在过去的几个月里，我一直在为我的多人游戏运行一个 socketio 服务器。它似乎运行正常，但一两天后就会崩溃并出现这些错误：[2024-06-18 14:55:02 +0300] [250...

过去几个月我一直在为我的多人游戏运行一个 socketio 服务器。

它似乎运行正常，但一两天后就会因以下错误而崩溃：

[2024-06-18 14:55:02 +0300] [250979] [INFO] Handling signal: int
[2024-06-18 14:55:02 +0300] [250981] [ERROR] Exception in worker process
Traceback (most recent call last):
  File "/usr/lib/python3.8/ssl.py", line 1019, in _create
    self.getpeername()
OSError: [Errno 107] Transport endpoint is not connected
 
During handling of the above exception, another exception occurred:
 
Traceback (most recent call last):
  File "/usr/local/lib/python3.8/dist-packages/gunicorn/arbiter.py", line 609, in spawn_worker
    worker.init_process()
  File "/usr/local/lib/python3.8/dist-packages/gunicorn/workers/geventlet.py", line 143, in init_process
    super().init_process()
  File "/usr/local/lib/python3.8/dist-packages/gunicorn/workers/base.py", line 142, in init_process
    self.run()
  File "/usr/local/lib/python3.8/dist-packages/gunicorn/workers/geventlet.py", line 182, in run
    a.wait()
  File "/usr/local/lib/python3.8/dist-packages/eventlet/greenthread.py", line 225, in wait
    return self._exit_event.wait()
  File "/usr/local/lib/python3.8/dist-packages/eventlet/event.py", line 131, in wait
    current.throw(*self._exc)
  File "/usr/local/lib/python3.8/dist-packages/eventlet/greenthread.py", line 265, in main
    result = function(*args, **kwargs)
  File "/usr/local/lib/python3.8/dist-packages/gunicorn/workers/geventlet.py", line 83, in _eventlet_serve
    conn, addr = sock.accept()
  File "/usr/local/lib/python3.8/dist-packages/eventlet/greenio/base.py", line 228, in accept
    self._trampoline(fd, read=True, timeout=self.gettimeout(), timeout_exc=_timeout_exc)
  File "/usr/local/lib/python3.8/dist-packages/eventlet/greenio/base.py", line 206, in _trampoline
    return trampoline(fd, read=read, write=write, timeout=timeout,
  File "/usr/local/lib/python3.8/dist-packages/eventlet/hubs/__init__.py", line 157, in trampoline
    return hub.switch()
  File "/usr/local/lib/python3.8/dist-packages/eventlet/hubs/hub.py", line 310, in switch
    return self.greenlet.switch()
  File "/usr/local/lib/python3.8/dist-packages/gunicorn/workers/geventlet.py", line 102, in _eventlet_stop
    client.wait()
  File "/usr/local/lib/python3.8/dist-packages/eventlet/greenthread.py", line 225, in wait
    return self._exit_event.wait()
  File "/usr/local/lib/python3.8/dist-packages/eventlet/event.py", line 131, in wait
    current.throw(*self._exc)
  File "/usr/local/lib/python3.8/dist-packages/eventlet/greenthread.py", line 265, in main
    result = function(*args, **kwargs)
  File "/usr/local/lib/python3.8/dist-packages/gunicorn/workers/geventlet.py", line 156, in handle
    client = ssl_wrap_socket(client, self.cfg)
  File "/usr/local/lib/python3.8/dist-packages/gunicorn/sock.py", line 229, in ssl_wrap_socket
    return ssl_context(conf).wrap_socket(sock,
  File "/usr/local/lib/python3.8/dist-packages/eventlet/green/ssl.py", line 436, in wrap_socket
    return GreenSSLSocket(sock, *a, _context=self, **kw)
  File "/usr/local/lib/python3.8/dist-packages/eventlet/green/ssl.py", line 65, in __new__
    ret = _original_sslsocket._create(
  File "/usr/lib/python3.8/ssl.py", line 1031, in _create
    notconn_pre_handshake_data = self.recv(1)
  File "/usr/lib/python3.8/ssl.py", line 1257, in recv
    return super().recv(buflen, flags)
ConnectionResetError: [Errno 104] Connection reset by peer

以下是服务器代码：

from flask import Flask, request, jsonify, render_template
import uuid
import ssl
import time
from flask_socketio import SocketIO
from threading import Lock
import logging
 
 
 
 
app = Flask(__name__)
socketio = SocketIO(app, host='0.0.0.0', port=5000, cors_allowed_origins='*')  # Allows connections from any IP address
 
applications = {}
#app.logger.setLevel(logging.DEBUG)
 
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)
 
"""
context = SSL.Context(SSL.TLSv1_2_METHOD)
context.use_privatekey_file('/etc/ssl/private/private-unencrypted.key')
context.use_certificate_file('/etc/ssl/certificate.crt')
context.check_privatekey()  # Optional: Check if the key matches the certificate
"""
 
context = ssl.SSLContext(ssl.PROTOCOL_TLSv1_2)
context.load_cert_chain('/etc/ssl/chained.pem', '/etc/ssl/private/private-unencrypted.key')
 
 
 
 
 
 
connected_clients = {}
 
@socketio.on('connect')
def handle_connect():
    print("Connection established!")
 
@socketio.on('MakeRoom') 
def make_room(data):
    splitted = data.split('/')
    aplication_id = splitted[0]
    loby_id = splitted[1]
    hosted = int(splitted[2])
    user_id = uuid.uuid4().hex
 
    client_id = request.sid
 
 
 
    if(hosted == 0):
        print("peer connecting")
        check_lobbies_periodically()
        host_id,host_client_id = find_host(aplication_id,loby_id)
        if(host_client_id == None):
            socketio.emit("HostNotFound","",room = client_id)
            print("Host not found for user")
            return
 
 
        #print(f"host_client_id : {host_client_id}" )
        socketio.emit('PeerConnected',user_id,room=host_client_id)
    else:
        print(f"Created host : {client_id}")
    connected_clients[(aplication_id, loby_id,hosted,user_id)] = client_id
    print(f"got data : {aplication_id} + {loby_id} + {client_id}")
 
@socketio.on('SendOffer')
def send_offer(data):
 
    splitted = data.split(';/;/;/')
    aplication_id = splitted[0]
    loby_id = splitted[1]
    guid = splitted[2]
    sdp = splitted[3]
 
    client_id = get_client_id(aplication_id,loby_id,guid)
    myguid = get_guid(aplication_id,loby_id,request.sid)
 
    print(f"sending Offer from {request.sid}|{myguid} to {client_id}|{guid}")
 
    if client_id:
        message = sdp + ";;//" + myguid
        socketio.emit('OfferReceived', message, room=client_id)
        return f'Message sent to Unity client with Application ID: {aplication_id} and Lobby ID: {loby_id}'
    else:
        return 'Client not found for the given IDs in send_offer'
 
@socketio.on('SendICE')
def send_ice(data):
    #print("send_ice : " + data)
    splitted = data.split(';/;/;/')
    aplication_id = splitted[0]
    loby_id = splitted[1]
    guid = splitted[2]
    ice = splitted[3]
 
    client_id = get_client_id(aplication_id,loby_id,guid)
    myguid = get_guid(aplication_id,loby_id,request.sid)
 
    print(f"sending ice from {request.sid}|{myguid} to {client_id}|{guid}")
 
    if client_id:
        message = ice + ";;//" + myguid
        socketio.emit('IceGot', message, room=client_id)
        return f'Message sent to Unity client with Application ID: {aplication_id} and Lobby ID: {loby_id}'
    else:
        return 'Client not found for the given IDs in send_ice'
 
clients_lock = Lock()
 
@socketio.on('disconnect')
def handle_disconnect():
    print("Received disconnect")
    sid = request.sid
 
    with clients_lock:
        for (app_id, lobby_id, host, user_id), client_id in connected_clients.copy().items():
            if client_id == sid:
                try:
                    if host == 1:
                        host_disconnected(app_id, lobby_id)
                    del connected_clients[(app_id, lobby_id, host, user_id)]
                except KeyError:
                    print("user not found in dictionary")
                    pass
                break
 
def host_disconnected(appId,lobbyId):
    clients_to_disconnect = []
    for key, client_id in connected_clients.copy().items():
        app_id, lobby_id, hosted, user_id = key
        if app_id == appId and lobbyId == lobby_id and hosted == 0:
            clients_to_disconnect.append(client_id)
 
    for client_id in clients_to_disconnect:
        socketio.emit('HostDisconnected', "", room=client_id)
        #socketio.disconnect(client_id)
 
 
 
@socketio.on('SendAnswer')
def handle_post_request(data):
    #print("Sending answer:" + data)
    splitted = data.split(';/;/;/')
    aplication_id = splitted[0]
    loby_id = splitted[1]
    guid = splitted[2]
    sdp = splitted[3]
 
    host_id, client_id = find_host(aplication_id,loby_id)
 
 
 
    if(client_id == None):
        socketio.emit("HostNotFound","",room = client_id)
        print("Host not found for user on answer creation")
        return
 
 
    myguid = get_guid(aplication_id,loby_id,request.sid)
 
    print(f"sending answer from {request.sid}|{myguid} to {client_id}|{guid}")
 
    message = sdp + ";/;/;/" + myguid
    socketio.emit('AnswerCreated', message, room=client_id)
 
def get_guid(application_id, lobby_id, client_id):
    for key, client_ids in connected_clients.items():
        if key[0] == application_id and key[1] == lobby_id and client_ids == client_id:
            return key[3]
    return None
 
def get_client_id(application_id, lobby_id, user_id):
    for key, client_id in connected_clients.items():
        if key[0] == application_id and key[1] == lobby_id and key[3] == user_id:
            return client_id
    return None
def find_host(application_id,lobby_id):
    for key, client_id in connected_clients.items():
        print(f"searching for host keys : {key[0]} == {application_id} {key[1]} == {lobby_id} and host == {key[2]}")
        if key[0] == application_id and key[1] == lobby_id and key[2] == 1:
            user_id = key[3]
            return user_id, client_id
    return None, None
 
 
# Function to add a new application
def add_application(application_id):
    if application_id not in applications:
        applications[application_id] = []
 
# Function to add a lobby to an application
def add_lobby(application_id, lobby_id, lobby_info):
    if application_id in applications:
        applications[application_id].append({"lobby_id": lobby_id, "lobby_info": lobby_info, "last_update": int(time.time())})
        return 1
    else:
        return 2
 
# Function to delete a lobby from an application
def delete_lobby(application_id, lobby_id):
    if application_id in applications:
        lobbies = applications[application_id]
        for lobby in lobbies:
            if lobby["lobby_id"] == lobby_id:
                lobbies.remove(lobby)
                return 0 
        return 1
    else:
        return 2
 
# Function to update lobby information
def update_lobby(application_id, lobby_id, new_lobby_info):
    if application_id in applications:
        lobbies = applications[application_id]
        for lobby in lobbies:
            if lobby["lobby_id"] == lobby_id:
                lobby["lobby_info"] = new_lobby_info
                return 0
        return 1
    else:
        return 2
 
@app.route('/', methods=['GET','POST'])
def create_or_update_lobby():
 
    Action = -1
    try:
        Action = int(request.form.get('Action'))
    except: 
        form_data = request.form.to_dict()
 
        # Print the form data to the console (for debugging)
        print(form_data)
        print("Received request form without Action key : {form_data)}" )
 
    if(Action != -1):
        application_id = request.form.get('application_id')
        add_application(application_id)
        lobby_data = request.form.get('lobby_data')
 
        if Action == 0:
            lobby_id = uuid.uuid4().hex
            retValue = add_lobby(application_id,lobby_id,lobby_data)
            if retValue == 2:
                return "Application not found", 500
            if retValue == 1:
                return jsonify({'lobby_id': lobby_id}), 200
 
        lobby_id = request.form.get('lobby_id')
        if Action == 1:
            retValue = update_lobby(application_id,lobby_id,lobby_data)
            if retValue == 2:
                return "Application not found", 500
            if retValue == 1:
                return f"Lobby {lobby_id} not found in application {application_id}.", 500
            if retValue == 0:
                return f"Lobby {lobby_id} updated.", 200
        elif Action == 2:
            retValue = delete_lobby(application_id,lobby_id)
            if retValue == 2:
                return "Application not found", 500
            if retValue == 1:
                return f"Lobby {lobby_id} not found in application {application_id}.", 500
            if retValue == 0:
                return f"Lobby {lobby_id} deleted.", 200
        elif Action == 3:
            return jsonify(get_lobbies(application_id)), 200
        elif Action == 4:
            found = 0
            if application_id in applications:
                lobbies = applications[application_id]
                for lobby in lobbies:
                    #print(f"Comparing : --{lobby['lobby_id']}-- with --{lobby_id}--")
                    #print(f"types : {type(lobby['lobby_id']), {lobby_id}}")
                    if lobby['lobby_id'] == lobby_id:
                        lobby["last_update"] = int(time.time())
                        found = 1
                        break  
            if found == 1: 
                return f"Lobby {lobby_id} update time updated", 200
            elif found == 0 : 
                return f"Lobby with id {lobby_id} not found", 580
    else: return f"Action key not found in arguments", 400         
 
 
def get_lobbies(application_id):
    if application_id in applications:
        lobbies = applications[application_id]
        simplified_lobbies = [{"lobby_id": lobby["lobby_id"], "lobby_info": lobby["lobby_info"]} for lobby in lobbies]
        return simplified_lobbies
    else:
        return []
 
 
def print_lobbies_periodically():
    while True:
        print("All Lobbies:")
        for application_id, lobbies in applications.items():
            print(f"Application ID: {application_id}")
            for lobby in lobbies:
                print(f"Lobby ID: {lobby['lobby_id']}, Lobby Info: {lobby['lobby_info']}, Last Update: {lobby['last_update']}")
        time.sleep(5)  
 
def check_lobbies_periodically():
    currentTime = int(time.time())
    for application_id, lobbies in applications.items():
        for lobby in lobbies:
            if(currentTime - int(lobby['last_update']) > 15):
                print(f"Lobby in application : {application_id} with id : {lobby['lobby_id']} timed out")
                delete_lobby(application_id,lobby['lobby_id'])

我用 gunicorn 运行它，但当我像运行普通 flask 应用程序一样运行它时也会出现同样的情况。这是在 ubuntu 上。

一旦该过程停止并重新启动，它就会再次正常工作，但几天后就会再次重复。

我尝试使用以下命令通过 gunicorn 运行整个程序：gunicorn --workers 1 --worker-class eventlet --bind 0.0.0.0:5000 --certfile=/etc/ssl/chained.pem --keyfile=/etc/ssl/private/private-unencrypted.key --error-logfile ./error.txt --access-logfile ./access.txt RequestManager:app

我尝试记录崩溃发生时的情况，似乎是断开连接时发生的，但真的不确定，无法准确指出。

尝试了其他一些方法，基本上没有什么办法了，似乎没有什么可以解决这个问题。