Re: handling 1xx responses

On 4 Sep 2002, Robert Collins wrote:

> On Wed, 2002-09-04 at 14:03, Alex Rousskov wrote:
> > On Wed, 4 Sep 2002, Henrik Nordstrom wrote:
> >
> > > After a 101 response the proxy must effectively switch to tunnel mode
> > > unless it knows the new protocol.
> >
> > A proxy also has a choice to not "forward" Upgrade header if the proxy
> > does not support the described protocol switching mechanism. In fact,
> > it is probably the best choice because tunneling may not be enough for
> > some protocols. Upgrade is a hop-by-hop header.
>
> It's not a choice: 13.5.1 states that hop by hop headers 'are not stored
> by caches or forwarded by proxies'.

As with any hop-by-hop header, it is or is not a choice depending on
the wording interpretation or "point of view": A proxy may emit
Upgrade header which for an outside observer may look like forwarding.
That is why I quoted "forwarding".

The important thing is that "forwarding" MUST be a conscious decision
based on header analysis, not the default action.

Alex.

-- 
                            | HTTP performance - Web Polygraph benchmark
www.measurement-factory.com | HTTP compliance+ - Co-Advisor test suite
                            | all of the above - PolyBox appliance