Add threading_performance_report.md

src/http_handler.hpp

@@ -67,9 +67,9 @@ struct HttpHandler : ConnectionHandler {
     for (int threadId = 0; threadId < kFinalStageThreads; ++threadId) {
       finalStageThreads.emplace_back([this, threadId]() {
         pthread_setname_np(pthread_self(),
-                           ("stage-0-" + std::to_string(threadId)).c_str());
+                           ("stage-1-" + std::to_string(threadId)).c_str());
         for (;;) {
-          auto guard = pipeline.acquire(0, threadId);
+          auto guard = pipeline.acquire(1, threadId);
           for (auto it = guard.batch.begin(); it != guard.batch.end(); ++it) {
             if ((it.index() % kFinalStageThreads) == threadId) {
               auto &c = *it;
@@ -85,6 +85,20 @@ struct HttpHandler : ConnectionHandler {
         }
       });
     }
+    stage0Thread = std::thread{[this]() {
+      pthread_setname_np(pthread_self(), "stage-0");
+      for (;;) {
+        auto guard = pipeline.acquire(0, 0, 0, false);
+        for (auto it = guard.batch.begin(); it != guard.batch.end(); ++it) {
+          auto &c = *it;
+          if (!c) {
+            return;
+          }
+          for (volatile int i = 0; i < 1200; i = i + 1)
+            ;
+        }
+      }
+    }};
   }
   ~HttpHandler() {
     {
@@ -93,6 +107,7 @@ struct HttpHandler : ConnectionHandler {
         c = {};
       }
     }
+    stage0Thread.join();
     for (auto &thread : finalStageThreads) {
       thread.join();
     }
@@ -122,8 +137,9 @@ struct HttpHandler : ConnectionHandler {
 private:
   static constexpr int kFinalStageThreads = 2;
   static constexpr int kLogSize = 12;
-  ThreadPipeline<std::unique_ptr<Connection>> pipeline{kLogSize,
-                                                       {kFinalStageThreads}};
+  ThreadPipeline<std::unique_ptr<Connection>> pipeline{
+      kLogSize, {/*noop serial thread*/ 1, kFinalStageThreads}};
+  std::thread stage0Thread;
   std::vector<std::thread> finalStageThreads;
 
   // Route handlers