一种基于任务计算密度优先的改进EDF实时调度算法研究  

Research on an Improved EDF Real-time Scheduling Algorithm Based on Task Computing Density First

作　　者：李赞[1] 黄燕挺[1] Li Zan;Huang Yanting(Zhongshan Institute,University of Electronic Science and Technology,Zhongshan 528400)

机构地区：[1]电子科技大学中山学院,中山528400

出　　处：《现代计算机》2022年第3期66-69,共4页Modern Computer

摘　　要：实时系统为了保证系统中多个任务的稳定执行,会根据任务的优先级、空闲时长以及截止时间等属性选择任务运行,实现系统资源的合理分配,达到系统实时性和可调度性要求。EDF和LLF是较常提及的调度算法,然而LLF算法的设计逻辑存在缺陷,EDF算法的实现细节不够完善,本文提出了一种基于任务需求计算密度优先的改进EDF算法,是一种价值较高的实时调度算法。In order to ensure the stable execution of multiple tasks in the system,the real-time system will choose target task according to the attributes such as task priority,idle time and deadline,so as to realize the reasonable allocation of system re⁃sources and meet the requirements of real-time and schedulability of the system.EDF and LLF are commonly mentioned schedul⁃ing algorithms,but the design logic of LLF algorithm is flawed,and the implementation details of EDF algorithm are not perfect,This paper presents an improved EDF algorithm based on the required computing density of the task,which is a real-time schedul⁃ing algorithm with high implementation value.

关 键 词：实时系统 EDF LLF 需求计算密度 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]