[149433] in North American Network Operators' Group
Re: bufferbloat videos are up.
daemon@ATHENA.MIT.EDU (Leo Bicknell)
Fri Feb 3 23:30:36 2012
From: Leo Bicknell <bicknell@ufp.org>
In-Reply-To: <alpine.DEB.2.00.1202040451570.8029@uplift.swm.pp.se>
Date: Fri, 3 Feb 2012 22:29:40 -0600
To: Mikael Abrahamsson <swmike@swm.pp.se>
Cc: North American Network Operators' Group <nanog@nanog.org>
Errors-To: nanog-bounces+nanog.discuss=bloom-picayune.mit.edu@nanog.org
On Feb 3, 2012, at 10:09 PM, Mikael Abrahamsson wrote:
> So basically I agree with your problem statement, however I think it =
would be benficial if your proposed solution was a bit more specific, or =
at least pointed more in that direction. To propose a solution that =
sounds more like "limit buffers to 100ms or less and everything will be =
fine" would indeed remove some of the problem, but it would hurt =
performance for some applications.
The key to the solution is better Adaptive Queue Management, or AQM. As =
long as we have to decide on fixed queue sizes for all traffic, we're =
forced to cater to the most common traffic type.
It would be nice to put queues of different RTT into different queues. =
Today that is basically impossible.
--=20
Leo Bicknell - bicknell@ufp.org - CCIE 3440
PGP keys at http://www.ufp.org/~bicknell/
