liuyu/pgvector
1
0
Fork 0
mirror of https://github.com/pgvector/pgvector.git synced 2026-07-11 23:26:55 +08:00
Code Issues Packages Projects Releases Wiki Activity

Added test for IVFFlat insert recall

Browse Source
This commit is contained in:
Andrew Kane
2023-09-01 00:30:02 -07:00
parent 1809ffa52b
commit 88dabaa41c
1 changed files with 117 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

117
test/t/017_ivfflat_insert_recall.pl Normal file
View File

@@ -0,0 +1,117 @@
use strict;
use warnings;
use PostgresNode;
use TestLib;
use Test::More;
my $node;
my @queries = ();
my @expected;
my $limit = 20;
sub test_recall
{
my ($probes, $min, $operator) = @_;
my $correct = 0;
my $total = 0;
my $explain = $node->safe_psql("postgres", qq(
SET enable_seqscan = off;
SET ivfflat.probes = $probes;
EXPLAIN ANALYZE SELECT i FROM tst 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;
SELECT i FROM tst ORDER BY v $operator '$queries[$i]' LIMIT $limit;
));
my @actual_ids = split("\n", $actual);
my %actual_set = map { $_ => 1 } @actual_ids;
my @expected_ids = split("\n", $expected[$i]);
foreach (@expected_ids)
{
if (exists($actual_set{$_}))
{
$correct++;
}
$total++;
}
}
cmp_ok($correct / $total, ">=", $min, $operator);
}
# Initialize node
$node = get_new_node('node');
$node->init;
$node->start;
# Create table
$node->safe_psql("postgres", "CREATE EXTENSION vector;");
$node->safe_psql("postgres", "CREATE TABLE tst (i serial, v vector(3));");
# 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_ip_ops", "vector_cosine_ops");
for my $i (0 .. $#operators)
{
my $operator = $operators[$i];
my $opclass = $opclasses[$i];
# Add index
$node->safe_psql("postgres", "CREATE INDEX idx ON tst USING ivfflat (v $opclass);");
# Use concurrent inserts
$node->pgbench(
"--no-vacuum --client=10 --transactions=1000",
0,
[qr{actually processed}],
[qr{^$}],
"concurrent INSERTs",
{
"017_ivfflat_insert_recall_$opclass" => "INSERT INTO tst (v) SELECT ARRAY[random(), random(), random()] FROM generate_series(1, 10) i;"
}
);
# Get exact results
@expected = ();
foreach (@queries)
{
my $res = $node->safe_psql("postgres", qq(
SET enable_indexscan = off;
SELECT i FROM tst ORDER BY v $operator '$_' LIMIT $limit;
));
push(@expected, $res);
}
# Test approximate results
if ($operator ne "<#>")
{
# TODO fix test
test_recall(1, 0.71, $operator);
test_recall(10, 0.95, $operator);
}
# Account for equal distances
test_recall(100, 0.9925, $operator);
$node->safe_psql("postgres", "DROP INDEX idx;");
$node->safe_psql("postgres", "TRUNCATE tst;");
}
done_testing();