perf(search): share a thread-local RNG for HNSW and drop seed (#2398)

src/search/hnsw_indexer.cc

@@ -173,16 +173,19 @@ StatusOr<double> ComputeSimilarity(const VectorItem& left, const VectorItem& rig
 }
 
 HnswIndex::HnswIndex(const SearchKey& search_key, HnswVectorFieldMetadata* vector, engine::Storage* storage,
-                     std::random_device::result_type seed)
+                     std::optional<std::random_device::result_type> seed)
     : search_key(search_key),
       metadata(vector),
       storage(storage),
-      generator(std::mt19937(seed)),
+      seed(seed),
       m_level_normalization_factor(1.0 / std::log(metadata->m)) {}
 
 uint16_t HnswIndex::RandomizeLayer() {
+  if (!generator) {
+    generator = std::make_unique<std::mt19937>(seed.value_or(std::random_device()()));
+  }
   std::uniform_real_distribution<double> level_dist(0.0, 1.0);
-  double r = level_dist(generator);
+  double r = level_dist(*generator);
   double log_val = -std::log(r);
   double layer_val = log_val * m_level_normalization_factor;
   return static_cast<uint16_t>(std::floor(layer_val));

src/search/hnsw_indexer.h

@@ -20,6 +20,8 @@
 
 #pragma once
 
+#include <memory>
+#include <optional>
 #include <random>
 #include <string>
 #include <vector>
@@ -89,11 +91,12 @@ struct HnswIndex {
   HnswVectorFieldMetadata* metadata;
   engine::Storage* storage = nullptr;
 
-  std::mt19937 generator;
+  std::optional<std::random_device::result_type> seed;
+  std::unique_ptr<std::mt19937> generator;
   double m_level_normalization_factor;
 
   HnswIndex(const SearchKey& search_key, HnswVectorFieldMetadata* vector, engine::Storage* storage,
-            std::random_device::result_type seed = std::random_device()());
+            std::optional<std::random_device::result_type> seed = std::nullopt);
 
   static StatusOr<std::vector<VectorItem>> DecodeNodesToVectorItems(engine::Context& ctx,
                                                                     const std::vector<NodeKey>& node_key,

tests/cppunit/hnsw_index_test.cc

@@ -118,6 +118,12 @@ TEST_F(HnswIndexTest, ComputeSimilarity) {
   hnsw_index->metadata->distance_metric = redis::DistanceMetric::L2;
 }
 
+TEST_F(HnswIndexTest, RandomGeneratorIsInitializedLazily) {
+  EXPECT_FALSE(hnsw_index->generator);
+  hnsw_index->RandomizeLayer();
+  EXPECT_TRUE(hnsw_index->generator);
+}
+
 TEST_F(HnswIndexTest, RandomizeLayer) {
   constexpr size_t kSampleSize = 50000;