sagemaker custom ml model in container

2022/11/09 05:21:09 [error] 11#11: *213 upstream prematurely closed connection while reading response header from upstream, client: 169.254.178.2, server: , request: "POST /invocations HTTP/1.1", upstream: "http://unix:/tmp/gunicorn.sock:/invocations", host: "169.254.180.2:8080" In this model we provide S3 audio object URL to given output audio S3 URL after processing. nginx.conf is as follows:

daemon off; # Prevent forking


pid /tmp/nginx.pid;
error_log /var/log/nginx/error.log;

events {
  # defaults
}

http {
  include /etc/nginx/mime.types;
  default_type application/octet-stream;
  access_log /var/log/nginx/access.log combined;
  client_max_body_size 0;
  client_body_timeout 999;
  client_header_timeout 999;
  keepalive_timeout 999;
  fastcgi_buffers 8 16k;
  fastcgi_buffer_size 32k;
  fastcgi_connect_timeout 999;
  fastcgi_send_timeout 999;
  fastcgi_read_timeout 999;

  upstream gunicorn {
    #server 0.0.0.0:4602;
    server unix:/tmp/gunicorn.sock fail_timeout=0;
  }

  server {
    listen 8080 deferred;
    client_max_body_size 0;

    keepalive_timeout 1200s;
    proxy_read_timeout 3600s;

    location ~ ^/(ping|async-invocations|invocations) {
      proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
      proxy_set_header Host $http_host;
      proxy_redirect off;
      proxy_pass http://gunicorn;
    }

    location / {
      return 404 "{}";
    }
  }
}```

and serve.py as follows:

```python
import multiprocessing
import os
import signal
import subprocess
import sys

cpu_count = multiprocessing.cpu_count()

model_server_timeout = os.environ.get('MODEL_SERVER_TIMEOUT', 999)
model_server_workers = int(os.environ.get('MODEL_SERVER_WORKERS', cpu_count))


def sigterm_handler(nginx_pid, gunicorn_pid):
    try:
        os.kill(nginx_pid, signal.SIGQUIT)
    except OSError:
        pass
    try:
        os.kill(gunicorn_pid, signal.SIGTERM)
    except OSError:
        pass

    sys.exit(0)


def start_server():
    print('Starting the inference server with {} workers.'.format(model_server_workers))
    print(model_server_timeout)
    # link the log streams to stdout/err so they will be logged to the container logs
    subprocess.check_call(['ln', '-sf', '/dev/stdout', '/var/log/nginx/access.log'])
    subprocess.check_call(['ln', '-sf', '/dev/stderr', '/var/log/nginx/error.log'])

    nginx = subprocess.Popen(['nginx', '-c', '/opt/program/nginx.conf'])
    gunicorn = subprocess.Popen(['gunicorn',
                                 '--timeout', str(model_server_timeout),
                                 '-k', 'sync',
                                 '-b', 'unix:/tmp/gunicorn.sock',
                                 '-w', str(model_server_workers),
                                 'wsgi:app'])

    signal.signal(signal.SIGTERM, lambda a, b: sigterm_handler(nginx.pid, gunicorn.pid))

    # If either subprocess exits, so do we.
    pids = set([nginx.pid, gunicorn.pid])
    while True:
        pid, _ = os.wait()
        if pid in pids:
            break

    sigterm_handler(nginx.pid, gunicorn.pid)
    print('Inference server exiting')


# The main routine just invokes the start function.

if __name__ == '__main__':
    start_server()