add timeout for gunicorn (#733)

paddlehub/commands/serving.py

@@ -27,8 +27,6 @@ from paddlehub.commands.base_command import BaseCommand, ENTRY
 from paddlehub.serving import app_single as app
 from paddlehub.common.dir import CONF_HOME
 from paddlehub.common.hub_server import CacheUpdater
-from paddlehub.serving.model_service.base_model_service import cv_module_info
-from paddlehub.serving.model_service.base_model_service import nlp_module_info
 import multiprocessing
 import time
 import signal
@@ -232,7 +230,8 @@ class ServingCommand(BaseCommand):
         options = {
             "bind": "0.0.0.0:%s" % port,
             "workers": self.args.workers,
-            "pid": "./pid.txt"
+            "pid": "./pid.txt",
+            "timeout": self.args.config.get('timeout', 30)
         }
         self.dump_pid_file()
         StandaloneApplication(
@@ -250,18 +249,6 @@ class ServingCommand(BaseCommand):
         self.dump_pid_file()
         app.run(configs=self.modules_info, port=port)
 
-    @staticmethod
-    def start_multi_app_with_file(configs):
-        port = configs.get("port", 8866)
-        if ServingCommand.is_port_occupied("127.0.0.1", port) is True:
-            print("Port %s is occupied, please change it." % port)
-            return False
-        workers = configs.get("workers", number_of_workers())
-        options = {"bind": "0.0.0.0:%s" % port, "workers": workers}
-        StandaloneApplication(
-            app.create_app(init_flag=False, configs=configs), options).run()
-        print("PaddleHub Serving has been stopped.")
-
     def start_app_with_args(self, workers):
         module = self.args.modules
         if module is not None:

paddlehub/serving/app_single.py

@@ -28,24 +28,6 @@ def gen_result(status, msg, data):
     return {"status": status, "msg": msg, "results": data}
 
 
-def predict_v2(module_info, input):
-    serving_method_name = module_info["method_name"]
-    serving_method = getattr(module_info["module"], serving_method_name)
-    predict_args = module_info["predict_args"].copy()
-    predict_args.update({"data": input})
-
-    for item in serving_method.__code__.co_varnames:
-        if item in module_info.keys():
-            predict_args.update({item: module_info[item]})
-    try:
-        output = serving_method(**predict_args)
-    except Exception as err:
-        curr = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(time.time()))
-        print(curr, " - ", err)
-        return gen_result("-1", "Please check data format!", "")
-    return gen_result("0", "", output)
-
-
 def predict_v2_advanced(module_info, input):
     serving_method_name = module_info["method_name"]
     serving_method = getattr(module_info["module"], serving_method_name)

paddlehub/serving/templates/serving_config.json

@@ -21,6 +21,7 @@
     }
   },
   "port": 8866,
-  "use_multiprocess": false,
-  "workers": 2
+  "use_multiprocess": true,
+  "workers": 2,
+  "timeout": 30
 }