期刊文献+

采用高维路由节点构建直连式可扩展路由器

Constructing Direct Scalable Router with High Radix Router Node
下载PDF
导出
摘要 可扩展路由器是当前核心路由器研究的热点,直连式可扩展路由器是可扩展路由器研究的一种重要分支.但是,目前直连式可扩展路由器的研究局限于采用低维路由节点的方式进行扩展,这种方式构建的路由器其可扩展互连结构的网络直径增长较快而等分带宽增长较慢.针对该问题,提出采用高维路由节点构建直连式可扩展路由器的思想,认为构建直连式可扩展路由时,路由节点的维要根据路由节点的交换容量和分组延时决定.在分组延时小于某个界的情况下,路由节点的交换容量越大它的维也应该越高这样才能使路由器的可扩展互连结构有最大的等分带宽和最小的网络直径,使路由器在满足分组延时要求的情况下具有最大的交换容量.从理论上分析了该思想的可行性,仿真结果进一步验证了理论分析的正确性. Scalable router is a very hot research spot for Internet core router, and the method which constructs scalable router with a direct network is a very important research direction in this area. However, most current researches concentrate on the method with low radix router node to realize the direct network. This method results in the direct network with high increasing diameter and low increasing bisection bandwidth. To solve this problem, we propose an idea of constructing direct network with high radix router node in scalable router. That is, on some packet latency condition, the radix of a router node in scalable router should be determined by the switch throughput of the router node. Then the direct network can get the lowest diameter and the highest bisection bandwidth, and router gets the highest switch throughput under this packet latency constraint. With high radix router node, the direct scalable router may get many different aspects on performance, such as switch throughput, packet latency, internal routing algorithm, load balancing, flow control and fault tolerance, etc. Here, we only study the switch throughput and packet latency, which are two very important factors on performance. We first give theory analysis on switch throughput and packet latency, comparing the change rule of these two factors. Then, we give the simulation results to verify the correctness of the theory analysis.
出处 《计算机研究与发展》 EI CSCD 北大核心 2013年第1期218-224,共7页 Journal of Computer Research and Development
基金 国家自然科学基金项目(60903184) 国家"八六三"高技术研究发展计划基金项目(2008AA01A323)
关键词 可扩展路由器 可扩展互连结构 高维路由节点 交换容量 分组延时 throughput scalable router scalable interconnect{on network~ high radix router node switch packet latency
  • 相关文献

参考文献14

  • 1McKeown N. Scheduling algorithms for input-queued cell switches [D]. Berkeley, CA: University of California at Berkeley, 1995.
  • 2Lillevik S L. The Touchstone 30 gigaflop DELTA prototype [C] //Proe of Distributed Memory Computing Conf (DMCC). Los Alamitos, CA: IEEE Computer Society, 1991, 671-677.
  • 3Dally W J, Towles B. Principles and Practices of Intereonnection Networks[M]. San Francisco, CA:Morgan Kaufmann, 2004: 45-55.
  • 4Peter R N, Dally W J. The J-machine network [C]//Proc of the 1991 IEEE Int Conf on Computer Design on VLSI in Computer & Processors. Piscataway, NJ: IEEE, 1992: 420-423.
  • 5管剑波.集群路由器体系结构及其关键技术的研究[D].长沙:国防科学技术大学,2005.
  • 6Dally W J. Scalable switching fabrics for Internet routers [R]. Palo Alto, CA: Stanford University and Avici Systems Inc, 1999.
  • 7Kessler R E, Schwarzmeier J L. Cray T3D dimension for Cray research[C] //Proc of Computer Society Int Conf (COMPCON). Los CA: IEEEComputer Society, 1993:176-182 : A new the IEEE.
  • 8Chang Chengshang, Lee Duanshin, Jou Yishean. Load balanced Birkhoff-von Neumann switches [C] //Proc of 2001 IEEE Workshop on High Performance Switching and Routing. Piseataway, NJ: IEEE, 2001:276-280.
  • 9Keslassy I, Chuang S T, Yu K, et al. Scaling Internet routers using optics [C] //Proc of the 2003 Conf on Applications, Technologies, Architectures, and Protocols for Computer Communications (SIGCOMM' 03). New York: ACM, 2003:189-200.
  • 10Scott S, Abts D, Kim J, et al. The black widow high radix clos network[C]//Proe of the 33rd Int Syrnp on Computer Architecture ( ISCA ' 06 ). Los Alamitos, CA: IEEE Computer Society, 2006:16-28.

二级参考文献5

共引文献17

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