On a Real-Time Scheduling Problem

Abstract

We study the problem of scheduling periodic-time-critical tasks on multiprocessor computing systems. A periodic-time-critical task consists of an infinite number of requests, each of which has a prescribed deadline. The scheduling problem is to specify an order in which the requests of a set of tasks are to be executed and the processor to be used, with the goal of meeting all the deadlines with a minimum number of processors. Since the problem of determining the minimum number of processors is difficult, we consider two heuristic algorithms. These are easy to implement and yield a number of processors that is reasonably close to the minimum number. We also analyze the worst-case behavior of these heuristics.

An optimal boundary fair scheduling algorithm for multiprocessor real-time systems

“…Although rate monotonic (RM) scheduling and earliest deadline first (EDF) have been shown to be optimal in uni-processor periodic real-time systems, for static and dynamic priority assignments, respectively [18], neither of them is optimal for multiprocessor real-time systems [11]. Traditionally, there are two major approaches for scheduling real-time tasks in multiprocessor real-time systems:…”

“…partitioned and global scheduling [10,11]. In partitioned scheduling, each task is assigned to a specific processor and processors can only execute tasks that are assigned to them.…”

“…In general, there are two major approaches for scheduling real-time tasks in multiprocessor realtime systems: partitioned and global scheduling [10,11]. With the emergence of multicore processors, where the shared cache architecture can significantly alleviate the task migration overhead for global scheduling, there is a reviving interest in global scheduling and many interesting results have been reported in recent years.…”

Worst-case utilization bound for EDF scheduling on real-time multiprocessor systems

“…Thus, searching for optimal allocation algorithms is not practical. Several heuristic allocation algorithms have been proposed [7], [5], [1], [2], [8]. One of these, known as the First Fit (FF) algorithm, which is focused on in this paper.…”

“…If all the tasks have an utilization factor under a value «, the worst-case achievable utilization is proved to be that given by equation (2).…”