Skip to content

fix: guard HNSW prefetches against empty neighbor lists #1320

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
bluayer wants to merge 2 commits into
base: main
Choose a base branch
from
+29 −2
Open

fix: guard HNSW prefetches against empty neighbor lists #1320

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8be3f77
fix: invalid prefetch
bluayer Aug 25, 2026
dc197b7
fix: HNSW test level metadata consistency
bluayer Aug 25, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
26 changes: 26 additions & 0 deletions testing/vector_test.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1295,6 +1295,32 @@ TEST_F(VectorIndexTest, HnswAddPointReplaceDeletedDoesNotDuplicateLabel) {
EXPECT_FALSE(algo.isMarkedDeleted(1));
}

TEST_F(VectorIndexTest, HnswHandlesEmptyNeighborLists) {
hnswlib::L2Space space{1};
VectorHNSW<float>::HNSWIndex algo(
&space, /*max_elements=*/2, /*normalized=*/false, /*m_value=*/2,
/*ef_construction=*/10, /*allow_replace_deleted=*/false);
auto query = [](float value) {
absl::string_view bytes(reinterpret_cast<const char *>(&value),
sizeof(value));
return QueryVector(VectorRecord::Construct(bytes, kDefaultMagnitude),
bytes.size(), false);
};
auto entry = query(0.0f);
auto point = query(1.0f);
auto update = query(2.0f);
algo.addPoint(std::move(entry), 0, 2);
auto *links = algo.get_linklist_at_level(0, 0);
algo.setListCount(links, 0);
reinterpret_cast<hnswlib::tableint *>(links + 1)[0] = algo.max_elements_;
EXPECT_NO_THROW(algo.searchBaseLayer(0, point, 0));
algo.addPoint(std::move(point), 1, 1);
links = algo.get_linklist_at_level(0, 2);
algo.setListCount(links, 0);
reinterpret_cast<hnswlib::tableint *>(links + 1)[0] = algo.max_elements_;
EXPECT_NO_THROW(algo.updatePoint(std::move(update), 1, 1.0));
}

// ---- Happy path ----------------------------------------------------------
TEST_F(VectorIndexTest, LoadValidatesEmptyIndex) {
auto golden = BuildGoldenChunks({}, kGoldenMax);
Expand Down
5 changes: 3 additions & 2 deletions third_party/hnswlib/hnswalg.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -347,9 +347,9 @@ class HierarchicalNSW
size_t size = getListCount((linklistsizeint *)data);
tableint *datal = (tableint *)(data + 1);
#ifdef USE_PREFETCH
__builtin_prefetch((char *)(visited_array + *(data + 1)), 0, 3);
__builtin_prefetch((char *)(visited_array + *(data + 1) + 64), 0, 3);
if (size > 0) {
__builtin_prefetch((char *)(visited_array + *datal), 0, 3);
__builtin_prefetch((char *)(visited_array + *datal + 64), 0, 3);
__builtin_prefetch(GetDataByInternalId(*datal)->GetRawVector(), 0, 3);
}
if (size > 1) {
Expand Down Expand Up @@ -1516,6 +1516,7 @@ class HierarchicalNSW
std::unique_lock<std::mutex> lock(link_list_locks_[currObj]);
data = get_linklist_at_level(currObj, level);
int size = getListCount(data);
if (size == 0) break;
tableint *datal = (tableint *)(data + 1);
#ifdef USE_PREFETCH
__builtin_prefetch(GetDataByInternalId(*datal)->GetRawVector(), 0, 3);
Expand Down
Loading