ISSN 1000-9825, CODEN RUXUEW E-mail: jos@iscas.ac.cn
Journal of Software, Vol.18, No.11, November 2007, pp.2800−2809 http://www.jos.org.cn
DOI: 10.1360/jos182800 Tel/Fax: +86-10-62562563
© 2007 by Journal of Software. All rights reserved.
缓冲交叉开关交换结构性能分析
∗
孙书韬
1,3+
, 贺思敏
2
, 郑燕峰
2
, 高 文
1,2
1
(中国科学院 研究生院,京 100049)
2
(中国科学院 计算技研究所,京 100080)
3
(中国传媒大学 计算与软件学院,京 100024)
Performance Analysis of a Buffered Crossbar Switch
SUN Shu-Tao
1,3+
, HE Si-Min
2
, ZHENG Yan-Feng
2
, GAO Wen
1,2
1
(Graduate University, The Chinese Academy of Sciences, Beijing 100049, China)
2
(Institute of Computing Technology, The Chinese Academy of Sciences, Beijing 100080, China)
3
(School of Computer and Software, Communication University of China, Beijing 100024, China)
+ Corresponding author: Phn: +86-10-65783396, Fax: +86-10-65783241, E-mail: stsun@cuc.edu.cn
Sun ST, He SM, Zheng YF, Gao W. Performance analysis of a buffered crossbar switch. Journal of Software,
2007,18(11):2800−2809. http://www.jos.org.cn/1000-9825/18/2800.htm
Abstract: This paper analyzes the performance of a buffered crossbar switch under bursty traffic. It derives the
saturated throughput for a buffered crossbar switch with multiple queues at each input port by the proposed analytic
model. The saturation throughput sharply decreases from 1 and converges to 0.5 with the increasing of average burst
length, and it approaches 1 as the number of queues per input increases. The accuracy of the theoretic analysis is
also investigated by extensive simulation. Results from this paper can be used as a guidance to design optimal
buffered crossbar switches.
Key words: buffered crossbar switch; input queuing; scheduling; modeling; performance analysis
摘 要: 分析了种缓冲交叉开关交换结构在突发流量到达下的性能.通过建立分析模型,给出了每个输入端口
有单个或多个输入队列的缓冲交叉开关结构的饱和吞吐.结果显示,对于单输入队列结构而,随着突发平均长度
的增加,饱和吞吐速从 1 下降,并收敛于 0.5.随着每个输入端口输入队列数目的增加,饱和吞吐率逐渐接近 1.仿真
实证了分析模型的准确性.该结果可用于指导基于缓冲交叉开关的路由交换设备的优化设计.
关键词: 缓冲交叉开关交换结构;输入排队;调度;建模;性能分析
中图法分类号: TP393 文献标识码: A
输入排队技广泛用于高速路由交换设备.对于无缓冲的交叉开关结的性能, 人们进行了充分的研究.
∗ Supported by the National Natural Science Foundation of China under Grant Nos.69983008, 60773150, 90604029 (国家自然科学基
金); the Knowledge Innovation Program of the Chinese Academy of Sciences under Grant No.KGCXZ-103 (中国科学院知识创新工程);
the Basic Research Fund of Institute of Computing Technology, the Chinese Academy of Sciences, under Grant No.20056090 (中国科学
院计算技研究所基础研究基金)
Received 2005-10-13; Accepted 2006-08-21