Dave, the value to be found in that NANOG post in my message no. 168 was not, IMO, what he said face value, but for its catalyzing effect in getting one to think about concepts related to QoS at what appear to us today to be ridiculously high speeds.
How does a system take the time, for instance, to discriminate between the nuances of a particular packet's requirements and those of another's, when traveling at a rate measured in the terabits of data per second. Or greater.
One of his points was that you simply don't. You instead treat entire flows in aggregate, comprised of groups <which perhaps have been labeled> of like services with similar needs, as such, but not at the granularity of an individual user's packet.
Curtis, others, do you care to jump in here?
FAC
ps - I was not able to open the real-internet.org article, for some reason. I was going by the quotations in the NANOG poster's original message, only. |
