[28755] in North American Network Operators' Group
[Fwd: Re: Optical Crossconnects and IP]
daemon@ATHENA.MIT.EDU (Andrew Bender)
Mon May 15 11:29:50 2000
Message-ID: <39201741.727863B@thrupoint.net>
Date: Mon, 15 May 2000 11:26:57 -0400
From: Andrew Bender <abender@thrupoint.net>
MIME-Version: 1.0
To: nanog@merit.edu
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
Errors-To: owner-nanog-outgoing@merit.edu
Vadim Antonov wrote:
> I would like to inject some sanity into the traffic engineering
> discussion by reminding about some small fact of life:
>
> Nobody knows how to measure how what the demanded/available bandwidth
> ratio is when the circuit is overloaded.
I think the point of TE is to avoid overbooking in the first place,
and also calculate a suitably assured protection path. (or just build
for the busy hour, of course)
> What it means that by and large traffic engineering is done by seat of
> the pants.
May be so, but at some point every business will be accountable to
operating cost. This is the hallmark of a mature sector in a commodity
market, in fact.
> PPS Pluris core technology allows to treat traffic as a liquid - unlike simple
> IP routing it works by splitting aggregated streams, which can be sent
> along different paths.
Not by hashing flows I hope. Otherwise, I suspect that non-Newtonian
CFD per macroflow can't possibly be a time-complexity win over the
"simple" MCF optimization problem... :P
Regards,
Andrew Bender
thrupoint.net
