[Iccrg] (no subject)

[Saverio Mascolo]

On Thu, Apr 24, 2008 at 7:40 PM, Michael Welzl <michael.welzl at uibk.ac.at> wrote:

  > dear welzl,

  Hi Mascolo   :-))



  > referring to the section '3.2 Challenge 2: Corruption Loss' of the draft,
  i
  > think that an important point is missing here, which is the basic idea
  > introduced at Mobiocm 2001 in the TCP Westwood paper.
  >
  > The key concept of westwood tcp is the following:


  That's all fine, but of course there are a million ideas for improving
  TCP in wireless links that we didn't put there - what we don't want
  to miss are the open research issues, not all their possible solutions...


dear Michael ,

i do not think it is one of million ideas, since it is   unique and  relevant under the assumption of lossy link. 
another relevant piece of work that you may want  cite  to improve  this draft is the icnp08 paper:
David A. Eckhardt, Peter Steenkiste: 
Improving Wireless LAN Performance via Adaptive Local Error Control. 327-338

which very clearly explains that you have to design a good wireless link so that losses not due to congestion should not be relevant (indeed this is the case in current 3G  systems obtained via ARQ). this is old stuff today, already documented in RFC 3819 - Advice for Internet Subnetwork Designers, by P. Karn.

best
saverio






  Cheers,
  Michael
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://oakham.cs.ucl.ac.uk/pipermail/iccrg/attachments/20080424/1122432d/attachment.html