Compare commits

...

91 Commits

Author SHA1 Message Date
Andrew Kane
2627c5ff77 Version bump to 0.8.0 [skip ci] 2024-10-30 13:06:34 -07:00
Andrew Kane
34b3cfdc43 Updated min Postgres version in META.json [skip ci] 2024-10-30 13:06:12 -07:00
Andrew Kane
cd218aae5a Removed unneeded code 2024-10-30 13:05:10 -07:00
Andrew Kane
ba9367f86c Updated readme [skip ci] 2024-10-30 12:58:00 -07:00
Andrew Kane
9c20550a41 Updated readme 2024-10-30 12:54:42 -07:00
Andrew Kane
e3e74fe94e Updated readme [skip ci] 2024-10-29 00:04:35 -07:00
Andrew Kane
96a5a44632 Updated readme [skip ci] 2024-10-28 23:52:16 -07:00
Andrew Kane
67e1392a83 Updated readme [skip ci] 2024-10-28 22:58:56 -07:00
Andrew Kane
e530a1a026 Updated readme [skip ci] 2024-10-28 22:49:41 -07:00
Andrew Kane
6170e2645b Updated readme [skip ci] 2024-10-28 22:44:44 -07:00
Andrew Kane
e6bae175f1 Updated readme [skip ci] 2024-10-28 22:26:50 -07:00
Andrew Kane
52b777e04a Updated readme [skip ci] 2024-10-28 22:01:27 -07:00
Andrew Kane
307271214f Updated readme [skip ci] 2024-10-28 21:42:05 -07:00
Andrew Kane
6e9f74ddce Updated readme [skip ci] 2024-10-28 20:04:09 -07:00
Andrew Kane
258215ad97 Improved test [skip ci] 2024-10-28 15:54:39 -07:00
Andrew Kane
fb87b6da91 Fixed test 2024-10-28 13:55:26 -07:00
Andrew Kane
a2a0b377f0 Removed memory limit debug message from HNSW index scans (EXPLAIN ANALYZE can be used instead) 2024-10-28 13:46:49 -07:00
Andrew Kane
2f770307b8 Removed unused variable [skip ci] 2024-10-28 13:38:42 -07:00
Andrew Kane
c04e16ff5b Removed debug message from IVFFlat index scans [skip ci] 2024-10-28 13:36:57 -07:00
Andrew Kane
bd4d272f26 Updated changelog [skip ci] 2024-10-28 13:05:27 -07:00
Andrew Kane
8bb797cc2f Updated changelog [skip ci] 2024-10-28 13:00:55 -07:00
Andrew Kane
fe6ec03dac Improved filtering section [skip ci] 2024-10-28 12:08:27 -07:00
Andrew Kane
c1161f8889 Updated readme [skip ci] 2024-10-28 02:08:53 -07:00
Andrew Kane
c530a3c490 Updated comment [skip ci] 2024-10-28 00:56:10 -07:00
Andrew Kane
d8b9e8ef73 Updated readme [skip ci] 2024-10-28 00:55:25 -07:00
Andrew Kane
00894efed5 Updated readme [skip ci] 2024-10-28 00:45:26 -07:00
Andrew Kane
0aa0f6619b Updated readme [skip ci] 2024-10-28 00:43:39 -07:00
Andrew Kane
38d053001e Updated readme [skip ci] 2024-10-28 00:32:12 -07:00
Andrew Kane
ccb95407e7 Updated readme [skip ci] 2024-10-28 00:09:26 -07:00
Andrew Kane
04d5e934a1 Scan 2000 more tuples with default work_mem 2024-10-27 22:23:28 -07:00
Andrew Kane
b163b5b196 Moved code [skip ci] 2024-10-27 22:21:43 -07:00
Andrew Kane
6a30c1e824 Fixed test [skip ci] 2024-10-27 21:10:51 -07:00
Andrew Kane
2db1b19644 Use greater than [skip ci] 2024-10-27 21:07:22 -07:00
Andrew Kane
305d62146e Updated comment [skip ci] 2024-10-27 21:05:32 -07:00
Andrew Kane
f9d627c9a9 Updated default value of hnsw.scan_mem_multiplier [skip ci] 2024-10-27 21:05:04 -07:00
Andrew Kane
38f42820be Added test for hnsw.scan_mem_multiplier [skip ci] 2024-10-27 20:05:58 -07:00
Andrew Kane
15c8245b42 Updated readme [skip ci] 2024-10-27 19:30:40 -07:00
Andrew Kane
572a9ab404 Updated readme [skip ci] 2024-10-27 18:58:50 -07:00
Andrew Kane
00492d7e57 Ensure max memory fits into Size for HNSW index scans 2024-10-27 14:21:15 -07:00
Andrew Kane
857d716d9e Renamed iterative_search to iterative_scan 2024-10-27 14:02:22 -07:00
Andrew Kane
c5dd2af750 Added comments [skip ci] 2024-10-25 21:39:03 -07:00
Andrew Kane
78b877bdaf Revert "Renamed iterative_search to iterative_scan"
This reverts commit 7043cce893.
2024-10-24 20:32:07 -07:00
Andrew Kane
7043cce893 Renamed iterative_search to iterative_scan 2024-10-24 20:31:43 -07:00
Andrew Kane
62039d74f6 Added iterative search section to readme [skip ci] 2024-10-24 18:05:29 -07:00
Andrew Kane
ac6576e53a Added hnsw.search_mem_multiplier option 2024-10-24 18:02:20 -07:00
Andrew Kane
67eff41c44 Updated changelog [skip ci] 2024-10-23 15:12:40 -07:00
Andrew Kane
1291b12090 Added Postgres 18 to CI [skip ci] 2024-10-22 00:38:19 -07:00
Andrew Kane
24522700b8 Improved hnswrescan 2024-10-21 23:41:32 -07:00
Andrew Kane
bfb3a45b31 Use consistent order [skip ci] 2024-10-21 21:47:03 -07:00
Andrew Kane
e718eb8da4 Updated range and defaults for iterative search parameters 2024-10-21 20:38:50 -07:00
Andrew Kane
049972a4a3 Improved test output [skip ci] 2024-10-13 17:22:49 -07:00
Andrew Kane
61027645e9 Improved test output [skip ci] 2024-10-13 17:21:38 -07:00
Andrew Kane
a41b327b33 Speed up test [skip ci] 2024-10-13 17:12:12 -07:00
Andrew Kane
7f735ebd9b Added test for strict order [skip ci] 2024-10-13 17:04:03 -07:00
Andrew Kane
02b01e1ca9 Show tuples with memory usage [skip ci] 2024-10-12 22:05:13 -07:00
Andrew Kane
388e42f6e6 Fixed flaky test [skip ci] 2024-10-11 15:48:19 -07:00
Andrew Kane
bf379eed86 Use a memory context for IVFFlat index scans 2024-10-11 15:46:38 -07:00
Andrew Kane
e1bc929429 Simplify lists for IvfflatScanOpaque [skip ci] 2024-10-11 15:29:23 -07:00
Andrew Kane
38285aacc7 Revert "Updated IVFFlat to support multiple attributes (not enabled yet)"
This reverts commit 772ab69de6.
2024-10-11 15:01:54 -07:00
Andrew Kane
a2408e60fa Revert "Added IndexTuple to HNSW elements (first step to support multiple attributes)"
This reverts commit 53a8734bac.
2024-10-11 14:57:57 -07:00
Andrew Kane
53a8734bac Added IndexTuple to HNSW elements (first step to support multiple attributes) 2024-10-11 14:12:01 -07:00
Andrew Kane
7484625227 Added comments [skip ci] 2024-10-11 11:59:36 -07:00
Andrew Kane
d1ebb8db73 Use -1 for no limit for ivfflat.max_probes [skip ci] 2024-10-11 11:43:32 -07:00
Andrew Kane
42af8aa1d1 Updated GUC descriptions [skip ci] 2024-10-11 11:26:27 -07:00
Andrew Kane
9d15a76b60 Improved enum naming [skip ci] 2024-10-11 11:20:36 -07:00
Andrew Kane
a3a20f9816 Simplified GUC names [skip ci] 2024-10-11 11:18:01 -07:00
Andrew Kane
b26a21b848 Added regression tests for iterative search [skip ci] 2024-10-11 11:07:11 -07:00
Andrew Kane
2dc392ed6c Updated GUC names [skip ci] 2024-10-10 23:50:11 -07:00
Andrew Kane
960d2848cb Updated comment [skip ci] 2024-10-10 21:02:33 -07:00
Andrew Kane
8e88b481a6 Use a lower max allocation size than default to allow scanning more tuples for iterative search before exceeding work_mem [skip ci] 2024-10-10 20:57:57 -07:00
Andrew Kane
124018b8dd Added HnswInitSearchCandidate function 2024-10-10 19:30:47 -07:00
Andrew Kane
35b252a3e3 Switched to macos-13 on CI [skip ci] 2024-10-10 18:33:35 -07:00
Andrew Kane
2832e746f0 Use get_float8_infinity instead of INFINITY
Co-authored-by: "Jonathan S. Katz" <jkatz@amazon.com>
2024-10-10 18:16:39 -07:00
Andrew Kane
961cb17d80 Added iterative search for HNSW [skip ci] 2024-10-10 18:14:39 -07:00
Andrew Kane
c91ed7b2c3 Added iterative search for IVFFlat [skip ci] 2024-10-10 18:12:27 -07:00
Andrew Kane
48fe70c219 Fixed sortdesc for multiple attributes [skip ci] 2024-10-10 15:22:23 -07:00
Andrew Kane
29908405ab List assignment does not change with scaling [skip ci] 2024-10-10 15:16:08 -07:00
Andrew Kane
08d0340655 Improved IVFFlat vacuum test [skip ci] 2024-10-10 14:24:26 -07:00
Andrew Kane
7d2eb49c2a Fixed list assignment for cosine distance and non-normalized vectors for IVFFlat 2024-10-10 12:54:13 -07:00
Andrew Kane
772ab69de6 Updated IVFFlat to support multiple attributes (not enabled yet) 2024-10-10 12:34:03 -07:00
Andrew Kane
e13e9a9614 Improved scoping [skip ci] 2024-10-10 12:19:08 -07:00
Andrew Kane
e2fab306ac Added tupdesc to buildstate [skip ci] 2024-10-10 12:18:41 -07:00
Andrew Kane
edc2126a4a Renamed tupdesc to sortdesc [skip ci] 2024-10-10 12:16:57 -07:00
Andrew Kane
2cbd08b6c0 Moved unions and macros [skip ci] 2024-10-10 09:41:26 -07:00
Andrew Kane
fa6782985a Added HnswQuery struct for query data 2024-10-09 23:45:47 -07:00
Andrew Kane
32ab27d72a Added HnswSupport struct for support functions 2024-10-09 23:10:26 -07:00
Andrew Kane
064db12de7 Moved procinfo initialization for inserts [skip ci] 2024-10-09 21:59:21 -07:00
Andrew Kane
45a6eef9e0 Improved variable name [skip ci] 2024-10-09 21:52:10 -07:00
Andrew Kane
17266ed409 Use inMemory for conditionals 2024-10-09 21:49:32 -07:00
Andrew Kane
a98534e5ab DRY HNSW procinfo 2024-10-09 21:03:18 -07:00
Andrew Kane
57c05c59a2 DRY code for forming index value 2024-10-09 20:50:17 -07:00
30 changed files with 1231 additions and 287 deletions

View File

@@ -8,8 +8,8 @@ jobs:
fail-fast: false fail-fast: false
matrix: matrix:
include: include:
# - postgres: 18 - postgres: 18
# os: ubuntu-24.04 os: ubuntu-24.04
- postgres: 17 - postgres: 17
os: ubuntu-24.04 os: ubuntu-24.04
- postgres: 16 - postgres: 16
@@ -49,7 +49,7 @@ jobs:
- postgres: 16 - postgres: 16
os: macos-14 os: macos-14
- postgres: 14 - postgres: 14
os: macos-12 os: macos-13
steps: steps:
- uses: actions/checkout@v4 - uses: actions/checkout@v4
- uses: ankane/setup-postgres@v1 - uses: ankane/setup-postgres@v1

View File

@@ -1,9 +1,10 @@
## 0.8.0 (unreleased) ## 0.8.0 (2024-10-30)
- Added support for iterative index scans
- Added casts for arrays to `sparsevec` - Added casts for arrays to `sparsevec`
- Improved cost estimation - Improved cost estimation for better index selection when filtering
- Improved performance of HNSW index scans
- Improved performance of HNSW inserts and on-disk index builds - Improved performance of HNSW inserts and on-disk index builds
- Reduced memory usage for HNSW index scans
- Dropped support for Postgres 12 - Dropped support for Postgres 12
## 0.7.4 (2024-08-05) ## 0.7.4 (2024-08-05)

View File

@@ -2,7 +2,7 @@
"name": "vector", "name": "vector",
"abstract": "Open-source vector similarity search for Postgres", "abstract": "Open-source vector similarity search for Postgres",
"description": "Supports L2 distance, inner product, and cosine distance", "description": "Supports L2 distance, inner product, and cosine distance",
"version": "0.7.4", "version": "0.8.0",
"maintainer": [ "maintainer": [
"Andrew Kane <andrew@ankane.org>" "Andrew Kane <andrew@ankane.org>"
], ],
@@ -12,7 +12,7 @@
"prereqs": { "prereqs": {
"runtime": { "runtime": {
"requires": { "requires": {
"PostgreSQL": "12.0.0" "PostgreSQL": "13.0.0"
} }
} }
}, },
@@ -20,7 +20,7 @@
"vector": { "vector": {
"file": "sql/vector.sql", "file": "sql/vector.sql",
"docfile": "README.md", "docfile": "README.md",
"version": "0.7.4", "version": "0.8.0",
"abstract": "Open-source vector similarity search for Postgres" "abstract": "Open-source vector similarity search for Postgres"
} }
}, },

View File

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

View File

@@ -1,5 +1,5 @@
EXTENSION = vector EXTENSION = vector
EXTVERSION = 0.7.4 EXTVERSION = 0.8.0
DATA_built = sql\$(EXTENSION)--$(EXTVERSION).sql DATA_built = sql\$(EXTENSION)--$(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 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

116
README.md
View File

@@ -17,11 +17,11 @@ Plus [ACID](https://en.wikipedia.org/wiki/ACID) compliance, point-in-time recove
### Linux and Mac ### Linux and Mac
Compile and install the extension (supports Postgres 12+) Compile and install the extension (supports Postgres 13+)
```sh ```sh
cd /tmp cd /tmp
git clone --branch v0.7.4 https://github.com/pgvector/pgvector.git git clone --branch v0.8.0 https://github.com/pgvector/pgvector.git
cd pgvector cd pgvector
make make
make install # may need sudo make install # may need sudo
@@ -46,7 +46,7 @@ Then use `nmake` to build:
```cmd ```cmd
set "PGROOT=C:\Program Files\PostgreSQL\16" set "PGROOT=C:\Program Files\PostgreSQL\16"
cd %TEMP% cd %TEMP%
git clone --branch v0.7.4 https://github.com/pgvector/pgvector.git git clone --branch v0.8.0 https://github.com/pgvector/pgvector.git
cd pgvector cd pgvector
nmake /F Makefile.win nmake /F Makefile.win
nmake /F Makefile.win install nmake /F Makefile.win install
@@ -324,7 +324,7 @@ For a large number of workers, you may also need to increase `max_parallel_worke
### Indexing Progress ### Indexing Progress
Check [indexing progress](https://www.postgresql.org/docs/current/progress-reporting.html#CREATE-INDEX-PROGRESS-REPORTING) with Postgres 12+ Check [indexing progress](https://www.postgresql.org/docs/current/progress-reporting.html#CREATE-INDEX-PROGRESS-REPORTING)
```sql ```sql
SELECT phase, round(100.0 * blocks_done / nullif(blocks_total, 0), 1) AS "%" FROM pg_stat_progress_create_index; 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 ### Indexing Progress
Check [indexing progress](https://www.postgresql.org/docs/current/progress-reporting.html#CREATE-INDEX-PROGRESS-REPORTING) with Postgres 12+ Check [indexing progress](https://www.postgresql.org/docs/current/progress-reporting.html#CREATE-INDEX-PROGRESS-REPORTING)
```sql ```sql
SELECT phase, round(100.0 * tuples_done / nullif(tuples_total, 0), 1) AS "%" FROM pg_stat_progress_create_index; SELECT phase, round(100.0 * tuples_done / nullif(tuples_total, 0), 1) AS "%" FROM pg_stat_progress_create_index;
@@ -427,30 +427,126 @@ Note: `%` is only populated during the `loading tuples` phase
## Filtering ## 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 ```sql
SELECT * FROM items WHERE category_id = 123 ORDER BY embedding <-> '[3,1,2]' LIMIT 5; SELECT * FROM items WHERE category_id = 123 ORDER BY embedding <-> '[3,1,2]' LIMIT 5;
``` ```
Create an index on one [or more](https://www.postgresql.org/docs/current/indexes-multicolumn.html) of the `WHERE` columns for exact search 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.
```sql ```sql
CREATE INDEX ON items (category_id); CREATE INDEX ON items (category_id);
``` ```
Or a [partial index](https://www.postgresql.org/docs/current/indexes-partial.html) on the vector column for approximate search For multiple columns, consider a [multicolumn index](https://www.postgresql.org/docs/current/indexes-multicolumn.html).
```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 ```sql
CREATE INDEX ON items USING hnsw (embedding vector_l2_ops) WHERE (category_id = 123); CREATE INDEX ON items USING hnsw (embedding vector_l2_ops) WHERE (category_id = 123);
``` ```
Use [partitioning](https://www.postgresql.org/docs/current/ddl-partitioning.html) for approximate search on many different values of the `WHERE` columns If filtering by many different values, consider [partitioning](https://www.postgresql.org/docs/current/ddl-partitioning.html).
```sql ```sql
CREATE TABLE items (embedding vector(3), category_id int) PARTITION BY LIST(category_id); CREATE TABLE items (embedding vector(3), category_id int) PARTITION BY LIST(category_id);
``` ```
## Iterative Index Scans
*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`).
Iterative scans can use strict or relaxed ordering.
Strict ensures results are in the exact order by distance
```sql
SET hnsw.iterative_scan = strict_order;
```
Relaxed allows results to be slightly out of order by distance, but provides better recall
```sql
SET hnsw.iterative_scan = relaxed_order;
# or
SET ivfflat.iterative_scan = relaxed_order;
```
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
```sql
WITH relaxed_results AS MATERIALIZED (
SELECT id, embedding <-> '[1,2,3]' AS distance FROM items WHERE category_id = 123 ORDER BY distance LIMIT 5
) SELECT * FROM relaxed_results 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)
```sql
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)
```sql
SET hnsw.max_scan_tuples = 20000;
```
Note: This is approximate and does not affect the initial scan
Specify the max amount of memory to use, as a multiple of `work_mem` (1 by default)
```sql
SET hnsw.scan_mem_multiplier = 2;
```
Note: Try increasing this if increasing `hnsw.max_scan_tuples` does not improve recall
#### IVFFlat
Specify the max number of probes
```sql
SET ivfflat.max_probes = 100;
```
Note: If this is lower than `ivfflat.probes`, `ivfflat.probes` will be used
## Half-Precision Vectors ## Half-Precision Vectors
*Added in 0.7.0* *Added in 0.7.0*
@@ -1057,7 +1153,7 @@ This adds pgvector to the [Postgres image](https://hub.docker.com/_/postgres) (r
You can also build the image manually: You can also build the image manually:
```sh ```sh
git clone --branch v0.7.4 https://github.com/pgvector/pgvector.git git clone --branch v0.8.0 https://github.com/pgvector/pgvector.git
cd pgvector cd pgvector
docker build --pull --build-arg PG_MAJOR=17 -t myuser/pgvector . docker build --pull --build-arg PG_MAJOR=17 -t myuser/pgvector .
``` ```

View File

@@ -18,7 +18,17 @@
#define MarkGUCPrefixReserved(x) EmitWarningsOnPlaceholders(x) #define MarkGUCPrefixReserved(x) EmitWarningsOnPlaceholders(x)
#endif #endif
static const struct config_enum_entry hnsw_iterative_scan_options[] = {
{"off", HNSW_ITERATIVE_SCAN_OFF, false},
{"relaxed_order", HNSW_ITERATIVE_SCAN_RELAXED, false},
{"strict_order", HNSW_ITERATIVE_SCAN_STRICT, false},
{NULL, 0, false}
};
int hnsw_ef_search; int hnsw_ef_search;
int hnsw_iterative_scan;
int hnsw_max_scan_tuples;
double hnsw_scan_mem_multiplier;
int hnsw_lock_tranche_id; int hnsw_lock_tranche_id;
static relopt_kind hnsw_relopt_kind; static relopt_kind hnsw_relopt_kind;
@@ -69,6 +79,20 @@ HnswInit(void)
"Valid range is 1..1000.", &hnsw_ef_search, "Valid range is 1..1000.", &hnsw_ef_search,
HNSW_DEFAULT_EF_SEARCH, HNSW_MIN_EF_SEARCH, HNSW_MAX_EF_SEARCH, PGC_USERSET, 0, NULL, NULL, NULL); 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",
NULL, &hnsw_iterative_scan,
HNSW_ITERATIVE_SCAN_OFF, hnsw_iterative_scan_options, PGC_USERSET, 0, NULL, NULL, NULL);
/* This is approximate and does not affect the initial scan */
DefineCustomIntVariable("hnsw.max_scan_tuples", "Sets the max number of tuples to visit for iterative scans",
NULL, &hnsw_max_scan_tuples,
20000, 1, INT_MAX, 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"); MarkGUCPrefixReserved("hnsw");
} }
@@ -113,6 +137,10 @@ hnswcostestimate(PlannerInfo *root, IndexPath *path, double loop_count,
*indexSelectivity = 0; *indexSelectivity = 0;
*indexCorrelation = 0; *indexCorrelation = 0;
*indexPages = 0; *indexPages = 0;
#if PG_VERSION_NUM >= 180000
/* See "On disable_cost" thread on pgsql-hackers */
path->path.disabled_nodes = 2;
#endif
return; return;
} }

View File

@@ -88,6 +88,9 @@
/* Ensure fits on page and in uint8 */ /* Ensure fits on page and in uint8 */
#define HnswGetMaxLevel(m) Min(((BLCKSZ - MAXALIGN(SizeOfPageHeaderData) - MAXALIGN(sizeof(HnswPageOpaqueData)) - offsetof(HnswNeighborTupleData, indextids) - sizeof(ItemIdData)) / (sizeof(ItemPointerData)) / (m)) - 2, 255) #define HnswGetMaxLevel(m) Min(((BLCKSZ - MAXALIGN(SizeOfPageHeaderData) - MAXALIGN(sizeof(HnswPageOpaqueData)) - offsetof(HnswNeighborTupleData, indextids) - sizeof(ItemIdData)) / (sizeof(ItemPointerData)) / (m)) - 2, 255)
#define HnswGetSearchCandidate(membername, ptr) pairingheap_container(HnswSearchCandidate, membername, ptr)
#define HnswGetSearchCandidateConst(membername, ptr) pairingheap_const_container(HnswSearchCandidate, membername, ptr)
#define HnswGetValue(base, element) PointerGetDatum(HnswPtrAccess(base, (element)->value)) #define HnswGetValue(base, element) PointerGetDatum(HnswPtrAccess(base, (element)->value))
#if PG_VERSION_NUM < 140005 #if PG_VERSION_NUM < 140005
@@ -106,8 +109,18 @@
/* Variables */ /* Variables */
extern int hnsw_ef_search; extern int hnsw_ef_search;
extern int hnsw_iterative_scan;
extern int hnsw_max_scan_tuples;
extern double hnsw_scan_mem_multiplier;
extern int hnsw_lock_tranche_id; extern int hnsw_lock_tranche_id;
typedef enum HnswIterativeScanMode
{
HNSW_ITERATIVE_SCAN_OFF,
HNSW_ITERATIVE_SCAN_RELAXED,
HNSW_ITERATIVE_SCAN_STRICT
} HnswIterativeScanMode;
typedef struct HnswElementData HnswElementData; typedef struct HnswElementData HnswElementData;
typedef struct HnswNeighborArray HnswNeighborArray; typedef struct HnswNeighborArray HnswNeighborArray;
@@ -129,6 +142,7 @@ struct HnswElementData
uint8 heaptidsLength; uint8 heaptidsLength;
uint8 level; uint8 level;
uint8 deleted; uint8 deleted;
uint8 version;
uint32 hash; uint32 hash;
HnswNeighborsPtr neighbors; HnswNeighborsPtr neighbors;
BlockNumber blkno; BlockNumber blkno;
@@ -237,6 +251,18 @@ typedef struct HnswTypeInfo
void (*checkValue) (Pointer v); void (*checkValue) (Pointer v);
} HnswTypeInfo; } HnswTypeInfo;
typedef struct HnswSupport
{
FmgrInfo *procinfo;
FmgrInfo *normprocinfo;
Oid collation;
} HnswSupport;
typedef struct HnswQuery
{
Datum value;
} HnswQuery;
typedef struct HnswBuildState typedef struct HnswBuildState
{ {
/* Info */ /* Info */
@@ -256,9 +282,7 @@ typedef struct HnswBuildState
double reltuples; double reltuples;
/* Support functions */ /* Support functions */
FmgrInfo *procinfo; HnswSupport support;
FmgrInfo *normprocinfo;
Oid collation;
/* Variables */ /* Variables */
HnswGraph graphData; HnswGraph graphData;
@@ -306,10 +330,10 @@ typedef struct HnswElementTupleData
uint8 type; uint8 type;
uint8 level; uint8 level;
uint8 deleted; uint8 deleted;
uint8 unused; uint8 version;
ItemPointerData heaptids[HNSW_HEAPTIDS]; ItemPointerData heaptids[HNSW_HEAPTIDS];
ItemPointerData neighbortid; ItemPointerData neighbortid;
uint16 unused2; uint16 unused;
Vector data; Vector data;
} HnswElementTupleData; } HnswElementTupleData;
@@ -318,24 +342,42 @@ typedef HnswElementTupleData * HnswElementTuple;
typedef struct HnswNeighborTupleData typedef struct HnswNeighborTupleData
{ {
uint8 type; uint8 type;
uint8 unused; uint8 version;
uint16 count; uint16 count;
ItemPointerData indextids[FLEXIBLE_ARRAY_MEMBER]; ItemPointerData indextids[FLEXIBLE_ARRAY_MEMBER];
} HnswNeighborTupleData; } HnswNeighborTupleData;
typedef HnswNeighborTupleData * HnswNeighborTuple; typedef HnswNeighborTupleData * HnswNeighborTuple;
typedef union
{
struct pointerhash_hash *pointers;
struct offsethash_hash *offsets;
struct tidhash_hash *tids;
} visited_hash;
typedef union
{
HnswElement element;
ItemPointerData indextid;
} HnswUnvisited;
typedef struct HnswScanOpaqueData typedef struct HnswScanOpaqueData
{ {
const HnswTypeInfo *typeInfo; const HnswTypeInfo *typeInfo;
bool first; bool first;
List *w; List *w;
visited_hash v;
pairingheap *discarded;
HnswQuery q;
int m;
int64 tuples;
double previousDistance;
Size maxMemory;
MemoryContext tmpCtx; MemoryContext tmpCtx;
/* Support functions */ /* Support functions */
FmgrInfo *procinfo; HnswSupport support;
FmgrInfo *normprocinfo;
Oid collation;
} HnswScanOpaqueData; } HnswScanOpaqueData;
typedef HnswScanOpaqueData * HnswScanOpaque; typedef HnswScanOpaqueData * HnswScanOpaque;
@@ -353,8 +395,7 @@ typedef struct HnswVacuumState
int efConstruction; int efConstruction;
/* Support functions */ /* Support functions */
FmgrInfo *procinfo; HnswSupport support;
Oid collation;
/* Variables */ /* Variables */
struct tidhash_hash *deleted; struct tidhash_hash *deleted;
@@ -370,30 +411,32 @@ typedef struct HnswVacuumState
int HnswGetM(Relation index); int HnswGetM(Relation index);
int HnswGetEfConstruction(Relation index); int HnswGetEfConstruction(Relation index);
FmgrInfo *HnswOptionalProcInfo(Relation index, uint16 procnum); FmgrInfo *HnswOptionalProcInfo(Relation index, uint16 procnum);
void HnswInitSupport(HnswSupport * support, Relation index);
Datum HnswNormValue(const HnswTypeInfo * typeInfo, Oid collation, Datum value); Datum HnswNormValue(const HnswTypeInfo * typeInfo, Oid collation, Datum value);
bool HnswCheckNorm(FmgrInfo *procinfo, Oid collation, Datum value); bool HnswCheckNorm(HnswSupport * support, Datum value);
Buffer HnswNewBuffer(Relation index, ForkNumber forkNum); Buffer HnswNewBuffer(Relation index, ForkNumber forkNum);
void HnswInitPage(Buffer buf, Page page); void HnswInitPage(Buffer buf, Page page);
void HnswInit(void); void HnswInit(void);
List *HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool inserting, HnswElement skipElement); List *HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation index, HnswSupport * support, int m, bool inserting, HnswElement skipElement, visited_hash * v, pairingheap **discarded, bool initVisited, int64 *tuples);
HnswElement HnswGetEntryPoint(Relation index); HnswElement HnswGetEntryPoint(Relation index);
void HnswGetMetaPageInfo(Relation index, int *m, HnswElement * entryPoint); void HnswGetMetaPageInfo(Relation index, int *m, HnswElement * entryPoint);
void *HnswAlloc(HnswAllocator * allocator, Size size); void *HnswAlloc(HnswAllocator * allocator, Size size);
HnswElement HnswInitElement(char *base, ItemPointer tid, int m, double ml, int maxLevel, HnswAllocator * alloc); HnswElement HnswInitElement(char *base, ItemPointer tid, int m, double ml, int maxLevel, HnswAllocator * alloc);
HnswElement HnswInitElementFromBlock(BlockNumber blkno, OffsetNumber offno); HnswElement HnswInitElementFromBlock(BlockNumber blkno, OffsetNumber offno);
void HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, FmgrInfo *procinfo, Oid collation, int m, int efConstruction, bool existing); void HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, HnswSupport * support, int m, int efConstruction, bool existing);
HnswSearchCandidate *HnswEntryCandidate(char *base, HnswElement em, Datum q, Relation rel, FmgrInfo *procinfo, Oid collation, bool loadVec); HnswSearchCandidate *HnswEntryCandidate(char *base, HnswElement em, HnswQuery * q, Relation rel, HnswSupport * support, bool loadVec);
void HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, BlockNumber insertPage, ForkNumber forkNum, bool building); void HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, BlockNumber insertPage, ForkNumber forkNum, bool building);
void HnswSetNeighborTuple(char *base, HnswNeighborTuple ntup, HnswElement e, int m); void HnswSetNeighborTuple(char *base, HnswNeighborTuple ntup, HnswElement e, int m);
void HnswAddHeapTid(HnswElement element, ItemPointer heaptid); void HnswAddHeapTid(HnswElement element, ItemPointer heaptid);
HnswNeighborArray *HnswInitNeighborArray(int lm, HnswAllocator * allocator); HnswNeighborArray *HnswInitNeighborArray(int lm, HnswAllocator * allocator);
void HnswInitNeighbors(char *base, HnswElement element, int m, HnswAllocator * alloc); void HnswInitNeighbors(char *base, HnswElement element, int m, HnswAllocator * alloc);
bool HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull, ItemPointer heap_tid, bool building); bool HnswInsertTupleOnDisk(Relation index, HnswSupport * support, Datum value, ItemPointer heaptid, bool building);
void HnswUpdateNeighborsOnDisk(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement e, int m, bool checkExisting, bool building); void HnswUpdateNeighborsOnDisk(Relation index, HnswSupport * support, HnswElement e, int m, bool checkExisting, bool building);
void HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHeaptids, bool loadVec); void HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHeaptids, bool loadVec);
void HnswLoadElement(HnswElement element, double *distance, Datum *q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec, double *maxDistance); void HnswLoadElement(HnswElement element, double *distance, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec, double *maxDistance);
bool HnswFormIndexValue(Datum *out, Datum *values, bool *isnull, const HnswTypeInfo * typeInfo, HnswSupport * support);
void HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element); void HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element);
void HnswUpdateConnection(char *base, HnswNeighborArray * neighbors, HnswElement newElement, float distance, int lm, int *updateIdx, Relation index, FmgrInfo *procinfo, Oid collation); void HnswUpdateConnection(char *base, HnswNeighborArray * neighbors, HnswElement newElement, float distance, int lm, int *updateIdx, Relation index, HnswSupport * support);
bool HnswLoadNeighborTids(HnswElement element, ItemPointerData *indextids, Relation index, int m, int lm, int lc); bool HnswLoadNeighborTids(HnswElement element, ItemPointerData *indextids, Relation index, int m, int lm, int lc);
void HnswInitLockTranche(void); void HnswInitLockTranche(void);
const HnswTypeInfo *HnswGetTypeInfo(Relation index); const HnswTypeInfo *HnswGetTypeInfo(Relation index);

View File

@@ -366,7 +366,7 @@ AddElementInMemory(char *base, HnswGraph * graph, HnswElement element)
* Update neighbors * Update neighbors
*/ */
static void static void
UpdateNeighborsInMemory(char *base, FmgrInfo *procinfo, Oid collation, HnswElement e, int m) UpdateNeighborsInMemory(char *base, HnswSupport * support, HnswElement e, int m)
{ {
for (int lc = e->level; lc >= 0; lc--) for (int lc = e->level; lc >= 0; lc--)
{ {
@@ -388,7 +388,7 @@ UpdateNeighborsInMemory(char *base, FmgrInfo *procinfo, Oid collation, HnswEleme
Assert(neighborElement); Assert(neighborElement);
LWLockAcquire(&neighborElement->lock, LW_EXCLUSIVE); LWLockAcquire(&neighborElement->lock, LW_EXCLUSIVE);
HnswUpdateConnection(base, HnswGetNeighbors(base, neighborElement, lc), e, hc->distance, lm, NULL, NULL, procinfo, collation); HnswUpdateConnection(base, HnswGetNeighbors(base, neighborElement, lc), e, hc->distance, lm, NULL, NULL, support);
LWLockRelease(&neighborElement->lock); LWLockRelease(&neighborElement->lock);
} }
} }
@@ -398,7 +398,7 @@ UpdateNeighborsInMemory(char *base, FmgrInfo *procinfo, Oid collation, HnswEleme
* Update graph in memory * Update graph in memory
*/ */
static void static void
UpdateGraphInMemory(FmgrInfo *procinfo, Oid collation, HnswElement element, int m, int efConstruction, HnswElement entryPoint, HnswBuildState * buildstate) UpdateGraphInMemory(HnswSupport * support, HnswElement element, int m, int efConstruction, HnswElement entryPoint, HnswBuildState * buildstate)
{ {
HnswGraph *graph = buildstate->graph; HnswGraph *graph = buildstate->graph;
char *base = buildstate->hnswarea; char *base = buildstate->hnswarea;
@@ -411,7 +411,7 @@ UpdateGraphInMemory(FmgrInfo *procinfo, Oid collation, HnswElement element, int
AddElementInMemory(base, graph, element); AddElementInMemory(base, graph, element);
/* Update neighbors */ /* Update neighbors */
UpdateNeighborsInMemory(base, procinfo, collation, element, m); UpdateNeighborsInMemory(base, support, element, m);
/* Update entry point if needed (already have lock) */ /* Update entry point if needed (already have lock) */
if (entryPoint == NULL || element->level > entryPoint->level) if (entryPoint == NULL || element->level > entryPoint->level)
@@ -424,9 +424,8 @@ UpdateGraphInMemory(FmgrInfo *procinfo, Oid collation, HnswElement element, int
static void static void
InsertTupleInMemory(HnswBuildState * buildstate, HnswElement element) InsertTupleInMemory(HnswBuildState * buildstate, HnswElement element)
{ {
FmgrInfo *procinfo = buildstate->procinfo;
Oid collation = buildstate->collation;
HnswGraph *graph = buildstate->graph; HnswGraph *graph = buildstate->graph;
HnswSupport *support = &buildstate->support;
HnswElement entryPoint; HnswElement entryPoint;
LWLock *entryLock = &graph->entryLock; LWLock *entryLock = &graph->entryLock;
LWLock *entryWaitLock = &graph->entryWaitLock; LWLock *entryWaitLock = &graph->entryWaitLock;
@@ -458,10 +457,10 @@ InsertTupleInMemory(HnswBuildState * buildstate, HnswElement element)
} }
/* Find neighbors for element */ /* Find neighbors for element */
HnswFindElementNeighbors(base, element, entryPoint, NULL, procinfo, collation, m, efConstruction, false); HnswFindElementNeighbors(base, element, entryPoint, NULL, support, m, efConstruction, false);
/* Update graph in memory */ /* Update graph in memory */
UpdateGraphInMemory(procinfo, collation, element, m, efConstruction, entryPoint, buildstate); UpdateGraphInMemory(support, element, m, efConstruction, entryPoint, buildstate);
/* Release entry lock */ /* Release entry lock */
LWLockRelease(entryLock); LWLockRelease(entryLock);
@@ -473,30 +472,19 @@ InsertTupleInMemory(HnswBuildState * buildstate, HnswElement element)
static bool static bool
InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, HnswBuildState * buildstate) InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, HnswBuildState * buildstate)
{ {
const HnswTypeInfo *typeInfo = buildstate->typeInfo;
HnswGraph *graph = buildstate->graph; HnswGraph *graph = buildstate->graph;
HnswElement element; HnswElement element;
HnswAllocator *allocator = &buildstate->allocator; HnswAllocator *allocator = &buildstate->allocator;
HnswSupport *support = &buildstate->support;
Size valueSize; Size valueSize;
Pointer valuePtr; Pointer valuePtr;
LWLock *flushLock = &graph->flushLock; LWLock *flushLock = &graph->flushLock;
char *base = buildstate->hnswarea; char *base = buildstate->hnswarea;
Datum value;
/* Detoast once for all calls */ /* Form index value */
Datum value = PointerGetDatum(PG_DETOAST_DATUM(values[0])); if (!HnswFormIndexValue(&value, values, isnull, buildstate->typeInfo, support))
return false;
/* Check value */
if (typeInfo->checkValue != NULL)
typeInfo->checkValue(DatumGetPointer(value));
/* Normalize if needed */
if (buildstate->normprocinfo != NULL)
{
if (!HnswCheckNorm(buildstate->normprocinfo, buildstate->collation, value))
return false;
value = HnswNormValue(typeInfo, buildstate->collation, value);
}
/* Get datum size */ /* Get datum size */
valueSize = VARSIZE_ANY(DatumGetPointer(value)); valueSize = VARSIZE_ANY(DatumGetPointer(value));
@@ -509,7 +497,7 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
{ {
LWLockRelease(flushLock); LWLockRelease(flushLock);
return HnswInsertTupleOnDisk(index, value, values, isnull, heaptid, true); return HnswInsertTupleOnDisk(index, support, value, heaptid, true);
} }
/* /*
@@ -541,7 +529,7 @@ InsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid, Hn
LWLockRelease(flushLock); LWLockRelease(flushLock);
return HnswInsertTupleOnDisk(index, value, values, isnull, heaptid, true); return HnswInsertTupleOnDisk(index, support, value, heaptid, true);
} }
/* Ok, we can proceed to allocate the element */ /* Ok, we can proceed to allocate the element */
@@ -704,9 +692,7 @@ InitBuildState(HnswBuildState * buildstate, Relation heap, Relation index, Index
buildstate->indtuples = 0; buildstate->indtuples = 0;
/* Get support functions */ /* Get support functions */
buildstate->procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC); HnswInitSupport(&buildstate->support, index);
buildstate->normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
buildstate->collation = index->rd_indcollation[0];
InitGraph(&buildstate->graphData, NULL, (Size) maintenance_work_mem * 1024L); InitGraph(&buildstate->graphData, NULL, (Size) maintenance_work_mem * 1024L);
buildstate->graph = &buildstate->graphData; buildstate->graph = &buildstate->graphData;

View File

@@ -36,7 +36,7 @@ GetInsertPage(Relation index)
* Check for a free offset * Check for a free offset
*/ */
static bool static bool
HnswFreeOffset(Relation index, Buffer buf, Page page, HnswElement element, Size etupSize, Size ntupSize, Buffer *nbuf, Page *npage, OffsetNumber *freeOffno, OffsetNumber *freeNeighborOffno, BlockNumber *newInsertPage) HnswFreeOffset(Relation index, Buffer buf, Page page, HnswElement element, Size etupSize, Size ntupSize, Buffer *nbuf, Page *npage, OffsetNumber *freeOffno, OffsetNumber *freeNeighborOffno, BlockNumber *newInsertPage, uint8 *tupleVersion)
{ {
OffsetNumber offno; OffsetNumber offno;
OffsetNumber maxoffno = PageGetMaxOffsetNumber(page); OffsetNumber maxoffno = PageGetMaxOffsetNumber(page);
@@ -98,6 +98,7 @@ HnswFreeOffset(Relation index, Buffer buf, Page page, HnswElement element, Size
{ {
*freeOffno = offno; *freeOffno = offno;
*freeNeighborOffno = neighborOffno; *freeNeighborOffno = neighborOffno;
*tupleVersion = etup->version;
return true; return true;
} }
else if (*nbuf != buf) else if (*nbuf != buf)
@@ -153,6 +154,7 @@ AddElementOnDisk(Relation index, HnswElement e, int m, BlockNumber insertPage, B
OffsetNumber freeOffno = InvalidOffsetNumber; OffsetNumber freeOffno = InvalidOffsetNumber;
OffsetNumber freeNeighborOffno = InvalidOffsetNumber; OffsetNumber freeNeighborOffno = InvalidOffsetNumber;
BlockNumber newInsertPage = InvalidBlockNumber; BlockNumber newInsertPage = InvalidBlockNumber;
uint8 tupleVersion;
char *base = NULL; char *base = NULL;
/* Calculate sizes */ /* Calculate sizes */
@@ -202,7 +204,7 @@ AddElementOnDisk(Relation index, HnswElement e, int m, BlockNumber insertPage, B
} }
/* Next, try space from a deleted element */ /* Next, try space from a deleted element */
if (HnswFreeOffset(index, buf, page, e, etupSize, ntupSize, &nbuf, &npage, &freeOffno, &freeNeighborOffno, &newInsertPage)) if (HnswFreeOffset(index, buf, page, e, etupSize, ntupSize, &nbuf, &npage, &freeOffno, &freeNeighborOffno, &newInsertPage, &tupleVersion))
{ {
if (nbuf != buf) if (nbuf != buf)
{ {
@@ -212,6 +214,10 @@ AddElementOnDisk(Relation index, HnswElement e, int m, BlockNumber insertPage, B
npage = GenericXLogRegisterBuffer(state, nbuf, 0); npage = GenericXLogRegisterBuffer(state, nbuf, 0);
} }
/* Set tuple version */
etup->version = tupleVersion;
ntup->version = tupleVersion;
break; break;
} }
@@ -368,7 +374,7 @@ HnswLoadNeighbors(HnswElement element, Relation index, int m, int lm, int lc)
* Load elements for insert * Load elements for insert
*/ */
static void static void
LoadElementsForInsert(HnswNeighborArray * neighbors, Datum q, int *idx, Relation index, FmgrInfo *procinfo, Oid collation) LoadElementsForInsert(HnswNeighborArray * neighbors, HnswQuery * q, int *idx, Relation index, HnswSupport * support)
{ {
char *base = NULL; char *base = NULL;
@@ -378,7 +384,7 @@ LoadElementsForInsert(HnswNeighborArray * neighbors, Datum q, int *idx, Relation
HnswElement element = HnswPtrAccess(base, hc->element); HnswElement element = HnswPtrAccess(base, hc->element);
double distance; double distance;
HnswLoadElement(element, &distance, &q, index, procinfo, collation, true, NULL); HnswLoadElement(element, &distance, q, index, support, true, NULL);
hc->distance = distance; hc->distance = distance;
/* Prune element if being deleted */ /* Prune element if being deleted */
@@ -394,7 +400,7 @@ LoadElementsForInsert(HnswNeighborArray * neighbors, Datum q, int *idx, Relation
* Get update index * Get update index
*/ */
static int static int
GetUpdateIndex(HnswElement element, HnswElement newElement, float distance, int m, int lm, int lc, Relation index, FmgrInfo *procinfo, Oid collation, MemoryContext updateCtx) GetUpdateIndex(HnswElement element, HnswElement newElement, float distance, int m, int lm, int lc, Relation index, HnswSupport * support, MemoryContext updateCtx)
{ {
char *base = NULL; char *base = NULL;
int idx = -1; int idx = -1;
@@ -419,12 +425,14 @@ GetUpdateIndex(HnswElement element, HnswElement newElement, float distance, int
idx = -2; idx = -2;
else else
{ {
Datum q = HnswGetValue(base, element); HnswQuery q;
LoadElementsForInsert(neighbors, q, &idx, index, procinfo, collation); q.value = HnswGetValue(base, element);
LoadElementsForInsert(neighbors, &q, &idx, index, support);
if (idx == -1) if (idx == -1)
HnswUpdateConnection(base, neighbors, newElement, distance, lm, &idx, index, procinfo, collation); HnswUpdateConnection(base, neighbors, newElement, distance, lm, &idx, index, support);
} }
MemoryContextSwitchTo(oldCtx); MemoryContextSwitchTo(oldCtx);
@@ -529,7 +537,7 @@ UpdateNeighborOnDisk(HnswElement element, HnswElement newElement, int idx, int m
* Update neighbors * Update neighbors
*/ */
void void
HnswUpdateNeighborsOnDisk(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement e, int m, bool checkExisting, bool building) HnswUpdateNeighborsOnDisk(Relation index, HnswSupport * support, HnswElement e, int m, bool checkExisting, bool building)
{ {
char *base = NULL; char *base = NULL;
@@ -552,7 +560,7 @@ HnswUpdateNeighborsOnDisk(Relation index, FmgrInfo *procinfo, Oid collation, Hns
HnswElement neighborElement = HnswPtrAccess(base, hc->element); HnswElement neighborElement = HnswPtrAccess(base, hc->element);
int idx; int idx;
idx = GetUpdateIndex(neighborElement, e, hc->distance, m, lm, lc, index, procinfo, collation, updateCtx); idx = GetUpdateIndex(neighborElement, e, hc->distance, m, lm, lc, index, support, updateCtx);
/* New element was not selected as a neighbor */ /* New element was not selected as a neighbor */
if (idx == -1) if (idx == -1)
@@ -652,7 +660,7 @@ FindDuplicateOnDisk(Relation index, HnswElement element, bool building)
* Update graph on disk * Update graph on disk
*/ */
static void static void
UpdateGraphOnDisk(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement element, int m, int efConstruction, HnswElement entryPoint, bool building) UpdateGraphOnDisk(Relation index, HnswSupport * support, HnswElement element, int m, int efConstruction, HnswElement entryPoint, bool building)
{ {
BlockNumber newInsertPage = InvalidBlockNumber; BlockNumber newInsertPage = InvalidBlockNumber;
@@ -668,7 +676,7 @@ UpdateGraphOnDisk(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement
HnswUpdateMetaPage(index, 0, NULL, newInsertPage, MAIN_FORKNUM, building); HnswUpdateMetaPage(index, 0, NULL, newInsertPage, MAIN_FORKNUM, building);
/* Update neighbors */ /* Update neighbors */
HnswUpdateNeighborsOnDisk(index, procinfo, collation, element, m, false, building); HnswUpdateNeighborsOnDisk(index, support, element, m, false, building);
/* Update entry point if needed */ /* Update entry point if needed */
if (entryPoint == NULL || element->level > entryPoint->level) if (entryPoint == NULL || element->level > entryPoint->level)
@@ -679,14 +687,12 @@ UpdateGraphOnDisk(Relation index, FmgrInfo *procinfo, Oid collation, HnswElement
* Insert a tuple into the index * Insert a tuple into the index
*/ */
bool bool
HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull, ItemPointer heap_tid, bool building) HnswInsertTupleOnDisk(Relation index, HnswSupport * support, Datum value, ItemPointer heaptid, bool building)
{ {
HnswElement entryPoint; HnswElement entryPoint;
HnswElement element; HnswElement element;
int m; int m;
int efConstruction = HnswGetEfConstruction(index); int efConstruction = HnswGetEfConstruction(index);
FmgrInfo *procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
Oid collation = index->rd_indcollation[0];
LOCKMODE lockmode = ShareLock; LOCKMODE lockmode = ShareLock;
char *base = NULL; char *base = NULL;
@@ -701,7 +707,7 @@ HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull,
HnswGetMetaPageInfo(index, &m, &entryPoint); HnswGetMetaPageInfo(index, &m, &entryPoint);
/* Create an element */ /* Create an element */
element = HnswInitElement(base, heap_tid, m, HnswGetMl(m), HnswGetMaxLevel(m), NULL); element = HnswInitElement(base, heaptid, m, HnswGetMl(m), HnswGetMaxLevel(m), NULL);
HnswPtrStore(base, element->value, DatumGetPointer(value)); HnswPtrStore(base, element->value, DatumGetPointer(value));
/* Prevent concurrent inserts when likely updating entry point */ /* Prevent concurrent inserts when likely updating entry point */
@@ -719,10 +725,10 @@ HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull,
} }
/* Find neighbors for element */ /* Find neighbors for element */
HnswFindElementNeighbors(base, element, entryPoint, index, procinfo, collation, m, efConstruction, false); HnswFindElementNeighbors(base, element, entryPoint, index, support, m, efConstruction, false);
/* Update graph on disk */ /* Update graph on disk */
UpdateGraphOnDisk(index, procinfo, collation, element, m, efConstruction, entryPoint, building); UpdateGraphOnDisk(index, support, element, m, efConstruction, entryPoint, building);
/* Release lock */ /* Release lock */
UnlockPage(index, HNSW_UPDATE_LOCK, lockmode); UnlockPage(index, HNSW_UPDATE_LOCK, lockmode);
@@ -734,31 +740,19 @@ HnswInsertTupleOnDisk(Relation index, Datum value, Datum *values, bool *isnull,
* Insert a tuple into the index * Insert a tuple into the index
*/ */
static void static void
HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heap_tid) HnswInsertTuple(Relation index, Datum *values, bool *isnull, ItemPointer heaptid)
{ {
Datum value; Datum value;
const HnswTypeInfo *typeInfo = HnswGetTypeInfo(index); const HnswTypeInfo *typeInfo = HnswGetTypeInfo(index);
FmgrInfo *normprocinfo; HnswSupport support;
Oid collation = index->rd_indcollation[0];
/* Detoast once for all calls */ HnswInitSupport(&support, index);
value = PointerGetDatum(PG_DETOAST_DATUM(values[0]));
/* Check value */ /* Form index value */
if (typeInfo->checkValue != NULL) if (!HnswFormIndexValue(&value, values, isnull, typeInfo, &support))
typeInfo->checkValue(DatumGetPointer(value)); return;
/* Normalize if needed */ HnswInsertTupleOnDisk(index, &support, value, heaptid, false);
normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
if (normprocinfo != NULL)
{
if (!HnswCheckNorm(normprocinfo, collation, value))
return;
value = HnswNormValue(typeInfo, collation, value);
}
HnswInsertTupleOnDisk(index, value, values, isnull, heap_tid, false);
} }
/* /*

View File

@@ -5,39 +5,74 @@
#include "pgstat.h" #include "pgstat.h"
#include "storage/bufmgr.h" #include "storage/bufmgr.h"
#include "storage/lmgr.h" #include "storage/lmgr.h"
#include "utils/float.h"
#include "utils/memutils.h" #include "utils/memutils.h"
/* /*
* Algorithm 5 from paper * Algorithm 5 from paper
*/ */
static List * static List *
GetScanItems(IndexScanDesc scan, Datum q) GetScanItems(IndexScanDesc scan, Datum value)
{ {
HnswScanOpaque so = (HnswScanOpaque) scan->opaque; HnswScanOpaque so = (HnswScanOpaque) scan->opaque;
Relation index = scan->indexRelation; Relation index = scan->indexRelation;
FmgrInfo *procinfo = so->procinfo; HnswSupport *support = &so->support;
Oid collation = so->collation;
List *ep; List *ep;
List *w; List *w;
int m; int m;
HnswElement entryPoint; HnswElement entryPoint;
char *base = NULL; char *base = NULL;
HnswQuery *q = &so->q;
/* Get m and entry point */ /* Get m and entry point */
HnswGetMetaPageInfo(index, &m, &entryPoint); HnswGetMetaPageInfo(index, &m, &entryPoint);
q->value = value;
so->m = m;
if (entryPoint == NULL) if (entryPoint == NULL)
return NIL; return NIL;
ep = list_make1(HnswEntryCandidate(base, entryPoint, q, index, procinfo, collation, false)); ep = list_make1(HnswEntryCandidate(base, entryPoint, q, index, support, false));
for (int lc = entryPoint->level; lc >= 1; lc--) for (int lc = entryPoint->level; lc >= 1; lc--)
{ {
w = HnswSearchLayer(base, q, ep, 1, lc, index, procinfo, collation, m, false, NULL); w = HnswSearchLayer(base, q, ep, 1, lc, index, support, m, false, NULL, NULL, NULL, true, NULL);
ep = w; ep = w;
} }
return HnswSearchLayer(base, q, ep, hnsw_ef_search, 0, index, procinfo, collation, m, false, NULL); 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);
}
/*
* Resume scan at ground level with discarded candidates
*/
static List *
ResumeScanItems(IndexScanDesc scan)
{
HnswScanOpaque so = (HnswScanOpaque) scan->opaque;
Relation index = scan->indexRelation;
List *ep = NIL;
char *base = NULL;
int batch_size = hnsw_ef_search;
if (pairingheap_is_empty(so->discarded))
return NIL;
/* Get next batch of candidates */
for (int i = 0; i < batch_size; i++)
{
HnswSearchCandidate *sc;
if (pairingheap_is_empty(so->discarded))
break;
sc = HnswGetSearchCandidate(w_node, pairingheap_remove_first(so->discarded));
ep = lappend(ep, sc);
}
return HnswSearchLayer(base, &so->q, ep, batch_size, 0, index, &so->support, so->m, false, NULL, &so->v, &so->discarded, false, &so->tuples);
} }
/* /*
@@ -60,13 +95,24 @@ GetScanValue(IndexScanDesc scan)
Assert(!VARATT_IS_EXTENDED(DatumGetPointer(value))); Assert(!VARATT_IS_EXTENDED(DatumGetPointer(value)));
/* Normalize if needed */ /* Normalize if needed */
if (so->normprocinfo != NULL) if (so->support.normprocinfo != NULL)
value = HnswNormValue(so->typeInfo, so->collation, value); value = HnswNormValue(so->typeInfo, so->support.collation, value);
} }
return value; 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 * Prepare for an index scan
*/ */
@@ -75,20 +121,28 @@ hnswbeginscan(Relation index, int nkeys, int norderbys)
{ {
IndexScanDesc scan; IndexScanDesc scan;
HnswScanOpaque so; HnswScanOpaque so;
double maxMemory;
scan = RelationGetIndexScan(index, nkeys, norderbys); scan = RelationGetIndexScan(index, nkeys, norderbys);
so = (HnswScanOpaque) palloc(sizeof(HnswScanOpaqueData)); so = (HnswScanOpaque) palloc(sizeof(HnswScanOpaqueData));
so->typeInfo = HnswGetTypeInfo(index); so->typeInfo = HnswGetTypeInfo(index);
so->first = true;
so->tmpCtx = AllocSetContextCreate(CurrentMemoryContext,
"Hnsw scan temporary context",
ALLOCSET_DEFAULT_SIZES);
/* Set support functions */ /* Set support functions */
so->procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC); HnswInitSupport(&so->support, index);
so->normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
so->collation = index->rd_indcollation[0]; /*
* 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; scan->opaque = so;
@@ -104,6 +158,11 @@ hnswrescan(IndexScanDesc scan, ScanKey keys, int nkeys, ScanKey orderbys, int no
HnswScanOpaque so = (HnswScanOpaque) scan->opaque; HnswScanOpaque so = (HnswScanOpaque) scan->opaque;
so->first = true; 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); MemoryContextReset(so->tmpCtx);
if (keys && scan->numberOfKeys > 0) if (keys && scan->numberOfKeys > 0)
@@ -161,26 +220,89 @@ hnswgettuple(IndexScanDesc scan, ScanDirection dir)
so->first = false; so->first = false;
#if defined(HNSW_MEMORY) #if defined(HNSW_MEMORY)
elog(INFO, "memory: %zu KB", MemoryContextMemAllocated(so->tmpCtx, false) / 1024); ShowMemoryUsage(so);
#endif #endif
} }
while (list_length(so->w) > 0) for (;;)
{ {
char *base = NULL; char *base = NULL;
HnswSearchCandidate *hc = llast(so->w); HnswSearchCandidate *sc;
HnswElement element = HnswPtrAccess(base, hc->element); HnswElement element;
ItemPointer heaptid; ItemPointer heaptid;
if (list_length(so->w) == 0)
{
if (hnsw_iterative_scan == HNSW_ITERATIVE_SCAN_OFF)
break;
/* Empty index */
if (so->discarded == NULL)
break;
/* Reached max number of tuples or memory limit */
if (so->tuples >= hnsw_max_scan_tuples || MemoryContextMemAllocated(so->tmpCtx, false) > so->maxMemory)
{
if (pairingheap_is_empty(so->discarded))
break;
/* Return remaining tuples */
so->w = lappend(so->w, HnswGetSearchCandidate(w_node, pairingheap_remove_first(so->discarded)));
}
else
{
/*
* Locking ensures when neighbors are read, the elements they
* reference will not be deleted (and replaced) during the
* iteration.
*
* Elements loaded into memory on previous iterations may have
* been deleted (and replaced), so when reading neighbors, the
* element version must be checked.
*/
LockPage(scan->indexRelation, HNSW_SCAN_LOCK, ShareLock);
so->w = ResumeScanItems(scan);
UnlockPage(scan->indexRelation, HNSW_SCAN_LOCK, ShareLock);
#if defined(HNSW_MEMORY)
ShowMemoryUsage(so);
#endif
}
if (list_length(so->w) == 0)
break;
}
sc = llast(so->w);
element = HnswPtrAccess(base, sc->element);
/* Move to next element if no valid heap TIDs */ /* Move to next element if no valid heap TIDs */
if (element->heaptidsLength == 0) if (element->heaptidsLength == 0)
{ {
so->w = list_delete_last(so->w); so->w = list_delete_last(so->w);
/* Mark memory as free for next iteration */
if (hnsw_iterative_scan != HNSW_ITERATIVE_SCAN_OFF)
{
pfree(element);
pfree(sc);
}
continue; continue;
} }
heaptid = &element->heaptids[--element->heaptidsLength]; heaptid = &element->heaptids[--element->heaptidsLength];
if (hnsw_iterative_scan == HNSW_ITERATIVE_SCAN_STRICT)
{
if (sc->distance < so->previousDistance)
continue;
so->previousDistance = sc->distance;
}
MemoryContextSwitchTo(oldCtx); MemoryContextSwitchTo(oldCtx);
scan->xs_heaptid = *heaptid; scan->xs_heaptid = *heaptid;

View File

@@ -100,19 +100,6 @@ hash_offset(Size offset)
#define SH_DEFINE #define SH_DEFINE
#include "lib/simplehash.h" #include "lib/simplehash.h"
typedef union
{
pointerhash_hash *pointers;
offsethash_hash *offsets;
tidhash_hash *tids;
} visited_hash;
typedef union
{
HnswElement element;
ItemPointerData indextid;
} HnswUnvisited;
/* /*
* Get the max number of connections in an upper layer for each element in the index * Get the max number of connections in an upper layer for each element in the index
*/ */
@@ -153,6 +140,17 @@ HnswOptionalProcInfo(Relation index, uint16 procnum)
return index_getprocinfo(index, 1, procnum); return index_getprocinfo(index, 1, procnum);
} }
/*
* Init support functions
*/
void
HnswInitSupport(HnswSupport * support, Relation index)
{
support->procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
support->collation = index->rd_indcollation[0];
support->normprocinfo = HnswOptionalProcInfo(index, HNSW_NORM_PROC);
}
/* /*
* Normalize value * Normalize value
*/ */
@@ -166,9 +164,9 @@ HnswNormValue(const HnswTypeInfo * typeInfo, Oid collation, Datum value)
* Check if non-zero norm * Check if non-zero norm
*/ */
bool bool
HnswCheckNorm(FmgrInfo *procinfo, Oid collation, Datum value) HnswCheckNorm(HnswSupport * support, Datum value)
{ {
return DatumGetFloat8(FunctionCall1Coll(procinfo, collation, value)) > 0; return DatumGetFloat8(FunctionCall1Coll(support->normprocinfo, support->collation, value)) > 0;
} }
/* /*
@@ -253,6 +251,8 @@ HnswInitElement(char *base, ItemPointer heaptid, int m, double ml, int maxLevel,
element->level = level; element->level = level;
element->deleted = 0; element->deleted = 0;
/* Start at one to make it easier to find issues */
element->version = 1;
HnswInitNeighbors(base, element, m, allocator); HnswInitNeighbors(base, element, m, allocator);
@@ -394,6 +394,33 @@ HnswUpdateMetaPage(Relation index, int updateEntry, HnswElement entryPoint, Bloc
UnlockReleaseBuffer(buf); UnlockReleaseBuffer(buf);
} }
/*
* Form index value
*/
bool
HnswFormIndexValue(Datum *out, Datum *values, bool *isnull, const HnswTypeInfo * typeInfo, HnswSupport * support)
{
/* Detoast once for all calls */
Datum value = PointerGetDatum(PG_DETOAST_DATUM(values[0]));
/* Check value */
if (typeInfo->checkValue != NULL)
typeInfo->checkValue(DatumGetPointer(value));
/* Normalize if needed */
if (support->normprocinfo != NULL)
{
if (!HnswCheckNorm(support, value))
return false;
value = HnswNormValue(typeInfo, support->collation, value);
}
*out = value;
return true;
}
/* /*
* Set element tuple, except for neighbor info * Set element tuple, except for neighbor info
*/ */
@@ -405,6 +432,7 @@ HnswSetElementTuple(char *base, HnswElementTuple etup, HnswElement element)
etup->type = HNSW_ELEMENT_TUPLE_TYPE; etup->type = HNSW_ELEMENT_TUPLE_TYPE;
etup->level = element->level; etup->level = element->level;
etup->deleted = 0; etup->deleted = 0;
etup->version = element->version;
for (int i = 0; i < HNSW_HEAPTIDS; i++) for (int i = 0; i < HNSW_HEAPTIDS; i++)
{ {
if (i < element->heaptidsLength) if (i < element->heaptidsLength)
@@ -447,6 +475,7 @@ HnswSetNeighborTuple(char *base, HnswNeighborTuple ntup, HnswElement e, int m)
} }
ntup->count = idx; ntup->count = idx;
ntup->version = e->version;
} }
/* /*
@@ -457,6 +486,7 @@ HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHe
{ {
element->level = etup->level; element->level = etup->level;
element->deleted = etup->deleted; element->deleted = etup->deleted;
element->version = etup->version;
element->neighborPage = ItemPointerGetBlockNumber(&etup->neighbortid); element->neighborPage = ItemPointerGetBlockNumber(&etup->neighbortid);
element->neighborOffno = ItemPointerGetOffsetNumber(&etup->neighbortid); element->neighborOffno = ItemPointerGetOffsetNumber(&etup->neighbortid);
element->heaptidsLength = 0; element->heaptidsLength = 0;
@@ -486,16 +516,16 @@ HnswLoadElementFromTuple(HnswElement element, HnswElementTuple etup, bool loadHe
* Calculate the distance between values * Calculate the distance between values
*/ */
static inline double static inline double
HnswGetDistance(Datum a, Datum b, FmgrInfo *procinfo, Oid collation) HnswGetDistance(Datum a, Datum b, HnswSupport * support)
{ {
return DatumGetFloat8(FunctionCall2Coll(procinfo, collation, a, b)); return DatumGetFloat8(FunctionCall2Coll(support->procinfo, support->collation, a, b));
} }
/* /*
* Load an element and optionally get its distance from q * Load an element and optionally get its distance from q
*/ */
static void static void
HnswLoadElementImpl(BlockNumber blkno, OffsetNumber offno, double *distance, Datum *q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec, double *maxDistance, HnswElement * element) HnswLoadElementImpl(BlockNumber blkno, OffsetNumber offno, double *distance, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec, double *maxDistance, HnswElement * element)
{ {
Buffer buf; Buffer buf;
Page page; Page page;
@@ -513,10 +543,10 @@ HnswLoadElementImpl(BlockNumber blkno, OffsetNumber offno, double *distance, Dat
/* Calculate distance */ /* Calculate distance */
if (distance != NULL) if (distance != NULL)
{ {
if (DatumGetPointer(*q) == NULL) if (DatumGetPointer(q->value) == NULL)
*distance = 0; *distance = 0;
else else
*distance = HnswGetDistance(*q, PointerGetDatum(&etup->data), procinfo, collation); *distance = HnswGetDistance(q->value, PointerGetDatum(&etup->data), support);
} }
/* Load element */ /* Load element */
@@ -535,40 +565,51 @@ HnswLoadElementImpl(BlockNumber blkno, OffsetNumber offno, double *distance, Dat
* Load an element and optionally get its distance from q * Load an element and optionally get its distance from q
*/ */
void void
HnswLoadElement(HnswElement element, double *distance, Datum *q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec, double *maxDistance) HnswLoadElement(HnswElement element, double *distance, HnswQuery * q, Relation index, HnswSupport * support, bool loadVec, double *maxDistance)
{ {
HnswLoadElementImpl(element->blkno, element->offno, distance, q, index, procinfo, collation, loadVec, maxDistance, &element); HnswLoadElementImpl(element->blkno, element->offno, distance, q, index, support, loadVec, maxDistance, &element);
} }
/* /*
* Get the distance for an element * Get the distance for an element
*/ */
static double static double
GetElementDistance(char *base, HnswElement element, Datum q, FmgrInfo *procinfo, Oid collation) GetElementDistance(char *base, HnswElement element, HnswQuery * q, HnswSupport * support)
{ {
Datum value = HnswGetValue(base, element); Datum value = HnswGetValue(base, element);
return HnswGetDistance(q, value, procinfo, collation); 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 * Create a candidate for the entry point
*/ */
HnswSearchCandidate * HnswSearchCandidate *
HnswEntryCandidate(char *base, HnswElement entryPoint, Datum q, Relation index, FmgrInfo *procinfo, Oid collation, bool loadVec) 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)
if (index == NULL) distance = GetElementDistance(base, entryPoint, q, support);
sc->distance = GetElementDistance(base, entryPoint, q, procinfo, collation);
else else
HnswLoadElement(entryPoint, &sc->distance, &q, index, procinfo, collation, loadVec, NULL); HnswLoadElement(entryPoint, &distance, q, index, support, loadVec, NULL);
return sc;
}
#define HnswGetSearchCandidate(membername, ptr) pairingheap_container(HnswSearchCandidate, membername, ptr) return HnswInitSearchCandidate(base, entryPoint, distance);
#define HnswGetSearchCandidateConst(membername, ptr) pairingheap_const_container(HnswSearchCandidate, membername, ptr) }
/* /*
* Compare candidate distances * Compare candidate distances
@@ -585,6 +626,21 @@ CompareNearestCandidates(const pairingheap_node *a, const pairingheap_node *b, v
return 0; return 0;
} }
/*
* Compare discarded candidate distances
*/
static int
CompareNearestDiscardedCandidates(const pairingheap_node *a, const pairingheap_node *b, void *arg)
{
if (HnswGetSearchCandidateConst(w_node, a)->distance < HnswGetSearchCandidateConst(w_node, b)->distance)
return 1;
if (HnswGetSearchCandidateConst(w_node, a)->distance > HnswGetSearchCandidateConst(w_node, b)->distance)
return -1;
return 0;
}
/* /*
* Compare candidate distances * Compare candidate distances
*/ */
@@ -604,9 +660,9 @@ CompareFurthestCandidates(const pairingheap_node *a, const pairingheap_node *b,
* Init visited * Init visited
*/ */
static inline void static inline void
InitVisited(char *base, visited_hash * v, Relation index, int ef, int m) InitVisited(char *base, visited_hash * v, bool inMemory, int ef, int m)
{ {
if (index != NULL) if (!inMemory)
v->tids = tidhash_create(CurrentMemoryContext, ef * m * 2, NULL); v->tids = tidhash_create(CurrentMemoryContext, ef * m * 2, NULL);
else if (base != NULL) else if (base != NULL)
v->offsets = offsethash_create(CurrentMemoryContext, ef * m * 2, NULL); v->offsets = offsethash_create(CurrentMemoryContext, ef * m * 2, NULL);
@@ -618,9 +674,9 @@ InitVisited(char *base, visited_hash * v, Relation index, int ef, int m)
* Add to visited * Add to visited
*/ */
static inline void static inline void
AddToVisited(char *base, visited_hash * v, HnswElementPtr elementPtr, Relation index, bool *found) AddToVisited(char *base, visited_hash * v, HnswElementPtr elementPtr, bool inMemory, bool *found)
{ {
if (index != NULL) if (!inMemory)
{ {
HnswElement element = HnswPtrAccess(base, elementPtr); HnswElement element = HnswPtrAccess(base, elementPtr);
ItemPointerData indextid; ItemPointerData indextid;
@@ -681,7 +737,7 @@ HnswLoadUnvisitedFromMemory(char *base, HnswElement element, HnswUnvisited * unv
HnswCandidate *hc = &localNeighborhood->items[i]; HnswCandidate *hc = &localNeighborhood->items[i];
bool found; bool found;
AddToVisited(base, v, hc->element, NULL, &found); AddToVisited(base, v, hc->element, true, &found);
if (!found) if (!found)
unvisited[(*unvisitedLength)++].element = HnswPtrAccess(base, hc->element); unvisited[(*unvisitedLength)++].element = HnswPtrAccess(base, hc->element);
@@ -705,8 +761,11 @@ HnswLoadNeighborTids(HnswElement element, ItemPointerData *indextids, Relation i
ntup = (HnswNeighborTuple) PageGetItem(page, PageGetItemId(page, element->neighborOffno)); ntup = (HnswNeighborTuple) PageGetItem(page, PageGetItemId(page, element->neighborOffno));
/* Ensure expected neighbors */ /*
if (ntup->count != (element->level + 2) * m) * Ensure the neighbor tuple has not been deleted or replaced between
* index scan iterations
*/
if (ntup->version != element->version || ntup->count != (element->level + 2) * m)
{ {
UnlockReleaseBuffer(buf); UnlockReleaseBuffer(buf);
return false; return false;
@@ -752,24 +811,37 @@ HnswLoadUnvisitedFromDisk(HnswElement element, HnswUnvisited * unvisited, int *u
* Algorithm 2 from paper * Algorithm 2 from paper
*/ */
List * List *
HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, FmgrInfo *procinfo, Oid collation, int m, bool inserting, HnswElement skipElement) HnswSearchLayer(char *base, HnswQuery * q, List *ep, int ef, int lc, Relation index, HnswSupport * support, int m, bool inserting, HnswElement skipElement, visited_hash * v, pairingheap **discarded, bool initVisited, int64 *tuples)
{ {
List *w = NIL; List *w = NIL;
pairingheap *C = pairingheap_allocate(CompareNearestCandidates, NULL); pairingheap *C = pairingheap_allocate(CompareNearestCandidates, NULL);
pairingheap *W = pairingheap_allocate(CompareFurthestCandidates, NULL); pairingheap *W = pairingheap_allocate(CompareFurthestCandidates, NULL);
int wlen = 0; int wlen = 0;
visited_hash v; visited_hash vh;
ListCell *lc2; ListCell *lc2;
HnswNeighborArray *localNeighborhood = NULL; HnswNeighborArray *localNeighborhood = NULL;
Size neighborhoodSize = 0; Size neighborhoodSize = 0;
int lm = HnswGetLayerM(m, lc); int lm = HnswGetLayerM(m, lc);
HnswUnvisited *unvisited = palloc(lm * sizeof(HnswUnvisited)); HnswUnvisited *unvisited = palloc(lm * sizeof(HnswUnvisited));
int unvisitedLength; int unvisitedLength;
bool inMemory = index == NULL;
InitVisited(base, &v, index, ef, m); if (v == NULL)
{
v = &vh;
initVisited = true;
}
if (initVisited)
{
InitVisited(base, v, inMemory, ef, m);
if (discarded != NULL)
*discarded = pairingheap_allocate(CompareNearestDiscardedCandidates, NULL);
}
/* Create local memory for neighborhood if needed */ /* Create local memory for neighborhood if needed */
if (index == NULL) if (inMemory)
{ {
neighborhoodSize = HNSW_NEIGHBOR_ARRAY_SIZE(lm); neighborhoodSize = HNSW_NEIGHBOR_ARRAY_SIZE(lm);
localNeighborhood = palloc(neighborhoodSize); localNeighborhood = palloc(neighborhoodSize);
@@ -781,7 +853,14 @@ HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, F
HnswSearchCandidate *sc = (HnswSearchCandidate *) lfirst(lc2); HnswSearchCandidate *sc = (HnswSearchCandidate *) lfirst(lc2);
bool found; bool found;
AddToVisited(base, &v, sc->element, index, &found); if (initVisited)
{
AddToVisited(base, v, sc->element, inMemory, &found);
/* OK to count elements instead of tuples */
if (tuples != NULL)
(*tuples)++;
}
pairingheap_add(C, &sc->c_node); pairingheap_add(C, &sc->c_node);
pairingheap_add(W, &sc->w_node); pairingheap_add(W, &sc->w_node);
@@ -806,10 +885,14 @@ HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, F
cElement = HnswPtrAccess(base, c->element); cElement = HnswPtrAccess(base, c->element);
if (index == NULL) if (inMemory)
HnswLoadUnvisitedFromMemory(base, cElement, unvisited, &unvisitedLength, &v, lc, localNeighborhood, neighborhoodSize); HnswLoadUnvisitedFromMemory(base, cElement, unvisited, &unvisitedLength, v, lc, localNeighborhood, neighborhoodSize);
else else
HnswLoadUnvisitedFromDisk(cElement, unvisited, &unvisitedLength, &v, index, m, lm, lc); HnswLoadUnvisitedFromDisk(cElement, unvisited, &unvisitedLength, v, index, m, lm, lc);
/* OK to count elements instead of tuples */
if (tuples != NULL)
(*tuples) += unvisitedLength;
for (int i = 0; i < unvisitedLength; i++) for (int i = 0; i < unvisitedLength; i++)
{ {
@@ -820,10 +903,10 @@ HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, F
f = HnswGetSearchCandidate(w_node, pairingheap_first(W)); f = HnswGetSearchCandidate(w_node, pairingheap_first(W));
if (index == NULL) if (inMemory)
{ {
eElement = unvisited[i].element; eElement = unvisited[i].element;
eDistance = GetElementDistance(base, eElement, q, procinfo, collation); eDistance = GetElementDistance(base, eElement, q, support);
} }
else else
{ {
@@ -833,25 +916,30 @@ HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, F
/* Avoid any allocations if not adding */ /* Avoid any allocations if not adding */
eElement = NULL; eElement = NULL;
HnswLoadElementImpl(blkno, offno, &eDistance, &q, index, procinfo, collation, inserting, alwaysAdd ? NULL : &f->distance, &eElement); HnswLoadElementImpl(blkno, offno, &eDistance, q, index, support, inserting, alwaysAdd || discarded != NULL ? NULL : &f->distance, &eElement);
if (eElement == NULL) if (eElement == NULL)
continue; continue;
} }
if (!(eDistance < f->distance || alwaysAdd)) if (eElement == NULL || !(eDistance < f->distance || alwaysAdd))
continue; {
if (discarded != NULL)
{
/* Create a new candidate */
e = HnswInitSearchCandidate(base, eElement, eDistance);
pairingheap_add(*discarded, &e->w_node);
}
Assert(!eElement->deleted); continue;
}
/* Make robust to issues */ /* Make robust to issues */
if (eElement->level < lc) if (eElement->level < lc)
continue; continue;
/* Create a new candidate */ /* Create a new candidate */
e = palloc(sizeof(HnswSearchCandidate)); e = HnswInitSearchCandidate(base, eElement, eDistance);
HnswPtrStore(base, e->element, eElement);
e->distance = eDistance;
pairingheap_add(C, &e->c_node); pairingheap_add(C, &e->c_node);
pairingheap_add(W, &e->w_node); pairingheap_add(W, &e->w_node);
@@ -866,7 +954,12 @@ HnswSearchLayer(char *base, Datum q, List *ep, int ef, int lc, Relation index, F
/* No need to decrement wlen */ /* No need to decrement wlen */
if (wlen > ef) if (wlen > ef)
pairingheap_remove_first(W); {
HnswSearchCandidate *d = HnswGetSearchCandidate(w_node, pairingheap_remove_first(W));
if (discarded != NULL)
pairingheap_add(*discarded, &d->w_node);
}
} }
} }
} }
@@ -934,7 +1027,7 @@ CompareCandidateDistancesOffset(const ListCell *a, const ListCell *b)
* Check if an element is closer to q than any element from R * Check if an element is closer to q than any element from R
*/ */
static bool static bool
CheckElementCloser(char *base, HnswCandidate * e, List *r, FmgrInfo *procinfo, Oid collation) CheckElementCloser(char *base, HnswCandidate * e, List *r, HnswSupport * support)
{ {
HnswElement eElement = HnswPtrAccess(base, e->element); HnswElement eElement = HnswPtrAccess(base, e->element);
Datum eValue = HnswGetValue(base, eElement); Datum eValue = HnswGetValue(base, eElement);
@@ -945,7 +1038,7 @@ CheckElementCloser(char *base, HnswCandidate * e, List *r, FmgrInfo *procinfo, O
HnswCandidate *ri = lfirst(lc2); HnswCandidate *ri = lfirst(lc2);
HnswElement riElement = HnswPtrAccess(base, ri->element); HnswElement riElement = HnswPtrAccess(base, ri->element);
Datum riValue = HnswGetValue(base, riElement); Datum riValue = HnswGetValue(base, riElement);
float distance = HnswGetDistance(eValue, riValue, procinfo, collation); float distance = HnswGetDistance(eValue, riValue, support);
if (distance <= e->distance) if (distance <= e->distance)
return false; return false;
@@ -958,7 +1051,7 @@ CheckElementCloser(char *base, HnswCandidate * e, List *r, FmgrInfo *procinfo, O
* Algorithm 4 from paper * Algorithm 4 from paper
*/ */
static List * static List *
SelectNeighbors(char *base, List *c, int lm, FmgrInfo *procinfo, Oid collation, bool *closerSet, HnswCandidate * newCandidate, HnswCandidate * *pruned, bool sortCandidates) SelectNeighbors(char *base, List *c, int lm, HnswSupport * support, bool *closerSet, HnswCandidate * newCandidate, HnswCandidate * *pruned, bool sortCandidates)
{ {
List *r = NIL; List *r = NIL;
List *w = list_copy(c); List *w = list_copy(c);
@@ -992,7 +1085,7 @@ SelectNeighbors(char *base, List *c, int lm, FmgrInfo *procinfo, Oid collation,
/* Use previous state of r and wd to skip work when possible */ /* Use previous state of r and wd to skip work when possible */
if (mustCalculate) if (mustCalculate)
e->closer = CheckElementCloser(base, e, r, procinfo, collation); e->closer = CheckElementCloser(base, e, r, support);
else if (list_length(added) > 0) else if (list_length(added) > 0)
{ {
/* Keep Valgrind happy for in-memory, parallel builds */ /* Keep Valgrind happy for in-memory, parallel builds */
@@ -1005,7 +1098,7 @@ SelectNeighbors(char *base, List *c, int lm, FmgrInfo *procinfo, Oid collation,
*/ */
if (e->closer) if (e->closer)
{ {
e->closer = CheckElementCloser(base, e, added, procinfo, collation); e->closer = CheckElementCloser(base, e, added, support);
if (!e->closer) if (!e->closer)
removedAny = true; removedAny = true;
@@ -1018,7 +1111,7 @@ SelectNeighbors(char *base, List *c, int lm, FmgrInfo *procinfo, Oid collation,
*/ */
if (removedAny) if (removedAny)
{ {
e->closer = CheckElementCloser(base, e, r, procinfo, collation); e->closer = CheckElementCloser(base, e, r, support);
if (e->closer) if (e->closer)
added = lappend(added, e); added = lappend(added, e);
} }
@@ -1026,7 +1119,7 @@ SelectNeighbors(char *base, List *c, int lm, FmgrInfo *procinfo, Oid collation,
} }
else if (e == newCandidate) else if (e == newCandidate)
{ {
e->closer = CheckElementCloser(base, e, r, procinfo, collation); e->closer = CheckElementCloser(base, e, r, support);
if (e->closer) if (e->closer)
added = lappend(added, e); added = lappend(added, e);
} }
@@ -1077,7 +1170,7 @@ AddConnections(char *base, HnswElement element, List *neighbors, int lc)
* Update connections * Update connections
*/ */
void void
HnswUpdateConnection(char *base, HnswNeighborArray * neighbors, HnswElement newElement, float distance, int lm, int *updateIdx, Relation index, FmgrInfo *procinfo, Oid collation) HnswUpdateConnection(char *base, HnswNeighborArray * neighbors, HnswElement newElement, float distance, int lm, int *updateIdx, Relation index, HnswSupport * support)
{ {
HnswCandidate newHc; HnswCandidate newHc;
@@ -1103,7 +1196,7 @@ HnswUpdateConnection(char *base, HnswNeighborArray * neighbors, HnswElement newE
c = lappend(c, &neighbors->items[i]); c = lappend(c, &neighbors->items[i]);
c = lappend(c, &newHc); c = lappend(c, &newHc);
SelectNeighbors(base, c, lm, procinfo, collation, &neighbors->closerSet, &newHc, &pruned, true); SelectNeighbors(base, c, lm, support, &neighbors->closerSet, &newHc, &pruned, true);
/* Should not happen */ /* Should not happen */
if (pruned == NULL) if (pruned == NULL)
@@ -1174,17 +1267,20 @@ PrecomputeHash(char *base, HnswElement element)
* Algorithm 1 from paper * Algorithm 1 from paper
*/ */
void void
HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, FmgrInfo *procinfo, Oid collation, int m, int efConstruction, bool existing) HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint, Relation index, HnswSupport * support, int m, int efConstruction, bool existing)
{ {
List *ep; List *ep;
List *w; List *w;
int level = element->level; int level = element->level;
int entryLevel; int entryLevel;
Datum q = HnswGetValue(base, element); HnswQuery q;
HnswElement skipElement = existing ? element : NULL; HnswElement skipElement = existing ? element : NULL;
bool inMemory = index == NULL;
q.value = HnswGetValue(base, element);
/* Precompute hash */ /* Precompute hash */
if (index == NULL) if (inMemory)
PrecomputeHash(base, element); PrecomputeHash(base, element);
/* No neighbors if no entry point */ /* No neighbors if no entry point */
@@ -1192,13 +1288,13 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
return; return;
/* Get entry point and level */ /* Get entry point and level */
ep = list_make1(HnswEntryCandidate(base, entryPoint, q, index, procinfo, collation, true)); ep = list_make1(HnswEntryCandidate(base, entryPoint, &q, index, support, true));
entryLevel = entryPoint->level; entryLevel = entryPoint->level;
/* 1st phase: greedy search to insert level */ /* 1st phase: greedy search to insert level */
for (int lc = entryLevel; lc >= level + 1; lc--) for (int lc = entryLevel; lc >= level + 1; lc--)
{ {
w = HnswSearchLayer(base, q, ep, 1, lc, index, procinfo, collation, m, true, skipElement); w = HnswSearchLayer(base, &q, ep, 1, lc, index, support, m, true, skipElement, NULL, NULL, true, NULL);
ep = w; ep = w;
} }
@@ -1217,7 +1313,7 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
List *lw = NIL; List *lw = NIL;
ListCell *lc2; ListCell *lc2;
w = HnswSearchLayer(base, q, ep, efConstruction, lc, index, procinfo, collation, m, true, skipElement); w = HnswSearchLayer(base, &q, ep, efConstruction, lc, index, support, m, true, skipElement, NULL, NULL, true, NULL);
/* Convert search candidates to candidates */ /* Convert search candidates to candidates */
foreach(lc2, w) foreach(lc2, w)
@@ -1233,7 +1329,7 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
/* Elements being deleted or skipped can help with search */ /* Elements being deleted or skipped can help with search */
/* but should be removed before selecting neighbors */ /* but should be removed before selecting neighbors */
if (index != NULL) if (!inMemory)
lw = RemoveElements(base, lw, skipElement); lw = RemoveElements(base, lw, skipElement);
/* /*
@@ -1241,7 +1337,7 @@ HnswFindElementNeighbors(char *base, HnswElement element, HnswElement entryPoint
* sortCandidates to true for in-memory builds to enable closer * sortCandidates to true for in-memory builds to enable closer
* caching, but there does not seem to be a difference in performance. * caching, but there does not seem to be a difference in performance.
*/ */
neighbors = SelectNeighbors(base, lw, lm, procinfo, collation, &HnswGetNeighbors(base, element, lc)->closerSet, NULL, NULL, false); neighbors = SelectNeighbors(base, lw, lm, support, &HnswGetNeighbors(base, element, lc)->closerSet, NULL, NULL, false);
AddConnections(base, element, neighbors, lc); AddConnections(base, element, neighbors, lc);

View File

@@ -184,13 +184,12 @@ static void
RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswElement entryPoint) RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswElement entryPoint)
{ {
Relation index = vacuumstate->index; Relation index = vacuumstate->index;
HnswSupport *support = &vacuumstate->support;
Buffer buf; Buffer buf;
Page page; Page page;
GenericXLogState *state; GenericXLogState *state;
int m = vacuumstate->m; int m = vacuumstate->m;
int efConstruction = vacuumstate->efConstruction; int efConstruction = vacuumstate->efConstruction;
FmgrInfo *procinfo = vacuumstate->procinfo;
Oid collation = vacuumstate->collation;
BufferAccessStrategy bas = vacuumstate->bas; BufferAccessStrategy bas = vacuumstate->bas;
HnswNeighborTuple ntup = vacuumstate->ntup; HnswNeighborTuple ntup = vacuumstate->ntup;
Size ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(element->level, m); Size ntupSize = HNSW_NEIGHBOR_TUPLE_SIZE(element->level, m);
@@ -205,7 +204,7 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
element->heaptidsLength = 0; element->heaptidsLength = 0;
/* Find neighbors for element, skipping itself */ /* Find neighbors for element, skipping itself */
HnswFindElementNeighbors(base, element, entryPoint, index, procinfo, collation, m, efConstruction, true); HnswFindElementNeighbors(base, element, entryPoint, index, support, m, efConstruction, true);
/* Zero memory for each element */ /* Zero memory for each element */
MemSet(ntup, 0, HNSW_TUPLE_ALLOC_SIZE); MemSet(ntup, 0, HNSW_TUPLE_ALLOC_SIZE);
@@ -229,7 +228,7 @@ RepairGraphElement(HnswVacuumState * vacuumstate, HnswElement element, HnswEleme
UnlockReleaseBuffer(buf); UnlockReleaseBuffer(buf);
/* Update neighbors */ /* Update neighbors */
HnswUpdateNeighborsOnDisk(index, procinfo, collation, element, m, true, false); HnswUpdateNeighborsOnDisk(index, support, element, m, true, false);
} }
/* /*
@@ -239,6 +238,7 @@ static void
RepairGraphEntryPoint(HnswVacuumState * vacuumstate) RepairGraphEntryPoint(HnswVacuumState * vacuumstate)
{ {
Relation index = vacuumstate->index; Relation index = vacuumstate->index;
HnswSupport *support = &vacuumstate->support;
HnswElement highestPoint = &vacuumstate->highestPoint; HnswElement highestPoint = &vacuumstate->highestPoint;
HnswElement entryPoint; HnswElement entryPoint;
MemoryContext oldCtx = MemoryContextSwitchTo(vacuumstate->tmpCtx); MemoryContext oldCtx = MemoryContextSwitchTo(vacuumstate->tmpCtx);
@@ -256,7 +256,7 @@ RepairGraphEntryPoint(HnswVacuumState * vacuumstate)
LockPage(index, HNSW_UPDATE_LOCK, ShareLock); LockPage(index, HNSW_UPDATE_LOCK, ShareLock);
/* Load element */ /* Load element */
HnswLoadElement(highestPoint, NULL, NULL, index, vacuumstate->procinfo, vacuumstate->collation, true, NULL); HnswLoadElement(highestPoint, NULL, NULL, index, support, true, NULL);
/* Repair if needed */ /* Repair if needed */
if (NeedsUpdated(vacuumstate, highestPoint)) if (NeedsUpdated(vacuumstate, highestPoint))
@@ -294,7 +294,7 @@ RepairGraphEntryPoint(HnswVacuumState * vacuumstate)
* is outdated, this can remove connections at higher levels in * is outdated, this can remove connections at higher levels in
* the graph until they are repaired, but this should be fine. * the graph until they are repaired, but this should be fine.
*/ */
HnswLoadElement(entryPoint, NULL, NULL, index, vacuumstate->procinfo, vacuumstate->collation, true, NULL); HnswLoadElement(entryPoint, NULL, NULL, index, support, true, NULL);
if (NeedsUpdated(vacuumstate, entryPoint)) if (NeedsUpdated(vacuumstate, entryPoint))
{ {
@@ -527,6 +527,14 @@ MarkDeleted(HnswVacuumState * vacuumstate)
for (int i = 0; i < ntup->count; i++) for (int i = 0; i < ntup->count; i++)
ItemPointerSetInvalid(&ntup->indextids[i]); ItemPointerSetInvalid(&ntup->indextids[i]);
/* Increment version */
/* This is used to avoid incorrect reads for iterative scans */
/* Reserve some bits for future use */
etup->version++;
if (etup->version > 15)
etup->version = 1;
ntup->version = etup->version;
/* /*
* We modified the tuples in place, no need to call * We modified the tuples in place, no need to call
* PageIndexTupleOverwrite * PageIndexTupleOverwrite
@@ -573,13 +581,13 @@ InitVacuumState(HnswVacuumState * vacuumstate, IndexVacuumInfo *info, IndexBulkD
vacuumstate->callback_state = callback_state; vacuumstate->callback_state = callback_state;
vacuumstate->efConstruction = HnswGetEfConstruction(index); vacuumstate->efConstruction = HnswGetEfConstruction(index);
vacuumstate->bas = GetAccessStrategy(BAS_BULKREAD); vacuumstate->bas = GetAccessStrategy(BAS_BULKREAD);
vacuumstate->procinfo = index_getprocinfo(index, 1, HNSW_DISTANCE_PROC);
vacuumstate->collation = index->rd_indcollation[0];
vacuumstate->ntup = palloc0(HNSW_TUPLE_ALLOC_SIZE); vacuumstate->ntup = palloc0(HNSW_TUPLE_ALLOC_SIZE);
vacuumstate->tmpCtx = AllocSetContextCreate(CurrentMemoryContext, vacuumstate->tmpCtx = AllocSetContextCreate(CurrentMemoryContext,
"Hnsw vacuum temporary context", "Hnsw vacuum temporary context",
ALLOCSET_DEFAULT_SIZES); ALLOCSET_DEFAULT_SIZES);
HnswInitSupport(&vacuumstate->support, index);
/* Get m from metapage */ /* Get m from metapage */
HnswGetMetaPageInfo(index, &vacuumstate->m, NULL); HnswGetMetaPageInfo(index, &vacuumstate->m, NULL);

View File

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

View File

@@ -17,8 +17,16 @@
#endif #endif
int ivfflat_probes; int ivfflat_probes;
int ivfflat_iterative_scan;
int ivfflat_max_probes;
static relopt_kind ivfflat_relopt_kind; 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 * Initialize index options and variables
*/ */
@@ -33,6 +41,15 @@ IvfflatInit(void)
"Valid range is 1..lists.", &ivfflat_probes, "Valid range is 1..lists.", &ivfflat_probes,
IVFFLAT_DEFAULT_PROBES, IVFFLAT_MIN_LISTS, IVFFLAT_MAX_LISTS, PGC_USERSET, 0, NULL, NULL, NULL); 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"); MarkGUCPrefixReserved("ivfflat");
} }
@@ -82,6 +99,10 @@ ivfflatcostestimate(PlannerInfo *root, IndexPath *path, double loop_count,
*indexSelectivity = 0; *indexSelectivity = 0;
*indexCorrelation = 0; *indexCorrelation = 0;
*indexPages = 0; *indexPages = 0;
#if PG_VERSION_NUM >= 180000
/* See "On disable_cost" thread on pgsql-hackers */
path->path.disabled_nodes = 2;
#endif
return; return;
} }

View File

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

View File

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

View File

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

View File

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

View File

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

View File

@@ -99,6 +99,32 @@ SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <+> (SELECT NULL::vector)) t2
4 4
(1 row) (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; DROP TABLE t;
-- unlogged -- unlogged
CREATE UNLOGGED TABLE t (val vector(3)); CREATE UNLOGGED TABLE t (val vector(3));
@@ -139,4 +165,31 @@ SET hnsw.ef_search = 0;
ERROR: 0 is outside the valid range for parameter "hnsw.ef_search" (1 .. 1000) ERROR: 0 is outside the valid range for parameter "hnsw.ef_search" (1 .. 1000)
SET hnsw.ef_search = 1001; SET hnsw.ef_search = 1001;
ERROR: 1001 is outside the valid range for parameter "hnsw.ef_search" (1 .. 1000) 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; DROP TABLE t;

View File

@@ -81,6 +81,37 @@ SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <=> (SELECT NULL::vector)) t2
3 3
(1 row) (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; DROP TABLE t;
-- unlogged -- unlogged
CREATE UNLOGGED TABLE t (val vector(3)); CREATE UNLOGGED TABLE t (val vector(3));
@@ -109,4 +140,27 @@ SHOW ivfflat.probes;
1 1
(1 row) (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; DROP TABLE t;

View File

@@ -57,6 +57,23 @@ SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <+> (SELECT NULL::vector)) t2
DROP TABLE t; 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 -- unlogged
CREATE UNLOGGED TABLE t (val vector(3)); CREATE UNLOGGED TABLE t (val vector(3));
@@ -81,4 +98,17 @@ SHOW hnsw.ef_search;
SET hnsw.ef_search = 0; SET hnsw.ef_search = 0;
SET hnsw.ef_search = 1001; 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; DROP TABLE t;

View File

@@ -44,6 +44,25 @@ SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <=> (SELECT NULL::vector)) t2
DROP TABLE t; 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 -- unlogged
CREATE UNLOGGED TABLE t (val vector(3)); CREATE UNLOGGED TABLE t (val vector(3));
@@ -62,4 +81,16 @@ CREATE INDEX ON t USING ivfflat (val vector_l2_ops) WITH (lists = 32769);
SHOW ivfflat.probes; 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; DROP TABLE t;

View File

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

View File

@@ -0,0 +1,54 @@
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();

View File

@@ -0,0 +1,125 @@
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();

View File

@@ -0,0 +1,59 @@
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", qq(
SET maintenance_work_mem = '128MB';
SET max_parallel_maintenance_workers = 2;
CREATE INDEX ON tst USING hnsw (v vector_l2_ops)
));
my $count = $node->safe_psql("postgres", qq(
SET enable_seqscan = off;
SET hnsw.iterative_scan = relaxed_order;
SET hnsw.max_scan_tuples = 100000;
SET hnsw.scan_mem_multiplier = 2;
SELECT COUNT(*) FROM (SELECT v FROM tst WHERE i % 10000 = 0 ORDER BY v <-> (SELECT v FROM tst LIMIT 1) LIMIT 11) t;
));
is($count, 10);
foreach ((30000, 50000, 70000))
{
my $max_tuples = $_;
my $expected = $max_tuples / 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.max_scan_tuples = $max_tuples;
SET hnsw.scan_mem_multiplier = 2;
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();

View File

@@ -0,0 +1,118 @@
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 $dim = 3;
my $array_sql = join(",", ('random()') x $dim);
my @cs = (50, 500);
sub test_recall
{
my ($c, $ef_search, $min, $operator, $mode) = @_;
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;
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 hnsw.ef_search = $ef_search;
SET hnsw.iterative_scan = $mode;
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 $mode $c");
}
# Initialize node
$node = PostgreSQL::Test::Cluster->new('node');
$node->init;
$node->start;
# Create table
$node->safe_psql("postgres", "CREATE EXTENSION vector;");
$node->safe_psql("postgres", "CREATE TABLE tst (i int4, v vector($dim));");
$node->safe_psql("postgres",
"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(1, 50000) i;"
);
# Generate queries
for (1 .. 20)
{
my @r = ();
for (1 .. $dim)
{
push(@r, rand());
}
push(@queries, "[" . join(",", @r) . "]");
}
# 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", qq(
SET maintenance_work_mem = '128MB';
CREATE INDEX idx ON tst USING hnsw (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, $res);
}
test_recall($c, 40, 0.99, $operator, "strict_order");
test_recall($c, 40, 0.99, $operator, "relaxed_order");
}
$node->safe_psql("postgres", "DROP INDEX idx;");
}
done_testing();

View File

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