Non preemptive static priority with network calculus

The paper addresses performance analysis of embedded real time networks. We use network calculus to assess the quality of service of a residual flow in a context of aggregation with non preemptive fixed priority scheduling. The main contribution concerns the evaluation of the residual service, given to the low priority flows. In previous works, the effect of the non-preemption seems to be not well taken into account. In particular, when a non preemptive flow is served, it benefits from the full speed from the server, even if, from a long term point of view, it gets only a fractional part. The modeling of this aspect is the starting point of this work.