Scheduling and Priority Mapping for Static Real-Time Middleware

This paperpresents a middleware real-time scheduling technique for static,distributed, real-time applications. The technique uses globaldeadline monotonic priority assignment to clients and the DistributedPriority Ceiling protocol to provide concurrency control andpriorities for server execution. The paper presents a new algorithmfor mapping the potentially large number of unique global prioritiesrequired by this scheduling technique to the restricted set ofpriorities provided by commercial real-time operating systems.This algorithm is called Lowest Overlap First Priority Mapping;we prove that it is optimal among direct priority mapping algorithms.This paper also presents the implementation of these real-timemiddleware scheduling techniques in a Scheduling Service thatmeets the interface proposed for such a service in the Real-TimeCORBA 1.0 standard. Our prototype Scheduling Service is integratedwith the commercial PERTS tool that provides schedulability analysisand automated generation of global and local priorities for clientsand servers.