基于MrsP协议的任务划分优化算法

多处理器实时系统中,调度和资源共享是核心问题,与之相对应的调度算法和共享资源访问协议将直接影响系统的性能,这就要求调度算法和资源访问协议在保证实时性的基础上尽量发挥硬件平台的计算能力。然而,现有的调度算法多假设任务相互独立,没有考虑任务之间的资源共享,共享资源访问协议也多侧重于规则和最坏响应时间分析。对此,将P-RM算法和MrsP协议相结合,得出了多处理器实时系统的整体可调度性条件。文中根据MrsP协议的特性,提出了一种减小阻塞时间的任务划分算法,通过改进任务利用率的计算方式解决了关键区重复计算的问题,与之前的任务划分算法相比,也解决了关键区重复计算以及任务分类后拆分再分配的问题。实验表明,该算法所需要的处理器数目减少了15%~20%。

Task Partitioning Optimization Algorithm Based on MrsP Protocol

Scheduling and resource sharing are the core problems in multiprocessor real-time systems, the corresponding scheduling algorithm and shared resource access protocol will directly affect the performance of the system, which requires the scheduling algorithm and resource access protocol to maximize the computing power of the hardware platform on the basis of ensuring real-time performance. However, most existing scheduling algorithms assume that tasks are independent of each other and do not consider resource sharing among tasks. Besides, shared resource access protocols also focus on rules and worst-case response time analysis. In this regard, the whole schedule ability condition of multiprocessor real-time system is obtained by combining P-RM algorithm and MrsP protocol. According to the characteristics of the MrsP protocol, this study proposes a task division algorithm to reduce the blocking time. By improving the calculation method of the task utilization, the proposed method solves the problem of repeated calculation in the critical area. Compared with the previous task partitioning algorithm, the proposed algorithm also solves the key area of double-counting and splits the redistribution after task classification problem. Experiments resalts show that the number of processors required by the algorithm is reduced by 15% to 20%.