Server emitting 5 times each

[SpringsTea]

I have a flask-socketio server setup through uwsgi. I had too many connections which made everything unstable, so in production it runs through uwsgi with nginx as a proxy. Here is my wsgi.ini

[uwsgi]
module = app:app
gevent=1000

master = true
processes = 5

socket = tmp/myproject.sock
chmod-socket = 777
vacuum = true

die-on-term = true

#logto = ./logs/wsgi/uwsgi.log
log-5xx = true
disable-logging=True

And my nginx config:

user www-data;
worker_processes auto;
pid /run/nginx.pid;
include /etc/nginx/modules-enabled/*.conf;

events {
    worker_connections 1024;
    # multi_accept on;
}

                                                           
server {		
  listen 5960;                                                  
  server_name ibnnetwork;    
  
  location / {                                                  
	  include uwsgi_params;                                     
	  uwsgi_pass unix:///var/wsgi/ibn/IBNServer/tmp/myproject.sock; 
  }                                                             
}  

http {

    ##
    # Basic Settings
    ##

    sendfile on;
    tcp_nopush on;
    types_hash_max_size 2048;
    # server_tokens off;

    # server_names_hash_bucket_size 64;
    # server_name_in_redirect off;

    include /etc/nginx/mime.types;
    default_type application/octet-stream;

    ##
    # SSL Settings
    ##

    ssl_protocols TLSv1 TLSv1.1 TLSv1.2 TLSv1.3; # Dropping SSLv3, ref: POODLE
    ssl_prefer_server_ciphers on;

    include /etc/nginx/conf.d/*.conf;
    include /etc/nginx/sites-enabled/*;
}

The problem I'm having is that when I have my server emit, it will emit 5 times. I'm guessing each process is emitting, and my clients are hearing all of them. GPT suggested I use clustering to solve the problem, but couldn't give a correct setup to accomplish this and I can't find any documentation on the topic.

Could someone please point me in the right direction?

[miguelgrinberg]

The documentation shows working uwsgi and nginx configurations. Yours are completely different. Why is that?

I suggest you start from the documented configuration:

• uWSGI
• nginx
• using multiple worker processes

[miguelgrinberg]

@SpringsTea I don't believe uwsgi_pass works with WebSocket, that is only for HTTP traffic if I remember correctly. As I said above, the configuration that I share in the documentation is verified to work. Start from that, then make the changes that you need one at a time and confirm that everything continues to work. I cannot really tell you what's wrong because you have deviated from the working configuration in several ways.

[SpringsTea]

So I've got it working with more or less the config in the documentation.
Unfortunately, my issue has not been resolved which is real weird since I didn't implement the multiple processes. I can only assume the issue is gevent related?

My ini:

[uwsgi]
http = :5961
gevent = 1000
master = true
http-websockets
wsgi-file = app.py
callable = app

And my nginx

server {
    listen 5960;
    server_name IBN;

    location / {
        include proxy_params;
        proxy_pass http://127.0.0.1:5961;
    }

    location /socket.io {
        include proxy_params;
        proxy_http_version 1.1;
        proxy_buffering off;
        proxy_set_header Upgrade $http_upgrade;
        proxy_set_header Connection "Upgrade";
        proxy_pass http://127.0.0.1:5961/socket.io;
    }
}

I am monkey patching gevent so i can run a background process on a schedule. It collects data from sql and then emits a message out that it's complete to all ready clients. So I have this in my entry point file:

from gevent import monkey
monkey.patch_all()

import modules.server.scheduler as scheduler

And then in the scheduler I have a APScheduler that runs a function that emits. It creates it's socket connection like this

from flask_socketio import SocketIO
socketio = SocketIO(message_queue="redis://{}:{}/0".format(config.REDIS_SERVER, config.REDIS_PORT))

But my scheduler seems to be firing 5 times each time, causing 5 emits. I always assumed this was due to the multiple worker processes. I even have a redis lock system set up to try and prevent this from happening, but the lock is being ignored.

[miguelgrinberg]

I suggest you ask someone familiar with your scheduler why is it firing multiple times.

[SpringsTea]

It's not the scheduler. If I run my app without wsgi, just as the flask test server, it works fine.

[miguelgrinberg]

I have no other suggestions to make. You said your scheduler was firing 5 times in your previous comment, I was just following up on your own statement.