Fixed crash with debugging disabled [skip ci]

Fix CREATE INDEX CONCURRENTLY crash on ivfflat with assertion-enabled PostgreSQL

.github/workflows/build.yml

@@ -23,7 +23,7 @@ jobs:
           - postgres: 13
             os: ubuntu-22.04
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6
       - uses: ankane/setup-postgres@v1
         with:
           postgres-version: ${{ matrix.postgres }}
@@ -37,10 +37,10 @@ jobs:
       - run: make installcheck
       - if: ${{ failure() }}
         run: cat regression.diffs
-      # - run: |
-      #     sudo apt-get update
-      #     sudo apt-get install libipc-run-perl
-      # - run: make prove_installcheck
+      - run: |
+          sudo apt-get update
+          sudo apt-get install libipc-run-perl
+      - run: make prove_installcheck
   mac:
     runs-on: ${{ matrix.os }}
     if: ${{ !startsWith(github.ref_name, 'windows') }}
@@ -53,7 +53,7 @@ jobs:
           - postgres: 14
             os: macos-15-intel
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6
       - uses: ankane/setup-postgres@v1
         with:
           postgres-version: ${{ matrix.postgres }}
@@ -65,21 +65,21 @@ jobs:
       - if: ${{ failure() }}
         run: cat regression.diffs
       # Homebrew Postgres does not enable TAP tests, so need to download
-      # - run: |
-      #     brew install cpanm
-      #     cpanm --notest IPC::Run
-      #     wget -q https://github.com/postgres/postgres/archive/refs/tags/$TAG.tar.gz
-      #     tar xf $TAG.tar.gz
-      #     mv postgres-$TAG postgres
-      #   env:
-      #     TAG: ${{ matrix.postgres == 18 && 'REL_18_0' || 'REL_14_19' }}
-      # - run: make prove_installcheck PROVE_FLAGS="-I ./postgres/src/test/perl -I ./test/perl"
-      #   env:
-      #     PERL5LIB: /Users/runner/perl5/lib/perl5
-      # - run: make clean && $(brew --prefix llvm@$LLVM_VERSION)/bin/scan-build --status-bugs make
-      #   env:
-      #     LLVM_VERSION: ${{ matrix.os == 'macos-26' && 20 || 18 }}
-      #     PG_CFLAGS: -DUSE_ASSERT_CHECKING
+      - run: |
+          brew install cpanm
+          cpanm --notest IPC::Run
+          wget -q https://github.com/postgres/postgres/archive/refs/tags/$TAG.tar.gz
+          tar xf $TAG.tar.gz
+          mv postgres-$TAG postgres
+        env:
+          TAG: ${{ matrix.postgres == 18 && 'REL_18_2' || 'REL_14_21' }}
+      - run: make prove_installcheck PROVE_FLAGS="-I ./postgres/src/test/perl -I ./test/perl"
+        env:
+          PERL5LIB: /Users/runner/perl5/lib/perl5
+      - run: make clean && $(brew --prefix llvm@$LLVM_VERSION)/bin/scan-build --status-bugs make
+        env:
+          LLVM_VERSION: ${{ matrix.os == 'macos-26' && 20 || 18 }}
+          PG_CFLAGS: -DUSE_ASSERT_CHECKING
   windows:
     runs-on: ${{ matrix.os }}
     if: ${{ !startsWith(github.ref_name, 'mac') }}
@@ -92,7 +92,7 @@ jobs:
           - postgres: 14
             os: windows-2022
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6
       - uses: ankane/setup-postgres@v1
         with:
           postgres-version: ${{ matrix.postgres }}
@@ -106,4 +106,38 @@ jobs:
         shell: cmd
       - if: ${{ failure() }}
         run: cat regression.diffs
-
+  i386:
+    if: ${{ !startsWith(github.ref_name, 'mac') && !startsWith(github.ref_name, 'windows') }}
+    runs-on: ubuntu-latest
+    container:
+      image: debian:12
+      options: --platform linux/386
+    steps:
+      - run: apt-get update && apt-get install -y build-essential git libipc-run-perl postgresql-15 postgresql-server-dev-15 sudo
+      - run: service postgresql start
+      - run: |
+          git clone https://github.com/${{ github.repository }}.git pgvector
+          cd pgvector
+          git fetch origin ${{ github.ref }}
+          git reset --hard FETCH_HEAD
+          make
+          make install
+          chown -R postgres .
+          sudo -u postgres make installcheck
+          sudo -u postgres make prove_installcheck
+        env:
+          PG_CFLAGS: -DUSE_ASSERT_CHECKING -Wall -Wextra -Werror -Wno-unused-parameter -Wno-sign-compare
+      - if: ${{ failure() }}
+        run: cat pgvector/regression.diffs
+  valgrind:
+    if: ${{ !startsWith(github.ref_name, 'mac') && !startsWith(github.ref_name, 'windows') }}
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v6
+      - uses: ankane/setup-postgres-valgrind@v1
+        with:
+          postgres-version: 18
+          check-ub: yes
+      - run: make OPTFLAGS=""
+      - run: sudo --preserve-env=PG_CONFIG make install
+      - run: make installcheck

CHANGELOG.md

@@ -1,5 +1,6 @@
-## 0.8.2 (unreleased)
+## 0.8.2 (2026-02-25)
 
+- Fixed buffer overflow with parallel HNSW index build - [more info](https://github.com/pgvector/pgvector/issues/959)
 - Improved `install` target on Windows
 - Fixed `Index Searches` in `EXPLAIN` output for Postgres 18
 

Dockerfile

@@ -5,7 +5,7 @@ ARG DEBIAN_CODENAME=bookworm
 FROM postgres:$PG_MAJOR-$DEBIAN_CODENAME
 ARG PG_MAJOR
 
-ADD https://github.com/pgvector/pgvector.git#v0.8.1 /tmp/pgvector
+ADD https://github.com/pgvector/pgvector.git#v0.8.2 /tmp/pgvector
 
 RUN apt-get update && \
 		apt-mark hold locales && \

LICENSE

@@ -1,4 +1,4 @@
-Portions Copyright (c) 1996-2025, PostgreSQL Global Development Group
+Portions Copyright (c) 1996-2026, PostgreSQL Global Development Group
 
 Portions Copyright (c) 1994, The Regents of the University of California
 

META.json

@@ -2,7 +2,7 @@
 	"name": "vector",
 	"abstract": "Open-source vector similarity search for Postgres",
 	"description": "Supports L2 distance, inner product, and cosine distance",
-	"version": "0.8.1",
+	"version": "0.8.2",
 	"maintainer": [
 		"Andrew Kane <andrew@ankane.org>"
 	],
@@ -20,7 +20,7 @@
 		"vector": {
 			"file": "sql/vector.sql",
 			"docfile": "README.md",
-			"version": "0.8.1",
+			"version": "0.8.2",
 			"abstract": "Open-source vector similarity search for Postgres"
 		}
 	},

Makefile

@@ -1,5 +1,5 @@
 EXTENSION = vector
-EXTVERSION = 0.8.1
+EXTVERSION = 0.8.2
 
 MODULE_big = vector
 DATA = $(wildcard sql/*--*--*.sql)
@@ -27,6 +27,11 @@ ifneq ($(filter ppc64%, $(shell uname -m)), )
 	OPTFLAGS =
 endif
 
+# RISC-V64 doesn't support -march=native
+ifeq ($(shell uname -m), riscv64)
+	OPTFLAGS =
+endif
+
 # For auto-vectorization:
 # - GCC (needs -ftree-vectorize OR -O3) - https://gcc.gnu.org/projects/tree-ssa/vectorization.html
 # - Clang (could use pragma instead) - https://llvm.org/docs/Vectorizers.html

Makefile.win

@@ -1,5 +1,5 @@
 EXTENSION = vector
-EXTVERSION = 0.8.1
+EXTVERSION = 0.8.2
 
 DATA_built = sql\$(EXTENSION)--$(EXTVERSION).sql
 OBJS = src\bitutils.obj src\bitvec.obj src\halfutils.obj src\halfvec.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\sparsevec.obj src\vector.obj

README.md

@@ -11,6 +11,8 @@ Store your vectors with the rest of your data. Supports:
 
 Plus [ACID](https://en.wikipedia.org/wiki/ACID) compliance, point-in-time recovery, JOINs, and all of the other [great features](https://www.postgresql.org/about/) of Postgres
 
+Have a lot of vectors? Use [quantization](#scaling) to scale
+
 [![Build Status](https://github.com/pgvector/pgvector/actions/workflows/build.yml/badge.svg)](https://github.com/pgvector/pgvector/actions)
 
 ## Installation
@@ -21,7 +23,7 @@ Compile and install the extension (supports Postgres 13+)
 
 ```sh
 cd /tmp
-git clone --branch v0.8.1 https://github.com/pgvector/pgvector.git
+git clone --branch v0.8.2 https://github.com/pgvector/pgvector.git
 cd pgvector
 make
 make install # may need sudo
@@ -38,7 +40,7 @@ Ensure [C++ support in Visual Studio](https://learn.microsoft.com/en-us/cpp/buil
 ```cmd
 set "PGROOT=C:\Program Files\PostgreSQL\18"
 cd %TEMP%
-git clone --branch v0.8.1 https://github.com/pgvector/pgvector.git
+git clone --branch v0.8.2 https://github.com/pgvector/pgvector.git
 cd pgvector
 nmake /F Makefile.win
 nmake /F Makefile.win install
@@ -314,6 +316,8 @@ For a large number of workers, you may need to increase `max_parallel_workers` (
 
 The [index options](#index-options) also have a significant impact on build time (use the defaults unless seeing low recall)
 
+Use [binary quantization](#binary-quantization) for faster build times at scale
+
 ### Indexing Progress
 
 Check [indexing progress](https://www.postgresql.org/docs/current/progress-reporting.html#CREATE-INDEX-PROGRESS-REPORTING)
@@ -443,13 +447,7 @@ Exact indexes work well for conditions that match a low percentage of rows. Othe
 CREATE INDEX ON items USING hnsw (embedding vector_l2_ops);
 ```
 
-With approximate indexes, filtering is applied *after* the index is scanned. If a condition matches 10% of rows, with HNSW and the default `hnsw.ef_search` of 40, only 4 rows will match on average. For more rows, increase `hnsw.ef_search`.
-
-```sql
-SET hnsw.ef_search = 200;
-```
-
-Starting with 0.8.0, you can enable [iterative index scans](#iterative-index-scans), which will automatically scan more of the index when needed.
+With approximate indexes, filtering is applied *after* the index is scanned. If a condition matches 10% of rows, with HNSW and the default `hnsw.ef_search` of 40, only 4 rows will match on average. For more rows, enable [iterative index scans](#iterative-index-scans), which will automatically scan more of the index when needed.
 
 ```sql
 SET hnsw.iterative_scan = strict_order;
@@ -673,6 +671,10 @@ SHOW shared_buffers;
 
 Be sure to restart Postgres for changes to take effect.
 
+### Storing
+
+Use the `halfvec` type instead of `vector` for a smaller working set.
+
 ### Loading
 
 Use `COPY` for bulk loading data ([example](https://github.com/pgvector/pgvector-python/blob/master/examples/loading/example.py)).
@@ -687,6 +689,8 @@ Add any indexes *after* loading the initial data for best performance.
 
 See index build time for [HNSW](#index-build-time) and [IVFFlat](#index-build-time-1).
 
+Use [binary quantization](#binary-quantization) for smaller indexes and faster build times at scale.
+
 In production environments, create indexes concurrently to avoid blocking writes.
 
 ```sql
@@ -717,6 +721,8 @@ SELECT * FROM items ORDER BY embedding <#> '[3,1,2]' LIMIT 5;
 
 #### Approximate Search
 
+Use [binary quantization](#binary-quantization) with re-ranking to keep indexes in-memory at scale.
+
 To speed up queries with an IVFFlat index, increase the number of inverted lists (at the expense of recall).
 
 ```sql
@@ -732,21 +738,20 @@ REINDEX INDEX CONCURRENTLY index_name;
 VACUUM table_name;
 ```
 
+## Scaling
+
+For a smaller working set:
+
+1. Use the `halfvec` type instead of `vector` for tables
+2. Use [binary quantization](#binary-quantization) for indexes (with re-ranking for search)
+
+Scale vertically by increasing memory, CPU, and storage on a single instance. Use existing tools to [tune parameters](#tuning) and [monitor performance](#monitoring).
+
+Scale horizontally with [replicas](https://www.postgresql.org/docs/current/hot-standby.html), or use [Citus](https://github.com/citusdata/citus), [PgDog](https://github.com/pgdogdev/pgdog), or another approach for sharding ([example](https://github.com/pgvector/pgvector-python/blob/master/examples/citus/example.py)).
+
 ## Monitoring
 
-Monitor performance with [pg_stat_statements](https://www.postgresql.org/docs/current/pgstatstatements.html) (be sure to add it to `shared_preload_libraries`).
-
-```sql
-CREATE EXTENSION pg_stat_statements;
-```
-
-Get the most time-consuming queries with:
-
-```sql
-SELECT query, calls, ROUND((total_plan_time + total_exec_time) / calls) AS avg_time_ms,
-    ROUND((total_plan_time + total_exec_time) / 60000) AS total_time_min
-    FROM pg_stat_statements ORDER BY total_plan_time + total_exec_time DESC LIMIT 20;
-```
+Use existing tools like [pg_stat_statements](https://www.postgresql.org/docs/current/pgstatstatements.html) or [PgHero](https://github.com/ankane/pghero) to monitor performance.
 
 Monitor recall by comparing results from approximate search with exact search.
 
@@ -757,14 +762,6 @@ SELECT ...
 COMMIT;
 ```
 
-## Scaling
-
-Scale pgvector the same way you scale Postgres.
-
-Scale vertically by increasing memory, CPU, and storage on a single instance. Use existing tools to [tune parameters](#tuning) and [monitor performance](#monitoring).
-
-Scale horizontally with [replicas](https://www.postgresql.org/docs/current/hot-standby.html), or use [Citus](https://github.com/citusdata/citus) or another approach for sharding ([example](https://github.com/pgvector/pgvector-python/blob/master/examples/citus/example.py)).
-
 ## Languages
 
 Use pgvector from any language with a Postgres client. You can even generate and store vectors in one language and query them in another.
@@ -776,6 +773,7 @@ Algol | [pgvector-algol](https://github.com/pgvector/pgvector-algol)
 C | [pgvector-c](https://github.com/pgvector/pgvector-c)
 C++ | [pgvector-cpp](https://github.com/pgvector/pgvector-cpp)
 C#, F#, Visual Basic | [pgvector-dotnet](https://github.com/pgvector/pgvector-dotnet)
+COBOL | [pgvector-cobol](https://github.com/pgvector/pgvector-cobol)
 Crystal | [pgvector-crystal](https://github.com/pgvector/pgvector-crystal)
 D | [pgvector-d](https://github.com/pgvector/pgvector-d)
 Dart | [pgvector-dart](https://github.com/pgvector/pgvector-dart)
@@ -877,6 +875,8 @@ No, but like other index types, you’ll likely see better performance if they d
 SELECT pg_size_pretty(pg_relation_size('index_name'));
 ```
 
+Use [half-precision indexing](#half-precision-indexing) or [binary quantization](#binary-quantization) for smaller indexes.
+
 ## Troubleshooting
 
 #### Why isn’t a query using an index?
@@ -1151,23 +1151,23 @@ This adds pgvector to the [Postgres image](https://hub.docker.com/_/postgres) (r
 
 Supported tags are:
 
-- `pg18-trixie`, `0.8.1-pg18-trixie`
-- `pg18-bookworm`, `0.8.1-pg18-bookworm`, `pg18`, `0.8.1-pg18`
-- `pg17-trixie`, `0.8.1-pg17-trixie`
-- `pg17-bookworm`, `0.8.1-pg17-bookworm`, `pg17`, `0.8.1-pg17`
-- `pg16-trixie`, `0.8.1-pg16-trixie`
-- `pg16-bookworm`, `0.8.1-pg16-bookworm`, `pg16`, `0.8.1-pg16`
-- `pg15-trixie`, `0.8.1-pg15-trixie`
-- `pg15-bookworm`, `0.8.1-pg15-bookworm`, `pg15`, `0.8.1-pg15`
-- `pg14-trixie`, `0.8.1-pg14-trixie`
-- `pg14-bookworm`, `0.8.1-pg14-bookworm`, `pg14`, `0.8.1-pg14`
-- `pg13-trixie`, `0.8.1-pg13-trixie`
-- `pg13-bookworm`, `0.8.1-pg13-bookworm`, `pg13`, `0.8.1-pg13`
+- `pg18-trixie`, `0.8.2-pg18-trixie`
+- `pg18-bookworm`, `0.8.2-pg18-bookworm`, `pg18`, `0.8.2-pg18`
+- `pg17-trixie`, `0.8.2-pg17-trixie`
+- `pg17-bookworm`, `0.8.2-pg17-bookworm`, `pg17`, `0.8.2-pg17`
+- `pg16-trixie`, `0.8.2-pg16-trixie`
+- `pg16-bookworm`, `0.8.2-pg16-bookworm`, `pg16`, `0.8.2-pg16`
+- `pg15-trixie`, `0.8.2-pg15-trixie`
+- `pg15-bookworm`, `0.8.2-pg15-bookworm`, `pg15`, `0.8.2-pg15`
+- `pg14-trixie`, `0.8.2-pg14-trixie`
+- `pg14-bookworm`, `0.8.2-pg14-bookworm`, `pg14`, `0.8.2-pg14`
+- `pg13-trixie`, `0.8.2-pg13-trixie`
+- `pg13-bookworm`, `0.8.2-pg13-bookworm`, `pg13`, `0.8.2-pg13`
 
 You can also build the image manually:
 
 ```sh
-git clone --branch v0.8.1 https://github.com/pgvector/pgvector.git
+git clone --branch v0.8.2 https://github.com/pgvector/pgvector.git
 cd pgvector
 docker build --pull --build-arg PG_MAJOR=18 -t myuser/pgvector .
 ```

sql/vector--0.8.1--0.8.2.sql

@@ -0,0 +1,2 @@
+-- complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "ALTER EXTENSION vector UPDATE TO '0.8.2'" to load this file. \quit

src/bitutils.c

@@ -169,7 +169,7 @@ BitJaccardDistanceAvx512Popcount(uint32 bytes, unsigned char *ax, unsigned char
 #endif
 
 TARGET_XSAVE static bool
-SupportsAvx512Popcount()
+SupportsAvx512Popcount(void)
 {
 	unsigned int exx[4] = {0, 0, 0, 0};
 

src/halfvec.c

@@ -23,6 +23,10 @@
 #include "varatt.h"
 #endif
 
+#if PG_VERSION_NUM >= 170000
+#include "parser/scansup.h"
+#endif
+
 #define STATE_DIMS(x) (ARR_DIMS(x)[0] - 1)
 #define CreateStateDatums(dim) palloc(sizeof(Datum) * (dim + 1))
 
@@ -133,9 +137,9 @@ InitHalfVector(int dim)
 	return result;
 }
 
-/*
- * Check for whitespace, since array_isspace() is static
- */
+#if PG_VERSION_NUM >= 170000
+#define halfvec_isspace(ch) scanner_isspace(ch)
+#else
 static inline bool
 halfvec_isspace(char ch)
 {
@@ -148,6 +152,7 @@ halfvec_isspace(char ch)
 		return true;
 	return false;
 }
+#endif
 
 /*
  * Check state array

src/hnsw.c

@@ -12,11 +12,8 @@
 #include "fmgr.h"
 #include "hnsw.h"
 #include "miscadmin.h"
-#include "nodes/nodes.h"
-#include "nodes/pathnodes.h"
 #include "nodes/pg_list.h"
-#include "storage/lockdefs.h"
-#include "storage/shmem.h"
+#include "storage/lwlock.h"
 #include "utils/float.h"
 #include "utils/guc.h"
 #include "utils/relcache.h"
@@ -261,6 +258,11 @@ hnswvalidate(Oid opclassoid)
 	return true;
 }
 
+static void
+hnswunguardbatch(IndexScanDesc scan, IndexScanBatch batch)
+{
+}
+
 /*
  * Define index handler
  *
@@ -270,6 +272,68 @@ FUNCTION_PREFIX PG_FUNCTION_INFO_V1(hnswhandler);
 Datum
 hnswhandler(PG_FUNCTION_ARGS)
 {
+#if PG_VERSION_NUM >= 190000
+	static const IndexAmRoutine amroutine = {
+		.type = T_IndexAmRoutine,
+		.amstrategies = 0,
+		.amsupport = 3,
+		.amoptsprocnum = 0,
+		.amcanorder = false,
+		.amcanorderbyop = true,
+		.amcanhash = false,
+		.amconsistentequality = false,
+		.amconsistentordering = false,
+		.amcanbackward = false,
+		.amcanmarkpos = false,
+		.amcanunique = false,
+		.amcanmulticol = false,
+		.amoptionalkey = true,
+		.amsearcharray = false,
+		.amsearchnulls = false,
+		.amstorage = false,
+		.amclusterable = false,
+		.ampredlocks = false,
+		.amcanparallel = false,
+		.amcanbuildparallel = true,
+		.amcaninclude = false,
+		.amusemaintenanceworkmem = false,
+		.amsummarizing = false,
+		.amparallelvacuumoptions = VACUUM_OPTION_PARALLEL_BULKDEL,
+		.amkeytype = InvalidOid,
+
+		.ambuild = hnswbuild,
+		.ambuildempty = hnswbuildempty,
+		.aminsert = hnswinsert,
+		.aminsertcleanup = NULL,
+		.ambulkdelete = hnswbulkdelete,
+		.amvacuumcleanup = hnswvacuumcleanup,
+		.amcanreturn = NULL,
+		.amcostestimate = hnswcostestimate,
+		.amgettreeheight = NULL,
+		.amoptions = hnswoptions,
+		.amproperty = NULL,
+		.ambuildphasename = hnswbuildphasename,
+		.amvalidate = hnswvalidate,
+		.amadjustmembers = NULL,
+		.ambeginscan = hnswbeginscan,
+		.amrescan = hnswrescan,
+		.amgettuple = NULL,
+		.amgetbatch = hnswgetbatch,
+		.amunguardbatch = hnswunguardbatch,
+		.amkillitemsbatch = NULL,
+		.amgettransform = NULL,
+		.amgetbitmap = NULL,
+		.amendscan = hnswendscan,
+		.amposreset = NULL,
+		.amestimateparallelscan = NULL,
+		.aminitparallelscan = NULL,
+		.amparallelrescan = NULL,
+		.amtranslatestrategy = NULL,
+		.amtranslatecmptype = NULL,
+	};
+
+	PG_RETURN_POINTER(&amroutine);
+#else
 	IndexAmRoutine *amroutine = makeNode(IndexAmRoutine);
 
 	amroutine->amstrategies = 0;
@@ -343,4 +407,5 @@ hnswhandler(PG_FUNCTION_ARGS)
 #endif
 
 	PG_RETURN_POINTER(amroutine);
+#endif
 }

src/hnsw.h

@@ -10,6 +10,10 @@
 #include "lib/pairingheap.h"
 #include "nodes/execnodes.h"
 #include "port.h"				/* for random() */
+#include "storage/bufpage.h"
+#include "storage/condition_variable.h"
+#include "storage/lwlock.h"
+#include "storage/s_lock.h"
 #include "utils/relptr.h"
 #include "utils/sampling.h"
 #include "vector.h"
@@ -461,7 +465,7 @@ IndexBulkDeleteResult *hnswbulkdelete(IndexVacuumInfo *info, IndexBulkDeleteResu
 IndexBulkDeleteResult *hnswvacuumcleanup(IndexVacuumInfo *info, IndexBulkDeleteResult *stats);
 IndexScanDesc hnswbeginscan(Relation index, int nkeys, int norderbys);
 void		hnswrescan(IndexScanDesc scan, ScanKey keys, int nkeys, ScanKey orderbys, int norderbys);
-bool		hnswgettuple(IndexScanDesc scan, ScanDirection dir);
+IndexScanBatch hnswgetbatch(IndexScanDesc scan, IndexScanBatch priorbatch, ScanDirection dir);
 void		hnswendscan(IndexScanDesc scan);
 
 static inline HnswNeighborArray *

src/hnswbuild.c

@@ -36,6 +36,8 @@
  */
 #include "postgres.h"
 
+#include <limits.h>
+
 #include "access/genam.h"
 #include "access/parallel.h"
 #include "access/relscan.h"
@@ -47,36 +49,17 @@
 #include "catalog/index.h"
 #include "catalog/pg_type_d.h"
 #include "commands/progress.h"
-#include "common/relpath.h"
 #include "hnsw.h"
 #include "miscadmin.h"
 #include "nodes/execnodes.h"
 #include "optimizer/optimizer.h"
-#include "storage/block.h"
-#include "storage/buf.h"
 #include "storage/bufmgr.h"
-#include "storage/bufpage.h"
 #include "storage/condition_variable.h"
-#include "storage/dsm.h"
-#include "storage/itemid.h"
-#include "storage/itemptr.h"
-#include "storage/lockdefs.h"
-#include "storage/lwlock.h"
-#include "storage/off.h"
-#include "storage/shm_toc.h"
-#include "storage/shmem.h"
-#include "storage/spin.h"
 #include "tcop/tcopprot.h"
 #include "utils/datum.h"
 #include "utils/memutils.h"
 #include "utils/rel.h"
-#include "utils/relcache.h"
 #include "utils/snapmgr.h"
-#include "utils/snapshot.h"
-
-#if PG_VERSION_NUM < 190000
-#include "storage/item.h"
-#endif
 
 #if PG_VERSION_NUM >= 160000
 #include "varatt.h"
@@ -90,11 +73,6 @@
 
 #if PG_VERSION_NUM >= 140000
 #include "utils/backend_status.h"
-#endif
-
-#if PG_VERSION_NUM >= 170000
-#include "utils/wait_event_types.h"
-#elif PG_VERSION_NUM >= 140000
 #include "utils/wait_event.h"
 #endif
 
@@ -102,6 +80,8 @@
 #define PARALLEL_KEY_HNSW_AREA			UINT64CONST(0xA000000000000002)
 #define PARALLEL_KEY_QUERY_TEXT			UINT64CONST(0xA000000000000003)
 
+#define HNSW_MAX_GRAPH_MEMORY (SIZE_MAX / 2)
+
 /*
  * Create the metapage
  */
@@ -514,6 +494,7 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
 	LWLock	   *flushLock = &graph->flushLock;
 	char	   *base = buildstate->hnswarea;
 	Datum		value;
+	Size		memoryMargin;
 
 	/* Form index value */
 	if (!HnswFormIndexValue(&value, values, isnull, buildstate->typeInfo, support))
@@ -522,6 +503,9 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
 	/* Get datum size */
 	valueSize = VARSIZE_ANY(DatumGetPointer(value));
 
+	/* In a parallel build, add a margin so allocations never fail */
+	memoryMargin = base == NULL ? 0 : 1024 * 1024;
+
 	/* Ensure graph not flushed when inserting */
 	LWLockAcquire(flushLock, LW_SHARED);
 
@@ -543,7 +527,7 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
 	 * Check that we have enough memory available for the new element now that
 	 * we have the allocator lock, and flush pages if needed.
 	 */
-	if (graph->memoryUsed >= graph->memoryTotal)
+	if (graph->memoryUsed + memoryMargin >= graph->memoryTotal)
 	{
 		LWLockRelease(&graph->allocatorLock);
 
@@ -636,7 +620,7 @@ InitGraph(HnswGraph * graph, char *base, Size memoryTotal)
 	HnswPtrStore(base, graph->head, (HnswElement) NULL);
 	HnswPtrStore(base, graph->entryPoint, (HnswElement) NULL);
 	graph->memoryUsed = 0;
-	graph->memoryTotal = memoryTotal;
+	graph->memoryTotal = Min(memoryTotal, HNSW_MAX_GRAPH_MEMORY);
 	graph->flushed = false;
 	graph->indtuples = 0;
 	SpinLockInit(&graph->lock);
@@ -677,9 +661,17 @@ static void *
 HnswSharedMemoryAlloc(Size size, void *state)
 {
 	HnswBuildState *buildstate = (HnswBuildState *) state;
-	void	   *chunk = buildstate->hnswarea + buildstate->graph->memoryUsed;
+	Size		alignedSize = MAXALIGN(size);
+	void	   *chunk;
 
-	buildstate->graph->memoryUsed += MAXALIGN(size);
+	if (alignedSize > 1024 * 1024)
+		elog(ERROR, "hnsw allocation too large");
+
+	if (buildstate->graph->memoryUsed + alignedSize > buildstate->graph->memoryTotal)
+		elog(ERROR, "hnsw allocator out of memory");
+
+	chunk = buildstate->hnswarea + buildstate->graph->memoryUsed;
+	buildstate->graph->memoryUsed += alignedSize;
 	return chunk;
 }
 
@@ -811,7 +803,11 @@ HnswParallelScanAndInsert(Relation heapRel, Relation indexRel, HnswShared * hnsw
 	buildstate.hnswarea = hnswarea;
 	InitAllocator(&buildstate.allocator, &HnswSharedMemoryAlloc, &buildstate);
 	scan = table_beginscan_parallel(heapRel,
-									ParallelTableScanFromHnswShared(hnswshared));
+									ParallelTableScanFromHnswShared(hnswshared)
+#if PG_VERSION_NUM >= 190000
+									,SO_NONE
+#endif
+		);
 	reltuples = table_index_build_scan(heapRel, indexRel, indexInfo,
 									   true, progress, BuildCallback,
 									   (void *) &buildstate, scan);
@@ -965,6 +961,8 @@ HnswBeginParallel(HnswBuildState * buildstate, bool isconcurrent, int request)
 	if (esthnswarea > estother)
 		esthnswarea -= estother;
 
+	esthnswarea = Min(esthnswarea, HNSW_MAX_GRAPH_MEMORY);
+
 	shm_toc_estimate_chunk(&pcxt->estimator, esthnswarea);
 	shm_toc_estimate_keys(&pcxt->estimator, 2);
 
@@ -1007,8 +1005,7 @@ HnswBeginParallel(HnswBuildState * buildstate, bool isconcurrent, int request)
 								  snapshot);
 
 	hnswarea = (char *) shm_toc_allocate(pcxt->toc, esthnswarea);
-	/* Report less than allocated so never fails */
-	InitGraph(&hnswshared->graphData, hnswarea, esthnswarea - 1024 * 1024);
+	InitGraph(&hnswshared->graphData, hnswarea, esthnswarea);
 
 	/*
 	 * Avoid base address for relptr for Postgres < 14.5

src/hnswinsert.c

@@ -2,26 +2,14 @@
 
 #include "access/genam.h"
 #include "access/generic_xlog.h"
-#include "common/relpath.h"
 #include "hnsw.h"
 #include "nodes/execnodes.h"
-#include "storage/block.h"
-#include "storage/buf.h"
 #include "storage/bufmgr.h"
-#include "storage/bufpage.h"
-#include "storage/itemid.h"
-#include "storage/itemptr.h"
 #include "storage/lmgr.h"
-#include "storage/lockdefs.h"
-#include "storage/off.h"
+#include "storage/lwlock.h"
 #include "utils/datum.h"
 #include "utils/memutils.h"
 #include "utils/rel.h"
-#include "utils/relcache.h"
-
-#if PG_VERSION_NUM < 190000
-#include "storage/item.h"
-#endif
 
 #if PG_VERSION_NUM >= 160000
 #include "varatt.h"

src/hnswscan.c

@@ -1,17 +1,16 @@
 #include "postgres.h"
 
+#include <limits.h>
+
 #include "access/genam.h"
+#include "access/indexbatch.h"
 #include "access/relscan.h"
-#include "access/sdir.h"
-#include "access/skey.h"
 #include "hnsw.h"
 #include "lib/pairingheap.h"
 #include "miscadmin.h"
 #include "nodes/pg_list.h"
 #include "pgstat.h"
-#include "storage/itemptr.h"
 #include "storage/lmgr.h"
-#include "storage/lockdefs.h"
 #include "utils/float.h"
 #include "utils/memutils.h"
 #include "utils/relcache.h"
@@ -137,6 +136,11 @@ hnswbeginscan(Relation index, int nkeys, int norderbys)
 	double		maxMemory;
 
 	scan = RelationGetIndexScan(index, nkeys, norderbys);
+	scan->maxitemsbatch = hnsw_ef_search * HNSW_HEAPTIDS;
+	/* unused but must be > 0 */
+	scan->batch_index_opaque_static = MAXALIGN(1);
+	scan->batch_index_opaque_dyn = 0;
+	scan->batch_tuples_workspace = 0;
 
 	so = (HnswScanOpaque) palloc(sizeof(HnswScanOpaqueData));
 	so->typeInfo = HnswGetTypeInfo(index);
@@ -155,7 +159,7 @@ hnswbeginscan(Relation index, int nkeys, int norderbys)
 	/* Calculate max memory */
 	/* Add 256 extra bytes to fill last block when close */
 	maxMemory = (double) work_mem * hnsw_scan_mem_multiplier * 1024.0 + 256;
-	so->maxMemory = Min(maxMemory, (double) SIZE_MAX);
+	so->maxMemory = Min(maxMemory, (double) (SIZE_MAX / 2));
 
 	scan->opaque = so;
 
@@ -186,12 +190,13 @@ hnswrescan(IndexScanDesc scan, ScanKey keys, int nkeys, ScanKey orderbys, int no
 }
 
 /*
- * Fetch the next tuple in the given scan
+ * Fetch the next batch in the given scan
  */
-bool
-hnswgettuple(IndexScanDesc scan, ScanDirection dir)
+IndexScanBatch
+hnswgetbatch(IndexScanDesc scan, IndexScanBatch priorbatch, ScanDirection dir)
 {
 	HnswScanOpaque so = (HnswScanOpaque) scan->opaque;
+	IndexScanBatch batch = indexam_util_alloc_batch(scan);
 	MemoryContext oldCtx = MemoryContextSwitchTo(so->tmpCtx);
 
 	/*
@@ -247,6 +252,7 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
 		HnswSearchCandidate *sc;
 		HnswElement element;
 		ItemPointer heaptid;
+		int			nitems = 0;
 
 		if (list_length(so->w) == 0)
 		{
@@ -292,44 +298,64 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
 				break;
 		}
 
-		sc = llast(so->w);
-		element = HnswPtrAccess(base, sc->element);
-
-		/* Move to next element if no valid heap TIDs */
-		if (element->heaptidsLength == 0)
+		while (list_length(so->w) != 0)
 		{
-			so->w = list_delete_last(so->w);
+			sc = llast(so->w);
+			element = HnswPtrAccess(base, sc->element);
 
-			/* Mark memory as free for next iteration */
-			if (hnsw_iterative_scan != HNSW_ITERATIVE_SCAN_OFF)
+			/* Move to next element if no valid heap TIDs */
+			if (element->heaptidsLength == 0)
 			{
-				pfree(element);
-				pfree(sc);
+				so->w = list_delete_last(so->w);
+
+				/* Mark memory as free for next iteration */
+				if (hnsw_iterative_scan != HNSW_ITERATIVE_SCAN_OFF)
+				{
+					pfree(element);
+					pfree(sc);
+				}
+
+				continue;
 			}
 
+			heaptid = &element->heaptids[--element->heaptidsLength];
+
+			if (hnsw_iterative_scan == HNSW_ITERATIVE_SCAN_STRICT)
+			{
+				if (sc->distance < so->previousDistance)
+					continue;
+
+				so->previousDistance = sc->distance;
+			}
+
+			batch->items[nitems].tableTid = *heaptid;
+			batch->items[nitems].indexOffset = -1;
+			batch->items[nitems].tupleOffset = 0;
+			nitems++;
+
+			/* Keep batch size flexible */
+			if (nitems == scan->maxitemsbatch)
+				break;
+		}
+
+		/* Needed for strict iterative scans */
+		if (nitems == 0)
 			continue;
-		}
-
-		heaptid = &element->heaptids[--element->heaptidsLength];
-
-		if (hnsw_iterative_scan == HNSW_ITERATIVE_SCAN_STRICT)
-		{
-			if (sc->distance < so->previousDistance)
-				continue;
-
-			so->previousDistance = sc->distance;
-		}
 
 		MemoryContextSwitchTo(oldCtx);
 
-		scan->xs_heaptid = *heaptid;
 		scan->xs_recheck = false;
 		scan->xs_recheckorderby = false;
-		return true;
+
+		batch->firstItem = 0;
+		batch->lastItem = nitems - 1;
+		batch->dir = ForwardScanDirection;
+		return batch;
 	}
 
 	MemoryContextSwitchTo(oldCtx);
-	return false;
+	indexam_util_release_batch(scan, batch);
+	return NULL;
 }
 
 /*

src/hnswutils.c

@@ -5,24 +5,16 @@
 #include "access/genam.h"
 #include "access/generic_xlog.h"
 #include "common/hashfn.h"
-#include "common/relpath.h"
 #include "fmgr.h"
 #include "hnsw.h"
 #include "lib/pairingheap.h"
 #include "nodes/pg_list.h"
 #include "port/atomics.h"
 #include "sparsevec.h"
-#include "storage/block.h"
-#include "storage/buf.h"
 #include "storage/bufmgr.h"
-#include "storage/bufpage.h"
-#include "storage/itemptr.h"
-#include "storage/lwlock.h"
-#include "storage/off.h"
 #include "utils/datum.h"
 #include "utils/memdebug.h"
 #include "utils/rel.h"
-#include "utils/relcache.h"
 #include "vector.h"
 
 #if PG_VERSION_NUM >= 160000

src/hnswvacuum.c

@@ -3,24 +3,12 @@
 #include "access/genam.h"
 #include "access/generic_xlog.h"
 #include "commands/vacuum.h"
-#include "common/relpath.h"
 #include "hnsw.h"
 #include "nodes/pg_list.h"
-#include "storage/block.h"
-#include "storage/buf.h"
 #include "storage/bufmgr.h"
-#include "storage/bufpage.h"
-#include "storage/itemptr.h"
 #include "storage/lmgr.h"
-#include "storage/lockdefs.h"
-#include "storage/off.h"
 #include "utils/memutils.h"
 #include "utils/rel.h"
-#include "utils/relcache.h"
-
-#if PG_VERSION_NUM < 190000
-#include "storage/item.h"
-#endif
 
 #if PG_VERSION_NUM >= 160000
 #include "varatt.h"

src/ivfbuild.c

@@ -2,7 +2,6 @@
 
 #include <float.h>
 
-#include "access/attnum.h"
 #include "access/genam.h"
 #include "access/generic_xlog.h"
 #include "access/itup.h"
@@ -17,38 +16,20 @@
 #include "catalog/pg_operator_d.h"
 #include "catalog/pg_type_d.h"
 #include "commands/progress.h"
-#include "common/relpath.h"
-#include "executor/tuptable.h"
 #include "fmgr.h"
 #include "ivfflat.h"
 #include "miscadmin.h"
 #include "nodes/execnodes.h"
 #include "optimizer/optimizer.h"
-#include "storage/block.h"
-#include "storage/buf.h"
 #include "storage/bufmgr.h"
-#include "storage/bufpage.h"
 #include "storage/condition_variable.h"
-#include "storage/dsm.h"
-#include "storage/itemptr.h"
-#include "storage/lockdefs.h"
-#include "storage/off.h"
-#include "storage/shm_toc.h"
-#include "storage/shmem.h"
-#include "storage/spin.h"
 #include "tcop/tcopprot.h"
 #include "utils/memutils.h"
 #include "utils/rel.h"
-#include "utils/relcache.h"
 #include "utils/sampling.h"
 #include "utils/snapmgr.h"
-#include "utils/snapshot.h"
 #include "utils/tuplesort.h"
 
-#if PG_VERSION_NUM < 190000
-#include "storage/item.h"
-#endif
-
 #if PG_VERSION_NUM >= 160000
 #include "varatt.h"
 #endif
@@ -61,11 +42,6 @@
 
 #if PG_VERSION_NUM >= 140000
 #include "utils/backend_status.h"
-#endif
-
-#if PG_VERSION_NUM >= 170000
-#include "utils/wait_event_types.h"
-#elif PG_VERSION_NUM >= 140000
 #include "utils/wait_event.h"
 #endif
 
@@ -87,15 +63,13 @@ AddSample(Datum *values, IvfflatBuildState * buildstate)
 	Datum		value = PointerGetDatum(PG_DETOAST_DATUM(values[0]));
 
 	/*
-	 * Normalize with KMEANS_NORM_PROC since spherical distance function
-	 * expects unit vectors
+	 * Check with KMEANS_NORM_PROC that the value can be normalized since
+	 * spherical distance function expects unit vectors
 	 */
 	if (buildstate->kmeansnormprocinfo != NULL)
 	{
 		if (!IvfflatCheckNorm(buildstate->kmeansnormprocinfo, buildstate->collation, value))
 			return;
-
-		value = IvfflatNormValue(buildstate->typeInfo, buildstate->collation, value);
 	}
 
 	if (samples->length < targsamples)
@@ -106,7 +80,7 @@ AddSample(Datum *values, IvfflatBuildState * buildstate)
 	else
 	{
 		if (buildstate->rowstoskip < 0)
-			buildstate->rowstoskip = reservoir_get_next_S(&buildstate->rstate, samples->length, targsamples);
+			buildstate->rowstoskip = reservoir_get_next_S(&buildstate->rstate, buildstate->samplerows, targsamples);
 
 		if (buildstate->rowstoskip <= 0)
 		{
@@ -122,6 +96,9 @@ AddSample(Datum *values, IvfflatBuildState * buildstate)
 
 		buildstate->rowstoskip -= 1;
 	}
+
+	/* Increment after reservoir_get_next_S */
+	buildstate->samplerows += 1;
 }
 
 /*
@@ -158,6 +135,7 @@ SampleRows(IvfflatBuildState * buildstate)
 	int			targsamples = buildstate->samples->maxlen;
 	BlockNumber totalblocks = RelationGetNumberOfBlocks(buildstate->heap);
 
+	buildstate->samplerows = 0;
 	buildstate->rowstoskip = -1;
 
 	BlockSampler_Init(&buildstate->bs, totalblocks, targsamples, RandomInt());
@@ -167,8 +145,24 @@ SampleRows(IvfflatBuildState * buildstate)
 	{
 		BlockNumber targblock = BlockSampler_Next(&buildstate->bs);
 
+		/* Set anyvisible to false like table_index_build_scan */
 		table_index_build_range_scan(buildstate->heap, buildstate->index, buildstate->indexInfo,
-									 false, true, false, targblock, 1, SampleCallback, (void *) buildstate, NULL);
+									 false, false, false, targblock, 1, SampleCallback, (void *) buildstate, NULL);
+	}
+
+	/* Normalize if needed */
+	if (buildstate->kmeansnormprocinfo != NULL)
+	{
+		VectorArray samples = buildstate->samples;
+
+		for (int i = 0; i < samples->length; i++)
+		{
+			Datum		value = PointerGetDatum(VectorArrayGet(samples, i));
+			Datum		normValue = IvfflatNormValue(buildstate->typeInfo, buildstate->collation, value);
+
+			VectorArraySet(samples, i, DatumGetPointer(normValue));
+			pfree(DatumGetPointer(normValue));
+		}
 	}
 }
 
@@ -399,6 +393,9 @@ InitBuildState(IvfflatBuildState * buildstate, Relation heap, Relation index, In
 	TupleDescInitEntry(buildstate->sortdesc, (AttrNumber) 1, "list", INT4OID, -1, 0);
 	TupleDescInitEntry(buildstate->sortdesc, (AttrNumber) 2, "tid", TIDOID, -1, 0);
 	TupleDescInitEntry(buildstate->sortdesc, (AttrNumber) 3, "vector", TupleDescAttr(buildstate->tupdesc, 0)->atttypid, -1, 0);
+#if PG_VERSION_NUM >= 190000
+	TupleDescFinalize(buildstate->sortdesc);
+#endif
 
 	buildstate->slot = MakeSingleTupleTableSlot(buildstate->sortdesc, &TTSOpsVirtual);
 
@@ -460,7 +457,7 @@ ComputeCenters(IvfflatBuildState * buildstate)
 	buildstate->samples = VectorArrayInit(numSamples, buildstate->dimensions, buildstate->centers->itemsize);
 	if (buildstate->heap != NULL)
 	{
-		SampleRows(buildstate);
+		IvfflatBench("sample rows", SampleRows(buildstate));
 
 		if (buildstate->samples->length < buildstate->lists)
 		{
@@ -675,7 +672,11 @@ IvfflatParallelScanAndSort(IvfflatSpool * ivfspool, IvfflatShared * ivfshared, S
 	ivfspool->sortstate = InitBuildSortState(buildstate.sortdesc, sortmem, coordinate);
 	buildstate.sortstate = ivfspool->sortstate;
 	scan = table_beginscan_parallel(ivfspool->heap,
-									ParallelTableScanFromIvfflatShared(ivfshared));
+									ParallelTableScanFromIvfflatShared(ivfshared)
+#if PG_VERSION_NUM >= 190000
+									,SO_NONE
+#endif
+		);
 	reltuples = table_index_build_scan(ivfspool->heap, ivfspool->index, indexInfo,
 									   true, progress, BuildCallback,
 									   (void *) &buildstate, scan);

src/ivfflat.c

@@ -9,10 +9,7 @@
 #include "commands/vacuum.h"
 #include "fmgr.h"
 #include "ivfflat.h"
-#include "nodes/nodes.h"
-#include "nodes/pathnodes.h"
 #include "nodes/pg_list.h"
-#include "storage/lockdefs.h"
 #include "utils/float.h"
 #include "utils/guc.h"
 #include "utils/relcache.h"
@@ -178,6 +175,11 @@ ivfflatvalidate(Oid opclassoid)
 	return true;
 }
 
+static void
+ivfflatunguardbatch(IndexScanDesc scan, IndexScanBatch batch)
+{
+}
+
 /*
  * Define index handler
  *
@@ -187,6 +189,68 @@ FUNCTION_PREFIX PG_FUNCTION_INFO_V1(ivfflathandler);
 Datum
 ivfflathandler(PG_FUNCTION_ARGS)
 {
+#if PG_VERSION_NUM >= 190000
+	static const IndexAmRoutine amroutine = {
+		.type = T_IndexAmRoutine,
+		.amstrategies = 0,
+		.amsupport = 5,
+		.amoptsprocnum = 0,
+		.amcanorder = false,
+		.amcanorderbyop = true,
+		.amcanhash = false,
+		.amconsistentequality = false,
+		.amconsistentordering = false,
+		.amcanbackward = false,
+		.amcanmarkpos = false,
+		.amcanunique = false,
+		.amcanmulticol = false,
+		.amoptionalkey = true,
+		.amsearcharray = false,
+		.amsearchnulls = false,
+		.amstorage = false,
+		.amclusterable = false,
+		.ampredlocks = false,
+		.amcanparallel = false,
+		.amcanbuildparallel = true,
+		.amcaninclude = false,
+		.amusemaintenanceworkmem = false,
+		.amsummarizing = false,
+		.amparallelvacuumoptions = VACUUM_OPTION_PARALLEL_BULKDEL,
+		.amkeytype = InvalidOid,
+
+		.ambuild = ivfflatbuild,
+		.ambuildempty = ivfflatbuildempty,
+		.aminsert = ivfflatinsert,
+		.aminsertcleanup = NULL,
+		.ambulkdelete = ivfflatbulkdelete,
+		.amvacuumcleanup = ivfflatvacuumcleanup,
+		.amcanreturn = NULL,
+		.amcostestimate = ivfflatcostestimate,
+		.amgettreeheight = NULL,
+		.amoptions = ivfflatoptions,
+		.amproperty = NULL,
+		.ambuildphasename = ivfflatbuildphasename,
+		.amvalidate = ivfflatvalidate,
+		.amadjustmembers = NULL,
+		.ambeginscan = ivfflatbeginscan,
+		.amrescan = ivfflatrescan,
+		.amgettuple = NULL,
+		.amgetbatch = ivfflatgetbatch,
+		.amunguardbatch = ivfflatunguardbatch,
+		.amkillitemsbatch = NULL,
+		.amgettransform = NULL,
+		.amgetbitmap = NULL,
+		.amendscan = ivfflatendscan,
+		.amposreset = NULL,
+		.amestimateparallelscan = NULL,
+		.aminitparallelscan = NULL,
+		.amparallelrescan = NULL,
+		.amtranslatestrategy = NULL,
+		.amtranslatecmptype = NULL,
+	};
+
+	PG_RETURN_POINTER(&amroutine);
+#else
 	IndexAmRoutine *amroutine = makeNode(IndexAmRoutine);
 
 	amroutine->amstrategies = 0;
@@ -260,4 +324,5 @@ ivfflathandler(PG_FUNCTION_ARGS)
 #endif
 
 	PG_RETURN_POINTER(amroutine);
+#endif
 }

src/ivfflat.h

@@ -9,6 +9,7 @@
 #include "lib/pairingheap.h"
 #include "nodes/execnodes.h"
 #include "port.h"				/* for random() */
+#include "storage/condition_variable.h"
 #include "utils/sampling.h"
 #include "utils/tuplesort.h"
 #include "vector.h"
@@ -213,7 +214,8 @@ typedef struct IvfflatBuildState
 	/* Sampling */
 	BlockSamplerData bs;
 	ReservoirStateData rstate;
-	int			rowstoskip;
+	double		samplerows;
+	double		rowstoskip;
 
 	/* Sorting */
 	Tuplesortstate *sortstate;
@@ -342,7 +344,7 @@ IndexBulkDeleteResult *ivfflatbulkdelete(IndexVacuumInfo *info, IndexBulkDeleteR
 IndexBulkDeleteResult *ivfflatvacuumcleanup(IndexVacuumInfo *info, IndexBulkDeleteResult *stats);
 IndexScanDesc ivfflatbeginscan(Relation index, int nkeys, int norderbys);
 void		ivfflatrescan(IndexScanDesc scan, ScanKey keys, int nkeys, ScanKey orderbys, int norderbys);
-bool		ivfflatgettuple(IndexScanDesc scan, ScanDirection dir);
+IndexScanBatch ivfflatgetbatch(IndexScanDesc scan, IndexScanBatch priorbatch, ScanDirection dir);
 void		ivfflatendscan(IndexScanDesc scan);
 
 #endif

src/ivfinsert.c

@@ -5,26 +5,13 @@
 #include "access/genam.h"
 #include "access/generic_xlog.h"
 #include "access/itup.h"
-#include "common/relpath.h"
 #include "fmgr.h"
 #include "ivfflat.h"
 #include "nodes/execnodes.h"
-#include "storage/block.h"
-#include "storage/buf.h"
 #include "storage/bufmgr.h"
-#include "storage/bufpage.h"
-#include "storage/itemid.h"
-#include "storage/itemptr.h"
 #include "storage/lmgr.h"
-#include "storage/lockdefs.h"
-#include "storage/off.h"
 #include "utils/memutils.h"
 #include "utils/rel.h"
-#include "utils/relcache.h"
-
-#if PG_VERSION_NUM < 190000
-#include "storage/item.h"
-#endif
 
 /*
  * Find the list that minimizes the distance function

src/ivfscan.c

@@ -2,32 +2,21 @@
 
 #include <float.h>
 
-#include "access/attnum.h"
 #include "access/genam.h"
+#include "access/indexbatch.h"
 #include "access/itup.h"
 #include "access/relscan.h"
-#include "access/sdir.h"
-#include "access/skey.h"
 #include "access/tupdesc.h"
 #include "catalog/pg_operator_d.h"
 #include "catalog/pg_type_d.h"
-#include "common/relpath.h"
-#include "executor/tuptable.h"
 #include "fmgr.h"
 #include "lib/pairingheap.h"
 #include "ivfflat.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "storage/block.h"
-#include "storage/buf.h"
 #include "storage/bufmgr.h"
-#include "storage/bufpage.h"
-#include "storage/itemid.h"
-#include "storage/itemptr.h"
-#include "storage/off.h"
 #include "utils/memutils.h"
 #include "utils/rel.h"
-#include "utils/relcache.h"
 #include "utils/snapmgr.h"
 #include "utils/tuplesort.h"
 
@@ -273,6 +262,11 @@ ivfflatbeginscan(Relation index, int nkeys, int norderbys)
 	MemoryContext oldCtx;
 
 	scan = RelationGetIndexScan(index, nkeys, norderbys);
+	scan->maxitemsbatch = 1000;
+	/* unused but must be > 0 */
+	scan->batch_index_opaque_static = MAXALIGN(1);
+	scan->batch_index_opaque_dyn = 0;
+	scan->batch_tuples_workspace = 0;
 
 	/* Get lists and dimensions from metapage */
 	IvfflatGetMetaPageInfo(index, &lists, &dimensions);
@@ -310,6 +304,9 @@ ivfflatbeginscan(Relation index, int nkeys, int norderbys)
 	so->tupdesc = CreateTemplateTupleDesc(2);
 	TupleDescInitEntry(so->tupdesc, (AttrNumber) 1, "distance", FLOAT8OID, -1, 0);
 	TupleDescInitEntry(so->tupdesc, (AttrNumber) 2, "heaptid", TIDOID, -1, 0);
+#if PG_VERSION_NUM >= 190000
+	TupleDescFinalize(so->tupdesc);
+#endif
 
 	/* Prep sort */
 	so->sortstate = InitScanSortState(so->tupdesc);
@@ -357,14 +354,16 @@ ivfflatrescan(IndexScanDesc scan, ScanKey keys, int nkeys, ScanKey orderbys, int
 }
 
 /*
- * Fetch the next tuple in the given scan
+ * Fetch the next batch in the given scan
  */
-bool
-ivfflatgettuple(IndexScanDesc scan, ScanDirection dir)
+IndexScanBatch
+ivfflatgetbatch(IndexScanDesc scan, IndexScanBatch priorbatch, ScanDirection dir)
 {
 	IvfflatScanOpaque so = (IvfflatScanOpaque) scan->opaque;
+	IndexScanBatch batch = indexam_util_alloc_batch(scan);
 	ItemPointer heaptid;
 	bool		isnull;
+	int			nitems = 0;
 
 	/*
 	 * Index can be used to scan backward, but Postgres doesn't support
@@ -402,17 +401,37 @@ ivfflatgettuple(IndexScanDesc scan, ScanDirection dir)
 	while (!tuplesort_gettupleslot(so->sortstate, true, false, so->mslot, NULL))
 	{
 		if (so->listIndex == so->maxProbes)
-			return false;
+		{
+			indexam_util_release_batch(scan, batch);
+			return NULL;
+		}
 
 		IvfflatBench("GetScanItems", GetScanItems(scan, so->value));
 	}
 
-	heaptid = (ItemPointer) DatumGetPointer(slot_getattr(so->mslot, 2, &isnull));
+	for (;;)
+	{
+		heaptid = (ItemPointer) DatumGetPointer(slot_getattr(so->mslot, 2, &isnull));
+
+		batch->items[nitems].tableTid = *heaptid;
+		batch->items[nitems].indexOffset = -1;
+		batch->items[nitems].tupleOffset = 0;
+		nitems++;
+
+		if (nitems == scan->maxitemsbatch)
+			break;
+
+		if (!tuplesort_gettupleslot(so->sortstate, true, false, so->mslot, NULL))
+			break;
+	}
 
-	scan->xs_heaptid = *heaptid;
 	scan->xs_recheck = false;
 	scan->xs_recheckorderby = false;
-	return true;
+
+	batch->firstItem = 0;
+	batch->lastItem = nitems - 1;
+	batch->dir = ForwardScanDirection;
+	return batch;
 }
 
 /*

src/ivfutils.c

@@ -2,15 +2,11 @@
 
 #include "access/genam.h"
 #include "access/generic_xlog.h"
-#include "common/relpath.h"
 #include "fmgr.h"
 #include "halfutils.h"
 #include "halfvec.h"
 #include "ivfflat.h"
-#include "storage/block.h"
-#include "storage/buf.h"
 #include "storage/bufmgr.h"
-#include "storage/bufpage.h"
 #include "utils/relcache.h"
 #include "utils/varbit.h"
 #include "vector.h"

src/ivfvacuum.c

@@ -4,14 +4,8 @@
 #include "access/generic_xlog.h"
 #include "access/itup.h"
 #include "commands/vacuum.h"
-#include "common/relpath.h"
 #include "ivfflat.h"
-#include "storage/block.h"
-#include "storage/buf.h"
 #include "storage/bufmgr.h"
-#include "storage/bufpage.h"
-#include "storage/itemptr.h"
-#include "storage/off.h"
 #include "utils/relcache.h"
 
 #if PG_VERSION_NUM >= 180000

src/sparsevec.c

@@ -22,6 +22,10 @@
 #include "varatt.h"
 #endif
 
+#if PG_VERSION_NUM >= 170000
+#include "parser/scansup.h"
+#endif
+
 typedef struct SparseInputElement
 {
 	int32		index;
@@ -155,9 +159,9 @@ InitSparseVector(int dim, int nnz)
 	return result;
 }
 
-/*
- * Check for whitespace, since array_isspace() is static
- */
+#if PG_VERSION_NUM >= 170000
+#define sparsevec_isspace(ch) scanner_isspace(ch)
+#else
 static inline bool
 sparsevec_isspace(char ch)
 {
@@ -170,6 +174,7 @@ sparsevec_isspace(char ch)
 		return true;
 	return false;
 }
+#endif
 
 /*
  * Compare indices
@@ -177,10 +182,10 @@ sparsevec_isspace(char ch)
 static int
 CompareIndices(const void *a, const void *b)
 {
-	if (((SparseInputElement *) a)->index < ((SparseInputElement *) b)->index)
+	if (((const SparseInputElement *) a)->index < ((const SparseInputElement *) b)->index)
 		return -1;
 
-	if (((SparseInputElement *) a)->index > ((SparseInputElement *) b)->index)
+	if (((const SparseInputElement *) a)->index > ((const SparseInputElement *) b)->index)
 		return 1;
 
 	return 0;

src/vector.c

@@ -26,6 +26,10 @@
 #include "varatt.h"
 #endif
 
+#if PG_VERSION_NUM >= 170000
+#include "parser/scansup.h"
+#endif
+
 #define STATE_DIMS(x) (ARR_DIMS(x)[0] - 1)
 #define CreateStateDatums(dim) palloc(sizeof(Datum) * (dim + 1))
 
@@ -36,7 +40,7 @@
 #endif
 
 #if PG_VERSION_NUM >= 180000
-PG_MODULE_MAGIC_EXT(.name = "vector",.version = "0.8.1");
+PG_MODULE_MAGIC_EXT(.name = "vector", .version = "0.8.2");
 #else
 PG_MODULE_MAGIC;
 #endif
@@ -129,9 +133,9 @@ InitVector(int dim)
 	return result;
 }
 
-/*
- * Check for whitespace, since array_isspace() is static
- */
+#if PG_VERSION_NUM >= 170000
+#define vector_isspace(ch) scanner_isspace(ch)
+#else
 static inline bool
 vector_isspace(char ch)
 {
@@ -144,6 +148,7 @@ vector_isspace(char ch)
 		return true;
 	return false;
 }
+#endif
 
 /*
  * Check state array

test/t/005_ivfflat_query_recall.pl

@@ -16,29 +16,19 @@ $node->safe_psql("postgres",
 	"INSERT INTO tst SELECT i, ARRAY[random(), random(), random()] FROM generate_series(1, 100000) i;"
 );
 
-# Check each index type
-my @operators = ("<->", "<#>", "<=>");
-my @opclasses = ("vector_l2_ops", "vector_ip_ops", "vector_cosine_ops");
+# Add index
+$node->safe_psql("postgres", "CREATE INDEX ON tst USING ivfflat (v vector_l2_ops);");
 
-for my $i (0 .. $#operators)
+# Test 100% recall
+for (1 .. 20)
 {
-	my $operator = $operators[$i];
-	my $opclass = $opclasses[$i];
-
-	# Add index
-	$node->safe_psql("postgres", "CREATE INDEX ON tst USING ivfflat (v $opclass);");
-
-	# Test 100% recall
-	for (1 .. 20)
-	{
-		my $id = int(rand() * 100000);
-		my $query = $node->safe_psql("postgres", "SELECT v FROM tst WHERE i = $id;");
-		my $res = $node->safe_psql("postgres", qq(
-			SET enable_seqscan = off;
-			SELECT v FROM tst ORDER BY v <-> '$query' LIMIT 1;
-		));
-		is($res, $query);
-	}
+	my $id = int(rand() * 100000);
+	my $query = $node->safe_psql("postgres", "SELECT v FROM tst WHERE i = $id;");
+	my $res = $node->safe_psql("postgres", qq(
+		SET enable_seqscan = off;
+		SELECT v FROM tst ORDER BY v <-> '$query' LIMIT 1;
+	));
+	is($res, $query);
 }
 
 done_testing();

test/t/045_hnsw_low_memory_build.pl

@@ -0,0 +1,29 @@
+use strict;
+use warnings FATAL => 'all';
+use PostgreSQL::Test::Cluster;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+# Initialize node
+my $node = PostgreSQL::Test::Cluster->new('node');
+$node->init;
+$node->start;
+
+# Create table
+$node->safe_psql("postgres", "CREATE EXTENSION vector;");
+$node->safe_psql("postgres", "CREATE TABLE tst (v vector(3));");
+$node->safe_psql("postgres",
+	"INSERT INTO tst SELECT ARRAY[random(), random(), random()] FROM generate_series(1, 1000) i;"
+);
+
+my ($ret, $stdout, $stderr) = $node->psql("postgres", qq(
+	SET client_min_messages = DEBUG;
+	SET maintenance_work_mem = '3073kB';
+	ALTER TABLE tst SET (parallel_workers = 1);
+	CREATE INDEX ON tst USING hnsw (v vector_l2_ops);
+));
+is($ret, 0, $stderr);
+like($stderr, qr/using \d+ parallel workers/);
+like($stderr, qr/hnsw graph no longer fits into maintenance_work_mem after 0 tuples/);
+
+done_testing();

vector.control

@@ -1,4 +1,4 @@
 comment = 'vector data type and ivfflat and hnsw access methods'
-default_version = '0.8.1'
+default_version = '0.8.2'
 module_pathname = '$libdir/vector'
 relocatable = true