Re:How We Run BGP on Top of OpenFlow
by iSloth on Saturday March 26, 2016 @03:51PM
(#11367148)
Seems to be more, how to get bgp packets to an open flow server to do stuff...
I'd be interested as a network techy to see how they actually do the rest of bgp on openflow/sdn, like holding multiple full tables on the server and how the switch has enough memory to deal with that amount of information...
Re:How We Run BGP on Top of OpenFlow
by sspies on Saturday March 26, 2016 @04:19PM
(#11367283)
Actually, each tenant has just a view of the full table. There is no need to save the same routes for each customer over and over again. Furthermore, there is aggregation done before a route is installed on the switch.
Their strategy I believe was that if you were optimizing for latency(as opposed to price if you had multiple transit providers), was that it would do traceroutes out to your TOP 100 destination AS and find the AS path with the lowest latency and set the route preference within your AS to prefer a certain transit provider outbound.
How does your product work given that you don't have any control or interaction with the AWS AS?
Re:How We Run BGP on Top of OpenFlow
by pbarnes_1 on Saturday March 26, 2016 @07:44PM
(#11368055)
Your front page needs a much better description of what it is you actually do. I run networks/servers/routers and spent 15 minutes on your site and still don't get it...
Re:How We Run BGP on Top of OpenFlow
by bluecmd on Sunday March 27, 2016 @05:50AM
(#11369481)
Really cool! I would like to play with this, but not specially BGP. Is there a toolkit or code that I could use to get the PACKET_IN/PACKET_OUT <-> TAP behaviour?
The Wingdings J strikes again!
https://blogs.msdn.microsoft.com/oldnewthing/20060523-10/?p=...
http://chris.pirillo.com/j-smiley-outlook-email-problem-and-...
I'd be interested as a network techy to see how they actually do the rest of bgp on openflow/sdn, like holding multiple full tables on the server and how the switch has enough memory to deal with that amount of information...
http://www.internap.com/network-services/miro-controller/
Their strategy I believe was that if you were optimizing for latency(as opposed to price if you had multiple transit providers), was that it would do traceroutes out to your TOP 100 destination AS and find the AS path with the lowest latency and set the route preference within your AS to prefer a certain transit provider outbound.
How does your product work given that you don't have any control or interaction with the AWS AS?