[xcp] Embedding XCP signalling in IP header

[Bob Braden]

  *> From xcp-bounces at mailman.isi.edu  Wed Aug 18 05:42:23 2004
  *> From: Marko Zec <zec at icir.org>
  *> To: xcp at mailman.isi.edu
  *> Date: Wed, 18 Aug 2004 14:36:06 +0200
  *> User-Agent: KMail/1.6.2
  *> MIME-Version: 1.0
  *> Content-Disposition: inline
  *> Content-Transfer-Encoding: 7bit
  *> X-ISI-4-30-3-MailScanner: Found to be clean, Found to be clean, Found to be clean
  *> Subject: [xcp] Embedding XCP signalling in IP header
  *> List-Id: A mailing list to discuss the eXplicit Control Protocol
  *> 	<xcp.mailman.isi.edu>
  *> X-Spam-Status: No, hits=-4.9 required=5.0 tests=BAYES_00 autolearn=ham 
  *> 	version=2.63
  *> 
  *> Here's just a thought - perhaps XCP signalling could be embedded directly into 
  *> the IP header, by reusing the existing fragmentation fields?  The obvious 
  *> benefit from such a scheme would be transparent compatibility with existing 
  *> TCP implementations, which could make quite a difference for any real-world 
  *> deployment scenario.
  *> 
  *> http://tel.fer.hr/zec/xcp-hdr-encoding.txt
  *> 
  *> Would this make any sense?
  *> 

Nice try, but unfortunately, there are a lot of things wrong with your
approach.

1. I am much bemused (but not amused) by the irony of your citing
Stoica's SFQ thesis as justification.  In fact, Stoica wrote up his
protocol as an Internet Draft and submitted it to the RFC Editor for
publication as a non-IETF RFC.  The RFC Editor was delighted to be able
to publish such a substantive piece of research.  But first, we had to
get approval from the IESG for publication.  The IESG stomped all over
it and blocked its publication as an RFC, exactly on the grounds that
it misused the fragmentation fields in IP.  So, forget using the IP
header.

2. The format you give would be a horror to implement efficiently in
high-capacity routers.  Router vendors would just walk away.

3. We don't really know whether the floating-point representation you
suggest will actually work, from a numerical analysis viewpoint.
However, in any case it's almost certainly too hard to implement for
a high-capacity router.

4. It's a kludge.

Nice writeup, though.

Bob Braden


  *> Marko
  *> _______________________________________________
  *> xcp mailing list
  *> xcp at mailman.isi.edu
  *> http://mailman.isi.edu/mailman/listinfo/xcp
  *>