Re: Selective parenting

Bit of perl in a redirector?

tell squid to go direct but get your redirector to fetch HEAD requests off
this proxy and decide on that header what to return.

On Thu, 4 Nov 1999, Glenn F . Maynard wrote:

> Situation: We run a squid proxy locally, with the parent being our uplink's
> filtering proxy. This parent proxy (Bess) is *extremely slow* (probably
> overloaded). Here's my solution: make the assumption that if
> "http://www.foo.com/x/y" is blocked (or not blocked),
> "http://www.foo.com/x/.*" is also blocked (or not). This proxy adds the
> header "Pragma: BESSBLOCK" to blocked sites (the content is a fairly standard
> "you can't go there" page.) I don't have real access to the blocklist.
> Getting only headers through the other proxy could speed this up a bit more
> (all accesses would be direct), but could be a bit more complicated.
>
> Based on that assumption, I should be able to keep track of unblocked sites;
> if a URL falls under a previously unblocked path, bypass the parent. Only
> the first access to a given site will be slow. (Remembering blocked sites
> isn't needed.)
>
> Is there any way to do this within Squid's current architecture, or will I
> have to break out Squid's source? Would it be easier to write another
> simple proxy to do this (selectively using Squid or the filtering proxy
> based on the same conditions)? Has this (wishful thinking) been done before?
>
> --
> Glenn Maynard
>
Received on Thu Nov 04 1999 - 16:57:21 MST