[98477] in North American Network Operators' Group
Re: too many variables
daemon@ATHENA.MIT.EDU (bmanning@vacation.karoshi.com)
Thu Aug 9 17:35:49 2007
Date: Thu, 9 Aug 2007 21:10:54 +0000
From: bmanning@vacation.karoshi.com
To: Leigh Porter <leigh.porter@ukbroadband.com>
Cc: Patrick Giagnocavo <patrick@zill.net>, nanog@nanog.org
In-Reply-To: <46BB6682.9020200@ukbroadband.com>
Errors-To: owner-nanog@merit.edu
On Thu, Aug 09, 2007 at 08:09:54PM +0100, Leigh Porter wrote:
>
>
> Yes a very big unless. Multi-core processors are already available that
> would make very large BGP convergence possible. Change the algorithm as
> well and perhaps add some multi-threading to it and it's even better.
i'll be happy to review the data sheets and prices of routers
w/ multicore processors. pointers accepted.
changing the algorithm might be a bit harder, as i think you'll
need to change the BGP core spec for that.
--bill
>
>
> --
> Leigh Porter
>
>
> Patrick Giagnocavo wrote:
> >
> >
> >On Aug 9, 2007, at 12:21 PM, bmanning@vacation.karoshi.com wrote:
> >
> >> so putting a stake in the ground, BGP will stop working @ around
> >> 2,500,000 routes - can't converge... regardless of IPv4 or IPv6.
> >> unless the CPU's change or the convergence algorithm changes.
> >
> >That is a pretty big "unless" .
> >
> >Cordially
> >
> >Patrick Giagnocavo
> >patrick@zill.net
> >
> >
