计算机工程与应用 ›› 2011, Vol. 47 ›› Issue (27): 19-23.

• 博士论坛 • 上一篇    下一篇

面向托管的数据库即服务系统及资源优化技术

王卓昊1,2,王希诚1   

  1. 1.大连理工大学 电子信息与电气工程学部 计算机科学与技术学院,辽宁 大连 116023
    2.科学技术部 信息中心,北京 100862
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2011-09-21 发布日期:2011-09-21

Database as a service system for business database application hosting and its resource optimization technique

WANG Zhuohao1,2,WANG Xicheng1   

  1. 1.College of Computer Science and Technology,Faculty of Electronic Information and Electrical Engineering,Dalian University of Technology,Dalian,Liaoning 116023,China
    2.Information Center,Ministry of Science and Technology,Beijing 100862,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-09-21 Published:2011-09-21

摘要: 数据库即服务(DBaaS)是云计算的一个研究热点,而数据应用托管则是当前DBaaS的一个重要应用领域。为满足行业数据应用托管中对DBaaS提出的数据隔离、性能隔离及可靠性保障等方面的要求,提出一种无共享架构下基于虚拟机、支持副本的多租户数据托管方法及相应的数据库即服务系统。针对该系统中面向租户的虚拟机资源(CPU、内存等)动态优化这一核心问题,建立了基于虚拟机的系统资源效用函数和数据库性能计算模型,并在基础上给出了一种根据租户数据请求负载并采用贪心方式的虚拟机资源动态优化算法。结合科技信息服务数据库托管应用示例进行了实验,实验结果表明提出的方法可以根据各个租户的数据库负载动态优化虚拟机的资源分配,能够在满足性能需求同时达到了提高系统资源利用率的目的。

关键词: 数据库即服务, 虚拟机, 无共享架构, 资源动态优化

Abstract: Database as a Service(DBaaS) is becoming a research hotspot of cloud computing.As a main application domain,business database application hosting puts forward the requirements of data and performance isolation and reliability guarantee.To satisfy these requirements,this paper proposes a virtual machine based database hosting method and corresponding DBaaS system.Furthermore,aiming at the key problem of resource(such as CPU,memory,etc.) optimal allocation for virtual machines which host database applications of different tenants,the paper formalizes the constraint programming problem,and solves the problem through a greedy algorithm based on a performance model and a utility function.The application example and experiment show that,the algorithm can optimize the resource cost while meeting database performance demand of each tenant.

Key words: Database as a Service(DBaaS), virtual machine, shared-nothing architecture, dynamic resource optimization