一种基于性能评估的元任务调度算法  

Performance-Evaluation-Based Meta-Task Scheduling Algorithm

作　　者：胡周君[1] 胡志刚[1] 李林[1] 

机构地区：[1]中南大学信息科学与工程学院,长沙410083

出　　处：《西安交通大学学报》2008年第8期972-976,共5页Journal of Xi'an Jiaotong University

基　　金：国家自然科学基金资助项目(60673165;60433020)

摘　　要：在保障本地任务QoS需求及尊重网格节点的本地调度策略的条件下,提出了一种资源动态性能评估方法,并得出了2个资源动态性能的评估尺度.基于网格资源可用性的相关结果,利用概率法得出网格节点服务于网格任务的平均能力.利用热力学中熵的概念对网格节点状态的动态变化不确定性进行了评估,并得到刻画网格节点状态不确定性的定量值.在资源动态性能评估的基础上,提出了一种基于性能评估的元任务调度算法.仿真与评估结果表明,所提算法在服务拒绝率、网格任务执行跨度方面优于以往算法,且在网格用户的QoS保障程度上有所增强.Providing non-trivial QoS for grid application under meeting local job＇s QoS requirements and local scheduling strategy of grid site, is an important objective and a new issue of task scheduling in service grid environment. A resource dynamic performance evaluation method is presented and two performance metrics are obtained. Based on resource availability characteristic of a grid site, probability theory is employed to evaluate the average capacity of a resource. Several states for grid sites are labeled, and the conception of entropy in thermodynamics is used to describe the uncertainty of the resource. Then, a performance-evaluation-based meta-task scheduling algorithm is proposed. On the basis of extended and revised gridSim, the algorithm is implemented and compared with two related existing algorithms. The experiment results show that the proposed algorithm outperforms the existing ones on both aspects of the service deny rate and the grid task makespan.

关 键 词：服务网格 性能评估 QOS保障 调度算法 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]