On 29-sep-04, at 23:41, Dean Anderson wrote:
Some time back we were talking about anycast being a bad thing on DNS Root
servers. It was suggested by that conversations typically take only one
path as a result of CEF-like caching. I noted that providers were working
on per packet load balancing. Well, here it is, in the "major vendor":
Per-Packet Load Balancing
http://www.cisco.com/univercd/cc/td/doc/product/software/ios120/ 120newft/120limit/120s/120s21/pplb.htm
Unless I'm very much mistaken, at least _some_ older Cisco boxes have been able to do this for a very long time.
Note though that it's *very* hard to create a setup where packets are delivered to different multicast instances, as it's hard to imagine how any real-world anycast setup could match the criteria in
http://www.cisco.com/en/US/tech/tk365/tk80/ technologies_tech_note09186a0080094431.shtml#bgpmpath
(Although a good way to guarantee this would be to use different ASes to source the different anycast instances.)
So, it seems that we need to review whether the use of anycast on the root
nameservers is a good idea.
I think the ship has sailed a long time on whether this was going to happen at all. However, now would be a good time to start a discussion on how much anycasting is enough. It would be good to keep a reasonable number of root servers non-anycasted.
I'll be happy to list the reasons for this (apart from general healthy conservatism) on some appropriate forum.
_______________________________________________ Ietf@xxxxxxxx https://www1.ietf.org/mailman/listinfo/ietf