Best-case analysis for improving the worst-case schedulability test for distributed hard real-time systems

Abstract

We present an improvement of the schedulability analysis technique for distributed hard real time systems that allows us to increase the maximum schedulable resource utilization. Since the improvement affects only the analysis technique, there is no additional implementation cost for the application itself. The improvement in the analysis consists of calculating a lower bound for the best case response time of tasks and messages, in order to reduce the estimated jitter in the activation of subsequent tasks and messages. This reduction of jitter implies reduced worst case bounds for the response times, and thus allows us to increase the maximum schedulable utilization. The paper explores two different ways to calculate a lower bound on the best case execution times. The paper also shows the results of simulations that we have carried out, in which we found that we could increase the maximum schedulable limit of the different resources by approximately 5% more utilization.