Cell Relay Archive

[James Carlson <carlson@ironbridgenetworks.com>]

Koen Peeters <koen@ciminko.be> writes:
> James Carlson wrote:
> > 
> > Walt Weber <waltweber@sprintmail.com> writes:
> > > How does a network using routers and IP over Sonet compare with a network
> > > using IP over ATM on a throughput as well as cost per bit basis?
> > 
> > If you want to do it as cost-per-bit, then ATM is about 15% more
> > expensive than raw IP (96/83).
> > 
> 
> I'm not sure this is really an issue !
> ATM gives you QOS with a overhead of 15% it seems.
> QOS in IP make the assumption of abundance in bandwidth ( = 50% extra
> bandwidth overhead ??).

Please reread what the original poster wrote.  He asked for a
comparison of the efficiency of IP over SONET versus IP over ATM.

This has nothing whatsoever to do with the question of whether or not
ATM actually does provide QoS or if it's worth the expense.  He wasn't
asking about any such thing.

> Newer ATM encapsulation techniques with QOS in mind use TCP over ATM,
> thereby getting rid of the IP overhead of TCP/IP. Is bandwidth really
> the issue ?

As the original poster noted, it certainly is an issue for the folks
paying for the links.  If you're not footing the bill, then I suppose
it is less important.  (TCP over ATM without IP?  References?)

-- 
James Carlson, Consulting S/W Engineer  <carlson@ironbridgenetworks.com>
IronBridge Networks / 55 Hayden Avenue  71.246W    Vox:  +1 781 372 8132
Lexington MA  02421-7996 / USA          42.423N    Fax:  +1 781 372 8090
"PPP Design and Debugging" --- http://people.ne.mediaone.net/carlson/ppp