[Iccrg] Heresy following "TCP: Train-wreck"

[Dirceu Cavendish]

OK, Bob. If you say we disagree, you know best :-)

Dirceu



----- Original Message ----
From: Bob Briscoe <rbriscoe at jungle.bt.co.uk>
To: Dirceu Cavendish <dirceu_cavendish at yahoo.com>
Cc: iccrg at cs.ucl.ac.uk
Sent: Monday, April 7, 2008 4:21:28 PM
Subject: Re: [Iccrg] Heresy following "TCP: Train-wreck"

Dirceu,

If you say we're agreeing, then OK.

But I read a lot of tell-tale signs in your various postings that 
imply to me you are still thinking the way I believe has been a 
mistake in the past.

For instance, it's not at all hopeless if all sessions don't pass 
through a core router - they still have to pass through the point 
where the user's trust domain attaches to the rest of the Internet. 
That's always the case (otherwise the user isn't attached to the 
Internet). So there is no problem* seeing all the user's flows in one 
place (or a small number of places if multi-homing).

However, let's leave this one at that for now.


Bob

* The outstanding problem is that you can't see congestion ahead in 
the rest of the Internet from the attachment point (our re-feedback 
solution is one way to ensure trustworthy information about remote 
congestion is visble in packets crossing this attachment point).



At 23:55 07/04/2008, Dirceu Cavendish wrote:
>Let me state one thing clearly, first of all. I am NOT disagreeing 
>that flow rate equality as a fairness criterion has its problems. 
>So, you do not have to be defensive, as your last paragraph below.
>
>Second, about routing, I think you were the one who did not captured 
>what I wanted to say - communication is always a two way process, so 
>I take the blame as well. I understand that multiple sessions do not 
>require diverse routes in order to "confuse" routers, so as to 
>defeat some fairness scheme. However, one may imagine that, the same 
>way the router of application "attachment" is able to correlate 
>multiple session into a single application - as one of your papers 
>mention, a core router might be able to do it, provided that all 
>sessions follow the same path. When that is not the case, then the 
>situation is REALLY hopeless...That is what I meant.
>
>I believe we are in violent agreement, overall :-)...

____________________________________________________________________________
Bob Briscoe, <bob.briscoe at bt.com>      Networks Research Centre, BT Research
B54/77 Adastral Park,Martlesham Heath,Ipswich,IP5 3RE,UK.    +44 1473 645196 


      ____________________________________________________________________________________
You rock. That's why Blockbuster's offering you one month of Blockbuster Total Access, No Cost.  
http://tc.deals.yahoo.com/tc/blockbuster/text5.com
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://oakham.cs.ucl.ac.uk/pipermail/iccrg/attachments/20080407/0dd912aa/attachment.html