基于动态等待时间阈值的延迟调度算法

摘要

针对已有的延迟调度算法存在的两个问题,即建立在节点会很快空闲的理论假设下有一定限制,当节点不会很快空闲时算法性能严重下降和基于静态的等待时间阈值不能适应云计算数据中心动态的负载变化及不同用户作业的需求,提出了一种基于动态等待时间阈值的延迟调度算法(dynamic waiting time delay scheduling,DWTDS).该算法通过给无本地数据节点设置节点最大等待时间,以适应节点不会很快空闲的情况；通过分析数据中心各动态参数,根据概率模型调整作业的等待时间阈值.实验验证该算法在响应时间及负载均衡性方面优于已有的延迟调度算法.%There are two deficiencies in the current delay scheduling algorithms. Firstly, a limitation of these policies is that servers are not always become idle quickly as assumed, the performance of the algorithms declined serious when servers are not become idle quickly. Secondly, delay scheduling algorithms based on static waiting time threshold, cannot adapt to dynamic load of a data center and the different user needs . To address this issue, this paper proposed a dynamic waiting time delay scheduling algorithm (DWTDS). the algorithm according to setting servers' biggest waiting time to adapt to the servers were not idle quickly, DWTDS adjusted jobs' waiting time threshold dynamically according to the information of variables factor in dada center. It shows that DWTDS outperforms previous delay scheduling algorithms in term of the job response time and load balance of the node.