论文部分内容阅读
科学计算、商业和Web应用导致人们对计算力的需求越来越高,而现有数据中心的资源利用率普遍偏低.因此,在云计算环境中,合理的分配任务、实现最佳的调度极其必要.针对云计算中Min-Min算法优先调度小任务,而Max-Min算法优先调度大任务而导致负载不均衡的问题,提出一种算法即Min-Max.该算法对时间贪心,将小任务和大任务“捆绑”在一起执行调度,从而有效地解决了负载不均衡的问题.实验表明:Min-Max与Min-Min算法相比,提高了系统整体资源利用率,在任务总执行时间上节约了9%;Min-Max与Max-Min相比,除提高了系统整体利用率之外,在任务总体完成时间、平均任务响应时间上分别节约了7%和9%.
Scientific computing, business and web applications have led to increasing demands for computational power, while resource utilization in existing data centers has generally been low, so in cloud computing environments, tasks are reasonably allocated to achieve optimal scheduling It is extremely necessary.Aiming at the problem that the min-min algorithm dispatches a little task in the cloud computing and the max-min algorithm dispatches the big task to cause the unbalanced load in priority, this paper proposes an algorithm called Min-Max, Task and the big task “Bundle ” together to implement the scheduling, which effectively solve the problem of load unbalances.Experiments show that: Min-Max and Min-Min algorithm compared to improve the overall system resource utilization, the total task 9% savings in execution time; Min-Max achieved an overall savings of 7% and 9% on mission completion time and average mission response time, respectively, compared to Max-Min, in addition to improving overall system utilization.