摘要
针对大多数现有的异构系统调度算法没有考虑由多类任务特别是抢占式任务所引起的可用性需求的不足,在现有基于可用性的非抢占式任务调度算法的基础上,通过计算任务的平均等待时间来确定优先级等级,对异构系统中多类抢占式任务的可用性约束的调度问题进行了探索,提出了一种基于可用性的抢占式优先调度算法P-SSAC。该算法在不增加硬件代价的前提条件下通过调度增加了系统的可用性,缩短了任务的平均等待时间,同时该算法可对抢占式的任务进行有效调度。仿真实验结果表明,该算法有效实现了异构系统可用性和任务等待时间之间的折中。
Most existing scheduling algorithms designed for heterogeneous systems do not factor in availability requirements imposed by multiclass tasks especially preemptive tasks.To remedy this shortcoming,based on the existing scheduling algorithm,this paper researched into the scheduling problem for multiclass preemptive tasks running in heterogeneous systems with availability constraints.In an effort to explore this issue,the paper calculated the average waiting time to give prioty to each node,and improved the existing algorithm to work under the preemptive model.This paper proposed a preemptive task scheduling algorithm based on availability in heterogeneous systems,which could improve the availability of heterogeneous systems without inducing the cost of the hardware while reducing average waiting time of tasks.Experimental results show that this algorithm can achieve a good trade-off between availability and waiting time.
出处
《计算机应用研究》
CSCD
北大核心
2010年第7期2498-2501,共4页
Application Research of Computers
基金
国家自然科学基金资助项目(90715029
60603053)
衡阳师范学院科学基金资助项目(07A30)
关键词
异构系统
可用性约束
多类任务
优先调度
抢占式
heterogeneous systems
availability constraints
multiclass tasks
priority scheduling
preemptive