计算机应用 ›› 2005, Vol. 25 ›› Issue (07): 1512-1513.

• 网络与分布式技术 • 上一篇    下一篇

一种多资源负载平衡算法——RLBA

刘克剑1,2,刘心松1,吴艾1   

  1. 1.电子科技大学 计算机科学与工程学院,四川 成都 610054; 2.西华大学 计算机与数理学院,,四川 成都 610039
  • 收稿日期:2004-12-13 修回日期:2005-03-07 发布日期:2005-07-01 出版日期:2005-07-01
  • 作者简介:刘克剑(1974-),男,湖北随州人,博士研究生,主要研究方向:分布式并行调度;刘心松(1940-),男,重庆石柱人,教授,博士生导师,主要研究方向:宽带网络、分布并行处理、操作系统、数据库;吴艾(1973-),男,四川资阳人,博士研究生,主要研究方向:分布式文件系统.

A  multi-resources  load-balancing  algorithm

LIU Ke-jian1,2,  LIU Xin-song1, WU Ai1   

  1. 1. School of Computer Science & Engineering,University of Electronic Science and Technology of China; 2. School of Computer & Mathematical-Physical Science,  Xihua Uninversity
  • Received:2004-12-13 Revised:2005-03-07 Online:2005-07-01 Published:2005-07-01

摘要:

讨论了一种适用于分布式系统的多种资源的负载平衡算法。调度时,首先将任务按照其所占用的系统资源比例进行分类,然后在线计算每个节点的综合资源负载,并按照节点与整个系统的平均综合资源负载的差值进行类型划分,最后在负载最小的节点类中按照均匀概率随机选择一个节点作为任务调度的对象。算法还考虑了调度时可能发生的倾泻现象,并给出了避免的方法。

关键词: 多资源, 负载平衡, 调度, 分布式系统, 调度倾泻

Abstract:

A multi-resources load-balancing algorithm in the distributed system was brought forward. While scheduling, first, the arriving tasks were classified by the resources which they would take up later, and then a load of each node was calculated online. Nodes in the system were also classified into some classes in term of the deference between load of a node and the average value of system. At last, a node in the least loading class was selected randomly and uniformly. The algorithm can avoid the schedulingpouring effect. It has been adopted in a distributed system and got a satisfying result.

Key words: multi-resources, load balancing, scheduling, distributed system, scheduling-pouring

中图分类号: