Re: Does the the web polygraph use http/1.1?

That's one reason to get the headers parsed into metadata rather than part of the stream passed around with storeClientCopy

I'm open to suggestions - I only started documenting the request/reply path yesterday.

I'm not actually sure that trailers can be fully supported without that step.

However there are some partial options:

We can send trailers quite happily. RFC 2616 requires clients to indicate their understanding of trailers with
TE: trailers
unless the fields going in the trailer are 100% optional metadata.
So we can fully support digest message body signing (that's all trailers are for).

What we cannot do is recieve and use trailers from origin or upstream servers - so we don't offer a TE: trailers in our requests.

Then when a cleaner way of supporting incoming trailers is coded, we can offer TE: trailers to upstream servers.

The crux of the issue is that we need some way to decide if a store client needs the trailer header fields.
Telling the client that the fields have arrived is trivial (the Trailer: header lists the trailing headers, when the last byte of
entity body is read, the client knows the trailers have arrived if they are going to.

What's more difficult is getting to the client side HttpReply to write those headers.

One issue that I'm thinking about is the incoming-outgoing reply difference. Currently we use an incoming Reply struct for http.c's
server side work, and a separate one, generated from the same headers for the outbound client.

Each client needs it's own HttpReply headers (for example for generating signatures, but I was thinking that the initial headers in
the reply should be provided intact by the store manager, and that the storeclient struct should link to those headers as well,
allowing the store to update all the attached clients headers.

I'll cover this more in reply to Adrians mail.

Rob

----- Original Message -----
From: "Henrik Nordstrom" <hno@hem.passagen.se>
To: "Robert Collins" <robert.collins@itdomain.com.au>
Cc: <squid-dev@squid-cache.org>
Sent: Saturday, January 13, 2001 9:29 PM
Subject: Re: Does the the web polygraph use http/1.1?

> Robert Collins wrote:
> > It currently always decodes the server side so we store an identity entity. Unfortunately (as per my email "storemanager") the
> > stored entity still has it's connection and transfer-encoding headers (this is a bug for all current squids AFAICT).
>
> How do you plan on handling trailers, especially wrt the store..
>
> /Henrik
>
>
Received on Sat Jan 13 2001 - 04:06:16 MST