期刊文献+

面向虚拟路由器的基于历史转发开销的资源调度算法 被引量:7

Historical Forwarding Overhead Based the Resource Scheduling Algorithm for the Virtual Router
下载PDF
导出
摘要 通过研究以Xen为代表的虚拟工具中资源调度算法,得知它们无法保证虚拟路由器中资源共享的公平性。该文提出一种基于历史转发开销的资源调度算法,用来确保路由器实例占用资源的公平性,尤其物理平台的输入/输出(I/O)资源。该算法通过统计路由器实例最近的报文转发开销来计算出路由器实例调度的优先级,确保平均吞吐量较低的路由器实例获得被调度的机会。同时,该算法通过设置优先级计算公式中处理延迟的值,达到对延迟敏感强的路由器实例的支持,以及通过预测报文处理时间决定待处理报文是否丢弃,避免不必要的系统开销。通过实验测试,相对于Credit算法,该文算法在确保虚拟路由器资源共享的公平性方面存在明显优势,并且能为延迟敏感的路由器实例提供支持。 The current resource scheduling algorithms can not offer promise for the fairness of shared resources based on research on the resource scheduling algorithms in the system virtualization tools represented by Xen. This paper proposes a Historical Forwarding Overhead Based the Resource Scheduling Algorithm (HFOB_RSA) to ensure that router instances occupy determinate physical resources including I/Os that should be proportional to actual requirements. This algorithm can determine the scheduling priority of router instances by calculating the last several forwarding overhead of each router instance to make those router instances with low real throughput have an opportunity for being scheduled. Meanwhile, this algorithm also sets the value of processing delay in priority formula to provide support for those delay-sensitive router instances and determines whether or not to discard the non-disposed packets in advance by forecasting their processing time to avoid the unwanted overhead. The experimental results prove that the HFOB_RSA has superiority over Credit algorithm in terms of the fairness of shared resources in the virtual router. And HFOB_RSA also is able to provide support for the delay-sensitive router instances.
出处 《电子与信息学报》 EI CSCD 北大核心 2015年第3期686-692,共7页 Journal of Electronics & Information Technology
基金 国家973计划项目(2012CB315906) 高等学校博士学科点专项科研基金(20114307110006)资助课题
关键词 网络虚拟化 虚拟路由器 路由器实例 资源调度算法 公平性 Network virtualization Virtual router Router instance Resource scheduling algorithm Fairness
  • 相关文献

参考文献1

同被引文献42

  • 1KREUTZ D, RAMOS F M V, ESTEVES V P, et al. Software-defined networking: A comprehensive survey[J]. Proceedings of the IEEE, 2015, 103(1): 14-76.
  • 2MAHALINGAM M, DUTT D, DUDA K, et al. Virtual extensible local area network (VXLAN): a framework for overlaying virtualized layer 2 networks over layer 3 networks [R]. 2014.
  • 3BERMAN M, CHASE J S, LANDWEBER L, et al. GENI: a federated testbed for innovative network experiments[J]. Computer Networks, 2014, 61: 5-23.
  • 4KOPONEN T, AMIDON K, BALLAND P, et al. Network virtualization in multi-tenant data centers[C]. Proceedings of the 11th USENIX Symposium on Networked Systems Design and Implementation, Seattle, USA, 2014: 203-216.
  • 5PAREKH A K and GALLAGER R G. A generalized processor sharing approach to flow control in integrated services networks: the single-node case[J]. IEEE/ACM Transactions on Networking, 1993, 1(3): 344-357.
  • 6BENNETT J C R and ZHANG H. WF2Q: worst-case fair weighted fair queueing[C]. Proceedings of IEEE INFOCOM'96, 1996, Vol. 1: 120-128.
  • 7GOVAL P, VIN H M, and CHENG H. Start-time fair queueing: A scheduling algorithm for integrated services packet switching networks[J]. IEEE/A CM Transactions on Networking, 1997, 5(5): 690-704.
  • 8BLANQUER J M and ZDEN B. Fair queuing for aggregated multiple finks[J]. ACM SIGCOMM Computer Communication Review, 2001, 31(4): 189-197.
  • 9SHREEDHAR M and VARGHESE G. Efficient fair queuing using deficit round-robin[J]. IEEE/ACM Transactions on Networking, 1996, 4(3): 375-385.
  • 10GUO C. SRR: an O (1) time complexity packet scheduler for flows in multi-service packet networks[J]. A CM SIGCOMM Computer Communication Review, 2001, 31(4): 211-222.

引证文献7

二级引证文献21

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