From 6a9eb2e355dee728d6fdbc198bcc61310f880612 Mon Sep 17 00:00:00 2001
From: Andrew Kane <andrew@ankane.org>
Date: Sat, 20 Jan 2024 20:43:27 -0800
Subject: [PATCH] Do not use index if large % of tuples will be filtered unless
 unless enable_seqscan = off

---
 src/hnsw.c                   | 28 ++++++++++++++++++++++++++++
 test/t/018_hnsw_filtering.pl |  7 ++++++-
 2 files changed, 34 insertions(+), 1 deletion(-)

diff --git a/src/hnsw.c b/src/hnsw.c
index 1719820..9da497d 100644
--- a/src/hnsw.c
+++ b/src/hnsw.c
@@ -94,6 +94,34 @@ hnswcostestimate(PlannerInfo *root, IndexPath *path, double loop_count,
 		return;
 	}
 
+	/*
+	 * Do not use index if large % of tuples will be filtered unless
+	 * enable_seqscan = off
+	 */
+	if (list_length(path->indexinfo->indrestrictinfo) > 0)
+	{
+		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));
 
 	index = index_open(path->indexinfo->indexoid, NoLock);
diff --git a/test/t/018_hnsw_filtering.pl b/test/t/018_hnsw_filtering.pl
index 058009c..64864e4 100644
--- a/test/t/018_hnsw_filtering.pl
+++ b/test/t/018_hnsw_filtering.pl
@@ -36,7 +36,12 @@ 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/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