An end-to-end approach to schedule tasks with shared resources in multiprocessor systems

Abstract

We propose an end-to-end approach to scheduling tasks that share resources in a multiprocessor or distributed systems. In our approach, each task is mapped into a chain of subtasks, depending on its resource accesses. After each subtask is assigned a proper priority, its worst-case response time can be bounded. Consequently the worst-case response time of each task can be obtained and the schedulability of each task can be verified by comparing the worst-case response time with its relative deadline.<>