Use of supercomputing towards the generation of a process execution plan in distributed real-time systems

This work consider the scheduling of periodic tasks or processes with real-time constraints in a distributed environment. Each task must be executed meeting deadlines, precedence relationships and resources constraints. The problem of scheduling tasks on a distributed environment can be viewed as a problem of assigning processes to the processors but keeping the schedulability in local environments. Thus, the problem can be divided in two phases: the first phase is assigning processes to processors and the second is to schedule assigned processes in each processor in the distributed environment. This paper focuses in the first phase. It introduces a heuristic mechanism for assigning processes in a distributed environment with real-time constraints. The heuristic mechanism has two alternative ways to perform: one takes into account the utilization factor and the other considers period. The performance of both alternatives proposed is evaluated via simulation on a high performance- computing platform. © 2010 IEEE