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 ›› 2013, Vol. 39 ›› Issue (4): 58-61. doi: 10.3969/j.issn.1000-3428.2013.04.014

• 体系结构与软件技术 • 上一篇    下一篇

基于缓存竞争优化的Linux进程调度策略

夏 厦,李 俊   

  1. (中国科学技术大学自动化系,合肥 230027)
  • 收稿日期:2012-04-28 出版日期:2013-04-15 发布日期:2013-04-12
  • 作者简介:夏 厦(1988-),男,硕士研究生,主研方向:网络传播与控制,操作系统;李 俊,副教授、博士
  • 基金资助:
    中央高校基本科研业务费专项基金资助项目(Wk2100100006)

Linux Process Scheduling Strategy Based on Cache Contention Optimization

XIA Sha, LI Jun   

  1. (Department of Automation, University of Science and Technology of China, Hefei 230027, China)
  • Received:2012-04-28 Online:2013-04-15 Published:2013-04-12

摘要: 分析Linux经典内核版本2.6.22的进程调度算法,利用性能监测单元的监测信息,给出3个性能指标CMR、CRR、OCIP对进程的缓存竞争性强弱进行刻画,以此为依据,采用轮询算法优化Linux下的进程调度顺序,尽量避免在CPU上同时运行多个缓存竞争力强的进程,减小系统因缓存竞争产生的性能损耗。在benchmark上的测试结果表明,该方法能够提升系统在中、高负载下运行时的性能,在高负载下运行时的性能提升比例可达6%左右。

关键词: Linux内核, 片上多处理器, 进程调度, 性能监测单元, 进程行为, 缓存竞争

Abstract: According to the analysis of the process scheduling algorithm of Linux kernel 2.6.22, through the information getting from Performance Monitor Unit(PMU), this paper puts forward three performance indexes CMR, CRR and OCIP to describe the process behavior of cache contention. On the basis of this, it uses polling algorithm to optimize the process scheduling in order to reduce the cache contention of Last Level Cache(LLC). Benchmark test results show that this algorithm can improve about 6% performance when the system load is high.

Key words: Linux kernel, Chip Multi-processor(CMP), process scheduling, Performance Monitor Unit(PMU), process behavior, cache contention

中图分类号: