Python多处理池无法装饰

Question

我试图基于多处理池编写装饰，但它不起作用，无法捕获异常，请显示我的代码：

def handle_request(response):
    print str(response)
def run_in_process(process_num):
    def _run_in_process(f):
        def __run_in_process(*args, **kwargs):
            pool = multiprocessing.Pool(processes=process_num)
            for i in range(process_num):
                pool.apply_async(f, args=args, kwds=kwargs, callback=kwargs.get("callback"))
            pool.close()
            pool.join()
        return __run_in_process
    return _run_in_process

@run_in_process(process_num)
def main():
    http_client = AsyncHTTPClient()
    http_client.fetch(url, callback=handle_request)
    global loop
    loop = tornado.ioloop.IOLoop.instance()
    if loop._running is False:
        loop.start()

if __name__ == '__main__':
    main()

显示我的日志：

/usr/bin/python2.7 /home/workspace/py_project/crawler/center/sample.py
Process finished with exit code 0

但是，当我改变自己的方式时，当我使用多处理时，它效果很好，就像：

def handle_request(response):
    print str(response)
def run_in_process(process_num):
    def _run_in_process(f):
        def __run_in_process(*args, **kwargs):
            _processes = []
            for i in xrange(process_num):
                p = multiprocessing.Process(target=f, args=args, kwargs=kwargs)
                p.start()
                _processes.append(p)
            for p in _processes:
                p.join()
        return __run_in_process
    return _run_in_process

@run_in_process(process_num)
def main():
    http_client = AsyncHTTPClient()
    http_client.fetch(url, callback=handle_request)
    global loop
    loop = tornado.ioloop.IOLoop.instance()
    if loop._running is False:
        loop.start()

if __name__ == '__main__':
    main()

显示我的日志：

/usr/bin/python2.7 /home/workspace/py_project/crawler/center/sample.py
HTTPResponse(_body=None,buffer=<_io.BytesIO object at 0x7f2fdaa21ef0>,code=200,effective_url='http://www.baidu.com',error=None,headers=<tornado.httputil.HTTPHeaders object at 0x7f2fdaa425d0>,reason='OK',request=<tornado.httpclient.HTTPRequest object at 0x7f2fdaa42250>,request_time=0.014312028884887695,time_info={})
HTTPResponse(_body=None,buffer=<_io.BytesIO object at 0x7f2fdaa21ef0>,code=200,effective_url='http://www.baidu.com',error=None,headers=<tornado.httputil.HTTPHeaders object at 0x7f2fdaa43450>,reason='OK',request=<tornado.httpclient.HTTPRequest object at 0x7f2fdaa430d0>,request_time=0.02327895164489746,time_info={})
HTTPResponse(_body=None,buffer=<_io.BytesIO object at 0x7f2fdaa21ef0>,code=200,effective_url='http://www.baidu.com',error=None,headers=<tornado.httputil.HTTPHeaders object at 0x7f2fdaa43510>,reason='OK',request=<tornado.httpclient.HTTPRequest object at 0x7f2fdaa43190>,request_time=0.026951074600219727,time_info={})
HTTPResponse(_body=None,buffer=<_io.BytesIO object at 0x7f2fdaa21ef0>,code=200,effective_url='http://www.baidu.com',error=None,headers=<tornado.httputil.HTTPHeaders object at 0x7f2fdaa42690>,reason='OK',request=<tornado.httpclient.HTTPRequest object at 0x7f2fdaa42310>,request_time=0.0552978515625,time_info={})
HTTPResponse(_body=None,buffer=<_io.BytesIO object at 0x7f2fdaa24ef0>,code=200,effective_url='http://www.baidu.com',error=None,headers=<tornado.httputil.HTTPHeaders object at 0x7f2fdaa39e10>,reason='OK',request=<tornado.httpclient.HTTPRequest object at 0x7f2fdaa39a90>,request_time=0.05612993240356445,time_info={})

我不明白发生了什么，而Gevent也发生了同样的事情。任何人都请我。

Answer 1

如果计划函数提出异常，则Python 2.7中的multiprocessing.Pool不会运行回调。这是在python 3中修复的，添加了error_callback。

我建议您按以下方式修改内部循环以实际查看错误：

results = []
pool = multiprocessing.Pool(processes=process_num)
for i in range(process_num):
    result = pool.apply_async(f, args=args, kwds=kwargs, callback=kwargs.get("callback"))
    results.append(result)
for result in results:
    result.get()  # this will raise the exception in the worker
pool.close()
pool.join()