django - gunicorn + redis: Does not work? -

i run django server redis [in-memory caching filtering duplicate records] integrated celery process [tasks insert data postgresql database asynchronously]. django server integrated redis via django-redis-cache caching enabled.

caches = {     'default': {         'backend': 'redis_cache.rediscache',         'location': '/tmp/redis.sock',   }, } 

if use ./manage.py runserver ip:8000 run server , start posting data, there's no problem during get/set attributes in redis single application , app runs smoothly.

but now, i'm planning migrate django gunicorn via command:

gunicorn myapp:wsgi_app -w 3 -b ip:8000 

as creates 3 workers django process, believe trying access same redis-server caching.

if start posting data using setup, message,

internal server error: /post/data/  file "/path/to/app/views.py", line 94, in savedata    value = cache.get(key)  file "/usr/local/lib/python2.7/dist-packages/redis_cache/cache.py", line 186, in    result = self.unpickle(value)  file "/usr/local/lib/python2.7/dist-packages/redis_cache/cache.py", line 248, in unpickle    return pickle.loads(value)  file "/usr/local/lib/python2.7/dist-packages/django/db/models/base.py", line 1035, in model_unpickle    return cls.__new__(cls)  typeerror: ('object.__new__(x): x not type object (nonetype)', <function model_unpickle @ 0x1c49aa0>, ((u'webapi', 'reading'), [], <function simple_class_factory @ 0x1c49a28>)) 

if check redis-server log [redis-cli monitor], empty records in them after start using gunicorn.

is there smart work around keep redis active gunicorn threads also?