In this paper, we address the problem of parametric schedulability analysis of distributed real-time systems scheduled by fixed priority. We propose two different approaches to parametric analysis. The first one is a novel analytic technique that extends single-processor sensitivity analysis to the case of distributed systems. The second approach is based on model checking of Parametric Stopwatch Automata (PSA): we generate a PSA model from a high-level description of the system, and then we

more »

... ly the Inverse Method to obtain all possible behaviours of the system. Both techniques have been implemented in two software tools, and they have been compared with classical holistic analysis on two meaningful test cases. The results show that the analytic method provides results similar to classical holistic analysis in a very efficient way, whereas the PSA approach is slower but covers the entire space of solutions. possible to model a larger class of constraints, and perform parametric analysis on many different variables, for example task offsets. This approach has been recently extended to distributed real-time systems [18] . Also grounded on PTA and PSA is the Inverse Method [6], applied in particular to schedulability analysis [13] . This method is very general because it permits to perform analysis on any system parameter. However, this generality may be paid in terms of complexity of the analysis. In this paper, we aim at performing fully parametric analysis of real-time distributed systems. We first present extensions of the methods proposed in [8] to the case of distributed real-time systems. We also present a model of a distributed real-time systems using PSA, and compare the two approaches against classical analysis in Mast.