Re: persistent TCP-connections between squids

From: Dean Gaudet <dgaudet-list-squid-dev@dont-contact.us>
Date: Tue, 19 Aug 1997 00:05:50 -0700 (PDT)

--MimeMultipartBoundary
Content-Type: TEXT/PLAIN; charset=US-ASCII

On Wed, 13 Aug 1997, Duane Wessels wrote:

> For now, Squid's persistent connections are implemented like this:
> There is an upper limit on the number of "idle" connections per
> host. An idle connection will be closed after some configurable
> timeout. Squid does not pipeline requests; rather than wait for
> one request to complete, Squid will open another connection to that
> host. I'm sure that will change (to become more complex) as the
> implementation evolves.

There's an interesting internet draft: draft-ietf-http-connection-00.txt
which talks about connection management. In particular about how proxies
should manage persistent connections. A fixed number is a bad idea due to
various DoS attacks.

> For example, for requests that do not have
> a content-length header, the client-side only knows the object is
> completely transferred when the connection is closed. Would you
> propose using some other kind of encapsulation protocol around HTTP?

HTTP/1.1 chunking is one solution to this.

Dean

--MimeMultipartBoundary--
Received on Tue Jul 29 2003 - 13:15:42 MDT

This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:11:22 MST