Added HNSW index type - #181

test/expected/hnsw_cosine.out

@@ -0,0 +1,26 @@
+SET enable_seqscan = off;
+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_cosine_ops);
+INSERT INTO t (val) VALUES ('[1,2,4]');
+SELECT * FROM t ORDER BY val <=> '[3,3,3]';
+   val   
+---------
+ [1,1,1]
+ [1,2,3]
+ [1,2,4]
+(3 rows)
+
+SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <=> '[0,0,0]') t2;
+ count 
+-------
+     3
+(1 row)
+
+SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <=> (SELECT NULL::vector)) t2;
+ count 
+-------
+     3
+(1 row)
+
+DROP TABLE t;

test/expected/hnsw_ip.out

@@ -0,0 +1,21 @@
+SET enable_seqscan = off;
+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_ip_ops);
+INSERT INTO t (val) VALUES ('[1,2,4]');
+SELECT * FROM t ORDER BY val <#> '[3,3,3]';
+   val   
+---------
+ [1,2,4]
+ [1,2,3]
+ [1,1,1]
+ [0,0,0]
+(4 rows)
+
+SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <#> (SELECT NULL::vector)) t2;
+ count 
+-------
+     4
+(1 row)
+
+DROP TABLE t;

test/expected/hnsw_l2.out

@@ -0,0 +1,30 @@
+SET enable_seqscan = off;
+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);
+INSERT INTO t (val) VALUES ('[1,2,4]');
+SELECT * FROM t ORDER BY val <-> '[3,3,3]';
+   val   
+---------
+ [1,2,3]
+ [1,2,4]
+ [1,1,1]
+ [0,0,0]
+(4 rows)
+
+SELECT * FROM t ORDER BY val <-> (SELECT NULL::vector);
+   val   
+---------
+ [0,0,0]
+ [1,1,1]
+ [1,2,3]
+ [1,2,4]
+(4 rows)
+
+SELECT COUNT(*) FROM t;
+ count 
+-------
+     5
+(1 row)
+
+DROP TABLE t;

test/expected/hnsw_options.out

@@ -0,0 +1,25 @@
+SET enable_seqscan = off;
+CREATE TABLE t (val vector(3));
+CREATE INDEX ON t USING hnsw (val vector_l2_ops) WITH (m = 3);
+ERROR:  value 3 out of bounds for option "m"
+DETAIL:  Valid values are between "4" and "100".
+CREATE INDEX ON t USING hnsw (val vector_l2_ops) WITH (m = 101);
+ERROR:  value 101 out of bounds for option "m"
+DETAIL:  Valid values are between "4" and "100".
+CREATE INDEX ON t USING hnsw (val vector_l2_ops) WITH (ef_construction = 9);
+ERROR:  value 9 out of bounds for option "ef_construction"
+DETAIL:  Valid values are between "10" and "1000".
+CREATE INDEX ON t USING hnsw (val vector_l2_ops) WITH (ef_construction = 1001);
+ERROR:  value 1001 out of bounds for option "ef_construction"
+DETAIL:  Valid values are between "10" and "1000".
+SHOW hnsw.ef_search;
+ hnsw.ef_search 
+----------------
+ 40
+(1 row)
+
+SET hnsw.ef_search = 9;
+ERROR:  9 is outside the valid range for parameter "hnsw.ef_search" (10 .. 1000)
+SET hnsw.ef_search = 1001;
+ERROR:  1001 is outside the valid range for parameter "hnsw.ef_search" (10 .. 1000)
+DROP TABLE t;

test/expected/hnsw_unlogged.out

@@ -0,0 +1,13 @@
+SET enable_seqscan = off;
+CREATE UNLOGGED 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);
+SELECT * FROM t ORDER BY val <-> '[3,3,3]';
+   val   
+---------
+ [1,2,3]
+ [1,1,1]
+ [0,0,0]
+(3 rows)
+
+DROP TABLE t;

test/sql/hnsw_cosine.sql

@@ -0,0 +1,13 @@
+SET enable_seqscan = off;
+
+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_cosine_ops);
+
+INSERT INTO t (val) VALUES ('[1,2,4]');
+
+SELECT * FROM t ORDER BY val <=> '[3,3,3]';
+SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <=> '[0,0,0]') t2;
+SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <=> (SELECT NULL::vector)) t2;
+
+DROP TABLE t;

test/sql/hnsw_ip.sql

@@ -0,0 +1,12 @@
+SET enable_seqscan = off;
+
+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_ip_ops);
+
+INSERT INTO t (val) VALUES ('[1,2,4]');
+
+SELECT * FROM t ORDER BY val <#> '[3,3,3]';
+SELECT COUNT(*) FROM (SELECT * FROM t ORDER BY val <#> (SELECT NULL::vector)) t2;
+
+DROP TABLE t;

test/sql/hnsw_l2.sql

@@ -0,0 +1,13 @@
+SET enable_seqscan = off;
+
+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);
+
+INSERT INTO t (val) VALUES ('[1,2,4]');
+
+SELECT * FROM t ORDER BY val <-> '[3,3,3]';
+SELECT * FROM t ORDER BY val <-> (SELECT NULL::vector);
+SELECT COUNT(*) FROM t;
+
+DROP TABLE t;

test/sql/hnsw_options.sql

@@ -0,0 +1,14 @@
+SET enable_seqscan = off;
+
+CREATE TABLE t (val vector(3));
+CREATE INDEX ON t USING hnsw (val vector_l2_ops) WITH (m = 3);
+CREATE INDEX ON t USING hnsw (val vector_l2_ops) WITH (m = 101);
+CREATE INDEX ON t USING hnsw (val vector_l2_ops) WITH (ef_construction = 9);
+CREATE INDEX ON t USING hnsw (val vector_l2_ops) WITH (ef_construction = 1001);
+
+SHOW hnsw.ef_search;
+
+SET hnsw.ef_search = 9;
+SET hnsw.ef_search = 1001;
+
+DROP TABLE t;

test/sql/hnsw_unlogged.sql

@@ -0,0 +1,9 @@
+SET enable_seqscan = off;
+
+CREATE UNLOGGED 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);
+
+SELECT * FROM t ORDER BY val <-> '[3,3,3]';
+
+DROP TABLE t;

test/t/010_hnsw_wal.pl

@@ -0,0 +1,99 @@
+# Based on postgres/contrib/bloom/t/001_wal.pl
+
+# Test generic xlog record work for hnsw index replication.
+use strict;
+use warnings;
+use PostgresNode;
+use TestLib;
+use Test::More;
+
+my $dim = 32;
+
+my $node_primary;
+my $node_replica;
+
+# Run few queries on both primary and replica and check their results match.
+sub test_index_replay
+{
+	my ($test_name) = @_;
+
+	# Wait for replica to catch up
+	my $applname = $node_replica->name;
+
+	my $server_version_num = $node_primary->safe_psql("postgres", "SHOW server_version_num");
+	my $caughtup_query = "SELECT pg_current_wal_lsn() <= replay_lsn FROM pg_stat_replication WHERE application_name = '$applname';";
+	$node_primary->poll_query_until('postgres', $caughtup_query)
+	  or die "Timed out while waiting for replica 1 to catch up";
+
+	my @r = ();
+	for (1 .. $dim) {
+		push(@r, rand());
+	}
+	my $sql = join(",", @r);
+
+	my $queries = qq(
+		SET enable_seqscan = off;
+		SELECT * FROM tst ORDER BY v <-> '[$sql]' LIMIT 10;
+	);
+
+	# Run test queries and compare their result
+	my $primary_result = $node_primary->safe_psql("postgres", $queries);
+	my $replica_result = $node_replica->safe_psql("postgres", $queries);
+
+	is($primary_result, $replica_result, "$test_name: query result matches");
+	return;
+}
+
+# Use ARRAY[random(), random(), random(), ...] over
+# SELECT array_agg(random()) FROM generate_series(1, $dim)
+# to generate different values for each row
+my $array_sql = join(",", ('random()') x $dim);
+
+# Initialize primary node
+$node_primary = get_new_node('primary');
+$node_primary->init(allows_streaming => 1);
+if ($dim > 32) {
+	# TODO use wal_keep_segments for Postgres < 13
+	$node_primary->append_conf('postgresql.conf', qq(wal_keep_size = 1GB));
+}
+if ($dim > 1500) {
+	$node_primary->append_conf('postgresql.conf', qq(maintenance_work_mem = 128MB));
+}
+$node_primary->start;
+my $backup_name = 'my_backup';
+
+# Take backup
+$node_primary->backup($backup_name);
+
+# Create streaming replica linking to primary
+$node_replica = get_new_node('replica');
+$node_replica->init_from_backup($node_primary, $backup_name,
+	has_streaming => 1);
+$node_replica->start;
+
+# Create hnsw index on primary
+$node_primary->safe_psql("postgres", "CREATE EXTENSION vector;");
+$node_primary->safe_psql("postgres", "CREATE TABLE tst (i int4, v vector($dim));");
+$node_primary->safe_psql("postgres",
+	"INSERT INTO tst SELECT i % 10, ARRAY[$array_sql] FROM generate_series(1, 1000) i;"
+);
+$node_primary->safe_psql("postgres", "CREATE INDEX ON tst USING hnsw (v vector_l2_ops);");
+
+# Test that queries give same result
+test_index_replay('initial');
+
+# Run 10 cycles of table modification. Run test queries after each modification.
+for my $i (1 .. 10)
+{
+	$node_primary->safe_psql("postgres", "DELETE FROM tst WHERE i = $i;");
+	test_index_replay("delete $i");
+	$node_primary->safe_psql("postgres", "VACUUM tst;");
+	test_index_replay("vacuum $i");
+	my ($start, $end) = (1001 + ($i - 1) * 100, 1000 + $i * 100);
+	$node_primary->safe_psql("postgres",
+		"INSERT INTO tst SELECT i % 10, ARRAY[$array_sql] FROM generate_series($start, $end) i;"
+	);
+	test_index_replay("insert $i");
+}
+
+done_testing();

test/t/011_hnsw_vacuum.pl

@@ -0,0 +1,43 @@
+use strict;
+use warnings;
+use PostgresNode;
+use TestLib;
+use Test::More;
+
+my $dim = 3;
+
+my @r = ();
+for (1 .. $dim) {
+	my $v = int(rand(1000)) + 1;
+	push(@r, "i % $v");
+}
+my $array_sql = join(", ", @r);
+
+# Initialize node
+my $node = get_new_node('node');
+$node->init;
+$node->start;
+
+# Create table and index
+$node->safe_psql("postgres", "CREATE EXTENSION vector;");
+$node->safe_psql("postgres", "CREATE TABLE tst (i int4, v vector($dim));");
+$node->safe_psql("postgres",
+	"INSERT INTO tst SELECT i % 10, ARRAY[$array_sql] FROM generate_series(1, 10000) i;"
+);
+$node->safe_psql("postgres", "CREATE INDEX ON tst USING hnsw (v vector_l2_ops);");
+
+# Get size
+my $size = $node->safe_psql("postgres", "SELECT pg_total_relation_size('tst_v_idx');");
+
+# Delete all, vacuum, and insert same data
+$node->safe_psql("postgres", "DELETE FROM tst;");
+$node->safe_psql("postgres", "VACUUM tst;");
+$node->safe_psql("postgres",
+	"INSERT INTO tst SELECT i % 10, ARRAY[$array_sql] FROM generate_series(1, 10000) i;"
+);
+
+# Check size
+my $new_size = $node->safe_psql("postgres", "SELECT pg_total_relation_size('tst_v_idx');");
+cmp_ok($new_size, "<=", $size * 1.01, "size does not increase too much");
+
+done_testing();

test/t/012_hnsw_build_recall.pl

@@ -0,0 +1,96 @@
+use strict;
+use warnings;
+use PostgresNode;
+use TestLib;
+use Test::More;
+
+my $node;
+my @queries = ();
+my @expected;
+my $limit = 20;
+
+sub test_recall
+{
+	my ($min, $operator) = @_;
+	my $correct = 0;
+	my $total = 0;
+
+	my $explain = $node->safe_psql("postgres", qq(
+		SET enable_seqscan = off;
+		EXPLAIN ANALYZE SELECT i FROM tst ORDER BY v $operator '$queries[0]' LIMIT $limit;
+	));
+	like($explain, qr/Index Scan/);
+
+	for my $i (0 .. $#queries) {
+		my $actual = $node->safe_psql("postgres", qq(
+			SET enable_seqscan = off;
+			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 int4, v vector(3));");
+$node->safe_psql("postgres",
+	"INSERT INTO tst SELECT i, ARRAY[random(), random(), random()] FROM generate_series(1, 10000) 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 = ("<->", "<#>", "<=>");
+
+foreach (@operators) {
+	my $operator = $_;
+
+	# Get exact results
+	@expected = ();
+	foreach (@queries) {
+		my $res = $node->safe_psql("postgres", "SELECT i FROM tst ORDER BY v $operator '$_' LIMIT $limit;");
+		push(@expected, $res);
+	}
+
+	# Add index
+	my $opclass;
+	if ($operator eq "<->") {
+		$opclass = "vector_l2_ops";
+	} elsif ($operator eq "<#>") {
+		$opclass = "vector_ip_ops";
+	} else {
+		$opclass = "vector_cosine_ops";
+	}
+	$node->safe_psql("postgres", "CREATE INDEX ON tst USING hnsw (v $opclass);");
+
+	if ($operator eq "<#>") {
+		test_recall(0.80, $operator);
+	} else {
+		test_recall(0.99, $operator);
+	}
+}
+
+done_testing();

test/t/013_hnsw_insert_recall.pl

@@ -0,0 +1,103 @@
+use strict;
+use warnings;
+use PostgresNode;
+use TestLib;
+use Test::More;
+
+my $node;
+my @queries = ();
+my @expected;
+my $limit = 20;
+
+sub test_recall
+{
+	my ($min, $operator) = @_;
+	my $correct = 0;
+	my $total = 0;
+
+	my $explain = $node->safe_psql("postgres", qq(
+		SET enable_seqscan = off;
+		EXPLAIN ANALYZE SELECT i FROM tst ORDER BY v $operator '$queries[0]' LIMIT $limit;
+	));
+	like($explain, qr/Index Scan/);
+
+	for my $i (0 .. $#queries) {
+		my $actual = $node->safe_psql("postgres", qq(
+			SET enable_seqscan = off;
+			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 int4, 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 = ("<->", "<#>", "<=>");
+
+foreach (@operators) {
+	my $operator = $_;
+
+	# Add index
+	my $opclass;
+	if ($operator eq "<->") {
+		$opclass = "vector_l2_ops";
+	} elsif ($operator eq "<#>") {
+		$opclass = "vector_ip_ops";
+	} else {
+		$opclass = "vector_cosine_ops";
+	}
+	$node->safe_psql("postgres", "CREATE INDEX idx ON tst USING hnsw (v $opclass);");
+
+	$node->safe_psql("postgres",
+		"INSERT INTO tst SELECT i, ARRAY[random(), random(), random()] FROM generate_series(1, 10000) 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, $res);
+	}
+
+	if ($operator eq "<#>") {
+		test_recall(0.80, $operator);
+	} else {
+		test_recall(0.99, $operator);
+	}
+
+	$node->safe_psql("postgres", "DROP INDEX idx;");
+	$node->safe_psql("postgres", "TRUNCATE tst;");
+}
+
+done_testing();

test/t/014_hnsw_inserts.pl

@@ -0,0 +1,58 @@
+use strict;
+use warnings;
+use PostgresNode;
+use TestLib;
+use Test::More;
+
+# Ensures elements and neighbors on both same and different pages
+my $dim = 1900;
+
+my $array_sql = join(",", ('random()') x $dim);
+
+# Initialize node
+my $node = get_new_node('node');
+$node->init;
+$node->start;
+
+# Create table and index
+$node->safe_psql("postgres", "CREATE EXTENSION vector;");
+$node->safe_psql("postgres", "CREATE TABLE tst (v vector($dim));");
+$node->safe_psql("postgres",
+	"INSERT INTO tst SELECT ARRAY[$array_sql] FROM generate_series(1, 100) i;"
+);
+$node->safe_psql("postgres", "CREATE INDEX ON tst USING hnsw (v vector_l2_ops);");
+
+$node->pgbench(
+	"--no-vacuum --client=5 --transactions=100",
+	0,
+	[qr{actually processed}],
+	[qr{^$}],
+	"concurrent INSERTs",
+	{
+		"007_inserts" => "INSERT INTO tst SELECT ARRAY[$array_sql] FROM generate_series(1, 10) i;"
+	}
+);
+
+sub idx_scan
+{
+	# Stats do not update instantaneously
+	# https://www.postgresql.org/docs/current/monitoring-stats.html#MONITORING-STATS-VIEWS
+	sleep(1);
+	$node->safe_psql("postgres", "SELECT idx_scan FROM pg_stat_user_indexes WHERE indexrelid = 'tst_v_idx'::regclass;");
+}
+
+my $expected = 100 + 5 * 100 * 10;
+
+my $count = $node->safe_psql("postgres", "SELECT COUNT(*) FROM tst;");
+is($count, $expected);
+is(idx_scan(), 0);
+
+$count = $node->safe_psql("postgres", qq(
+	SET enable_seqscan = off;
+	SET hnsw.ef_search = 400;
+	SELECT COUNT(*) FROM (SELECT v FROM tst ORDER BY v <-> (SELECT v FROM tst LIMIT 1)) t;
+));
+is($count, 400);
+is(idx_scan(), 1);
+
+done_testing();