Key points are not available for this paper at this time.
A class of algorithms called stochastic fairness queuing is presented. The algorithms are probabilistic variants of fairness queuing. They do not require an exact mapping and thus are suitable for high-speed software or firmware implementation. The algorithms span a broad range of CPU, memory, and fairness tradeoffs. It is shown that the worst-case execution-speed stochastic fairness queuing is faster than the best-case execution speed of all of the implementations of fair queuing presented. This advantage is larger for protocols with longer addresses, e.g. the ISO protocol suite.>
Paul E. McKenney (Wed,) studied this question.