期刊文献+

下一代光核心负载均衡分组交换机研究

On Next Generation Optic-Core Load-Balanced Packet Switch
下载PDF
导出
摘要 着重研究了在第五代交换机体系结构中极具竞争力的以阵列波导光栅路由器件为核心的负载均衡交换结构(AWGR-LB).负载均衡结构通常使用严格的时分复用方式,调度简单但性能不够理想;AWGR的使用能够大大提高交换机整体容量,但由于其波长速率仅为端口速率的1/N(其中N为端口数),其时延性能与传统交换矩阵相比仍有较大差距,因而不能提供良好的服务质量保证.文中提出了一种适应性时分复用调度算法,能够在保持100%吞吐率优势的同时,极大地改善负载均衡结构的时延性能;同时文中提出的双波导光栅路由器方案,使光交换矩阵能模拟传统交叉开关的工作模式,从而达到以端口线速率交换的效果,与适应性时分复用调度算法相结合,可进一步提高AWGR-LB的性能. This paper focuses on the Arrayed Waveguide Grating Router-Load Balanced(AWGR-LB) switch,a promising candidate for the fifth generation packet switching architecture.The LB switch needs little scheduling but its performance is not very satisfactory for its strict time-division multiplexing manner.AWGR-LB can greatly increase the switching capacity;nevertheless,the transmission delay within the switch fabric is too large compared with traditional ones for its channel rate within the fabric can only be implemented at one N-th of the port rate(N is the switch size),hence makes QoS unsatisfactory.This paper introduces an Adaptive TDM(ATDM) scheduling manner,which dramatically decreases the delay of LB switches while still keeping 100% throughput.By using the authors' dual AWGR design,which can emulate the operation of the traditional crossbar and provide port-rate switching,combined with the ATDM scheme,the performance of AWGR-LB can be further improved.
出处 《计算机学报》 EI CSCD 北大核心 2011年第7期1332-1341,共10页 Chinese Journal of Computers
基金 国家自然科学基金(60773102) “中国工程科技中长期发展战略研究”联合基金(U0970122) 四川大学基金(下一代Internet体系结构)资助~~
关键词 分组交换 负载均衡交换机 Byte-Focal交换机 时延性能 吞吐率 packet switch load-balanced switch Byte-Focal switch delay performance throughput
  • 相关文献

参考文献18

  • 1Karol M, Hluchyj M, Morgan S. Input versus output queueing on a space-division packet switch. IEEE Transactions on Communications, 1987, 35(12): 1347-1356. 被引量:1
  • 2Tamlr Y, Frazler G. High-performance multiqueue bu(fers for VLSI communication swltches//Proceedings of the 15th Annual International Symposium on Computer Architecture. Honolulu, Hawaii, USA, 1988:343-354. 被引量:1
  • 3Anderson T E, Owicki S S, Saxe J 13, Thacker C P. Highspeed switch scheduling for local-area networks. ACM Transactions on Computer System, 1993, 11(4) : 319-352. 被引量:1
  • 4McKeown N. The iSLIP scheduling algorithm for inputqueued switches. IEEE/ACM Transactions on Networking, 1999, 7(2): 188-201. 被引量:1
  • 5Li Yi-Han, Panwar S, Chao H. On the performance of a dual round-robin switch//Proceedings of IEEE Twentieth Annual Joint Conference of the IEEE Computer and Communications Societies (INFOCOM 2001). Anchorage, Alaska, USA, 2001, 3: 1688-1697. 被引量:1
  • 6Keslassy I, Chuang S, Yu K, Miller D, Horowitz M, Solgaard O, McKeown N. Scaling internet routers using optics//Proceedings of the 2003 Conference on Applications, Technologies, Architectures, and Protocols for Computer Communications ( SIGCOMM' 03). Karlsruhe, Germany, 2003:189-200. 被引量:1
  • 7Chang C, Lee D, Jou Y. Load balanced Birkhoff-von Neumann switches, Part I: One-stage buffering. Computer Communications, 2002, 25(6): 611-622. 被引量:1
  • 8Wang Xin, Yeung K L. Load balanced two-stage switches using arrayed waveguide grating routers//Proceedings of the IEEE Workshop on High Performance Switching and Routing (HPSR 2007). Brooklyn, New York, USA, 2007:1-6. 被引量:1
  • 9Keslassy I. The load-balanced router[Ph. D. dissertation]. Stanford University, Stanford, California, 2004. 被引量:1
  • 10Jaramillo J, Milan F, Srikant R. Padded frames: A novel algorithm for stable scheduling in load-balanced switches. IEEE/ACM Transactions on Networking, 2008, 16(5): 1212-1225. 被引量:1

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