Designing Buffer Capacity of Crosspoint-Queued Switch - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2014

Designing Buffer Capacity of Crosspoint-Queued Switch

Guo Chen
  • Function : Author
  • PersonId : 994291
Dan Pei
  • Function : Author
  • PersonId : 994292
Youjian Zhao
  • Function : Author
  • PersonId : 994293
Yongqian Sun
  • Function : Author
  • PersonId : 994294

Abstract

We use both theoretical analysis and simulations to study crosspoint-queued(CQ) buffer size’s impact on CQ switch’s throughput and delay performance under different traffic models, input loads, and scheduling algorithms. In this paper, 1) we present an exact closed-form formula for the CQ switch’s 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; 2) we show that the above results can serve as a conservative guidance on deciding the needed buffer size in pure CQ switches using work-conserving algorithms such as random, under independent Bernoulli traffic. 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 feasible crosspoint buffer size. Our work reveals the impact of buffer size on CQ switches’ performance and provides a theoretical guidance on designing the buffer size in pure CQ switch, which is an important step towards building ultra-high-speed switching fabrics.
Fichier principal
Vignette du fichier
978-3-662-44917-2_4_Chapter.pdf (563.29 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01403056 , version 1 (25-11-2016)

Licence

Attribution

Identifiers

Cite

Guo Chen, Dan Pei, Youjian Zhao, Yongqian Sun. Designing Buffer Capacity of Crosspoint-Queued Switch. 11th IFIP International Conference on Network and Parallel Computing (NPC), Sep 2014, Ilan, Taiwan. pp.35-48, ⟨10.1007/978-3-662-44917-2_4⟩. ⟨hal-01403056⟩
43 View
85 Download

Altmetric

Share

Gmail Facebook X LinkedIn More