[149063] in North American Network Operators' Group
RE: 10GE TOR port buffers (was Re: 10G switch recommendaton)
daemon@ATHENA.MIT.EDU (George Bonser)
Fri Jan 27 18:01:58 2012
From: George Bonser <gbonser@seven.com>
To: bas <kilobit@gmail.com>
Date: Fri, 27 Jan 2012 23:01:10 +0000
In-Reply-To: <CAEs2Zi+Rd14=kGiDtHSdsH80NVQbrrYRBR4o55cozgUyq=LHJw@mail.gmail.com>
Cc: "nanog@nanog.org" <nanog@nanog.org>
Errors-To: nanog-bounces+nanog.discuss=bloom-picayune.mit.edu@nanog.org
> -----Original Message-----
> From: bas=20
> Sent: Friday, January 27, 2012 2:54 PM
> To: George Bonser
> Subject: Re: 10GE TOR port buffers (was Re: 10G switch recommendaton)
>=20
> While I agree _again_!!!!!
>=20
> It does not explain why TOR boxes have little buffers and chassis box
> have many.....
Because that is what customers think they want so that is what they sell. =
Customers don't realize that the added buffers are killing performance.
I have had network sales reps tell me "you want this switch over here, it h=
as bigger buffers" when that is exactly the opposite of what I want unless =
I am sending a bunch of UDP through very brief microbursts. If you are sen=
ding TCP streams, what you want is less buffering. Spend the extra money on=
more bandwidth to relieve the congestion.
Going to 4 10G aggregated uplinks instead of 2 might get you a much better =
performance boost than increasing buffers. But it really depends on the en=
d to end application.
