Dynamic Per-flow Queuing to Reduce Competitions Among Large Number of Flows

WEI Jianhua; ZHU Lei; ZHANG Weichuan; FENG Zhi; GUO Peng

Article Contents

Article Navigation > Chinese Journal of Electronics > 2014 > 23(4): 783-789

WEI Jianhua, ZHU Lei, ZHANG Weichuan, et al., “Dynamic Per-flow Queuing to Reduce Competitions Among Large Number of Flows,” Chinese Journal of Electronics, vol. 23, no. 4, pp. 783-789, 2014,

Citation:

WEI Jianhua, ZHU Lei, ZHANG Weichuan, et al., “Dynamic Per-flow Queuing to Reduce Competitions Among Large Number of Flows,” Chinese Journal of Electronics, vol. 23, no. 4, pp. 783-789, 2014,

WEI Jianhua, ZHU Lei, ZHANG Weichuan, et al., “Dynamic Per-flow Queuing to Reduce Competitions Among Large Number of Flows,” Chinese Journal of Electronics, vol. 23, no. 4, pp. 783-789, 2014,

Citation:

WEI Jianhua, ZHU Lei, ZHANG Weichuan, et al., “Dynamic Per-flow Queuing to Reduce Competitions Among Large Number of Flows,” Chinese Journal of Electronics, vol. 23, no. 4, pp. 783-789, 2014,

PDF( 995 KB)

Dynamic Per-flow Queuing to Reduce Competitions Among Large Number of Flows

Electronics and Information College, Xi'an Polytechnic University, Xi'an 710048, China

Received Date: 2013-04-01
Rev Recd Date: 2013-09-01
Publish Date: 2014-10-05

Abstract

Abstract

Per-flow queuing is believed to be able to guarantee advanced Quality of service (QoS) for each flow at high speed routers. With the dramatic increase for both link speed and number of traffic flows, per-flow queuing confronts a great challenge, since millions of queues need to be maintained for implementation in a traditional sense. In this paper, setting only a small number of physical queues, we propose a Dynamic per-flow queuing (DPFQ) mechanism that achievesthe same performance as per-flow queuing at a cost of an additional Binary content addressable memory (BCAM). The proposed mechanism works due to the fact that the number of simultaneous active flows at a mini-time scale in the router buffer is much smaller than that of in-progress flows. In DPFQ, a physical queue is created on demand when a new flow comes, and released when the flow temporarily pauses or finishes. A small BCAM is occupied to map flows to queues, so as to guarantee that only the packets from the same flow are buffered in any assigned queue. Through analysis and simulation we show that using a small number of physical queues, DPFQ achieves both low operation delay and power consumption.
- Packet buffers,
- Memory management,
- Per-flow queuing

FullText(HTML)

References(18)

References

G. Appenzeller, I. Keslassy and N. McKeown, Sizing router buffers, Proc.of ACM SIGCOMM '04, Portland,Oregon,USA, pp.281-292, 2004.

M. Enachescu, Y. Ganjali, A. Goel, N. McKeown and T. Roughgarden, Part III: Routers with very small buffers, ACM SIGCOMM Computer Communication Review, Vol.35, No.3, pp.83-90, 2005.

S. Iyer, R. R. Kompella and N. McKeown, Analysis of a memory architecture for fast packet buffers, Proc.of IEEE High Performance Switching and Routing, Dallas, Texas,USA, pp.368-373, 2001.

J. Garcia, J. Corbal, L. Cerda and M. Valero, Design and implementation of high-performance memory systems for future packet buffers, Proc.of The 36th annual IEEE/ACM International Symposium on Microarchitecture, San Diego,California, USA, pp.372-384, 2003.

R. Braden, D. Clark and S. Shenker, Integrated services in the Internet architecture: An overview, Tech.Rep ,RFC1633, 1994.

V. P. Kumar, T. V. Lakshman and D. Stiliadis, Beyond best effort: Router architectures for the differentiated services of tomorrow's Internet, IEEE Communications Magazine, Vol.36, No.5, pp.152-164, 1998.

K. C. Claffy, H. W. Braun and G. C. Polyzos, A parameterizable methodology for Internet traffic flow profiling, IEEE Journal on Selected Areas in Communications, Vol.13, No.3, pp.1481-1494, 1995.

C. Hu, S. Wang, J. Tian, B. Liu, Y. Chen and Y. Cheng, ANLS:Adaptive non-linear sampling method for accurate flow size measurement, IEEE Transactions on Communications, Vol.60, No.3, pp.789-798, 2012.

C. Hu, K. Chen, Y. Tang and B. Liu, Dynamic queuing sharing mechanism for per-flow QoS control, IET Communications, Vol.4, No.4, pp.472-483, 2010.

C. Hu, X. Chen, Y. Tangand B. Liu, Per-flow queuing by dynamic queue sharing, Proc.of INFOCOM'07, Anchorage, Alaska, USA, pp.1613-1621, 2007.

P. Gupta and N. McKeown, Algorithms for packet classification, IEEE Network, Vol.15, No.2, pp.24-32, 2001.

A. Nikologiannis, I. Papaefstathiou, G. Kornaros and C. Kachris, An FPGA-based queue management system for high speed networking devices, Microprocessors and Microsystems, Vol.28, No.5, pp.223-236, 2004.

S. B. Fred, T. Bonald, A. Proutiere, G. Regnie and J. W. Roberts, Statistical bandwidth sharing: A study of congestion at flow level, Proc.of ACM SIGCOMM '01, San Diego, California, USA, pp.111-122, 2001.

W. Pi-Chung, L. Chun-Liang, Y. Yuan-Rung and C. Hung-Yi, CAM-based huffman decoding made power efficient, Proc.of The IEEE 19th International Conference on Advanced Information Networking and Applications, Taiwan, China, pp.909-914, 2005.

Agere Inc, Edge/access and multiservice network processors: App550 and app530, http://pdf.datasheetarchive.com/indexer files/Datasheet-026/DSA00457289.pdf, 2003-5.

C. Estan and G. Varghese, New directions in traffic measurement and accounting, ACM Transactions on Computer Systems, Vol.32, No.4, pp.1-42, 2002.

B. Suter, T. V. Lakshman, D. Stiliadis and A. K. Choudhury, Buffer management schemes for supporting TCP in gigabit routers with per-flow queueing, IEEE Journal on Selected Areas in Communications, Vol.17, No.6, pp.1159-1169, 1999.

C. K. Siew, G. Feng, F. Long and M. H. Er, Congestion control based on flow-state-dependent dynamic priority scheduling, IEE Proceedings Communications, Vol.152, No.5, pp.548-558, 2005.

Relative Articles

Supplements(0)

Cited By

Proportional views