[93839] in North American Network Operators' Group

home help back first fref pref prev next nref lref last post

Re: Collocation Access

daemon@ATHENA.MIT.EDU (Joe Provo)
Thu Dec 28 16:21:33 2006

Date: Thu, 28 Dec 2006 16:20:42 -0500
From: Joe Provo <nanog-post@rsuc.gweep.net>
To: nanog@merit.edu
Reply-To: nanog-post@rsuc.gweep.net
In-Reply-To: <A6411D37-B74B-4253-A129-BEE510E3DFC0@t1r.com>
Errors-To: owner-nanog@merit.edu


On Thu, Dec 28, 2006 at 02:06:30PM -0500, Daniel Golding wrote:
[snip]
> Time for a colocation reality check. 
[snip]
> Until supply catches up to demand, only price and power will matter  
> to most folks, along with an acceptable level of facility redundancy  
> (Tier III for most).

One 'reality check' that is required is that some of the time,
everything fails.  Can we please have redundant facilities rather 
than just facility redundancy?  Part of the whole packet-based, 
layer-services communications model is the simple "avoid central 
hardened SPoF".

Joe

-- 
             RSUC / GweepNet / Spunk / FnB / Usenix / SAGE

home help back first fref pref prev next nref lref last post