Schedulability Checking of Data Flow Tasks in Hard-Real-Time Distributed Systems

Current research on Real Time systems aims to reach new goals in two different directions: from a theoretical point of view the focus is mainly on shared memory systems while, on the other hand, a number of different implementative works make use of distributed system hardware platforms. Our goal is to investigate models which can integrate both views using distributed programs on loosely coupled networks as Real Time elements. This work introduces formal models of schedulability conditions presenting an algorithm able to deterministically decide whether the system can satisfy task requests, providing it with a heuristic mapping function. The algorithm is able to manage Coarse Grain Data Flow programs having Hard-Real-Time constraints: those which have catastrophic effects in case of deadline miss. A pseudo code of the algorithm and some experimental results are also presented in order to validate its applicability and functionality.