Updated SparsevecInnerProduct [skip ci]

Co-authored-by: chungkn from OneMount Group <kimngocchung.k2a@gmail.com>

.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

@@ -21,7 +21,7 @@ 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 +38,7 @@ 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
@@ -776,6 +776,7 @@ 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)
@@ -1151,23 +1152,23 @@ 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/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 +12,7 @@
 #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 "utils/float.h"
 #include "utils/guc.h"
 #include "utils/relcache.h"
@@ -270,6 +266,64 @@ 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,
+		.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 = hnswgettuple,
+		.amgetbitmap = NULL,
+		.amendscan = hnswendscan,
+		.ammarkpos = NULL,
+		.amrestrpos = 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 +397,5 @@ hnswhandler(PG_FUNCTION_ARGS)
 #endif
 
 	PG_RETURN_POINTER(amroutine);
+#endif
 }

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 +49,16 @@
 #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 +72,6 @@
 
 #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 +79,8 @@
 #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 +493,7 @@ 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 +502,9 @@ 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 +526,7 @@ 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 +619,7 @@ 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 +660,17 @@ 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;
 }
 
@@ -965,6 +956,8 @@ 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 +1000,7 @@ 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 +2,13 @@
 
 #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 "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 +1,15 @@
 #include "postgres.h"
 
+#include <limits.h>
+
 #include "access/genam.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"
@@ -155,7 +153,7 @@ 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;
 

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 +16,19 @@
 #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 +41,6 @@
 
 #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
 

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"
@@ -187,6 +184,64 @@ 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,
+		.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 = ivfflatgettuple,
+		.amgetbitmap = NULL,
+		.amendscan = ivfflatendscan,
+		.ammarkpos = NULL,
+		.amrestrpos = 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 +315,5 @@ ivfflathandler(PG_FUNCTION_ARGS)
 #endif
 
 	PG_RETURN_POINTER(amroutine);
+#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 +2,20 @@
 
 #include <float.h>
 
-#include "access/attnum.h"
 #include "access/genam.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"
 

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
@@ -890,28 +895,24 @@ SparsevecInnerProduct(SparseVector * a, SparseVector * b)
 	float	   *ax = SPARSEVEC_VALUES(a);
 	float	   *bx = SPARSEVEC_VALUES(b);
 	float		distance = 0.0;
-	int			bpos = 0;
+	int			i = 0;
+	int			j = 0;
 
-	for (int i = 0; i < a->nnz; i++)
+	while (i < a->nnz && j < b->nnz)
 	{
 		int			ai = a->indices[i];
+		int			bi = b->indices[j];
 
-		for (int j = bpos; j < b->nnz; j++)
+		if (ai == bi)
 		{
-			int			bi = b->indices[j];
-
-			/* Only update when the same index */
-			if (ai == bi)
-				distance += ax[i] * bx[j];
-
-			/* Update start for next iteration */
-			if (ai >= bi)
-				bpos = j + 1;
-
-			/* Found or passed it */
-			if (bi >= ai)
-				break;
+			distance += ax[i] * bx[j];
+			i++;
+			j++;
 		}
+		else if (ai < bi)
+			i++;
+		else
+			j++;
 	}
 
 	return distance;

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