Re: [squid-users] Another HTTP 1.1 Question

On Wed, Mar 14, 2007, Henrik Nordstrom wrote:
> tis 2007-03-13 klockan 11:57 +0800 skrev Adrian Chadd:
>
> > Are ECN/Window Scaling options which can be fiddled via syscalls per
> > socket FD?
>
> Probably not for ECN, but it looks like the window scaling can be
> influenced by the TCP_WINDOW_CLAMP setsockopt.
>
> Adding a TCP setsockopt for turning off ECN shouldn't be hard however..

I'm kind of surprised its not already implemented. Grr.

> > If they are then we could sneak them into the "retry" forwarding logic
> > and cache if/when they work.
>
> The window scaling problem is unfortunately not so easy to detect in
> Squid as it causes connections to hang after the request has been sent
> and acknowledged making it just look like the server takes ages to
> process the request, so it generally never reaches a retry condition..

The user will generally hit "reload" though; there's no harm in retrying
the request with a clamped tcp window and logging the issue.

I can't help but think having Squid optionally report "problematic" sites
to a central location so other cache operators benefit would be a good
idea.

> The ECN problem is easier as it causes connections to fail to establish.

Hm, guess we've signed ourselves up for more work then.

Adrian
Received on Wed Mar 14 2007 - 06:46:50 MDT