liuyu/pgvector
1
0
Fork 0
mirror of https://github.com/pgvector/pgvector.git synced 2026-07-09 22:30:58 +08:00
Code Issues Packages Projects Releases Wiki Activity

Improve total cost for cost estimation (#686)

Browse Source
This commit is contained in:
Andrew Kane
2024-10-08 12:42:03 -07:00
committed by GitHub
parent d5f4a0e435
commit 77688b4309
4 changed files with 53 additions and 42 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
test/t/017_hnsw_filtering.pl
View File

@@ -41,8 +41,7 @@ my $c = int(rand() * $nc);
my $explain = $node->safe_psql("postgres", qq(
EXPLAIN ANALYZE SELECT i FROM tst WHERE c = $c ORDER BY v <-> '$query' LIMIT $limit;
));
# TODO Do not use index
like($explain, qr/Index Scan using idx/);
like($explain, qr/Seq Scan/);
# Test attribute filtering with few rows removed
$explain = $node->safe_psql("postgres", qq(
@@ -60,8 +59,7 @@ like($explain, qr/Index Scan using idx/);
$explain = $node->safe_psql("postgres", qq(
EXPLAIN ANALYZE SELECT i FROM tst WHERE c < 1 ORDER BY v <-> '$query' LIMIT $limit;
));
# TODO Do not use index
like($explain, qr/Index Scan using idx/);
like($explain, qr/Seq Scan/);
# Test attribute filtering with few rows removed like
$explain = $node->safe_psql("postgres", qq(

13
test/t/039_hnsw_cost.pl
View File

@@ -17,12 +17,11 @@ $node->safe_psql("postgres", "CREATE EXTENSION vector;");
for my $dim (@dims)
{
my $array_sql = join(",", ('random()') x $dim);
my $n = $dim == 384 ? 3000 : 1000;
# Create table and index
$node->safe_psql("postgres", "CREATE TABLE tst (i int4, v vector($dim));");
$node->safe_psql("postgres",
"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(1, $n) i;"
"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(1, 2000) i;"
);
$node->safe_psql("postgres", "CREATE INDEX idx ON tst USING hnsw (v vector_l2_ops);");
$node->safe_psql("postgres", "ANALYZE tst;");
@@ -40,6 +39,16 @@ for my $dim (@dims)
));
like($explain, qr/Index Scan using idx/);
# 3x the rows are needed for distance filters
# since the planner uses DEFAULT_INEQ_SEL for the selectivity (should be 1)
# Recreate index for performance
$node->safe_psql("postgres", "DROP INDEX idx;");
$node->safe_psql("postgres",
"INSERT INTO tst SELECT i, ARRAY[$array_sql] FROM generate_series(2001, 6000) i;"
);
$node->safe_psql("postgres", "CREATE INDEX idx ON tst USING hnsw (v vector_l2_ops);");
$node->safe_psql("postgres", "ANALYZE tst;");
$explain = $node->safe_psql("postgres", qq(
EXPLAIN ANALYZE SELECT i FROM tst WHERE v <-> '$query' < 1 ORDER BY v <-> '$query' LIMIT $limit;
));