Removed duplicated macros [skip ci]

.github/workflows/build.yml

@@ -8,10 +8,18 @@ jobs:
       fail-fast: false
       matrix:
         include:
+          # - postgres: 18
+          #   os: ubuntu-24.04
+          - postgres: 17
+            os: ubuntu-24.04
           - postgres: 16
-            os: ubuntu-24.04-arm
+            os: ubuntu-22.04
+          - postgres: 15
+            os: ubuntu-22.04
           - postgres: 14
-            os: ubuntu-22.04-arm
+            os: ubuntu-20.04
+          - postgres: 13
+            os: ubuntu-20.04
     steps:
       - uses: actions/checkout@v4
       - uses: ankane/setup-postgres@v1
@@ -31,3 +39,94 @@ jobs:
           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') }}
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - postgres: 16
+            os: macos-14
+          - postgres: 14
+            os: macos-12
+    steps:
+      - uses: actions/checkout@v4
+      - uses: ankane/setup-postgres@v1
+        with:
+          postgres-version: ${{ matrix.postgres }}
+      - run: make
+        env:
+          PG_CFLAGS: -DUSE_ASSERT_CHECKING -Wall -Wextra -Werror -Wno-unused-parameter
+      - run: make install
+      - run: make installcheck
+      - 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 == 16 && 'REL_16_2' || 'REL_14_11' }}
+      - 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@15)/bin/scan-build --status-bugs make
+        env:
+          PG_CFLAGS: -DUSE_ASSERT_CHECKING
+  windows:
+    runs-on: windows-latest
+    if: ${{ !startsWith(github.ref_name, 'mac') }}
+    steps:
+      - uses: actions/checkout@v4
+      - uses: ankane/setup-postgres@v1
+        with:
+          postgres-version: 14
+      - run: |
+          call "C:\Program Files\Microsoft Visual Studio\2022\Enterprise\VC\Auxiliary\Build\vcvars64.bat" && ^
+          nmake /NOLOGO /F Makefile.win && ^
+          nmake /NOLOGO /F Makefile.win install && ^
+          nmake /NOLOGO /F Makefile.win installcheck && ^
+          nmake /NOLOGO /F Makefile.win clean && ^
+          nmake /NOLOGO /F Makefile.win uninstall
+        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@v4
+      - uses: ankane/setup-postgres-valgrind@v1
+        with:
+          postgres-version: 16
+          check-ub: yes
+      - run: make OPTFLAGS=""
+      - run: sudo --preserve-env=PG_CONFIG make install
+      - run: make installcheck

CHANGELOG.md

@@ -1,10 +1,10 @@
-## 0.8.0 (2024-10-30)
+## 0.8.0 (unreleased)
 
 - Added support for iterative index scans
 - Added casts for arrays to `sparsevec`
-- Improved cost estimation for better index selection when filtering
+- Improved cost estimation
-- Improved performance of HNSW index scans
 - Improved performance of HNSW inserts and on-disk index builds
+- Reduced memory usage for HNSW index scans
 - Dropped support for Postgres 12
 
 ## 0.7.4 (2024-08-05)

LICENSE

@@ -1,4 +1,4 @@
-Portions Copyright (c) 1996-2025, PostgreSQL Global Development Group
+Portions Copyright (c) 1996-2024, 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": "0.8.0",
+	"version": "0.7.4",
 	"maintainer": [
 		"Andrew Kane <andrew@ankane.org>"
 	],
@@ -12,7 +12,7 @@
 	"prereqs": {
 		"runtime": {
 			"requires": {
-				"PostgreSQL": "13.0.0"
+				"PostgreSQL": "12.0.0"
 			}
 		}
 	},
@@ -20,7 +20,7 @@
 		"vector": {
 			"file": "sql/vector.sql",
 			"docfile": "README.md",
-			"version": "0.8.0",
+			"version": "0.7.4",
 			"abstract": "Open-source vector similarity search for Postgres"
 		}
 	},

Makefile

@@ -1,5 +1,5 @@
 EXTENSION = vector
-EXTVERSION = 0.8.0
+EXTVERSION = 0.7.4
 
 MODULE_big = vector
 DATA = $(wildcard sql/*--*--*.sql)

Makefile.win

@@ -1,5 +1,5 @@
 EXTENSION = vector
-EXTVERSION = 0.8.0
+EXTVERSION = 0.7.4
 
 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

@@ -17,11 +17,11 @@ Plus [ACID](https://en.wikipedia.org/wiki/ACID) compliance, point-in-time recove
 
 ### Linux and Mac
 
-Compile and install the extension (supports Postgres 13+)
+Compile and install the extension (supports Postgres 12+)
 
 ```sh
 cd /tmp
-git clone --branch v0.8.0 https://github.com/pgvector/pgvector.git
+git clone --branch v0.7.4 https://github.com/pgvector/pgvector.git
 cd pgvector
 make
 make install # may need sudo
@@ -46,13 +46,13 @@ Then use `nmake` to build:
 ```cmd
 set "PGROOT=C:\Program Files\PostgreSQL\16"
 cd %TEMP%
-git clone --branch v0.8.0 https://github.com/pgvector/pgvector.git
+git clone --branch v0.7.4 https://github.com/pgvector/pgvector.git
 cd pgvector
 nmake /F Makefile.win
 nmake /F Makefile.win install
 ```
 
-Note: Postgres 17 is not supported with MSVC yet due to an [upstream issue](https://www.postgresql.org/message-id/flat/CAOdR5yF0krWrxycA04rgUKCgKugRvGWzzGLAhDZ9bzNv8g0Lag%40mail.gmail.com)
+Note: Postgres 17 is not supported yet due to an upstream issue
 
 See the [installation notes](#installation-notes---windows) if you run into issues
 
@@ -324,7 +324,7 @@ For a large number of workers, you may also need to increase `max_parallel_worke
 
 ### Indexing Progress
 
-Check [indexing progress](https://www.postgresql.org/docs/current/progress-reporting.html#CREATE-INDEX-PROGRESS-REPORTING)
+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;
@@ -410,7 +410,7 @@ For a large number of workers, you may also need to increase `max_parallel_worke
 
 ### Indexing Progress
 
-Check [indexing progress](https://www.postgresql.org/docs/current/progress-reporting.html#CREATE-INDEX-PROGRESS-REPORTING)
+Check [indexing progress](https://www.postgresql.org/docs/current/progress-reporting.html#CREATE-INDEX-PROGRESS-REPORTING) with Postgres 12+
 
 ```sql
 SELECT phase, round(100.0 * tuples_done / nullif(tuples_total, 0), 1) AS "%" FROM pg_stat_progress_create_index;
@@ -427,115 +427,92 @@ Note: `%` is only populated during the `loading tuples` phase
 
 ## Filtering
 
-There are a few ways to index nearest neighbor queries with a `WHERE` clause.
+There are a few ways to index nearest neighbor queries with a `WHERE` clause
 
 ```sql
 SELECT * FROM items WHERE category_id = 123 ORDER BY embedding <-> '[3,1,2]' LIMIT 5;
 ```
 
-A good place to start is creating an index on the filter column. This can provide fast, exact nearest neighbor search in many cases. Postgres has a number of [index types](https://www.postgresql.org/docs/current/indexes-types.html) for this: B-tree (default), hash, GiST, SP-GiST, GIN, and BRIN.
+Create an index on one [or more](https://www.postgresql.org/docs/current/indexes-multicolumn.html) of the `WHERE` columns for exact search
 
 ```sql
 CREATE INDEX ON items (category_id);
 ```
 
-For multiple columns, consider a [multicolumn index](https://www.postgresql.org/docs/current/indexes-multicolumn.html).
+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 (location_id, category_id);
-```
-
-Exact indexes work well for conditions that match a low percentage of rows. Otherwise, [approximate indexes](#indexing) can work better.
-
-```sql
-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.
-
-```sql
-SET hnsw.iterative_scan = strict_order;
-```
-
-If filtering by only a few distinct values, consider [partial indexing](https://www.postgresql.org/docs/current/indexes-partial.html).
 
 ```sql
 CREATE INDEX ON items USING hnsw (embedding vector_l2_ops) WHERE (category_id = 123);
 ```
 
-If filtering by many different values, consider [partitioning](https://www.postgresql.org/docs/current/ddl-partitioning.html).
+Use [partitioning](https://www.postgresql.org/docs/current/ddl-partitioning.html) for approximate search on many different values of the `WHERE` columns
 
 ```sql
 CREATE TABLE items (embedding vector(3), category_id int) PARTITION BY LIST(category_id);
 ```
 
-## Iterative Index Scans
+## Iterative Search [unreleased]
 
 *Added in 0.8.0*
 
-With approximate indexes, queries with filtering can return less results since filtering is applied *after* the index is scanned. Starting with 0.8.0, you can enable iterative index scans, which will automatically scan more of the index until enough results are found (or it reaches `hnsw.max_scan_tuples` or `ivfflat.max_probes`).
+With approximate indexes, you can end up with less results than expected due to filtering conditions in the query.
 
-Iterative scans can use strict or relaxed ordering.
+Starting with 0.8.0, you can enable iterative search. If too few results from the initial index scan match the query filters, it will resume scanning until enough results are found. This can significantly improve recall (at the cost of speed).
 
-Strict ensures results are in the exact order by distance
+```tsql
-
+SET hnsw.streaming = on;
-```sql
+-- or
-SET hnsw.iterative_scan = strict_order;
+SET ivfflat.streaming = on;
 ```
 
-Relaxed allows results to be slightly out of order by distance, but provides better recall
+However, there are some important caveats.
+
+### Iterative Caveats
+
+With iterative search, it’s possible for rows to be slightly out of order by distance. For strict ordering, use:
 
 ```sql
-SET hnsw.iterative_scan = relaxed_order;
+WITH approx_order AS MATERIALIZED (
-# or
+    SELECT *, embedding <-> '[1,2,3]' AS distance FROM items WHERE ... ORDER BY distance LIMIT 5
-SET ivfflat.iterative_scan = relaxed_order;
+) SELECT * FROM approx_order ORDER BY distance;
 ```
 
-With relaxed ordering, you can use a [materialized CTE](https://www.postgresql.org/docs/current/queries-with.html#QUERIES-WITH-CTE-MATERIALIZATION) to get strict ordering
+For distance filters, use a CTE and place the filter outside it.
 
 ```sql
-WITH relaxed_results AS MATERIALIZED (
+WITH approx_order AS MATERIALIZED (
-    SELECT id, embedding <-> '[1,2,3]' AS distance FROM items WHERE category_id = 123 ORDER BY distance LIMIT 5
+    SELECT *, embedding <-> '[1,2,3]' AS distance FROM items WHERE ... ORDER BY distance LIMIT 5
-) SELECT * FROM relaxed_results ORDER BY distance;
+) SELECT * FROM approx_order WHERE distance < 0.1 ORDER BY distance;
 ```
 
-For queries that filter by distance, use a materialized CTE and place the distance filter outside of it for best performance (due to the [current behavior](https://www.postgresql.org/message-id/flat/CAOdR5yGUoMQ6j7M5hNUXrySzaqZVGf_Ne%2B8fwZMRKTFxU1nbJg%40mail.gmail.com) of the Postgres executor)
+### Iterative Options
 
-```sql
+Since scanning a large portion of the index is expensive, there are options to control when the scan ends.
-WITH nearest_results AS MATERIALIZED (
-    SELECT id, embedding <-> '[1,2,3]' AS distance FROM items ORDER BY distance LIMIT 5
-) SELECT * FROM nearest_results WHERE distance < 5 ORDER BY distance;
-```
-
-Note: Place any other filters inside the CTE
-
-### Iterative Scan Options
-
-Since scanning a large portion of an approximate index is expensive, there are options to control when a scan ends.
 
 #### HNSW
 
-Specify the max number of tuples to visit (20,000 by default)
+Specify the max number of additional tuples visited
 
 ```sql
-SET hnsw.max_scan_tuples = 20000;
+SET hnsw.ef_stream = 10000;
 ```
 
-Note: This is approximate and does not affect the initial scan
+The scan will also end if reaches `work_mem`. You can see when this happens by enabling debug messages.
-
-Specify the max amount of memory to use, as a multiple of `work_mem` (1 by default)
 
 ```sql
-SET hnsw.scan_mem_multiplier = 2;
+SET client_min_messages = debug1;
 ```
 
-Note: Try increasing this if increasing `hnsw.max_scan_tuples` does not improve recall
+```text
+DEBUG:  hnsw index scan exceeded work_mem after 10000 tuples
+HINT:  Increase work_mem to scan more tuples.
+```
+
+If the server has enough memory, you can adjust this with:
+
+```sql
+SET work_mem = '8MB';
+```
 
 #### IVFFlat
 
@@ -545,8 +522,6 @@ Specify the max number of probes
 SET ivfflat.max_probes = 100;
 ```
 
-Note: If this is lower than `ivfflat.probes`, `ivfflat.probes` will be used
-
 ## Half-Precision Vectors
 
 *Added in 0.7.0*
@@ -801,12 +776,8 @@ 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)
 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)
 Elixir | [pgvector-elixir](https://github.com/pgvector/pgvector-elixir)
-Erlang | [pgvector-erlang](https://github.com/pgvector/pgvector-erlang)
-Fortran | [pgvector-fortran](https://github.com/pgvector/pgvector-fortran)
-Gleam | [pgvector-gleam](https://github.com/pgvector/pgvector-gleam)
 Go | [pgvector-go](https://github.com/pgvector/pgvector-go)
 Haskell | [pgvector-haskell](https://github.com/pgvector/pgvector-haskell)
 Java, Kotlin, Groovy, Scala | [pgvector-java](https://github.com/pgvector/pgvector-java)
@@ -820,7 +791,6 @@ Perl | [pgvector-perl](https://github.com/pgvector/pgvector-perl)
 PHP | [pgvector-php](https://github.com/pgvector/pgvector-php)
 Python | [pgvector-python](https://github.com/pgvector/pgvector-python)
 R | [pgvector-r](https://github.com/pgvector/pgvector-r)
-Raku | [pgvector-raku](https://github.com/pgvector/pgvector-raku)
 Ruby | [pgvector-ruby](https://github.com/pgvector/pgvector-ruby), [Neighbor](https://github.com/ankane/neighbor)
 Rust | [pgvector-rust](https://github.com/pgvector/pgvector-rust)
 Swift | [pgvector-swift](https://github.com/pgvector/pgvector-swift)
@@ -942,7 +912,7 @@ ALTER TABLE items ALTER COLUMN embedding SET STORAGE PLAIN;
 
 #### Why are there less results for a query after adding an HNSW index?
 
-Results are limited by the size of the dynamic candidate list (`hnsw.ef_search`), which is 40 by default. There may be even less results due to dead tuples or filtering conditions in the query. Enabling [iterative index scans](#iterative-index-scans) can help address this.
+Results are limited by the size of the dynamic candidate list (`hnsw.ef_search`). There may be even less results due to dead tuples or filtering conditions in the query. We recommend setting `hnsw.ef_search` to at least twice the `LIMIT` of the query. If you need more than 500 results, use an IVFFlat index instead.
 
 Also, note that `NULL` vectors are not indexed (as well as zero vectors for cosine distance).
 
@@ -954,7 +924,7 @@ The index was likely created with too little data for the number of lists. Drop
 DROP INDEX index_name;
 ```
 
-Results can also be limited by the number of probes (`ivfflat.probes`). Enabling [iterative index scans](#iterative-index-scans) can address this.
+Results can also be limited by the number of probes (`ivfflat.probes`).
 
 Also, note that `NULL` vectors are not indexed (as well as zero vectors for cosine distance).
 
@@ -1158,7 +1128,7 @@ This adds pgvector to the [Postgres image](https://hub.docker.com/_/postgres) (r
 You can also build the image manually:
 
 ```sh
-git clone --branch v0.8.0 https://github.com/pgvector/pgvector.git
+git clone --branch v0.7.4 https://github.com/pgvector/pgvector.git
 cd pgvector
 docker build --pull --build-arg PG_MAJOR=17 -t myuser/pgvector .
 ```
@@ -1208,7 +1178,7 @@ Note: Replace `17` with your Postgres server version
 Install the FreeBSD package with:
 
 ```sh
-pkg install postgresql16-pgvector
+pkg install postgresql15-pgvector
 ```
 
 or the port with:

src/hnsw.c

@@ -18,17 +18,18 @@
 #define MarkGUCPrefixReserved(x) EmitWarningsOnPlaceholders(x)
 #endif
 
-static const struct config_enum_entry hnsw_iterative_scan_options[] = {
+static const struct config_enum_entry hnsw_iterative_search_options[] = {
-	{"off", HNSW_ITERATIVE_SCAN_OFF, false},
+	{"off", HNSW_ITERATIVE_SEARCH_OFF, false},
-	{"relaxed_order", HNSW_ITERATIVE_SCAN_RELAXED, false},
+	{"strict", HNSW_ITERATIVE_SEARCH_STRICT, false},
-	{"strict_order", HNSW_ITERATIVE_SCAN_STRICT, false},
+	{"relaxed", HNSW_ITERATIVE_SEARCH_RELAXED, false},
+	/* TODO Change to strict before merging */
+	{"on", HNSW_ITERATIVE_SEARCH_RELAXED, false},
 	{NULL, 0, false}
 };
 
 int			hnsw_ef_search;
-int			hnsw_iterative_scan;
+int			hnsw_max_iterative_tuples;
-int			hnsw_max_scan_tuples;
+int			hnsw_iterative_search;
-double		hnsw_scan_mem_multiplier;
 int			hnsw_lock_tranche_id;
 static relopt_kind hnsw_relopt_kind;
 
@@ -79,19 +80,16 @@ HnswInit(void)
 							"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);
 
-	DefineCustomEnumVariable("hnsw.iterative_scan", "Sets the mode for iterative scans",
+	/* TODO Change name */
-							 NULL, &hnsw_iterative_scan,
+	DefineCustomEnumVariable("hnsw.streaming", "Iterative search mode",
-							 HNSW_ITERATIVE_SCAN_OFF, hnsw_iterative_scan_options, PGC_USERSET, 0, NULL, NULL, NULL);
+							 NULL, &hnsw_iterative_search,
+							 HNSW_ITERATIVE_SEARCH_OFF, hnsw_iterative_search_options, PGC_USERSET, 0, NULL, NULL, NULL);
 
-	/* This is approximate and does not affect the initial scan */
+	/* TODO Change name */
-	DefineCustomIntVariable("hnsw.max_scan_tuples", "Sets the max number of tuples to visit for iterative scans",
+	/* TODO Ensure ivfflat.max_probes uses same value for "all" */
-							NULL, &hnsw_max_scan_tuples,
+	DefineCustomIntVariable("hnsw.ef_stream", "Sets the max number of additional candidates to visit for streaming search",
-							20000, 1, INT_MAX, PGC_USERSET, 0, NULL, NULL, NULL);
+							"-1 means all", &hnsw_max_iterative_tuples,
-
+							HNSW_DEFAULT_EF_STREAM, HNSW_MIN_EF_STREAM, HNSW_MAX_EF_STREAM, PGC_USERSET, 0, NULL, NULL, NULL);
-	/* Same range as hash_mem_multiplier */
-	DefineCustomRealVariable("hnsw.scan_mem_multiplier", "Sets the multiple of work_mem to use for iterative scans",
-							 NULL, &hnsw_scan_mem_multiplier,
-							 1, 1, 1000, PGC_USERSET, 0, NULL, NULL, NULL);
 
 	MarkGUCPrefixReserved("hnsw");
 }
@@ -137,10 +135,6 @@ hnswcostestimate(PlannerInfo *root, IndexPath *path, double loop_count,
 		*indexSelectivity = 0;
 		*indexCorrelation = 0;
 		*indexPages = 0;
-#if PG_VERSION_NUM >= 180000
-		/* See "On disable_cost" thread on pgsql-hackers */
-		path->path.disabled_nodes = 2;
-#endif
 		return;
 	}
 

src/hnsw.h

@@ -42,6 +42,9 @@
 #define HNSW_DEFAULT_EF_SEARCH	40
 #define HNSW_MIN_EF_SEARCH		1
 #define HNSW_MAX_EF_SEARCH		1000
+#define HNSW_DEFAULT_EF_STREAM	-1
+#define HNSW_MIN_EF_STREAM		-1
+#define HNSW_MAX_EF_STREAM		INT_MAX
 
 /* Tuple types */
 #define HNSW_ELEMENT_TUPLE_TYPE  1
@@ -109,24 +112,23 @@
 
 /* Variables */
 extern int	hnsw_ef_search;
-extern int	hnsw_iterative_scan;
+extern int	hnsw_max_iterative_tuples;
-extern int	hnsw_max_scan_tuples;
+extern int	hnsw_iterative_search;
-extern double hnsw_scan_mem_multiplier;
 extern int	hnsw_lock_tranche_id;
 
-typedef enum HnswIterativeScanMode
+typedef enum HnswIterativeSearchType
 {
-	HNSW_ITERATIVE_SCAN_OFF,
+	HNSW_ITERATIVE_SEARCH_OFF,
-	HNSW_ITERATIVE_SCAN_RELAXED,
+	HNSW_ITERATIVE_SEARCH_STRICT,
-	HNSW_ITERATIVE_SCAN_STRICT
+	HNSW_ITERATIVE_SEARCH_RELAXED
-}			HnswIterativeScanMode;
+}			HnswIterativeSearchType;
 
 typedef struct HnswElementData HnswElementData;
 typedef struct HnswNeighborArray HnswNeighborArray;
 
 #define HnswPtrDeclare(type, relptrtype, ptrtype) \
 	relptr_declare(type, relptrtype); \
-	typedef union { type *ptr; relptrtype relptr; } ptrtype
+	typedef union { type *ptr; relptrtype relptr; } ptrtype;
 
 /* Pointers that can be absolute or relative */
 /* Use char for DatumPtr so works with Pointer */
@@ -373,7 +375,6 @@ typedef struct HnswScanOpaqueData
 	int			m;
 	int64		tuples;
 	double		previousDistance;
-	Size		maxMemory;
 	MemoryContext tmpCtx;
 
 	/* Support functions */

src/hnswscan.c

@@ -41,7 +41,7 @@ GetScanItems(IndexScanDesc scan, Datum value)
 		ep = w;
 	}
 
-	return HnswSearchLayer(base, q, ep, hnsw_ef_search, 0, index, support, m, false, NULL, &so->v, hnsw_iterative_scan != HNSW_ITERATIVE_SCAN_OFF ? &so->discarded : NULL, true, &so->tuples);
+	return HnswSearchLayer(base, q, ep, hnsw_ef_search, 0, index, support, m, false, NULL, &so->v, hnsw_iterative_search != HNSW_ITERATIVE_SEARCH_OFF ? &so->discarded : NULL, true, &so->tuples);
 }
 
 /*
@@ -102,17 +102,6 @@ GetScanValue(IndexScanDesc scan)
 	return value;
 }
 
-#if defined(HNSW_MEMORY)
-/*
- * Show memory usage
- */
-static void
-ShowMemoryUsage(HnswScanOpaque so)
-{
-	elog(INFO, "memory: %zu KB, tuples: " INT64_FORMAT, MemoryContextMemAllocated(so->tmpCtx, false) / 1024, so->tuples);
-}
-#endif
-
 /*
  * Prepare for an index scan
  */
@@ -121,29 +110,21 @@ hnswbeginscan(Relation index, int nkeys, int norderbys)
 {
 	IndexScanDesc scan;
 	HnswScanOpaque so;
-	double		maxMemory;
 
 	scan = RelationGetIndexScan(index, nkeys, norderbys);
 
 	so = (HnswScanOpaque) palloc(sizeof(HnswScanOpaqueData));
 	so->typeInfo = HnswGetTypeInfo(index);
+	so->first = true;
+	so->v.tids = NULL;
+	so->discarded = NULL;
+	so->tmpCtx = AllocSetContextCreate(CurrentMemoryContext,
+									   "Hnsw scan temporary context",
+									   ALLOCSET_DEFAULT_SIZES);
 
 	/* Set support functions */
 	HnswInitSupport(&so->support, index);
 
-	/*
-	 * Use a lower max allocation size than default to allow scanning more
-	 * tuples for iterative search before exceeding work_mem
-	 */
-	so->tmpCtx = AllocSetContextCreate(CurrentMemoryContext,
-									   "Hnsw scan temporary context",
-									   0, 8 * 1024, 256 * 1024);
-
-	/* 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);
-
 	scan->opaque = so;
 
 	return scan;
@@ -157,10 +138,13 @@ hnswrescan(IndexScanDesc scan, ScanKey keys, int nkeys, ScanKey orderbys, int no
 {
 	HnswScanOpaque so = (HnswScanOpaque) scan->opaque;
 
+	if (so->v.tids != NULL)
+		tidhash_reset(so->v.tids);
+
+	if (so->discarded != NULL)
+		pairingheap_reset(so->discarded);
+
 	so->first = true;
-	/* v and discarded are allocated in tmpCtx */
-	so->v.tids = NULL;
-	so->discarded = NULL;
 	so->tuples = 0;
 	so->previousDistance = -get_float8_infinity();
 	MemoryContextReset(so->tmpCtx);
@@ -220,7 +204,7 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
 		so->first = false;
 
 #if defined(HNSW_MEMORY)
-		ShowMemoryUsage(so);
+		elog(INFO, "memory: %zu KB", MemoryContextMemAllocated(so->tmpCtx, false) / 1024);
 #endif
 	}
 
@@ -233,15 +217,15 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
 
 		if (list_length(so->w) == 0)
 		{
-			if (hnsw_iterative_scan == HNSW_ITERATIVE_SCAN_OFF)
+			if (hnsw_iterative_search == HNSW_ITERATIVE_SEARCH_OFF)
 				break;
 
 			/* Empty index */
 			if (so->discarded == NULL)
 				break;
 
-			/* Reached max number of tuples or memory limit */
+			/* Reached max number of additional tuples */
-			if (so->tuples >= hnsw_max_scan_tuples || MemoryContextMemAllocated(so->tmpCtx, false) > so->maxMemory)
+			if (hnsw_max_iterative_tuples != -1 && so->tuples >= hnsw_ef_search + hnsw_max_iterative_tuples)
 			{
 				if (pairingheap_is_empty(so->discarded))
 					break;
@@ -249,6 +233,21 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
 				/* Return remaining tuples */
 				so->w = lappend(so->w, HnswGetSearchCandidate(w_node, pairingheap_remove_first(so->discarded)));
 			}
+			/* Prevent scans from consuming too much memory */
+			else if (MemoryContextMemAllocated(so->tmpCtx, false) > (Size) work_mem * 1024L)
+			{
+				if (pairingheap_is_empty(so->discarded))
+				{
+					ereport(DEBUG1,
+							(errmsg("hnsw index scan exceeded work_mem after " INT64_FORMAT " tuples", so->tuples),
+							 errhint("Increase work_mem to scan more tuples.")));
+
+					break;
+				}
+
+				/* Return remaining tuples */
+				so->w = lappend(so->w, HnswGetSearchCandidate(w_node, pairingheap_remove_first(so->discarded)));
+			}
 			else
 			{
 				/*
@@ -267,7 +266,7 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
 				UnlockPage(scan->indexRelation, HNSW_SCAN_LOCK, ShareLock);
 
 #if defined(HNSW_MEMORY)
-				ShowMemoryUsage(so);
+				elog(INFO, "memory: %zu KB", MemoryContextMemAllocated(so->tmpCtx, false) / 1024);
 #endif
 			}
 
@@ -284,7 +283,7 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
 			so->w = list_delete_last(so->w);
 
 			/* Mark memory as free for next iteration */
-			if (hnsw_iterative_scan != HNSW_ITERATIVE_SCAN_OFF)
+			if (hnsw_iterative_search != HNSW_ITERATIVE_SEARCH_OFF)
 			{
 				pfree(element);
 				pfree(sc);
@@ -295,7 +294,7 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
 
 		heaptid = &element->heaptids[--element->heaptidsLength];
 
-		if (hnsw_iterative_scan == HNSW_ITERATIVE_SCAN_STRICT)
+		if (hnsw_iterative_search == HNSW_ITERATIVE_SEARCH_STRICT)
 		{
 			if (sc->distance < so->previousDistance)
 				continue;

src/hnswutils.c

@@ -581,34 +581,21 @@ GetElementDistance(char *base, HnswElement element, HnswQuery * q, HnswSupport *
 	return HnswGetDistance(q->value, value, support);
 }
 
-/*
- * Allocate a search candidate
- */
-static HnswSearchCandidate *
-HnswInitSearchCandidate(char *base, HnswElement element, double distance)
-{
-	HnswSearchCandidate *sc = palloc(sizeof(HnswSearchCandidate));
-
-	HnswPtrStore(base, sc->element, element);
-	sc->distance = distance;
-	return sc;
-}
-
 /*
  * Create a candidate for the entry point
  */
 HnswSearchCandidate *
 HnswEntryCandidate(char *base, HnswElement entryPoint, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec)
 {
+	HnswSearchCandidate *sc = palloc(sizeof(HnswSearchCandidate));
 	bool		inMemory = index == NULL;
-	double		distance;
 
+	HnswPtrStore(base, sc->element, entryPoint);
 	if (inMemory)
-		distance = GetElementDistance(base, entryPoint, q, support);
+		sc->distance = GetElementDistance(base, entryPoint, q, support);
 	else
-		HnswLoadElement(entryPoint, &distance, q, index, support, loadVec, NULL);
+		HnswLoadElement(entryPoint, &sc->distance, q, index, support, loadVec, NULL);
-
+	return sc;
-	return HnswInitSearchCandidate(base, entryPoint, distance);
 }
 
 /*
@@ -857,7 +844,6 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
 		{
 			AddToVisited(base, v, sc->element, inMemory, &found);
 
-			/* OK to count elements instead of tuples */
 			if (tuples != NULL)
 				(*tuples)++;
 		}
@@ -890,7 +876,6 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
 		else
 			HnswLoadUnvisitedFromDisk(cElement, unvisited, &unvisitedLength, v, index, m, lm, lc);
 
-		/* OK to count elements instead of tuples */
 		if (tuples != NULL)
 			(*tuples) += unvisitedLength;
 
@@ -927,7 +912,9 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
 				if (discarded != NULL)
 				{
 					/* Create a new candidate */
-					e = HnswInitSearchCandidate(base, eElement, eDistance);
+					e = palloc(sizeof(HnswSearchCandidate));
+					HnswPtrStore(base, e->element, eElement);
+					e->distance = eDistance;
 					pairingheap_add(*discarded, &e->w_node);
 				}
 
@@ -939,7 +926,9 @@ HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation in
 				continue;
 
 			/* Create a new candidate */
-			e = HnswInitSearchCandidate(base, eElement, eDistance);
+			e = palloc(sizeof(HnswSearchCandidate));
+			HnswPtrStore(base, e->element, eElement);
+			e->distance = eDistance;
 			pairingheap_add(C, &e->c_node);
 			pairingheap_add(W, &e->w_node);
 
@@ -1393,7 +1382,7 @@ hnsw_halfvec_support(PG_FUNCTION_ARGS)
 	};
 
 	PG_RETURN_POINTER(&typeInfo);
-}
+};
 
 FUNCTION_PREFIX PG_FUNCTION_INFO_V1(hnsw_bit_support);
 Datum
@@ -1406,7 +1395,7 @@ hnsw_bit_support(PG_FUNCTION_ARGS)
 	};
 
 	PG_RETURN_POINTER(&typeInfo);
-}
+};
 
 FUNCTION_PREFIX PG_FUNCTION_INFO_V1(hnsw_sparsevec_support);
 Datum
@@ -1419,4 +1408,4 @@ hnsw_sparsevec_support(PG_FUNCTION_ARGS)
 	};
 
 	PG_RETURN_POINTER(&typeInfo);
-}
+};

src/ivfbuild.c

@@ -228,11 +228,11 @@ BuildCallback(Relation index, ItemPointer tid, Datum *values,
 static inline void
 GetNextTuple(Tuplesortstate *sortstate, TupleDesc tupdesc, TupleTableSlot *slot, IndexTuple *itup, int *list)
 {
+	Datum		value;
+	bool		isnull;
+
 	if (tuplesort_gettupleslot(sortstate, true, false, slot, NULL))
 	{
-		Datum		value;
-		bool		isnull;
-
 		*list = DatumGetInt32(slot_getattr(slot, 1, &isnull));
 		value = slot_getattr(slot, 3, &isnull);
 
@@ -254,8 +254,8 @@ InsertTuples(Relation index, IvfflatBuildState * buildstate, ForkNumber forkNum)
 	IndexTuple	itup = NULL;	/* silence compiler warning */
 	int64		inserted = 0;
 
-	TupleTableSlot *slot = MakeSingleTupleTableSlot(buildstate->sortdesc, &TTSOpsMinimalTuple);
+	TupleTableSlot *slot = MakeSingleTupleTableSlot(buildstate->tupdesc, &TTSOpsMinimalTuple);
-	TupleDesc	tupdesc = buildstate->tupdesc;
+	TupleDesc	tupdesc = RelationGetDescr(index);
 
 	pgstat_progress_update_param(PROGRESS_CREATEIDX_SUBPHASE, PROGRESS_IVFFLAT_PHASE_LOAD);
 
@@ -319,7 +319,6 @@ InitBuildState(IvfflatBuildState * buildstate, Relation heap, Relation index, In
 	buildstate->index = index;
 	buildstate->indexInfo = indexInfo;
 	buildstate->typeInfo = IvfflatGetTypeInfo(index);
-	buildstate->tupdesc = RelationGetDescr(index);
 
 	buildstate->lists = IvfflatGetLists(index);
 	buildstate->dimensions = TupleDescAttr(index->rd_att, 0)->atttypmod;
@@ -357,12 +356,12 @@ InitBuildState(IvfflatBuildState * buildstate, Relation heap, Relation index, In
 				 errmsg("dimensions must be greater than one for this opclass")));
 
 	/* Create tuple description for sorting */
-	buildstate->sortdesc = CreateTemplateTupleDesc(3);
+	buildstate->tupdesc = CreateTemplateTupleDesc(3);
-	TupleDescInitEntry(buildstate->sortdesc, (AttrNumber) 1, "list", INT4OID, -1, 0);
+	TupleDescInitEntry(buildstate->tupdesc, (AttrNumber) 1, "list", INT4OID, -1, 0);
-	TupleDescInitEntry(buildstate->sortdesc, (AttrNumber) 2, "tid", TIDOID, -1, 0);
+	TupleDescInitEntry(buildstate->tupdesc, (AttrNumber) 2, "tid", TIDOID, -1, 0);
-	TupleDescInitEntry(buildstate->sortdesc, (AttrNumber) 3, "vector", TupleDescAttr(buildstate->tupdesc, 0)->atttypid, -1, 0);
+	TupleDescInitEntry(buildstate->tupdesc, (AttrNumber) 3, "vector", RelationGetDescr(index)->attrs[0].atttypid, -1, 0);
 
-	buildstate->slot = MakeSingleTupleTableSlot(buildstate->sortdesc, &TTSOpsVirtual);
+	buildstate->slot = MakeSingleTupleTableSlot(buildstate->tupdesc, &TTSOpsVirtual);
 
 	buildstate->centers = VectorArrayInit(buildstate->lists, buildstate->dimensions, buildstate->typeInfo->itemSize(buildstate->dimensions));
 	buildstate->listInfo = palloc(sizeof(ListInfo) * buildstate->lists);
@@ -634,7 +633,7 @@ IvfflatParallelScanAndSort(IvfflatSpool * ivfspool, IvfflatShared * ivfshared, S
 	InitBuildState(&buildstate, ivfspool->heap, ivfspool->index, indexInfo);
 	memcpy(buildstate.centers->items, ivfcenters, buildstate.centers->itemsize * buildstate.centers->maxlen);
 	buildstate.centers->length = buildstate.centers->maxlen;
-	ivfspool->sortstate = InitBuildSortState(buildstate.sortdesc, sortmem, coordinate);
+	ivfspool->sortstate = InitBuildSortState(buildstate.tupdesc, sortmem, coordinate);
 	buildstate.sortstate = ivfspool->sortstate;
 	scan = table_beginscan_parallel(ivfspool->heap,
 									ParallelTableScanFromIvfflatShared(ivfshared));
@@ -951,7 +950,7 @@ AssignTuples(IvfflatBuildState * buildstate)
 	}
 
 	/* Begin serial/leader tuplesort */
-	buildstate->sortstate = InitBuildSortState(buildstate->sortdesc, maintenance_work_mem, coordinate);
+	buildstate->sortstate = InitBuildSortState(buildstate->tupdesc, maintenance_work_mem, coordinate);
 
 	/* Add tuples to sort */
 	if (buildstate->heap != NULL)

src/ivfflat.c

@@ -17,16 +17,8 @@
 #endif
 
 int			ivfflat_probes;
-int			ivfflat_iterative_scan;
-int			ivfflat_max_probes;
 static relopt_kind ivfflat_relopt_kind;
 
-static const struct config_enum_entry ivfflat_iterative_scan_options[] = {
-	{"off", IVFFLAT_ITERATIVE_SCAN_OFF, false},
-	{"relaxed_order", IVFFLAT_ITERATIVE_SCAN_RELAXED, false},
-	{NULL, 0, false}
-};
-
 /*
  * Initialize index options and variables
  */
@@ -41,15 +33,6 @@ IvfflatInit(void)
 							"Valid range is 1..lists.", &ivfflat_probes,
 							IVFFLAT_DEFAULT_PROBES, IVFFLAT_MIN_LISTS, IVFFLAT_MAX_LISTS, PGC_USERSET, 0, NULL, NULL, NULL);
 
-	DefineCustomEnumVariable("ivfflat.iterative_scan", "Sets the mode for iterative scans",
-							 NULL, &ivfflat_iterative_scan,
-							 IVFFLAT_ITERATIVE_SCAN_OFF, ivfflat_iterative_scan_options, PGC_USERSET, 0, NULL, NULL, NULL);
-
-	/* If this is less than probes, probes is used */
-	DefineCustomIntVariable("ivfflat.max_probes", "Sets the max number of probes for iterative scans",
-							NULL, &ivfflat_max_probes,
-							IVFFLAT_MAX_LISTS, IVFFLAT_MIN_LISTS, IVFFLAT_MAX_LISTS, PGC_USERSET, 0, NULL, NULL, NULL);
-
 	MarkGUCPrefixReserved("ivfflat");
 }
 
@@ -99,10 +82,6 @@ ivfflatcostestimate(PlannerInfo *root, IndexPath *path, double loop_count,
 		*indexSelectivity = 0;
 		*indexCorrelation = 0;
 		*indexPages = 0;
-#if PG_VERSION_NUM >= 180000
-		/* See "On disable_cost" thread on pgsql-hackers */
-		path->path.disabled_nodes = 2;
-#endif
 		return;
 	}
 

src/ivfflat.h

@@ -80,14 +80,6 @@
 
 /* Variables */
 extern int	ivfflat_probes;
-extern int	ivfflat_iterative_scan;
-extern int	ivfflat_max_probes;
-
-typedef enum IvfflatIterativeScanMode
-{
-	IVFFLAT_ITERATIVE_SCAN_OFF,
-	IVFFLAT_ITERATIVE_SCAN_RELAXED
-}			IvfflatIterativeScanMode;
 
 typedef struct VectorArrayData
 {
@@ -173,7 +165,6 @@ typedef struct IvfflatBuildState
 	Relation	index;
 	IndexInfo  *indexInfo;
 	const		IvfflatTypeInfo *typeInfo;
-	TupleDesc	tupdesc;
 
 	/* Settings */
 	int			dimensions;
@@ -207,7 +198,7 @@ typedef struct IvfflatBuildState
 
 	/* Sorting */
 	Tuplesortstate *sortstate;
-	TupleDesc	sortdesc;
+	TupleDesc	tupdesc;
 	TupleTableSlot *slot;
 
 	/* Memory */
@@ -256,11 +247,8 @@ typedef struct IvfflatScanOpaqueData
 {
 	const		IvfflatTypeInfo *typeInfo;
 	int			probes;
-	int			maxProbes;
 	int			dimensions;
 	bool		first;
-	Datum		value;
-	MemoryContext tmpCtx;
 
 	/* Sorting */
 	Tuplesortstate *sortstate;
@@ -277,9 +265,7 @@ typedef struct IvfflatScanOpaqueData
 
 	/* Lists */
 	pairingheap *listQueue;
-	BlockNumber *listPages;
+	IvfflatScanList lists[FLEXIBLE_ARRAY_MEMBER];	/* must come last */
-	int			listIndex;
-	IvfflatScanList *lists;
 }			IvfflatScanOpaqueData;
 
 typedef IvfflatScanOpaqueData * IvfflatScanOpaque;

src/ivfinsert.c

@@ -98,7 +98,7 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid, R
 	IvfflatGetMetaPageInfo(index, NULL, NULL);
 
 	/* Find the insert page - sets the page and list info */
-	FindInsertPage(index, &value, &insertPage, &listInfo);
+	FindInsertPage(index, values, &insertPage, &listInfo);
 	Assert(BlockNumberIsValid(insertPage));
 	originalInsertPage = insertPage;
 

src/ivfscan.c

@@ -10,7 +10,10 @@
 #include "miscadmin.h"
 #include "pgstat.h"
 #include "storage/bufmgr.h"
+
+#ifdef IVFFLAT_MEMORY
 #include "utils/memutils.h"
+#endif
 
 #define GetScanList(ptr) pairingheap_container(IvfflatScanList, ph_node, ptr)
 #define GetScanListConst(ptr) pairingheap_const_container(IvfflatScanList, ph_node, ptr)
@@ -62,7 +65,7 @@ GetScanLists(IndexScanDesc scan, Datum value)
 			/* Use procinfo from the index instead of scan key for performance */
 			distance = DatumGetFloat8(so->distfunc(so->procinfo, so->collation, PointerGetDatum(&list->center), value));
 
-			if (listCount < so->maxProbes)
+			if (listCount < so->probes)
 			{
 				IvfflatScanList *scanlist;
 
@@ -75,7 +78,7 @@ GetScanLists(IndexScanDesc scan, Datum value)
 				pairingheap_add(so->listQueue, &scanlist->ph_node);
 
 				/* Calculate max distance */
-				if (listCount == so->maxProbes)
+				if (listCount == so->probes)
 					maxDistance = GetScanList(pairingheap_first(so->listQueue))->distance;
 			}
 			else if (distance < maxDistance)
@@ -99,11 +102,6 @@ GetScanLists(IndexScanDesc scan, Datum value)
 
 		UnlockReleaseBuffer(cbuf);
 	}
-
-	for (int i = listCount - 1; i >= 0; i--)
-		so->listPages[i] = GetScanList(pairingheap_remove_first(so->listQueue))->startPage;
-
-	Assert(pairingheap_is_empty(so->listQueue));
 }
 
 /*
@@ -114,15 +112,13 @@ GetScanItems(IndexScanDesc scan, Datum value)
 {
 	IvfflatScanOpaque so = (IvfflatScanOpaque) scan->opaque;
 	TupleDesc	tupdesc = RelationGetDescr(scan->indexRelation);
+	double		tuples = 0;
 	TupleTableSlot *slot = so->vslot;
-	int			batchProbes = 0;
-
-	tuplesort_reset(so->sortstate);
 
 	/* Search closest probes lists */
-	while (so->listIndex < so->maxProbes && (++batchProbes) <= so->probes)
+	while (!pairingheap_is_empty(so->listQueue))
 	{
-		BlockNumber searchPage = so->listPages[so->listIndex++];
+		BlockNumber searchPage = GetScanList(pairingheap_remove_first(so->listQueue))->startPage;
 
 		/* Search all entry pages for list */
 		while (BlockNumberIsValid(searchPage))
@@ -160,6 +156,8 @@ GetScanItems(IndexScanDesc scan, Datum value)
 				ExecStoreVirtualTuple(slot);
 
 				tuplesort_puttupleslot(so->sortstate, slot);
+
+				tuples++;
 			}
 
 			searchPage = IvfflatPageGetOpaque(page)->nextblkno;
@@ -168,11 +166,13 @@ GetScanItems(IndexScanDesc scan, Datum value)
 		}
 	}
 
-	tuplesort_performsort(so->sortstate);
+	if (tuples < 100)
+		ereport(DEBUG1,
+				(errmsg("index scan found few tuples"),
+				 errdetail("Index may have been created with little data."),
+				 errhint("Recreate the index and possibly decrease lists.")));
 
-#if defined(IVFFLAT_MEMORY)
+	tuplesort_performsort(so->sortstate);
-	elog(INFO, "memory: %zu MB", MemoryContextMemAllocated(CurrentMemoryContext, true) / (1024 * 1024));
-#endif
 }
 
 /*
@@ -209,13 +209,7 @@ GetScanValue(IndexScanDesc scan)
 
 		/* Normalize if needed */
 		if (so->normprocinfo != NULL)
-		{
-			MemoryContext oldCtx = MemoryContextSwitchTo(so->tmpCtx);
-
 			value = IvfflatNormValue(so->typeInfo, so->collation, value);
-
-			MemoryContextSwitchTo(oldCtx);
-		}
 	}
 
 	return value;
@@ -246,30 +240,19 @@ ivfflatbeginscan(Relation index, int nkeys, int norderbys)
 	int			lists;
 	int			dimensions;
 	int			probes = ivfflat_probes;
-	int			maxProbes;
-	MemoryContext oldCtx;
 
 	scan = RelationGetIndexScan(index, nkeys, norderbys);
 
 	/* Get lists and dimensions from metapage */
 	IvfflatGetMetaPageInfo(index, &lists, &dimensions);
 
-	if (ivfflat_iterative_scan != IVFFLAT_ITERATIVE_SCAN_OFF)
-		maxProbes = Max(ivfflat_max_probes, probes);
-	else
-		maxProbes = probes;
-
 	if (probes > lists)
 		probes = lists;
 
-	if (maxProbes > lists)
+	so = (IvfflatScanOpaque) palloc(offsetof(IvfflatScanOpaqueData, lists) + probes * sizeof(IvfflatScanList));
-		maxProbes = lists;
-
-	so = (IvfflatScanOpaque) palloc(sizeof(IvfflatScanOpaqueData));
 	so->typeInfo = IvfflatGetTypeInfo(index);
 	so->first = true;
 	so->probes = probes;
-	so->maxProbes = maxProbes;
 	so->dimensions = dimensions;
 
 	/* Set support functions */
@@ -277,12 +260,6 @@ ivfflatbeginscan(Relation index, int nkeys, int norderbys)
 	so->normprocinfo = IvfflatOptionalProcInfo(index, IVFFLAT_NORM_PROC);
 	so->collation = index->rd_indcollation[0];
 
-	so->tmpCtx = AllocSetContextCreate(CurrentMemoryContext,
-									   "Ivfflat scan temporary context",
-									   ALLOCSET_DEFAULT_SIZES);
-
-	oldCtx = MemoryContextSwitchTo(so->tmpCtx);
-
 	/* Create tuple description for sorting */
 	so->tupdesc = CreateTemplateTupleDesc(2);
 	TupleDescInitEntry(so->tupdesc, (AttrNumber) 1, "distance", FLOAT8OID, -1, 0);
@@ -303,11 +280,6 @@ ivfflatbeginscan(Relation index, int nkeys, int norderbys)
 	so->bas = GetAccessStrategy(BAS_BULKREAD);
 
 	so->listQueue = pairingheap_allocate(CompareLists, scan);
-	so->listPages = palloc(maxProbes * sizeof(BlockNumber));
-	so->listIndex = 0;
-	so->lists = palloc(maxProbes * sizeof(IvfflatScanList));
-
-	MemoryContextSwitchTo(oldCtx);
 
 	scan->opaque = so;
 
@@ -322,9 +294,11 @@ ivfflatrescan(IndexScanDesc scan, ScanKey keys, int nkeys, ScanKey orderbys, int
 {
 	IvfflatScanOpaque so = (IvfflatScanOpaque) scan->opaque;
 
+	if (!so->first)
+		tuplesort_reset(so->sortstate);
+
 	so->first = true;
 	pairingheap_reset(so->listQueue);
-	so->listIndex = 0;
 
 	if (keys && scan->numberOfKeys > 0)
 		memmove(scan->keyData, keys, scan->numberOfKeys * sizeof(ScanKeyData));
@@ -340,8 +314,6 @@ bool
 ivfflatgettuple(IndexScanDesc scan, ScanDirection dir)
 {
 	IvfflatScanOpaque so = (IvfflatScanOpaque) scan->opaque;
-	ItemPointer heaptid;
-	bool		isnull;
 
 	/*
 	 * Index can be used to scan backward, but Postgres doesn't support
@@ -369,23 +341,28 @@ ivfflatgettuple(IndexScanDesc scan, ScanDirection dir)
 		IvfflatBench("GetScanLists", GetScanLists(scan, value));
 		IvfflatBench("GetScanItems", GetScanItems(scan, value));
 		so->first = false;
-		so->value = value;
+
+#if defined(IVFFLAT_MEMORY)
+		elog(INFO, "memory: %zu MB", MemoryContextMemAllocated(CurrentMemoryContext, true) / (1024 * 1024));
+#endif
+
+		/* Clean up if we allocated a new value */
+		if (value != scan->orderByData->sk_argument)
+			pfree(DatumGetPointer(value));
 	}
 
-	while (!tuplesort_gettupleslot(so->sortstate, true, false, so->mslot, NULL))
+	if (tuplesort_gettupleslot(so->sortstate, true, false, so->mslot, NULL))
 	{
-		if (so->listIndex == so->maxProbes)
+		bool		isnull;
-			return false;
+		ItemPointer heaptid = (ItemPointer) DatumGetPointer(slot_getattr(so->mslot, 2, &isnull));
 
-		IvfflatBench("GetScanItems", GetScanItems(scan, so->value));
+		scan->xs_heaptid = *heaptid;
+		scan->xs_recheck = false;
+		scan->xs_recheckorderby = false;
+		return true;
 	}
 
-	heaptid = (ItemPointer) DatumGetPointer(slot_getattr(so->mslot, 2, &isnull));
+	return false;
-
-	scan->xs_heaptid = *heaptid;
-	scan->xs_recheck = false;
-	scan->xs_recheckorderby = false;
-	return true;
 }
 
 /*
@@ -396,10 +373,12 @@ ivfflatendscan(IndexScanDesc scan)
 {
 	IvfflatScanOpaque so = (IvfflatScanOpaque) scan->opaque;
 
-	/* Free any temporary files */
+	pairingheap_free(so->listQueue);
 	tuplesort_end(so->sortstate);
+	FreeAccessStrategy(so->bas);
+	FreeTupleDesc(so->tupdesc);
 
-	MemoryContextDelete(so->tmpCtx);
+	/* TODO Free vslot and mslot without freeing TupleDesc */
 
 	pfree(so);
 	scan->opaque = NULL;

src/ivfutils.c

@@ -355,7 +355,7 @@ ivfflat_halfvec_support(PG_FUNCTION_ARGS)
 	};
 
 	PG_RETURN_POINTER(&typeInfo);
-}
+};
 
 FUNCTION_PREFIX PG_FUNCTION_INFO_V1(ivfflat_bit_support);
 Datum
@@ -370,4 +370,4 @@ ivfflat_bit_support(PG_FUNCTION_ARGS)
 	};
 
 	PG_RETURN_POINTER(&typeInfo);
-}
+};

src/ivfvacuum.c

@@ -26,7 +26,7 @@ ivfflatbulkdelete(IndexVacuumInfo *info, IndexBulkDeleteResult *stats,
 		Page		cpage;
 		OffsetNumber coffno;
 		OffsetNumber cmaxoffno;
-		BlockNumber listPages[MaxOffsetNumber];
+		BlockNumber startPages[MaxOffsetNumber];
 		ListInfo	listInfo;
 
 		cbuf = ReadBuffer(index, blkno);
@@ -40,7 +40,7 @@ ivfflatbulkdelete(IndexVacuumInfo *info, IndexBulkDeleteResult *stats,
 		{
 			IvfflatList list = (IvfflatList) PageGetItem(cpage, PageGetItemId(cpage, coffno));
 
-			listPages[coffno - FirstOffsetNumber] = list->startPage;
+			startPages[coffno - FirstOffsetNumber] = list->startPage;
 		}
 
 		listInfo.blkno = blkno;
@@ -50,7 +50,7 @@ ivfflatbulkdelete(IndexVacuumInfo *info, IndexBulkDeleteResult *stats,
 
 		for (coffno = FirstOffsetNumber; coffno <= cmaxoffno; coffno = OffsetNumberNext(coffno))
 		{
-			BlockNumber searchPage = listPages[coffno - FirstOffsetNumber];
+			BlockNumber searchPage = startPages[coffno - FirstOffsetNumber];
 			BlockNumber insertPage = InvalidBlockNumber;
 
 			/* Iterate over entry pages */

src/sparsevec.c

@@ -4,7 +4,6 @@
 #include <math.h>
 
 #include "catalog/pg_type.h"
-#include "common/shortest_dec.h"
 #include "common/string.h"
 #include "fmgr.h"
 #include "halfutils.h"
@@ -13,10 +12,17 @@
 #include "sparsevec.h"
 #include "utils/array.h"
 #include "utils/builtins.h"
-#include "utils/float.h"
 #include "utils/lsyscache.h"
 #include "vector.h"
 
+#if PG_VERSION_NUM >= 120000
+#include "common/shortest_dec.h"
+#include "utils/float.h"
+#else
+#include <float.h>
+#include "utils/builtins.h"
+#endif
+
 typedef struct SparseInputElement
 {
 	int32		index;

test/expected/hnsw_vector.out

@@ -99,32 +99,6 @@ SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <+> (SELECT NULL::vector)) t2
      4
 (1 row)
 
-DROP TABLE t;
--- iterative
-CREATE TABLE t (val vector(3));
-INSERT INTO t (val) VALUES ('[0,0,0]'), ('[1,2,3]'), ('[1,1,1]'), (NULL);
-CREATE INDEX ON t USING hnsw (val vector_l2_ops);
-SET hnsw.iterative_scan = strict_order;
-SET hnsw.ef_search = 1;
-SELECT * FROM t ORDER BY val <-> '[3,3,3]';
-   val   
----------
- [1,2,3]
- [1,1,1]
- [0,0,0]
-(3 rows)
-
-SET hnsw.iterative_scan = relaxed_order;
-SELECT * FROM t ORDER BY val <-> '[3,3,3]';
-   val   
----------
- [1,2,3]
- [1,1,1]
- [0,0,0]
-(3 rows)
-
-RESET hnsw.iterative_scan;
-RESET hnsw.ef_search;
 DROP TABLE t;
 -- unlogged
 CREATE UNLOGGED TABLE t (val vector(3));
@@ -165,31 +139,4 @@ SET hnsw.ef_search = 0;
 ERROR:  0 is outside the valid range for parameter "hnsw.ef_search" (1 .. 1000)
 SET hnsw.ef_search = 1001;
 ERROR:  1001 is outside the valid range for parameter "hnsw.ef_search" (1 .. 1000)
-SHOW hnsw.iterative_scan;
- hnsw.iterative_scan 
----------------------
- off
-(1 row)
-
-SET hnsw.iterative_scan = on;
-ERROR:  invalid value for parameter "hnsw.iterative_scan": "on"
-HINT:  Available values: off, relaxed_order, strict_order.
-SHOW hnsw.max_scan_tuples;
- hnsw.max_scan_tuples 
-----------------------
- 20000
-(1 row)
-
-SET hnsw.max_scan_tuples = 0;
-ERROR:  0 is outside the valid range for parameter "hnsw.max_scan_tuples" (1 .. 2147483647)
-SHOW hnsw.scan_mem_multiplier;
- hnsw.scan_mem_multiplier 
---------------------------
- 1
-(1 row)
-
-SET hnsw.scan_mem_multiplier = 0;
-ERROR:  0 is outside the valid range for parameter "hnsw.scan_mem_multiplier" (1 .. 1000)
-SET hnsw.scan_mem_multiplier = 1001;
-ERROR:  1001 is outside the valid range for parameter "hnsw.scan_mem_multiplier" (1 .. 1000)
 DROP TABLE t;

test/expected/ivfflat_vector.out

@@ -81,37 +81,6 @@ SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <=> (SELECT NULL::vector)) t2
      3
 (1 row)
 
-DROP TABLE t;
--- iterative
-CREATE TABLE t (val vector(3));
-INSERT INTO t (val) VALUES ('[0,0,0]'), ('[1,2,3]'), ('[1,1,1]'), (NULL);
-CREATE INDEX ON t USING ivfflat (val vector_l2_ops) WITH (lists = 3);
-SET ivfflat.iterative_scan = relaxed_order;
-SELECT * FROM t ORDER BY val <-> '[3,3,3]';
-   val   
----------
- [1,2,3]
- [1,1,1]
- [0,0,0]
-(3 rows)
-
-SET ivfflat.max_probes = 1;
-SELECT * FROM t ORDER BY val <-> '[3,3,3]';
-   val   
----------
- [1,2,3]
-(1 row)
-
-SET ivfflat.max_probes = 2;
-SELECT * FROM t ORDER BY val <-> '[3,3,3]';
-   val   
----------
- [1,2,3]
- [1,1,1]
-(2 rows)
-
-RESET ivfflat.iterative_scan;
-RESET ivfflat.max_probes;
 DROP TABLE t;
 -- unlogged
 CREATE UNLOGGED TABLE t (val vector(3));
@@ -140,27 +109,4 @@ SHOW ivfflat.probes;
  1
 (1 row)
 
-SET ivfflat.probes = 0;
-ERROR:  0 is outside the valid range for parameter "ivfflat.probes" (1 .. 32768)
-SET ivfflat.probes = 32769;
-ERROR:  32769 is outside the valid range for parameter "ivfflat.probes" (1 .. 32768)
-SHOW ivfflat.iterative_scan;
- ivfflat.iterative_scan 
-------------------------
- off
-(1 row)
-
-SET ivfflat.iterative_scan = on;
-ERROR:  invalid value for parameter "ivfflat.iterative_scan": "on"
-HINT:  Available values: off, relaxed_order.
-SHOW ivfflat.max_probes;
- ivfflat.max_probes 
---------------------
- 32768
-(1 row)
-
-SET ivfflat.max_probes = 0;
-ERROR:  0 is outside the valid range for parameter "ivfflat.max_probes" (1 .. 32768)
-SET ivfflat.max_probes = 32769;
-ERROR:  32769 is outside the valid range for parameter "ivfflat.max_probes" (1 .. 32768)
 DROP TABLE t;

test/sql/hnsw_vector.sql

@@ -57,23 +57,6 @@ SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <+> (SELECT NULL::vector)) t2
 
 DROP TABLE t;
 
--- iterative
-
-CREATE TABLE t (val vector(3));
-INSERT INTO t (val) VALUES ('[0,0,0]'), ('[1,2,3]'), ('[1,1,1]'), (NULL);
-CREATE INDEX ON t USING hnsw (val vector_l2_ops);
-
-SET hnsw.iterative_scan = strict_order;
-SET hnsw.ef_search = 1;
-SELECT * FROM t ORDER BY val <-> '[3,3,3]';
-
-SET hnsw.iterative_scan = relaxed_order;
-SELECT * FROM t ORDER BY val <-> '[3,3,3]';
-
-RESET hnsw.iterative_scan;
-RESET hnsw.ef_search;
-DROP TABLE t;
-
 -- unlogged
 
 CREATE UNLOGGED TABLE t (val vector(3));
@@ -98,17 +81,4 @@ SHOW hnsw.ef_search;
 SET hnsw.ef_search = 0;
 SET hnsw.ef_search = 1001;
 
-SHOW hnsw.iterative_scan;
-
-SET hnsw.iterative_scan = on;
-
-SHOW hnsw.max_scan_tuples;
-
-SET hnsw.max_scan_tuples = 0;
-
-SHOW hnsw.scan_mem_multiplier;
-
-SET hnsw.scan_mem_multiplier = 0;
-SET hnsw.scan_mem_multiplier = 1001;
-
 DROP TABLE t;

test/sql/ivfflat_vector.sql

@@ -44,25 +44,6 @@ SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <=> (SELECT NULL::vector)) t2
 
 DROP TABLE t;
 
--- iterative
-
-CREATE TABLE t (val vector(3));
-INSERT INTO t (val) VALUES ('[0,0,0]'), ('[1,2,3]'), ('[1,1,1]'), (NULL);
-CREATE INDEX ON t USING ivfflat (val vector_l2_ops) WITH (lists = 3);
-
-SET ivfflat.iterative_scan = relaxed_order;
-SELECT * FROM t ORDER BY val <-> '[3,3,3]';
-
-SET ivfflat.max_probes = 1;
-SELECT * FROM t ORDER BY val <-> '[3,3,3]';
-
-SET ivfflat.max_probes = 2;
-SELECT * FROM t ORDER BY val <-> '[3,3,3]';
-
-RESET ivfflat.iterative_scan;
-RESET ivfflat.max_probes;
-DROP TABLE t;
-
 -- unlogged
 
 CREATE UNLOGGED TABLE t (val vector(3));
@@ -81,16 +62,4 @@ CREATE INDEX ON t USING ivfflat (val vector_l2_ops) WITH (lists = 32769);
 
 SHOW ivfflat.probes;
 
-SET ivfflat.probes = 0;
-SET ivfflat.probes = 32769;
-
-SHOW ivfflat.iterative_scan;
-
-SET ivfflat.iterative_scan = on;
-
-SHOW ivfflat.max_probes;
-
-SET ivfflat.max_probes = 0;
-SET ivfflat.max_probes = 32769;
-
 DROP TABLE t;

test/t/002_ivfflat_vacuum.pl

@@ -6,7 +6,13 @@ use Test::More;
 
 my $dim = 3;
 
-my $array_sql = join(",", ('random()') x $dim);
+my @r = ();
+for (1 .. $dim)
+{
+	my $v = int(rand(1000)) + 1;
+	push(@r, "i % $v");
+}
+my $array_sql = join(", ", @r);
 
 # Initialize node
 my $node = PostgreSQL::Test::Cluster->new('node');
@@ -17,20 +23,19 @@ $node->start;
 $node->safe_psql("postgres", "CREATE EXTENSION vector;");
 $node->safe_psql("postgres", "CREATE TABLE tst (i int4, v vector($dim));");
 $node->safe_psql("postgres",
-	"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(1, 100000) i;"
+	"INSERT INTO tst SELECT i % 10, ARRAY[$array_sql] FROM generate_series(1, 100000) i;"
 );
 $node->safe_psql("postgres", "CREATE INDEX ON tst USING ivfflat (v vector_l2_ops);");
 
 # Get size
 my $size = $node->safe_psql("postgres", "SELECT pg_total_relation_size('tst_v_idx');");
 
-# Store values
-$node->safe_psql("postgres", "CREATE TABLE tmp AS SELECT * FROM tst;");
-
 # Delete all, vacuum, and insert same data
 $node->safe_psql("postgres", "DELETE FROM tst;");
 $node->safe_psql("postgres", "VACUUM tst;");
-$node->safe_psql("postgres", "INSERT INTO tst SELECT * FROM tmp;");
+$node->safe_psql("postgres",
+	"INSERT INTO tst SELECT i % 10, ARRAY[$array_sql] FROM generate_series(1, 100000) i;"
+);
 
 # Check size
 my $new_size = $node->safe_psql("postgres", "SELECT pg_total_relation_size('tst_v_idx');");

test/t/041_hnsw_streaming.pl

@@ -26,26 +26,25 @@ $node->safe_psql("postgres", qq(
 
 my $count = $node->safe_psql("postgres", qq(
 	SET enable_seqscan = off;
-	SET hnsw.iterative_scan = relaxed_order;
+	SET hnsw.streaming = on;
-	SET hnsw.max_scan_tuples = 100000;
+	SET work_mem = '8MB';
-	SET hnsw.scan_mem_multiplier = 2;
 	SELECT COUNT(*) FROM (SELECT v FROM tst WHERE i % 10000 = 0 ORDER BY v <-> (SELECT v FROM tst LIMIT 1) LIMIT 11) t;
 ));
 is($count, 10);
 
 foreach ((30000, 50000, 70000))
 {
-	my $max_tuples = $_;
+	my $ef_stream = $_;
-	my $expected = $max_tuples / 10000;
+	my $expected = $ef_stream / 10000;
 	my $sum = 0;
 
 	for my $i (1 .. 20)
 	{
 		$count = $node->safe_psql("postgres", qq(
 			SET enable_seqscan = off;
-			SET hnsw.iterative_scan = relaxed_order;
+			SET hnsw.streaming = on;
-			SET hnsw.max_scan_tuples = $max_tuples;
+			SET hnsw.ef_stream = $ef_stream;
-			SET hnsw.scan_mem_multiplier = 2;
+			SET work_mem = '8MB';
 			SELECT COUNT(*) FROM (SELECT v FROM tst WHERE i % 10000 = 0 ORDER BY v <-> (SELECT v FROM tst WHERE i = $i) LIMIT 11) t;
 		));
 		$sum += $count;
@@ -56,4 +55,13 @@ foreach ((30000, 50000, 70000))
 	cmp_ok($avg, '<', $expected + 2);
 }
 
+my ($ret, $stdout, $stderr) = $node->psql("postgres", qq(
+	SET enable_seqscan = off;
+	SET hnsw.streaming = on;
+	SET client_min_messages = debug1;
+	SET work_mem = '2MB';
+	SELECT COUNT(*) FROM (SELECT v FROM tst WHERE i % 10000 = 0 ORDER BY v <-> (SELECT v FROM tst LIMIT 1) LIMIT 11) t;
+));
+like($stderr, qr/hnsw index scan exceeded work_mem after \d+ tuples/);
+
 done_testing();

test/t/041_ivfflat_iterative_scan.pl

@@ -1,54 +0,0 @@
-use strict;
-use warnings FATAL => 'all';
-use PostgreSQL::Test::Cluster;
-use PostgreSQL::Test::Utils;
-use Test::More;
-
-my $dim = 3;
-my $array_sql = join(",", ('random()') x $dim);
-
-# Initialize node
-my $node = PostgreSQL::Test::Cluster->new('node');
-$node->init;
-$node->start;
-
-# Create table
-$node->safe_psql("postgres", "CREATE EXTENSION vector;");
-$node->safe_psql("postgres", "CREATE TABLE tst (i int4 PRIMARY KEY, v vector($dim));");
-$node->safe_psql("postgres",
-	"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(1, 100000) i;"
-);
-$node->safe_psql("postgres", "CREATE INDEX ON tst USING ivfflat (v vector_l2_ops);");
-
-my $count = $node->safe_psql("postgres", qq(
-	SET enable_seqscan = off;
-	SET ivfflat.probes = 10;
-	SET ivfflat.iterative_scan = relaxed_order;
-	SELECT COUNT(*) FROM (SELECT v FROM tst WHERE i % 10000 = 0 ORDER BY v <-> (SELECT v FROM tst LIMIT 1) LIMIT 11) t;
-));
-is($count, 10);
-
-foreach ((30, 50, 70))
-{
-	my $max_probes = $_;
-	my $expected = $max_probes / 10;
-	my $sum = 0;
-
-	for my $i (1 .. 20)
-	{
-		$count = $node->safe_psql("postgres", qq(
-			SET enable_seqscan = off;
-			SET ivfflat.probes = 10;
-			SET ivfflat.iterative_scan = relaxed_order;
-			SET ivfflat.max_probes = $max_probes;
-			SELECT COUNT(*) FROM (SELECT v FROM tst WHERE i % 10000 = 0 ORDER BY v <-> (SELECT v FROM tst WHERE i = $i) LIMIT 11) t;
-		));
-		$sum += $count;
-	}
-
-	my $avg = $sum / 20;
-	cmp_ok($avg, '>', $expected - 2);
-	cmp_ok($avg, '<', $expected + 2);
-}
-
-done_testing();

test/t/042_hnsw_streaming_recall.pl

@@ -10,18 +10,18 @@ my @expected;
 my $limit = 20;
 my $dim = 3;
 my $array_sql = join(",", ('random()') x $dim);
-my @cs = (50, 500);
+my @cs = (100, 1000);
 
 sub test_recall
 {
-	my ($c, $ef_search, $min, $operator, $mode) = @_;
+	my ($c, $ef_search, $min, $operator) = @_;
 	my $correct = 0;
 	my $total = 0;
 
 	my $explain = $node->safe_psql("postgres", qq(
 		SET enable_seqscan = off;
 		SET hnsw.ef_search = $ef_search;
-		SET hnsw.iterative_scan = $mode;
+		SET hnsw.streaming = on;
 		EXPLAIN ANALYZE SELECT i FROM tst WHERE i % $c = 0 ORDER BY v $operator '$queries[0]' LIMIT $limit;
 	));
 	like($explain, qr/Index Scan using idx on tst/);
@@ -31,7 +31,7 @@ sub test_recall
 		my $actual = $node->safe_psql("postgres", qq(
 			SET enable_seqscan = off;
 			SET hnsw.ef_search = $ef_search;
-			SET hnsw.iterative_scan = $mode;
+			SET hnsw.streaming = on;
 			SELECT i FROM tst WHERE i % $c = 0 ORDER BY v $operator '$queries[$i]' LIMIT $limit;
 		));
 		my @actual_ids = split("\n", $actual);
@@ -50,7 +50,7 @@ sub test_recall
 		$total += $limit;
 	}
 
-	cmp_ok($correct / $total, ">=", $min, "$operator $mode $c");
+	cmp_ok($correct / $total, ">=", $min, $operator);
 }
 
 # Initialize node
@@ -62,7 +62,7 @@ $node->start;
 $node->safe_psql("postgres", "CREATE EXTENSION vector;");
 $node->safe_psql("postgres", "CREATE TABLE tst (i int4, v vector($dim));");
 $node->safe_psql("postgres",
-	"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(1, 50000) i;"
+	"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(1, 100000) i;"
 );
 
 # Generate queries
@@ -108,8 +108,21 @@ for my $i (0 .. $#operators)
 			push(@expected, $res);
 		}
 
-		test_recall($c, 40, 0.99, $operator, "strict_order");
+		if ($c == 100)
-		test_recall($c, 40, 0.99, $operator, "relaxed_order");
+		{
+			test_recall($c, 40, 0.99, $operator);
+		}
+		else
+		{
+			if ($operator eq "<->")
+			{
+				test_recall($c, 40, 0.99, $operator);
+			}
+			else
+			{
+				test_recall($c, 40, 0.99, $operator);
+			}
+		}
 	}
 
 	$node->safe_psql("postgres", "DROP INDEX idx;");

test/t/042_ivfflat_iterative_scan_recall.pl

@@ -1,125 +0,0 @@
-use strict;
-use warnings FATAL => 'all';
-use PostgreSQL::Test::Cluster;
-use PostgreSQL::Test::Utils;
-use Test::More;
-
-my $node;
-my @queries = ();
-my @expected;
-my $limit = 20;
-my @cs = (100, 1000);
-
-sub test_recall
-{
-	my ($c, $probes, $min, $operator) = @_;
-	my $correct = 0;
-	my $total = 0;
-
-	my $explain = $node->safe_psql("postgres", qq(
-		SET enable_seqscan = off;
-		SET ivfflat.probes = $probes;
-		SET ivfflat.iterative_scan = relaxed_order;
-		EXPLAIN ANALYZE SELECT i FROM tst WHERE i % $c = 0 ORDER BY v $operator '$queries[0]' LIMIT $limit;
-	));
-	like($explain, qr/Index Scan using idx on tst/);
-
-	for my $i (0 .. $#queries)
-	{
-		my $actual = $node->safe_psql("postgres", qq(
-			SET enable_seqscan = off;
-			SET ivfflat.probes = $probes;
-			SET ivfflat.iterative_scan = relaxed_order;
-			SELECT i FROM tst WHERE i % $c = 0 ORDER BY v $operator '$queries[$i]' LIMIT $limit;
-		));
-		my @actual_ids = split("\n", $actual);
-
-		my @expected_ids = split("\n", $expected[$i]);
-		my %expected_set = map { $_ => 1 } @expected_ids;
-
-		foreach (@actual_ids)
-		{
-			if (exists($expected_set{$_}))
-			{
-				$correct++;
-			}
-		}
-
-		$total += $limit;
-	}
-
-	cmp_ok($correct / $total, ">=", $min, "$operator $c");
-}
-
-# Initialize node
-$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 (i int4, v vector(3));");
-$node->safe_psql("postgres",
-	"INSERT INTO tst SELECT i, ARRAY[random(), random(), random()] FROM generate_series(1, 100000) i;"
-);
-
-# Generate queries
-for (1 .. 20)
-{
-	my $r1 = rand();
-	my $r2 = rand();
-	my $r3 = rand();
-	push(@queries, "[$r1,$r2,$r3]");
-}
-
-# Check each index type
-my @operators = ("<->", "<=>");
-my @opclasses = ("vector_l2_ops", "vector_cosine_ops");
-
-for my $i (0 .. $#operators)
-{
-	my $operator = $operators[$i];
-	my $opclass = $opclasses[$i];
-
-	$node->safe_psql("postgres", "CREATE INDEX idx ON tst USING ivfflat (v $opclass);");
-
-	foreach (@cs)
-	{
-		my $c = $_;
-
-		# Get exact results
-		@expected = ();
-		foreach (@queries)
-		{
-			my $res = $node->safe_psql("postgres", qq(
-				SET enable_indexscan = off;
-				WITH top AS (
-					SELECT v $operator '$_' AS distance FROM tst WHERE i % $c = 0 ORDER BY distance LIMIT $limit
-				)
-				SELECT i FROM tst WHERE (v $operator '$_') <= (SELECT MAX(distance) FROM top)
-			));
-			push(@expected, $res);
-		}
-
-		if ($c == 100)
-		{
-			test_recall($c, 1, 0.57, $operator);
-			test_recall($c, 10, 0.98, $operator);
-		}
-		else
-		{
-			if ($operator eq "<->")
-			{
-				test_recall($c, 1, 0.80, $operator);
-			}
-			else
-			{
-				test_recall($c, 1, 0.88, $operator);
-			}
-		}
-	}
-
-	$node->safe_psql("postgres", "DROP INDEX idx;");
-}
-
-done_testing();

vector.control

@@ -1,4 +1,4 @@
 comment = 'vector data type and ivfflat and hnsw access methods'
-default_version = '0.8.0'
+default_version = '0.7.4'
 module_pathname = '$libdir/vector'
 relocatable = true