[96603] in North American Network Operators' Group
Re: RTT from NY to New Delhi?
daemon@ATHENA.MIT.EDU (Chris L. Morrow)
Wed May 16 10:25:27 2007
Date: Wed, 16 May 2007 14:09:19 +0000 (GMT)
From: "Chris L. Morrow" <christopher.morrow@verizonbusiness.com>
In-reply-to: <20070516133704.GA24612@roxanne.org>
To: Eric Gauthier <eric@roxanne.org>
Cc: Joe Maimon <jmaimon@ttec.com>, nanog <nanog@merit.edu>
Errors-To: owner-nanog@merit.edu
On Wed, 16 May 2007, Eric Gauthier wrote:
>
> Heya,
>
> > What should I expect?
> >
> > I am seeing ~350 from a vendor provided mpls cloud to a site in
> >
> > Sukhrali Chowk, Gurgaon, Haryana, India
>
> We just did a video conference between Boston and New Delhi, via NYC, and
> we were seeing around 250ms. However, VSNL was QoS'ing our traffic across
> their backbone, so I'd expect normal traffic to take a bit longer. When
> we originally investigated this, we were expecting to see around 300ms to
> 350ms.
hrm, qos doesn't necessarily mean longer RTT, it means preference in
(tight/busy/hot) paths, right? So... if VNSL's network along your path is
oc-48 with only 1mbps of traffic on it and you are taking only 1mbps more
... probably there isn't any change, yes? If it's a 1mbps path and you are
taking 1mbps then... other folks get starved out and potentially get
longer RTT.
(just trying to clarify the QOS boogie-man)
