基于反馈控制的多处理器任务调度算法

Proposing an Effective Scheduling Algorithm Based on Feedback Control for Multiprocessing Systems

在高度动态和不确定的计算环境下,系统的负载有极大的不确定性,传统的多处理器调度算法基于最坏执行时间悲观估计负载,造成了系统资源浪费。文章提出了一种基于反馈控制的多处理器任务调度算法,通过动态调整分配在各个处理器上的任务集合,使得每个处理器的CPU利用率保持在参考值附近,保证了任务的实时性。依据控制理论分析了算法的稳定性、稳态以及动态性能,并通过实验验证了算法的实时性和适应性。

Aim. Past scheduling algorithms are, in our opinion, too conservative in that they are based on WCET （worst-ease execution time）. We now propose what we believe to be a new and effective one. Section 2 of the full paper designs our effective scheduling algorithms it, by adjusting the task sets of processors dynamically, keeps the CPU utilization of each processor around its reference value and guarantees not missing the deadline of each task. Section 3 analyzes the stability of the scheduling algorithm, its steady-state performance and transient performance. Section 4 did experiments on the scheduling algorithm~ the experimental results, given in Figs. 4 and 5, prove preliminarily the correctness of our theoretical analysis and the effectiveness of our scheduling algorithm.