[87398] in North American Network Operators' Group
Re: The Qos PipeDream [Was: RE: Two Tiered Internet]
daemon@ATHENA.MIT.EDU (David Meyer)
Thu Dec 15 22:39:41 2005
Date: Thu, 15 Dec 2005 19:39:14 -0800
From: David Meyer <dmm@1-4-5.net>
To: "Christopher L. Morrow" <christopher.morrow@mci.com>
Cc: nanog@merit.edu
In-Reply-To: <20051216033456.GA5192@1-4-5.net>
Errors-To: owner-nanog@merit.edu
--VS++wcV0S1rZb1Fb
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
Content-Transfer-Encoding: quoted-printable
On Thu, Dec 15, 2005 at 07:34:56PM -0800, David Meyer wrote:
> On Fri, Dec 16, 2005 at 03:29:29AM +0000, Christopher L. Morrow wrote:
> >=20
> > On Thu, 15 Dec 2005, John Kristoff wrote:
> >=20
> > >
> > > On Thu, 15 Dec 2005 19:15:49 -0500 (EST)
> > > Sean Donelan <sean@donelan.com> wrote:
> > >
> > > > AT&T, Global Crossing, Level3, MCI, Savvis, Sprint, etc have sold
> > > > QOS services for years. Level3 says 20% of the traffic over its
> > >
> > > What do they mean by QoS? Is it IntServ, DiffServ, PVCs, the law of
> >=20
> > I think also mostly this applies to private network things as well...
> > which mostly ends up being: "backups get 20% of the pipe and oracle-for=
ms
> > gets 70%" (or some variation on that mix... what with 8 queues or whate=
ver
> > on the private network you can just go to town :) )
> >=20
> > Speaking to MCI's offering on the public network it's (not sold much) j=
ust
> > qos on the end link to the customer... It's supposed to help VOIP or ot=
her
> > jitter prone things behave 'better'. I'm not sure that we do much in the
> > way of qos towards the customer aside from respecting the bits on the
> > packets that arrive (no remarking as I recall). So, what does this get =
you
> > aside from 'feeling better' ?
> >=20
> > > averages or something else? I've had to deploy it on a campus network
> > > and in doing so it seems like I've tread into territory where few if
> > > any big networks are to be found. Nortel apparently removed DiffServ
> >=20
> > most large networks (as was said a few times I think) don't really need=
it
> > in their cores. I think I've seen a nice presentation regarding the
> > queuing delay induced on 'large pipe' networks, basically showing that =
qos
> > is pointless if your links are +ds3 and not 100% full. Someone might ha=
ve
> > a pointer handy for that?
=20
You might check slides 35-38 in
http://www.1-4-5.net/~dmm/sprintlink_and_mpls.ppt=20
Dave
--VS++wcV0S1rZb1Fb
Content-Type: application/pgp-signature
Content-Disposition: inline
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.2.4 (GNU/Linux)
iD8DBQFDojbhORgD1qCZ2KcRAqkuAJwL2qTqu2U2PMTSXZ+baYSCJNTpOgCgkgIe
FNdFOFQupKbt8T4FuktBdbs=
=dCsP
-----END PGP SIGNATURE-----
--VS++wcV0S1rZb1Fb--
