Update confict

core/predictor/framework/cache.cpp

@@ -55,7 +55,7 @@ int CubeCache::reload_data(const std::string& cache_path) {
 
   // loading data from cache files
   if (stat(cache_path.c_str(), &st) < 0 || !S_ISDIR(st.st_mode)) {
-    LOG(ERROR) << "invalid cache path " << cache_path;
+    LOG(WARNING) << "No cube cache directory " << cache_path << " provided, ignore it";
     return -1;
   }
   if ((dp = opendir(cache_path.c_str())) == nullptr) {

core/predictor/framework/server.cpp

@@ -96,6 +96,10 @@ int ServerManager::start_and_wait() {
     LOG(ERROR) << "Failed to start Paddle Inference Server";
     return -1;
   }
+
+  std::cout << "C++ Serving service started successfully!" << std::endl;
+  LOG(INFO) << "C++ Serving service started successfully!";
+
   _server.RunUntilAskedToQuit();
 
   ServerManager::stop_reloader();

python/paddle_serving_server/serve.py

@@ -233,7 +233,7 @@ def serve_args():
         "--request_cache_size",
         type=int,
         default=0,
-        help="Port of the Prometheus")
+        help="Max request cache size")
     parser.add_argument(
         "--use_dist_model",
         default=False,
@@ -274,11 +274,6 @@ def serve_args():
         default=False,
         action="store_true",
         help="The master serving of distributed inference")
-    parser.add_argument(
-        "--request_cache_size",
-        type=int,
-        default=0,
-        help="Port of the Prometheus")
     parser.add_argument(
         "--min_subgraph_size",
         type=str,