[123607] in North American Network Operators' Group
Re: 10GBase-t switch
daemon@ATHENA.MIT.EDU (Kevin Oberman)
Thu Mar 11 17:21:05 2010
To: Dave Temkin <davet1@gmail.com>
In-reply-to: Your message of "Thu, 11 Mar 2010 12:51:00 PST."
<4B9957B4.7080009@gmail.com>
Date: Thu, 11 Mar 2010 14:19:15 -0800
From: "Kevin Oberman" <oberman@es.net>
Cc: nanog@nanog.org
Errors-To: nanog-bounces+nanog.discuss=bloom-picayune.mit.edu@nanog.org
> Date: Thu, 11 Mar 2010 12:51:00 -0800
> From: Dave Temkin <davet1@gmail.com>
>
> Kevin Oberman wrote:
> >> Date: Thu, 11 Mar 2010 12:26:16 +0900
> >> From: Randy Bush <randy@psg.com>
> >>
> >>
> >>> arista 7120t-4s...
> >>>
> >> hot box. but you are giving away the secret sauce!
> >>
> >
> > Hot box for the datacenter, but small buffers make it unsuited for
> > long distances. In the right place, this box can't be beaten in the
> > price/performance realm.
> >
> >
> Can you point to another 1U box that has more than 16MB per-port buffer?
I cannot. It's just that this is not enough buffer for longer distances
with multiple well loaded ports.
As I keep saying, this is the best price/performance box I have seen. I
am not criticizing it, just pointing out that it may not be the solution
to all purposes.
--
R. Kevin Oberman, Network Engineer
Energy Sciences Network (ESnet)
Ernest O. Lawrence Berkeley National Laboratory (Berkeley Lab)
E-mail: oberman@es.net Phone: +1 510 486-8634
Key fingerprint:059B 2DDF 031C 9BA3 14A4 EADA 927D EBB3 987B 3751
