A systematic optimization process for multiple-instance resource sharing in real-time systems is presented. The authors derive the schedulability condition for systems with such resources and present an algorithm which can be used to divide a resource pool into smaller groups in order to improve the worst-case blocking behavior. They present the system model used and review some related work. The multi-instance priority ceiling protocol and its properties are discussed, the effect of resource preallocation on the schedulability of a system is studied, and an optimal resource preallocation algorithm is presented.>

In real-time systems, jobs must be finished before their deadlines. When several jobs have similar requests, handling related operations together may improve both the response times of individual jobs and the total execution time of the system. This is because many jobs have common operations which can be performed only once if jobs are coalesced as a single job. Scheduling algorithms which use the technique of job coalescing to meet more job deadlines are studied. Optimal scheduling algorithms for different system models are investigated. Due to the high complexities of these optimal algorithms, several online heuristic algorithms and their performances are investigated.>