作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程

• 体系结构与软件技术 • 上一篇    下一篇

一种面向多核系统的Linux 任务调度算法

曹 越a,b,c,顾乃杰a,b,c,任开新a,b,c,张 旭a,b,c,吴志强a,b,c   

  1. (中国科学技术大学a. 计算机科学与技术学院; b. 安徽省计算与通信软件重点实验室; c. 先进技术研究院,合肥230027)
  • 收稿日期:2014-03-24 出版日期:2015-02-15 发布日期:2015-02-13
  • 作者简介:曹 越(1990 - ),男,硕士研究生,主研方向:并行计算,流程优化;顾乃杰(通讯作者),教授、博士生导师;任开新,讲师; 张 旭,博士研究生;吴志强,硕士研究生。
  • 基金资助:
    “核高基”重大专项(2009ZX01028-002-003-005);高等学校学科创新引智计划基金资助项目(B07033)。

A Linux Task Scheduling Algorithm for Multi-core System

CAO Yue  a,b,c ,GU Naijie  a,b,c ,REN Kaixin  a,b,c ,ZHANG Xu  a,b,c ,WU Zhiqiang  a,b,c   

  1. (a. School of Computer Science and Technology; b. Anhui Province Key Laboratory of Computing and Communication Software;c. Institute of Advanced Technology,University of Science and Technology of China,Hefei 230027,China)
  • Received:2014-03-24 Online:2015-02-15 Published:2015-02-13

摘要: 针对Linux 任务调度算法在多核系统中交互性能差的问题,提出一种分组任务调度算法GFS。根据多核系统硬件特性,自动配置物理距离近的一组CPU 共享一个任务运行队列,通过平衡组内CPU 对任务运行队列的访问竞争与任务迁移的代价,实现组间任务运行队列的负载均衡,减少调度延迟。通过优先调度唤醒任务,加快多核系统中交互任务的响应速度。测试结果表明,在不同任务负载下,GFS 能够明显降低交互任务的平均响应时间,从而有效提高多核系统交互应用的调度性能。

关键词: 多核系统, 调度算法, 交互性能, 自动配置, 唤醒任务, 载均衡

Abstract: To improve interactive performance of Linux in multi-core systems,this paper designs and implements an improved task scheduling algorithm named Group Fair Schedule (GFS). According to the hardware characteristics of multi-core system, GFS allows to configure a group of CPUs with close affinity to share one task run queue automatically,so that the cost of competitive access,task migration inside a group and run queue load balance between groups can be weighed, and reduces scheduling delay. GFS gives priority to awakening tasks so that interactive performance of multi-core systems is improved. Test results show that GFS decreases the average response time of interactive tasks under different background loads, and improves interactive performance of multi-core systems effectively.

Key words: multi-core system, scheduling algorithm, interactive performance, automotive configuration, awakening task, load balance

中图分类号: