期刊文献+

TDDS:基于虚拟集群系统的任务部署与调度 被引量:3

TDDS:Task Deployment and Scheduling Based on Virtual Cluster System
下载PDF
导出
摘要 利用虚拟机的灵活性和快速部署能力,设计并实现了任务部署与调度系统(task deployment and dispatch system,TDDS).TDDS能够根据用户的需求,为用户的计算任务提供可以进行资源配置的集群计算环境,满足了用户对不同操作系统、不同应用程序和不同计算资源的需求.TDDS还使用了负载均衡策略,以提高物理集群资源的利用率.提出了两种虚拟机部署策略,用以加快虚拟集群部署的速度.TDDS尽量控制虚拟机系统镜像的大小和访问频率,以提高部署的效率.实验表明,TDDS系统能够快速灵活地部署用户所需要的计算环境和计算资源,负载均衡的调度策略也切实提高了物理集群处理任务的能力,提高了集群的使用率. The traditional computer cluster is not easy for management. For example, it is hard to install the systems, lack of secure isolation of different users; it cannot construct the customized environment according to the requirement of applications and users etc. Virtual machines can be used to tackle all these problems. A system called TDDS(task deployment and dispatch system) based on virtual machines has been designed and implemented. TDDS can build up the running environment according to the requirement from users and applications. In addition, TDDS builds the automatic application deployment and schedule system as well as load balancing among physical servers in the cluster. The main contribution of this dissertation includes: 1) Two different virtual machine setup methods are proposed for speeding up the application deployment based on customized virtual machines. 2) The task deployment and schedule mechanism are designed and implemented based on the virtual machines. TDDS can construct the virtual environment for distributed applications and schedule the tasks on the virtual platform. 3) Several experiments have been conducted to test the effectiveness and efficiency of computing environment and resources customized for user applications. The experiments indicate that TDDS can do the task deployment and scheduling efficiently. The load balancing schemes can be used to improve the processing capability of physical clusters i.e. achieving the goal of improving the usage efficiency.
出处 《计算机研究与发展》 EI CSCD 北大核心 2013年第5期1118-1124,共7页 Journal of Computer Research and Development
基金 国家自然科学基金项目(60973143) 国家"八六三"高技术研究发展计划基金项目(2012AA012600) 国家"九七三"重点基础研究发展计划基金项目(2010CB951903)
关键词 虚拟集群 虚拟机 集群 部署 调度 任务部署与调度系统 virtual cluster virtual machine cluster deployment scheduling task deployment anddispatch system(TDDS)
  • 相关文献

参考文献9

  • 1Nakada H, Yokoi T, Ebara T, et al. The design and implementatiorl of a virtual cluster management system [OL][2011-02- 13]. http://ninf, apgrid, org/papers/datal)ir evgm07nakada, pdf.
  • 2The ()SCAR Team. ()SCAR; Open source clusler application resources [OL] [2011-02-13]. htt p://oscar, openclustergroup. org/.
  • 3Bartholomew D. QEMU: A multi host, multi target emulator [OL]. (2006-03-30)[2011-02-13]. httpJ/www. linuxjournal, eom/article/8808.
  • 4Kivity A, Kamay Y, l,aor I), et al. KVM: The l,inux virtual machine monitor [OL]. (2007 07 19) [2011 -02 -13]. http://www, kernel, org/doe/ols/2OO7/ols2OO7vl pages 225-230, Ddf.
  • 5Paul B, Boris D. Keir F, et al. Xen and the art of virtualization [C] //Proc of the 19h ACM Symp Operating Systems Principles. New York: ACM, 2003:164-177.
  • 6Hitz D, Lau j, Malcolm M, File system design for an NFS file server appliance [C]//Proc of the USENIX Winter 1994 Technical Conf ( WTEC'94 ). Berkeley, CA: USENIX Association, 1994:19-19.
  • 7Bohe M, Sievers M, Birkenheuer G, et al. Non-intrusive virtualization management using libvirt [C] //Proe of the Conf on Design. Automation Test in Europe Conf Exhibition. l,euven. Belgium: European Design and Automation Association. 2010:574-579.
  • 8Gropp W, Lusk E. Doss N, et al. A high performance, portable implementation of the MPI message passing interface standard[J]. Parallel Computing, 1996, 22(6): 789-828.
  • 9张武生,薛巍,李建江,等.MPI并行程序没计实例教程[M].北京:清华大学出版社,2009:1-15.

同被引文献25

  • 1章文嵩.LVS集群的负载调度[EB/OL].http://www-900.ibm.com/developerWorks/cn/linux/cluster/lvs/part4/index.shtml,2002-05.
  • 2Peter M, Timothy G. The NIST definition of cloud compu- ting= draft[Z]. NIST Special Publication, 2011.
  • 3Michael A, Armando F, Rean G. A view of cloud computing[J]. Communications of the ACM,2010,53(4) .. 50-58.
  • 4Foster I, Yong Z, Raicu I. Could computing and grid compu ting 360-degree compared [C]//Grid Computing Environ ments Workshop,TX,Austin,2008=l 10.
  • 5Peter E J. A review of "cloud computing for libraries"[J] Journal of Access Services, 2013,10( 1 ) : 71 -73.
  • 6RAJKUMAR B, SHIN Y C, VENUGOPAL S, et al.Cloud computing and emerging IT platforms: Vision, hype, and reality for delivering computing as the 5th utility[J]. Future Generation Computer Systems,2009,25(6):599-616.
  • 7JIAO Y, WANG W. Design and implementation of load balancing of distributed-system-based Web server[C] // Proceedings of the 2010 Third International Symposium on Electronic Commerce and Security. Piscataway: IEEE Press, 2010: 337-342.
  • 8GILLY K, JUIZ C, PUIGJANER R. An up-to-date survey in Web load balancing[J]. World Wide Web, 2011, 14(2): 105-131.
  • 9SPEITKAMP B, BICHLER M. A mathematical programming approach for server consolidation problems in virtualized data centers[J]. IEEE Transactions on Services Computing,2010,3(4):266-278.
  • 10QIN X, XIE T. An availability-aware task scheduling strategy for heterogeneous systems[J]. IEEE Transactions on Computers, 2008,57(2):188-199..

引证文献3

二级引证文献20

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部