Journal of South China University of Technology (Natural Science Edition) ›› 2010, Vol. 38 ›› Issue (7): 1-6.doi: 10.3969/j.issn.1000-565X.2010.07.001

• Computer Science & Technology •     Next Articles

Task Scheduling Algorithm Based on Intelligent Network Disk Storage System

Zhao Yue-long  Liu Min-na  Wang Wen-feng   

  1. School of Computer Science and Engineering,South China University of Technology,Guangzhou 510006,Guangdong,China
  • Received:2009-05-20 Revised:2010-03-12 Online:2010-07-25 Published:2010-07-25
  • Contact: 赵跃龙（1958-）,男,教授,博士生导师,主要从事计算机系统结构和网络存储系统研究. E-mail:ylzhao1@scut.edu.cn
  • About author:赵跃龙（1958-）,男,教授,博士生导师,主要从事计算机系统结构和网络存储系统研究.
  • Supported by:

    国家自然科学基金资助项目（60573145）; 教育部博士点基金资助项目（200805610019）

PDF

870

Abstract:

Although the existing scheduling algorithm of intelligent network disk （ IND） storage system minimizes the weighted time cost of tasks,it may result in a starvation phenomenon because many tasks cannot be executed for a long time. In order to solve this problem,an controllable scheduling algorithm （ CSA） is proposed,which divides the tasks into several step chains,computes the ρ factor of tasks according to the execution time and weight of step chains,and selects the unexecuted step chain according to both the ρ factor and the execution time of the tasks of ρ factor. Experimental results indicate that,as compared with the existing IND algorithm,the proposed CAS is of similar total weighted time cost,lower average turnaround time cost of tasks and completion time cost of short tasks, and that it effectively eliminates the starvation with balanced efficiency and fairness.

Key words: intelligent network disk storage system, controllable scheduling algorithm, step chain, starvation phenomenon