The iTFF scheduling algorithm for input-queued switches

In crossbar-based input-queued scheduling, i SLIP algorithm is well known for its high throughput and low implementation complexity. However under bursty arrivals, its average input latency increases dramatically and quite a few cells will be dropped as the input buffer overflows. Motivated by cutting down the cell loss rate without increasing the average input latency, we present a novel-scheduling algorithm called iTFF (iterative "Time to leave" and "Full or not" First), which has better performance than i SLIP under bursty traffic conditions. Simulation results indicate that iTFF restrains the cell loss rate exponentially and yet maintains low average input latency. Moreover, iTFF can be proved to be stable for all admissible uniform i.i.d. Bernoulli traffic, and easily implemented in hardware to achieve high speed.