liuyu/pgvector
1
0
Fork 0
mirror of https://github.com/pgvector/pgvector.git synced 2026-07-03 19:20:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

Do not use index without limit or if limit + offset > expected tuples

Browse Source
This commit is contained in:
Andrew Kane
2024-01-20 15:16:30 -08:00
parent 042ddfdc8a
commit 63c4af0454
23 changed files with 177 additions and 45 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
test/t/007_ivfflat_inserts.pl
View File

@@ -49,7 +49,7 @@ is(idx_scan(), 0);
$count = $node->safe_psql("postgres", qq(
SET enable_seqscan = off;
SET ivfflat.probes = 100;
SELECT COUNT(*) FROM (SELECT v FROM tst ORDER BY v <-> (SELECT v FROM tst LIMIT 1)) t;
SELECT COUNT(*) FROM (SELECT v FROM tst ORDER BY v <-> (SELECT v FROM tst LIMIT 1) LIMIT 20000) t;
));
is($count, $expected);
is(idx_scan(), 1);

4
test/t/014_hnsw_inserts.pl
View File

@@ -42,7 +42,7 @@ for my $i (1 .. 20)
my $count = $node->safe_psql("postgres", qq(
SET enable_seqscan = off;
SELECT COUNT(*) FROM (SELECT v FROM tst ORDER BY v <-> (SELECT v FROM tst LIMIT 1)) t;
SELECT COUNT(*) FROM (SELECT v FROM tst ORDER BY v <-> (SELECT v FROM tst LIMIT 1) LIMIT 20) t;
));
is($count, 10);
@@ -63,7 +63,7 @@ $node->pgbench(
my $count = $node->safe_psql("postgres", qq(
SET enable_seqscan = off;
SET hnsw.ef_search = 1000;
SELECT COUNT(*) FROM (SELECT v FROM tst ORDER BY v <-> (SELECT v FROM tst LIMIT 1)) t;
SELECT COUNT(*) FROM (SELECT v FROM tst ORDER BY v <-> (SELECT v FROM tst LIMIT 1) LIMIT 1000) t;
));
# Elements may lose all incoming connections with the HNSW algorithm
# Vacuuming can fix this if one of the elements neighbors is deleted

5
test/t/015_hnsw_duplicates.pl
View File

@@ -23,10 +23,11 @@ sub insert_vectors
sub test_duplicates
{
# TODO Improve
my $res = $node->safe_psql("postgres", qq(
SET enable_seqscan = off;
SET hnsw.ef_search = 1;
SELECT COUNT(*) FROM (SELECT * FROM tst ORDER BY v <-> '[1,1,1]') t;
SET hnsw.ef_search = 10;
SELECT COUNT(*) FROM (SELECT * FROM tst ORDER BY v <-> '[1,1,1]' LIMIT 10) t;
));
is($res, 10);
}

64
test/t/019_ivfflat_limit.pl Normal file
View File

@@ -0,0 +1,64 @@
use strict;
use warnings;
use PostgresNode;
use TestLib;
use Test::More;
# Initialize node
my $node = get_new_node('node');
$node->init;
$node->start;
# Create table and index
$node->safe_psql("postgres", "CREATE EXTENSION vector;");
$node->safe_psql("postgres", "CREATE TABLE tst (v vector(3));");
$node->safe_psql("postgres",
"INSERT INTO tst SELECT ARRAY[random(), random(), random()] FROM generate_series(1, 1000) i;"
);
$node->safe_psql("postgres", "CREATE INDEX ON tst USING ivfflat (v vector_l2_ops) WITH (lists = 10);");
# Test limit
my $explain = $node->safe_psql("postgres", qq(
EXPLAIN ANALYZE SELECT * FROM tst ORDER BY v <-> '[1,2,3]' LIMIT 100;
));
like($explain, qr/Index Scan/);
# Test limit + offset
$explain = $node->safe_psql("postgres", qq(
EXPLAIN ANALYZE SELECT * FROM tst ORDER BY v <-> '[1,2,3]' LIMIT 90 OFFSET 10;
));
like($explain, qr/Index Scan/);
# Test limit with probes
$explain = $node->safe_psql("postgres", qq(
SET ivfflat.probes = 2;
EXPLAIN ANALYZE SELECT * FROM tst ORDER BY v <-> '[1,2,3]' LIMIT 200;
));
like($explain, qr/Index Scan/);
# Test limit > expected tuples
$explain = $node->safe_psql("postgres", qq(
EXPLAIN ANALYZE SELECT * FROM tst ORDER BY v <-> '[1,2,3]' LIMIT 101;
));
like($explain, qr/Seq Scan/);
# Test limit + offset > expected tuples
$explain = $node->safe_psql("postgres", qq(
EXPLAIN ANALYZE SELECT * FROM tst ORDER BY v <-> '[1,2,3]' LIMIT 91 OFFSET 10;
));
like($explain, qr/Seq Scan/);
# Test limit > expected tuples with probes
$explain = $node->safe_psql("postgres", qq(
SET ivfflat.probes = 2;
EXPLAIN ANALYZE SELECT * FROM tst ORDER BY v <-> '[1,2,3]' LIMIT 201;
));
like($explain, qr/Seq Scan/);
# Test no limit
$explain = $node->safe_psql("postgres", qq(
EXPLAIN ANALYZE SELECT * FROM tst ORDER BY v <-> '[1,2,3]';
));
like($explain, qr/Seq Scan/);
done_testing();

50
test/t/020_hnsw_limit.pl Normal file
View File

@@ -0,0 +1,50 @@
use strict;
use warnings;
use PostgresNode;
use TestLib;
use Test::More;
# Initialize node
my $node = get_new_node('node');
$node->init;
$node->start;
# Create table and index
$node->safe_psql("postgres", "CREATE EXTENSION vector;");
$node->safe_psql("postgres", "CREATE TABLE tst (v vector(3));");
$node->safe_psql("postgres",
"INSERT INTO tst SELECT ARRAY[random(), random(), random()] FROM generate_series(1, 1000) i;"
);
$node->safe_psql("postgres", "CREATE INDEX ON tst USING hnsw (v vector_l2_ops);");
# Test limit
my $explain = $node->safe_psql("postgres", qq(
EXPLAIN ANALYZE SELECT * FROM tst ORDER BY v <-> '[1,2,3]' LIMIT 40;
));
like($explain, qr/Index Scan/);
# Test limit + offset
$explain = $node->safe_psql("postgres", qq(
EXPLAIN ANALYZE SELECT * FROM tst ORDER BY v <-> '[1,2,3]' LIMIT 30 OFFSET 10;
));
like($explain, qr/Index Scan/);
# Test limit > ef_search
$explain = $node->safe_psql("postgres", qq(
EXPLAIN ANALYZE SELECT * FROM tst ORDER BY v <-> '[1,2,3]' LIMIT 41;
));
like($explain, qr/Seq Scan/);
# Test limit + offset > ef_search
$explain = $node->safe_psql("postgres", qq(
EXPLAIN ANALYZE SELECT * FROM tst ORDER BY v <-> '[1,2,3]' LIMIT 31 OFFSET 10;
));
like($explain, qr/Seq Scan/);
# Test no limit
$explain = $node->safe_psql("postgres", qq(
EXPLAIN ANALYZE SELECT * FROM tst ORDER BY v <-> '[1,2,3]';
));
like($explain, qr/Seq Scan/);
done_testing();