92 lines
3.5 KiB
Plaintext
92 lines
3.5 KiB
Plaintext
=======================
|
|
How to deploy with WSGI
|
|
=======================
|
|
|
|
Django's primary deployment platform is WSGI_, the Python standard for web
|
|
servers and applications.
|
|
|
|
.. _WSGI: http://www.wsgi.org
|
|
|
|
Django's :djadmin:`startproject` management command sets up a simple default
|
|
WSGI configuration for you, which you can tweak as needed for your project,
|
|
and direct any WSGI-compliant application server to use.
|
|
|
|
Django includes getting-started documentation for the following WSGI servers:
|
|
|
|
.. toctree::
|
|
:maxdepth: 1
|
|
|
|
modwsgi
|
|
apache-auth
|
|
gunicorn
|
|
uwsgi
|
|
|
|
The ``application`` object
|
|
--------------------------
|
|
|
|
The key concept of deploying with WSGI is the ``application`` callable which
|
|
the application server uses to communicate with your code. It's commonly
|
|
provided as an object named ``application`` in a Python module accessible to
|
|
the server.
|
|
|
|
The :djadmin:`startproject` command creates a file
|
|
:file:`<project_name>/wsgi.py` that contains such an ``application`` callable.
|
|
|
|
It's used both by Django's development server and in production WSGI
|
|
deployments.
|
|
|
|
WSGI servers obtain the path to the ``application`` callable from their
|
|
configuration. Django's built-in server, namely the :djadmin:`runserver`
|
|
command, read it from the :setting:`WSGI_APPLICATION` setting. By default, it's
|
|
set to ``<project_name>.wsgi.application``, which points to the ``application``
|
|
callable in :file:`<project_name>/wsgi.py`.
|
|
|
|
Configuring the settings module
|
|
-------------------------------
|
|
|
|
When the WSGI server loads your application, Django needs to import the
|
|
settings module — that's where your entire application is defined.
|
|
|
|
Django uses the :envvar:`DJANGO_SETTINGS_MODULE` environment variable to
|
|
locate the appropriate settings module. It must contain the dotted path to the
|
|
settings module. You can use a different value for development and production;
|
|
it all depends on how you organize your settings.
|
|
|
|
If this variable isn't set, the default :file:`wsgi.py` sets it to
|
|
``mysite.settings``, where ``mysite`` is the name of your project. That's how
|
|
:djadmin:`runserver` discovers the default settings file by default.
|
|
|
|
.. note::
|
|
|
|
Since environment variables are process-wide, this doesn't work when you
|
|
run multiple Django sites in the same process. This happens with mod_wsgi.
|
|
|
|
To avoid this problem, use mod_wsgi's daemon mode with each site in its
|
|
own daemon process, or override the value from the environment by
|
|
enforcing ``os.environ["DJANGO_SETTINGS_MODULE"] = "mysite.settings"`` in
|
|
your :file:`wsgi.py`.
|
|
|
|
|
|
Applying WSGI middleware
|
|
------------------------
|
|
|
|
To apply `WSGI middleware`_ you can simply wrap the application object. For
|
|
instance you could add these lines at the bottom of :file:`wsgi.py`::
|
|
|
|
from helloworld.wsgi import HelloWorldApplication
|
|
application = HelloWorldApplication(application)
|
|
|
|
You could also replace the Django WSGI application with a custom WSGI
|
|
application that later delegates to the Django WSGI application, if you want
|
|
to combine a Django application with a WSGI application of another framework.
|
|
|
|
.. _`WSGI middleware`: https://www.python.org/dev/peps/pep-3333/#middleware-components-that-play-both-sides
|
|
|
|
.. note::
|
|
|
|
Some third-party WSGI middleware do not call ``close`` on the response
|
|
object after handling a request — most notably Sentry's error reporting
|
|
middleware up to version 2.0.7. In those cases the
|
|
:data:`~django.core.signals.request_finished` signal isn't sent. This can
|
|
result in idle connections to database and memcache servers.
|