Hi Brian, I know that an ISP can learn infornation about path quality off of its network. I also know that many ISPs have no interest in learning about quality off of their network. You are right that discretely mapping empirical behaviour to datum such as AS Path, external_peering_link, and other various variables like Time of Day, etc... is difficult. Some folks have made progress on this, and use it to make things better, some in a manual fashion, some in a more and more automated fashion. Some people would suggest to solve off-net quality problems by a/ blaming, or b/ suggesting that the other network increase bandwidth, or c/ rerouting. In order to do c/ sometimes it is helpful to learn information about different paths, from different vantage points. So, I don't really want to delve too deep into the theory of what exactly DI is doing, I suspect they'll tell us if they are as clever as they seem to be. I do know, however, that the gaining information about external performance can be useful for optimizing egress traffic flows, both on a micro, mid, and macro basis. With regards to your suggestion below about standardization, I think it would be great if stuff like IPPM, IPDR and such were done in the realm of off-net performance. However, let's not confuse operational implementations (for example, off-net brains thinking about what to do) with standardized protocols required for interacting with others. Egress flow optimization can be done autonomous of standards, and is, today :-) -alan Thus spake Brian Wallingford (brian@meganet.net) on or about Thu, Oct 25, 2001 at 11:41:20PM -0400:
On Thu, 25 Oct 2001, Alan Hannan wrote:
: : I suspect that DI, like many other companies, is actively monitoring : external sites to track, study, and hopefully improve connectivity : quality to them.
So, you suspect that Digisle has come up with a scheme for jiving latency/path efficiency with as-paths, and integrating that into their own routing policies? Noone has done this well yet. Those who have tried have failed to realize the need for standardization, or have decided to ignore such in the interest of developing a patented, proprietary scheme (which is, based solely on common sense, doomed).
Conclusion: Digisle's probes are not at all justified. Hopefully, they're listening.
Admittedly, I may be misreading your theory. If so, please elaborate.
cheers, brian