nanog mailing list archives

Re: BGP offloading (fixing legacy router BGP scalability issues)


From: Pawel Rybczyk <nogs () border6 com>
Date: Thu, 02 Apr 2015 13:43:15 +0200

Hi Freddy,

As Paul has mentioned, you could check the David's project - SIR, look
at his presentation:
https://www.youtube.com/watch?v=o1njanXhQqM

We've also developed a platform for the BGP monitoring and routing
optimization which could solve your problem. It would inject to the
border routers only TOP X prefixes with which you exchange most of the
traffic. The added value would be that route orders point to best
performing transit (low latency, 0 packet loss) per distant prefix.

If you are interested to know more about our software please contact me
off-list.


-- 
Regards,
Pawel Rybczyk
Regional Manager
BORDER 6 sp. z o.o.
pawel.rybczyk () border6 com
office: +48 22 242 89 51 (ext.103)
mobile: +48 664 300 375


David Barroso's (Spotify) SDN Internet Router [0] comes to mind.

0 - https://github.com/dbarrosop/sir

On 4/2/2015 午後 07:47, Baldur Norddahl wrote:
Filtering countries is a bad idea, but it is probably possible to create
filters so 99% of your actual traffic is handled by a relatively small
subset of global routes and the remaining 1% routed via a default
route or
via a Linux box.

Anyone know of tools and methods to do this? How effective is it ( how
many
routes is necessary to capture 99% of the traffic)?

Regards

Baldur



Current thread: