[1501] in North American Network Operators' Group
Re: value of co-location
daemon@ATHENA.MIT.EDU (Kent W. England)
Tue Jan 23 12:39:39 1996
Date: Tue, 23 Jan 1996 09:02:27 -0800
To: "Paul 'Corwin' Frommeyer" <corwin@palas.com>, paul@vix.com
From: kwe@6SigmaNets.com (Kent W. England)
Cc: nanog@merit.edu, corwin@palas.com
...
>Clueing the various equipment manufacturers in as to what direction the
>hardware should be evolving in is probably at least worth the effort ...
>
>A fast .02 on my part would be that something in the way of non-blocking
>backplane design needs to be _advanced_ in order to be able to scale current
>router technology up.
Take a look at <http://galaxy.netstar.com/products/>. There is a nice
diagram that illustrates that a nonblocking switched backplane can work in
routers as well as cell switches. Note the aggregate bandwidth on this box.
I think MCI bought some of these for the vBNS before Dennis left for
Ipsilon. Ipsilon is cooking up some solutions for these problems but isn't
talking publicly about anything yet. Let us know, Dennis, when the press
releases are ready.
I wouldn't be surprised to see a lot more crosspoint switches in high speed
routers. What else can you do to get to OC-12? Oh, right, lots of cisco
chassis and about seven FDDI rings.
--Kent
