基于收益驱动请求分类的多目标动态优先请求调度  

Multi-objective Dynamic Priority Request Scheduling Based on Reward-driven Request Classification

作　　者：陈梅梅[1] CHEN Mei-mei(Department of Electronic Business, Glorious Sun School of Business and Management, Donghua University, Shanghai 200051, China)

机构地区：[1]东华大学旭日工商管理学院电子商务与物流系,上海200051

出　　处：《计算机科学》2016年第8期199-203,222,共6页Computer Science

摘　　要：请求调度通常需要在充分利用现有服务器资源的基础上满足响应时间最小化和系统吞吐量最大化的目标,但对于以盈利为目的的电子商务网站来说,关键还是要提高交易请求和VIP用户发起请求的达成率。针对电子商务网站请求调度的多重目标,首先提出了收益驱动的请求分类多维标准,在此基础上定义了请求优先级和调度优先级的概念,给出了基于请求分类的多目标动态优先调度算法MODP,并引入了基于事前过载判断而非负载测量的调度机制以避免控制延迟,有利于电子商务网站在多变的负载条件下自适应地实现差别服务和QoS保障。仿真实验证明了MODP机制与算法的有效性,将其与传统FCFS调度方法进行对比研究,结果表明:服务器无论在高载还是低载情况下,MODP调度策略在实现收益最大化、平均响应时间最小化的目标方面都具有明显的优势。The general target of request scheduling is to maximize throughput and minimize response time under the condition that existing system resource is in full use. But for a busy business Web system with the goal of revenue gene- ration,it is crucial to increase the completion rate of transaction related requests and requests from VIP. Aiming at the multiple objectives of request scheduling for business Web server, the multi-dimension criterion for reward-driven re- quest classification was firstly presented. Then, based on the definitions of request priority and scheduling priority, the algorithm of multi-objectives dynamic priority scheduling was proposed, which can provide DiffServ and QoS guarantee adaptively for business Web system under the variety workload. At the same time, the dynamic scheduling mechanism was introduced based on one-step-ahead overload estimation instead of the workload measurement to avoid the control delay. Simulation experiment shows the validity of this scheduling mechanism and algorithm, Through the comparison of the completion rate of transaction requests as well as the average response time with that of the traditional method FCFS, MODP proves its preferential principle under not only lower workload but also overload condition.

关 键 词：请求分类 请求优先级 请求调度 调度优化 商务网站 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]