Journal of Communications and Networks

The Korean Institute of Commucations and Information Sciences (한국통신학회)
권호 표지
DOI QR코드

DOI QR Code

Analyzing the Impact of Buffer Capacity on Crosspoint-Queued Switch Performance

  • Chen, Guo (Department of Computer Science and Technology, Tsinghua University) ;
  • Zhao, Youjian (Department of Computer Science and Technology, Tsinghua University) ;
  • Pei, Dan (Department of Computer Science and Technology, Tsinghua University) ;
  • Sun, Yongqian (Department of Computer Science and Technology, Tsinghua University)
  • Received : 2015.03.11
  • Accepted : 2015.08.13
  • Published : 2016.06.30
⟨ Previous Next ⟩

Abstract

We use both theoretical analysis and simulations to study the impact of crosspoint-queued (CQ) buffer size on CQ switch throughput and delay performance under different traffic models, input loads, and scheduling algorithms. In this paper, we present the following. 1) We prove the stability of CQ switch using any work-conserving scheduling algorithm. 2) We present an exact closed-form formula for the CQ switch throughput and a non-closed-form but convergent formula for its delay using static non-work-conserving random scheduling algorithms with any given buffer size under independent Bernoulli traffic. 3) We show that the above results can serve as a conservative guide on deciding the required buffer size in pure CQ switches using work-conserving algorithms such as the random scheduling, under independent Bernoulli traffic. 4) Furthermore, our simulation results under real-trace traffic show that simple round-robin and random work-conserving algorithms can achieve quite good throughput and delay performance with a feasible crosspoint buffer size. Our work reveals the impact of buffer size on the CQ switch performance and provides a theoretical guide on designing the buffer size in pure CQ switch, which is an important step toward building ultra-high-speed switch fabrics.

Keywords

Acknowledgement

Supported by : National Natural Science of China

References

  1. N. McKeown, "The iSLIP scheduling algorithm for input-queued switches," IEEE/ACM Trans. Netw., vol. 7, no. 2, pp. 188-201, Apr. 1999. https://doi.org/10.1109/90.769767
  2. Y. Li, S. Panwar, and H. Chao, "On the performance of a dual round-robin switch," in Proc. IEEE INFOCOM, 2001, pp. 1688-1697.
  3. R. Rojas-Cessa, E. Oki, Z. Jing, and H. Chao, "CIXB-1: Combined inputone-cell-crosspoint buffered switch," in Proc. HPSR, 2001, pp. 324-329.
  4. S. He et al., "On guaranteed smooth switching for buffered crossbar switches," IEEE/ACM Trans. Netw., vol. 16, no. 3, pp. 718-731, June 2008. https://doi.org/10.1109/TNET.2007.900402
  5. E. Oki, Z. Jing, R. Rojas-Cessa, and H. Chao, "Concurrent round-robinbased dispatching schemes for Clos-network switches," IEEE/ACMTrans. Netw., vol. 10, no. 6, pp. 830-844, 2002.
  6. S. Iyer, A. Awadallah, and N.McKeown, "Analysis of a packet switch with memories running slower than the line-rate," in Proc. IEEE INFOCOM, 2000, pp. 529-537.
  7. F. Abel et al., "Design issues in next-generation merchant switch fabrics," IEEE/ACM Trans. Netw., vol. 15, no. 6, pp. 1603-1615, Dec. 2007. https://doi.org/10.1109/TNET.2007.909727
  8. Y. Kanizo, D. Hay, and I. Keslassy, "The crosspoint-queued switch," in Proc. IEEE INFOCOM, Apr. 2009, pp. 729-737.
  9. M. Radonjic and I. Radusinovic, "Impact of scheduling algorithms on performance of crosspoint-queued switch," Annals of Telecommunications - Annales des Tlcommunications, vol. 66, pp. 363-376, 2011. [Online]. Available: http://dx.doi.org/10.1007/s12243-010-0214-y
  10. I. Radusinovic, M. Radonjic, A. Simurina, I. Maljevic, and Z. Veljovic, "A new analytical model for the CQ switch throughput calculation under the bursty traffic," AEU - International Journal of Electronics and Communications, vol. 66, no. 12, pp. 1038-1041, 2012. [Online]. Available: http://www.sciencedirect.com/science/article/pii/S143484111200129X https://doi.org/10.1016/j.aeue.2012.05.009
  11. Z. Cao and S. Panwar, "Efficient buffering and scheduling for a singlechip crosspoint-queued switch," IEEE Tran. Commun., vol. 62, no. 6, pp. 2034-2050, 2014. https://doi.org/10.1109/TCOMM.2014.2318695
  12. G. Chen, D. Pei, and Y. Zhao, "CQRD: A switch-based approach to flow interference in data center networks," in Proc. IEEE LCN, 2014, pp. 107-115.
  13. "Cisco CRS carrier routing system 16-slot line card chassis system description," Cisco Systems, Inc., 2012.
  14. J. Dai and B. Prabhakar, "The throughput of data switches with and without speedup," in Proc. IEEE INFOCOM, 2000, pp. 556-564.
  15. K. Trivedi, Probability and Statistics with Reliability, Queuing, and Computer Science Applications. Wiley New York, 2002.
  16. T. Bromwich, An Introduction to the Theory of Infinite Series. Macmillan, 1908.
  17. "Anonymized 2013 internet traces," 2013. [Online]. Available: https://data.caida.org/datasets/passive-2013/
  18. G. Chen, D. Pei, Y. Zhao, and Y. Sun, "Designing buffer capacity of crosspoint-queued switch," in Proc. NPC, 2014, pp. 35-48.