Probabilistic or deterministic QoS guarantees for flows scheduled with FP/DM

In this paper, we consider flows requiring quantitative end-to-end QoS guarantees. We focus more particularly on the end-to-end response times of flows and their probability of meeting their end-to-end deadlines. We assume that packets are scheduled according to their fixed priority, reflecting the importance degree of the flow. If on a node two packets have the same fixed priority, the packet with the smallest relative deadline on the node considered is scheduled first. Therefore, this non-preemptive scheduling, called FP/DM, takes into account the deadline constraint. The deterministic approach, based on a worst case analysis, may lead to a bound on the flow end-to-end response times that can be reached infrequently. A network dimensioning based on this bound can be expensive in terms of resources. That is why we are interested in probabilistic QoS guarantees. We then evaluate the benefits brought by FP/DM with regard to FP/FIFO. With the deterministic approach, we compare the worst case response times and the laxities of the flows considered. With the probabilistic approach, we compare the probabilities of meeting the deadlines for the flows considered as well as the p-schedulabibility of the flow se