通信学报 ›› 2015, Vol. 36 ›› Issue (7): 1-72.doi: 10.11959/j.issn.1000-436x.2015162

• 学术论文 •    下一篇

面向分布式环境的信号驱动任务调度算法

辛宇1,杨静1,谢志强2   

  1. 1 哈尔滨工程大学 计算机科学与技术学院,黑龙江 哈尔滨 150001
    2 哈尔滨理工大学 计算机科学与技术学院,黑龙江 哈尔滨 150001
  • 出版日期:2015-07-25 发布日期:2015-07-25
  • 基金资助:
    国家自然科学基金资助项目;国家自然科学基金资助项目;高等学校博士学科点基金资助项目;黑龙江省自然科学基金资助项目

Task scheduling algorithm for distributed environment based on signal-driven

Yu XIN1,Jing YANG1,Zhi-qiang XIE2   

  1. 1 College of Computer Science and Technology,Harbin Engineering University,Harbin 150001,China
    2 College of Computer Science and Technology,Harbin University of Science and Technology,Harbin 150001,China
  • Online:2015-07-25 Published:2015-07-25
  • Supported by:
    The National Natural Science Foundation of China;The National Natural Science Foundation of China;The National Natural Science Foundation of Heilongjiang Province

摘要:

为优化IaaS服务的执行效率,提出面向IaaS的信号驱动任务调度算法,该算法根据IaaS模型的结构特征建立控制子系统和节点子系统,根据任务的结构特征建立任务的DAG(directed acyclic graph)调度模型,并建立各任务分片的状态转化机制及控制子系统和节点子系统间的信号通信机制。以系统间信号交互的方式驱动任务分片的状态改变,并在每一调度时刻来临时利用并行优化选择策略分配任务分片。由于本算法采用了模拟IaaS模型的双系统控制方式,使本算法与IaaS模型的分布式体系相兼容且复杂度较低。最后通过实验验证了所提算法的有效性和实用性。

关键词: IaaS, 云计算, 任务调度, 信号驱动, 并行优化

Abstract:

In order to optimize the performance of user services in IaaS,the task scheduling algorithm for IaaS based on signal-driven is proposed,by which CS(control subsystem) and NS(inquiry nodes subsystem) based on the structural characteristics of the IaaS is established,and the DAG scheduling model based on the structural characteristics of the inquiry task is created.Then the conversion mechanism for the task partitions is created,constructing the signal communication mechanism for CS and NS,changing the status of the task partitions by signal-driven between the CS and NS,completing the task partitions allocation by POSS (parallel optimization selective strategy) in the scheduling time.This algorithm with low complexity is compatible with the distributed architecture of IaaS,because of utilizing dual system control mode.The effectiveness and practicality of this algorithm is verified by experiment.

Key words: IaaS, cloud computing, task scheduling, signal-driven, parallel optimization

No Suggested Reading articles found!