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

Signed-off-by: cqy123456 <[email protected]>

Author: cqy123456

knowhere/index/vector_index/IndexDiskANNConfig.cpp

@@ -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)) {

knowhere/index/vector_index/IndexDiskANNConfig.h

@@ -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

unittest/test_diskann.cpp

@@ -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) {
@@ -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;