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 ›› 2008, Vol. 34 ›› Issue (12): 56-57. doi: 10.3969/j.issn.1000-3428.2008.12.019

• 软件技术与数据 • 上一篇    下一篇

网格作业自适应迁移模型

王 涛,周兴社,杨志义,刘 亮,张海辉   

  1. (西北工业大学高性能计算研究与发展中心,西安 710072)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2008-06-20 发布日期:2008-06-20

Self-adaptive Migration Model for Grid Job

WANG Tao, ZHOU Xing-she, YANG Zhi-yi, LIU Liang, ZHANG Hai-hui   

  1. (Centre for High Performance Computing, Northwestern Polytechnical University, Xi’an 710072)
  • Received:1900-01-01 Revised:1900-01-01 Online:2008-06-20 Published:2008-06-20

摘要: 作业迁移是实现网格作业服务质量保证和系统高效能的重要方法。该文在分析传统进程迁移技术的基础上,根据网格系统的特点,提出一种全局作业与局部进程相结合的网格作业自适应迁移模型,给出网格作业自适应迁移策略、迁移对象选定原则、迁移时机确定机制和自适应迁移实现算法。试验结果以及在某校园计算网格中的应用验证了该模型的有效性。

关键词: 网格, 作业迁移, 本地资源管理系统

Abstract: Job migration is essential to guarantee the quality of services of grid jobs and high efficiency of grid system. Based on the feature of grid system, this paper analyzes the traditional process migration technology, and presents a self-adaptive job migration model combining with global jobs and local process. A self-adaptive job migration strategy, determining principle about migration object and time, and its algorithm are given. Experimental results and applications to a campus grid confirm the validity of the model.

Key words: grid, job migration, Local Resource Management System(LRMS)

中图分类号: