Skip to content
This repository has been archived by the owner on Aug 16, 2023. It is now read-only.

Modify the search list size if this value not set in struct or too small #911

Merged
merged 1 commit into from
May 29, 2023
Merged

Modify the search list size if this value not set in struct or too small #911

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
6 changes: 4 additions & 2 deletions knowhere/index/vector_index/IndexDiskANNConfig.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -219,13 +219,15 @@ to_json(Config& config, const DiskANNQueryConfig& query_conf) {
void
from_json(const Config& config, DiskANNQueryConfig& query_conf) {
CheckNumericParamAndSet<uint64_t>(config, kK, kKMinValue, kKMaxValue, query_conf.k);
if (config.contains(kSearchListSize)) {
auto search_list_threshold = query_conf.k < kKThreshold ? kKThreshold : query_conf.k;
if (config.contains(kSearchListSize) && config[kSearchListSize].get<uint32_t>() >= search_list_threshold) {
// The search_list_size should be no less than the k.
CheckNumericParamAndSet<uint32_t>(config, kSearchListSize, query_conf.k,
std::max(kSearchListSizeMaxValue, static_cast<uint32_t>(10 * query_conf.k)),
query_conf.search_list_size);
} else {
query_conf.search_list_size = query_conf.k < kKThreshold ? kKThreshold : query_conf.k;
// if search_list_size not set (==0), not in json string or smaller than k, modify the value.
query_conf.search_list_size = search_list_threshold;
}
CheckNumericParamAndSet<uint32_t>(config, kBeamwidth, kBeamwidthMinValue, kBeamwidthMaxValue, query_conf.beamwidth);
if (config.contains(kFilterThreshold)) {
Expand Down
2 changes: 1 addition & 1 deletion knowhere/index/vector_index/IndexDiskANNConfig.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -86,7 +86,7 @@ struct DiskANNQueryConfig {
uint64_t k;
// A list of search_list sizes to perform searches with. Larger parameters will result in slower latencies, but
// higher accuracies. Must be at least the value of k.
uint32_t search_list_size;
uint32_t search_list_size = 0;
// The beamwidth to be used for search. This is the maximum number of IO requests each query will issue per
// iteration of search code. Larger beamwidth will result in fewer IO round-trips per query but might result in
// slightly higher total number of IO requests to SSD per query. For the highest query throughput with a fixed SSD
Expand Down
10 changes: 7 additions & 3 deletions unittest/test_diskann.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -471,6 +471,13 @@ TEST_P(DiskANNTest, search_without_search_list_size) {
query_cfg["k"] = 32;
search_list_size = knowhere::DiskANNQueryConfig::Get(cfg).search_list_size;
EXPECT_EQ(search_list_size, 32);

knowhere::DiskANNQueryConfig tmp_config;
tmp_config.k = 10;
cfg.clear();
knowhere::DiskANNQueryConfig::Set(cfg, tmp_config);
search_list_size = knowhere::DiskANNQueryConfig::Get(cfg).search_list_size;
EXPECT_EQ(search_list_size, 16);
}

TEST_P(DiskANNTest, knn_search_test) {
Expand Down Expand Up @@ -719,9 +726,6 @@ TEST_P(DiskANNTest, config_test) {

// query config
knowhere::DiskANNQueryConfig query_conf_to_test = query_conf;
query_conf_to_test.k = 10;
query_conf_to_test.search_list_size = 9;
CheckConfigError<knowhere::DiskANNQueryConfig>(query_conf_to_test);

query_conf_to_test = query_conf;
query_conf_to_test.beamwidth = 0;
Expand Down