Distributed System

by Anonymous on 1 Apr 2009

As it seems to be working it is like this:

Client -> squid <-> http server

Which means the Squid always connects to the http server to get the files.

My question is, I would be more scalable if the
clients would be able to connect induvidually to the http server. like this:
client <-> squid
(squid modifies the http url for flv to http server instead
of serving it self)
client <-> http server (to download content)

2 Answers

by blake on 19 Jun 2009

Actually, videocache already works like this. Squid issues a 'HTTP 303 See Other' response which directs the user's browser to connect directly to the given URL. This provides the 'client <-> http server' connection you're looking for.

by Kulbir Saini on 27 Jun 2009


Blake is absolutely right. Clients connect to the http server directly.

Thanks Blake!

You need to sign in. Please sign in to add answer to this question.