Do not use index if large % of tuples will be filtered unless unless enable_seqscan = off

src/hnsw.c

@@ -95,17 +95,31 @@ hnswcostestimate(PlannerInfo *root, IndexPath *path, double loop_count,
 	}
 
 	/*
-	 * Do not use index if no limit or limit + offset > ef_search unless
+	 * Do not use index if large % of tuples will be filtered unless
 	 * enable_seqscan = off
 	 */
-	if (root->limit_tuples < 0 || root->limit_tuples > hnsw_ef_search)
+	if (list_length(path->indexinfo->indrestrictinfo) > 0)
 	{
-		*indexStartupCost = 1.0e10 - 1;
-		*indexTotalCost = 1.0e10 - 1;
-		*indexSelectivity = 0;
-		*indexCorrelation = 0;
-		*indexPages = 0;
-		return;
+		double		selectivity = 1;
+		ListCell   *lc;
+
+		foreach(lc, path->indexinfo->indrestrictinfo)
+		{
+			RestrictInfo *rinfo = lfirst(lc);
+
+			if (rinfo->norm_selec >= 0 && rinfo->norm_selec <= 1)
+				selectivity *= rinfo->norm_selec;
+		}
+
+		if (selectivity < 0.1)
+		{
+			*indexStartupCost = 1.0e10 - 1;
+			*indexTotalCost = 1.0e10 - 1;
+			*indexSelectivity = 0;
+			*indexCorrelation = 0;
+			*indexPages = 0;
+			return;
+		}
 	}
 
 	MemSet(&costs, 0, sizeof(costs));

src/ivfflat.c

@@ -105,20 +105,6 @@ ivfflatcostestimate(PlannerInfo *root, IndexPath *path, double loop_count,
 	 */
 	costs.numIndexTuples = path->indexinfo->tuples * ratio;
 
-	/*
-	 * Do not use index if no limit or limit + offset > expected tuples unless
-	 * enable_seqscan = off
-	 */
-	if (root->limit_tuples < 0 || root->limit_tuples > costs.numIndexTuples)
-	{
-		*indexStartupCost = 1.0e10 - 1;
-		*indexTotalCost = 1.0e10 - 1;
-		*indexSelectivity = 0;
-		*indexCorrelation = 0;
-		*indexPages = 0;
-		return;
-	}
-
 #if PG_VERSION_NUM >= 120000
 	genericcostestimate(root, path, loop_count, &costs);
 #else

test/t/018_hnsw_filtering.pl

@@ -0,0 +1,79 @@
+use strict;
+use warnings;
+use PostgresNode;
+use TestLib;
+use Test::More;
+
+my $dim = 3;
+my $nc = 50;
+my $limit = 20;
+
+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;");
+$node->safe_psql("postgres", "CREATE TABLE tst (i int4, v vector($dim), c int4);");
+$node->safe_psql("postgres",
+	"INSERT INTO tst SELECT i, ARRAY[$array_sql], i % $nc FROM generate_series(1, 10000) i;"
+);
+$node->safe_psql("postgres", "CREATE INDEX idx ON tst USING hnsw (v vector_l2_ops);");
+
+# Generate query
+my @r = ();
+for (1 .. $dim)
+{
+	push(@r, rand());
+}
+my $query = "[" . join(",", @r) . "]";
+my $c = int(rand() * $nc);
+
+# Test attribute filtering
+my $explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE c = $c ORDER BY v <-> '$query' LIMIT $limit;
+));
+like($explain, qr/Seq Scan/);
+
+# Test attribute filtering with few rows removed
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE c != $c ORDER BY v <-> '$query' LIMIT $limit;
+));
+like($explain, qr/Index Scan using idx/);
+
+# Test distance filtering
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE v <-> '$query' < 1 ORDER BY v <-> '$query' LIMIT $limit;
+));
+like($explain, qr/Index Scan using idx/);
+
+# Test distance filtering without order
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE v <-> '$query' < 1;
+));
+like($explain, qr/Seq Scan/);
+
+# Test distance filtering without limit
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE v <-> '$query' < 1 ORDER BY v <-> '$query';
+));
+like($explain, qr/Seq Scan/);
+
+# Test attribute index
+$node->safe_psql("postgres", "CREATE INDEX attribute_idx ON tst (c);");
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE c = $c ORDER BY v <-> '$query' LIMIT $limit;
+));
+like($explain, qr/Bitmap Index Scan on attribute_idx/);
+
+# Test partial index
+$node->safe_psql("postgres", "CREATE INDEX partial_idx ON tst USING hnsw (v vector_l2_ops) WHERE (c = $c);");
+$explain = $node->safe_psql("postgres", qq(
+	EXPLAIN ANALYZE SELECT i FROM tst WHERE c = $c ORDER BY v <-> '$query' LIMIT $limit;
+));
+like($explain, qr/Index Scan using partial_idx/);
+
+done_testing();

test/t/019_ivfflat_limit.pl

@@ -1,64 +0,0 @@
-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 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 + 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 > 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 > 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 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 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();

test/t/020_hnsw_limit.pl

@@ -1,62 +0,0 @@
-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 with CTE
-$explain = $node->safe_psql("postgres", qq(
-	EXPLAIN ANALYZE WITH cte AS (SELECT * FROM tst ORDER BY v <-> '[1,2,3]' LIMIT 40) SELECT * FROM cte;
-));
-like($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 > ef_search with CTE
-$explain = $node->safe_psql("postgres", qq(
-	EXPLAIN ANALYZE WITH cte AS (SELECT * FROM tst ORDER BY v <-> '[1,2,3]' LIMIT 41) SELECT * FROM cte;
-));
-like($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();