECT vector_norm('[3e37,4e37]')::real;
        5e+37
 (1 row)
 
-SELECT l2_distance('[0,0]'::vector, '[3,4]');
+SELECT l2_distance('[0,0]', '[3,4]');
  l2_distance 
 -------------
            5
 (1 row)
 
-SELECT l2_distance('[0,0]'::vector, '[0,1]');
+SELECT l2_distance('[0,0]', '[0,1]');
  l2_distance 
 -------------
            1
 (1 row)
 
-SELECT l2_distance('[1,2]'::vector, '[3]');
+SELECT l2_distance('[1,2]', '[3]');
 ERROR:  different vector dimensions 2 and 1
-SELECT l2_distance('[3e38]'::vector, '[-3e38]');
+SELECT l2_distance('[3e38]', '[-3e38]');
  l2_distance 
 -------------
     Infinity
 (1 row)
 
-SELECT inner_product('[1,2]'::vector, '[3,4]');
+SELECT inner_product('[1,2]', '[3,4]');
  inner_product 
 ---------------
             11
 (1 row)
 
-SELECT inner_product('[1,2]'::vector, '[3]');
+SELECT inner_product('[1,2]', '[3]');
 ERROR:  different vector dimensions 2 and 1
-SELECT inner_product('[3e38]'::vector, '[3e38]');
+SELECT inner_product('[3e38]', '[3e38]');
  inner_product 
 ---------------
       Infinity
 (1 row)
 
-SELECT cosine_distance('[1,2]'::vector, '[2,4]');
+SELECT cosine_distance('[1,2]', '[2,4]');
  cosine_distance 
 -----------------
                0
 (1 row)
 
-SELECT cosine_distance('[1,2]'::vector, '[0,0]');
+SELECT cosine_distance('[1,2]', '[0,0]');
  cosine_distance 
 -----------------
              NaN
 (1 row)
 
-SELECT cosine_distance('[1,1]'::vector, '[1,1]');
+SELECT cosine_distance('[1,1]', '[1,1]');
  cosine_distance 
 -----------------
                0
 (1 row)
 
-SELECT cosine_distance('[1,0]'::vector, '[0,2]');
+SELECT cosine_distance('[1,0]', '[0,2]');
  cosine_distance 
 -----------------
                1
 (1 row)
 
-SELECT cosine_distance('[1,1]'::vector, '[-1,-1]');
+SELECT cosine_distance('[1,1]', '[-1,-1]');
  cosine_distance 
 -----------------
                2
 (1 row)
 
-SELECT cosine_distance('[1,2]'::vector, '[3]');
+SELECT cosine_distance('[1,2]', '[3]');
 ERROR:  different vector dimensions 2 and 1
-SELECT cosine_distance('[1,1]'::vector, '[1.1,1.1]');
+SELECT cosine_distance('[1,1]', '[1.1,1.1]');
  cosine_distance 
 -----------------
                0
 (1 row)
 
-SELECT cosine_distance('[1,1]'::vector, '[-1.1,-1.1]');
+SELECT cosine_distance('[1,1]', '[-1.1,-1.1]');
  cosine_distance 
 -----------------
                2
 (1 row)
 
-SELECT cosine_distance('[3e38]'::vector, '[3e38]');
+SELECT cosine_distance('[3e38]', '[3e38]');
  cosine_distance 
 -----------------
              NaN
 (1 row)
 
-SELECT l1_distance('[0,0]'::vector, '[3,4]');
+SELECT l1_distance('[0,0]', '[3,4]');
  l1_distance 
 -------------
            7
 (1 row)
 
-SELECT l1_distance('[0,0]'::vector, '[0,1]');
+SELECT l1_distance('[0,0]', '[0,1]');
  l1_distance 
 -------------
            1
 (1 row)
 
-SELECT l1_distance('[1,2]'::vector, '[3]');
+SELECT l1_distance('[1,2]', '[3]');
 ERROR:  different vector dimensions 2 and 1
-SELECT l1_distance('[3e38]'::vector, '[-3e38]');
+SELECT l1_distance('[3e38]', '[-3e38]');
  l1_distance 
 -------------
     Infinity

test/expected/half.out

@@ -1,226 +0,0 @@
-SELECT '1.5'::half;
- half 
-------
- 1.5
-(1 row)
-
-SELECT '65504'::half;
- half  
--------
- 65504
-(1 row)
-
-SELECT '65505'::half;
-ERROR:  "65505" is out of range for type half
-LINE 1: SELECT '65505'::half;
-               ^
-SELECT '-65504'::half;
-  half  
---------
- -65504
-(1 row)
-
-SELECT '-65505'::half;
-ERROR:  "-65505" is out of range for type half
-LINE 1: SELECT '-65505'::half;
-               ^
-SELECT ''::half;
-ERROR:  invalid input syntax for type half: ""
-LINE 1: SELECT ''::half;
-               ^
-SELECT ' '::half;
-ERROR:  invalid input syntax for type half: " "
-LINE 1: SELECT ' '::half;
-               ^
-SELECT '-'::half;
-ERROR:  invalid input syntax for type half: "-"
-LINE 1: SELECT '-'::half;
-               ^
-SELECT ' 1.5'::half;
- half 
-------
- 1.5
-(1 row)
-
-SELECT '1.5 '::half;
- half 
-------
- 1.5
-(1 row)
-
-SELECT '1.5a'::half;
-ERROR:  invalid input syntax for type half: "1.5a"
-LINE 1: SELECT '1.5a'::half;
-               ^
-SELECT '{1,2,3}'::half[];
-  half   
----------
- {1,2,3}
-(1 row)
-
-SELECT '{1,2,3}'::half[]::real[];
- float4  
----------
- {1,2,3}
-(1 row)
-
-SELECT '65505'::integer::half;
- half  
--------
- 65504
-(1 row)
-
-SELECT 'NaN'::real::half;
- half 
-------
- NaN
-(1 row)
-
-SELECT 'Infinity'::real::half;
-   half   
-----------
- Infinity
-(1 row)
-
-SELECT '1e-38'::real::half;
-ERROR:  value out of range: underflow
-SELECT '1.5'::half::real;
- float4 
---------
-    1.5
-(1 row)
-
-SELECT '1.5'::real::half;
- half 
-------
- 1.5
-(1 row)
-
-SELECT '1.5'::half::double precision;
- float8 
---------
-    1.5
-(1 row)
-
-SELECT '1.5'::double precision::half;
- half 
-------
- 1.5
-(1 row)
-
-SELECT '1.5'::half::numeric;
- numeric 
----------
-     1.5
-(1 row)
-
-SELECT '1.5'::numeric::half;
- half 
-------
- 1.5
-(1 row)
-
-SELECT l2_distance('{0,0}'::half[], '{3,4}'::half[]);
- l2_distance 
--------------
-           5
-(1 row)
-
-SELECT l2_distance('{0,0}'::half[], '{0,1}'::half[]);
- l2_distance 
--------------
-           1
-(1 row)
-
-SELECT l2_distance('{1,2}'::half[], '{3}'::half[]);
-ERROR:  different dimensions 2 and 1
-SELECT '{0,0}'::half[] <-> '{3,4}'::half[];
- ?column? 
-----------
-        5
-(1 row)
-
-SELECT inner_product('{1,2}'::half[], '{3,4}'::half[]);
- inner_product 
----------------
-            11
-(1 row)
-
-SELECT inner_product('{1,2}'::half[], '{3}'::half[]);
-ERROR:  different dimensions 2 and 1
-SELECT inner_product('{65504}'::half[], '{65504}'::half[]);
- inner_product 
----------------
-    4290774016
-(1 row)
-
-SELECT '{1,2}'::half[] <#> '{3,4}'::half[];
- ?column? 
-----------
-      -11
-(1 row)
-
-SELECT cosine_distance('{1,2}'::half[], '{2,4}'::half[]);
- cosine_distance 
------------------
-               0
-(1 row)
-
-SELECT cosine_distance('{1,2}'::half[], '{0,0}'::half[]);
- cosine_distance 
------------------
-             NaN
-(1 row)
-
-SELECT cosine_distance('{1,1}'::half[], '{1,1}'::half[]);
- cosine_distance 
------------------
-               0
-(1 row)
-
-SELECT cosine_distance('{1,0}'::half[], '{0,2}'::half[]);
- cosine_distance 
------------------
-               1
-(1 row)
-
-SELECT cosine_distance('{1,1}'::half[], '{-1,-1}'::half[]);
- cosine_distance 
------------------
-               2
-(1 row)
-
-SELECT cosine_distance('{1,2}'::half[], '{3}'::half[]);
-ERROR:  different dimensions 2 and 1
-SELECT cosine_distance('{1,1}'::half[], '{1.1,1.1}'::half[]);
- cosine_distance 
------------------
-               0
-(1 row)
-
-SELECT cosine_distance('{1,1}'::half[], '{-1.1,-1.1}'::half[]);
- cosine_distance 
------------------
-               2
-(1 row)
-
-SELECT '{1,2}'::half[] <=> '{2,4}'::half[];
- ?column? 
-----------
-        0
-(1 row)
-
-SELECT l1_distance('{0,0}'::half[], '{3,4}');
- l1_distance 
--------------
-           7
-(1 row)
-
-SELECT l1_distance('{0,0}'::half[], '{0,1}');
- l1_distance 
--------------
-           1
-(1 row)
-
-SELECT l1_distance('{1,2}'::half[], '{3}');
-ERROR:  different dimensions 2 and 1

test/sql/copy.sql

@@ -1,7 +1,7 @@
-CREATE TABLE t (val vector(3), val2 half[]);
-INSERT INTO t (val, val2) VALUES ('[0,0,0]', '{0,0,0}'), ('[1,2,3]', '{1,2,3}'), ('[1,1,1]', '{1,1,1}'), (NULL, NULL);
+CREATE TABLE t (val vector(3));
+INSERT INTO t (val) VALUES ('[0,0,0]'), ('[1,2,3]'), ('[1,1,1]'), (NULL);
 
-CREATE TABLE t2 (val vector(3), val2 half[]);
+CREATE TABLE t2 (val vector(3));
 
 \copy t TO 'results/data.bin' WITH (FORMAT binary)
 \copy t2 FROM 'results/data.bin' WITH (FORMAT binary)

test/sql/functions.sql

@@ -13,29 +13,29 @@ SELECT vector_norm('[3,4]');
 SELECT vector_norm('[0,1]');
 SELECT vector_norm('[3e37,4e37]')::real;
 
-SELECT l2_distance('[0,0]'::vector, '[3,4]');
-SELECT l2_distance('[0,0]'::vector, '[0,1]');
-SELECT l2_distance('[1,2]'::vector, '[3]');
-SELECT l2_distance('[3e38]'::vector, '[-3e38]');
+SELECT l2_distance('[0,0]', '[3,4]');
+SELECT l2_distance('[0,0]', '[0,1]');
+SELECT l2_distance('[1,2]', '[3]');
+SELECT l2_distance('[3e38]', '[-3e38]');
 
-SELECT inner_product('[1,2]'::vector, '[3,4]');
-SELECT inner_product('[1,2]'::vector, '[3]');
-SELECT inner_product('[3e38]'::vector, '[3e38]');
+SELECT inner_product('[1,2]', '[3,4]');
+SELECT inner_product('[1,2]', '[3]');
+SELECT inner_product('[3e38]', '[3e38]');
 
-SELECT cosine_distance('[1,2]'::vector, '[2,4]');
-SELECT cosine_distance('[1,2]'::vector, '[0,0]');
-SELECT cosine_distance('[1,1]'::vector, '[1,1]');
-SELECT cosine_distance('[1,0]'::vector, '[0,2]');
-SELECT cosine_distance('[1,1]'::vector, '[-1,-1]');
-SELECT cosine_distance('[1,2]'::vector, '[3]');
-SELECT cosine_distance('[1,1]'::vector, '[1.1,1.1]');
-SELECT cosine_distance('[1,1]'::vector, '[-1.1,-1.1]');
-SELECT cosine_distance('[3e38]'::vector, '[3e38]');
+SELECT cosine_distance('[1,2]', '[2,4]');
+SELECT cosine_distance('[1,2]', '[0,0]');
+SELECT cosine_distance('[1,1]', '[1,1]');
+SELECT cosine_distance('[1,0]', '[0,2]');
+SELECT cosine_distance('[1,1]', '[-1,-1]');
+SELECT cosine_distance('[1,2]', '[3]');
+SELECT cosine_distance('[1,1]', '[1.1,1.1]');
+SELECT cosine_distance('[1,1]', '[-1.1,-1.1]');
+SELECT cosine_distance('[3e38]', '[3e38]');
 
-SELECT l1_distance('[0,0]'::vector, '[3,4]');
-SELECT l1_distance('[0,0]'::vector, '[0,1]');
-SELECT l1_distance('[1,2]'::vector, '[3]');
-SELECT l1_distance('[3e38]'::vector, '[-3e38]');
+SELECT l1_distance('[0,0]', '[3,4]');
+SELECT l1_distance('[0,0]', '[0,1]');
+SELECT l1_distance('[1,2]', '[3]');
+SELECT l1_distance('[3e38]', '[-3e38]');
 
 SELECT avg(v) FROM unnest(ARRAY['[1,2,3]'::vector, '[3,5,7]']) v;
 SELECT avg(v) FROM unnest(ARRAY['[1,2,3]'::vector, '[3,5,7]', NULL]) v;

test/sql/half.sql

@@ -1,53 +0,0 @@
-SELECT '1.5'::half;
-SELECT '65504'::half;
-SELECT '65505'::half;
-SELECT '-65504'::half;
-SELECT '-65505'::half;
-
-SELECT ''::half;
-SELECT ' '::half;
-SELECT '-'::half;
-SELECT ' 1.5'::half;
-SELECT '1.5 '::half;
-SELECT '1.5a'::half;
-
-SELECT '{1,2,3}'::half[];
-SELECT '{1,2,3}'::half[]::real[];
-
-SELECT '65505'::integer::half;
-SELECT 'NaN'::real::half;
-SELECT 'Infinity'::real::half;
-SELECT '1e-38'::real::half;
-
-SELECT '1.5'::half::real;
-SELECT '1.5'::real::half;
-
-SELECT '1.5'::half::double precision;
-SELECT '1.5'::double precision::half;
-
-SELECT '1.5'::half::numeric;
-SELECT '1.5'::numeric::half;
-
-SELECT l2_distance('{0,0}'::half[], '{3,4}'::half[]);
-SELECT l2_distance('{0,0}'::half[], '{0,1}'::half[]);
-SELECT l2_distance('{1,2}'::half[], '{3}'::half[]);
-SELECT '{0,0}'::half[] <-> '{3,4}'::half[];
-
-SELECT inner_product('{1,2}'::half[], '{3,4}'::half[]);
-SELECT inner_product('{1,2}'::half[], '{3}'::half[]);
-SELECT inner_product('{65504}'::half[], '{65504}'::half[]);
-SELECT '{1,2}'::half[] <#> '{3,4}'::half[];
-
-SELECT cosine_distance('{1,2}'::half[], '{2,4}'::half[]);
-SELECT cosine_distance('{1,2}'::half[], '{0,0}'::half[]);
-SELECT cosine_distance('{1,1}'::half[], '{1,1}'::half[]);
-SELECT cosine_distance('{1,0}'::half[], '{0,2}'::half[]);
-SELECT cosine_distance('{1,1}'::half[], '{-1,-1}'::half[]);
-SELECT cosine_distance('{1,2}'::half[], '{3}'::half[]);
-SELECT cosine_distance('{1,1}'::half[], '{1.1,1.1}'::half[]);
-SELECT cosine_distance('{1,1}'::half[], '{-1.1,-1.1}'::half[]);
-SELECT '{1,2}'::half[] <=> '{2,4}'::half[];
-
-SELECT l1_distance('{0,0}'::half[], '{3,4}');
-SELECT l1_distance('{0,0}'::half[], '{0,1}');
-SELECT l1_distance('{1,2}'::half[], '{3}');

test/t/012_hnsw_build_recall.pl

@@ -95,11 +95,10 @@ for my $i (0 .. $#operators)
 
 	$node->safe_psql("postgres", "DROP INDEX idx;");
 
-	# Build index in parallel
+	# Build index in parallel in memory
 	my ($ret, $stdout, $stderr) = $node->psql("postgres", qq(
 		SET client_min_messages = DEBUG;
 		SET min_parallel_table_scan_size = 1;
-		SET hnsw.enable_parallel_build = on;
 		CREATE INDEX idx ON tst USING hnsw (v $opclass);
 	));
 	is($ret, 0, $stderr);
@@ -109,6 +108,21 @@ for my $i (0 .. $#operators)
 	test_recall($min, $operator);
 
 	$node->safe_psql("postgres", "DROP INDEX idx;");
+
+	# Build index in parallel on disk
+	# Set parallel_workers on table to use workers with low maintenance_work_mem
+	($ret, $stdout, $stderr) = $node->psql("postgres", qq(
+		ALTER TABLE tst SET (parallel_workers = 2);
+		SET client_min_messages = DEBUG;
+		SET maintenance_work_mem = '4MB';
+		CREATE INDEX idx ON tst USING hnsw (v $opclass);
+		ALTER TABLE tst RESET (parallel_workers);
+	));
+	is($ret, 0, $stderr);
+	like($stderr, qr/using \d+ parallel workers/);
+	like($stderr, qr/hnsw graph no longer fits into maintenance_work_mem/);
+
+	$node->safe_psql("postgres", "DROP INDEX idx;");
 }
 
 done_testing();