International Journal of Computer Network and Information Security (IJCNIS)
IJCNIS Vol. 8, No. 9, 8 Sep. 2016
Cover page and Table of Contents: PDF (size: 686KB)
Interaction of High Speed TCPs with Recent AQMs through Experimental Evaluation
Full Text (PDF, 686KB), PP.41-47
Views: 0 Downloads: 0
Author(s)
Vandana Kushwaha
1,*
Ratneshwer
2
Index Terms
High Speed Networks, Congestion Control, Active Queue Management, TCP
Abstract
Congestion control approaches, source based approach and router based approach have their own limitations. In source based approach, it is difficult to get correct location of congestion and without proper admission control; we cannot effectively manage the congestion problem. Thus both the approaches have to work in coordination for effective congestion control. In this context, an interaction study plays an important role to verify how a TCP implemented at source end works with Active Queue Management at router end. In this paper, we analyzed the performance of different high speed TCP variants at the source end with some recent AQM approaches: CoDel and sfqCoDel. The main objective of this work is to obtain the interaction patterns of different high speed TCP variants like: HTCP, Compound, HSTCP, Scalable and Cubic with recently proposed AQMs: CoDel and sfqCoDel. Simulation results show that that if we want to achieve a better throughput, minimum delay and improved fairness simultaneously, Cubic-sfqCoDel may be a good choice of TCP-AQM combinations for high speed networks.
Cite This Paper
VandanaKushwaha, Ratneshwer, "Interaction of High Speed TCPs with Recent AQMs through Experimental Evaluation", International Journal of Computer Network and Information Security(IJCNIS), Vol.8, No.9, pp.41-47, 2016. DOI:10.5815/ijcnis.2016.09.06
Reference
[1]Chydzinski, A., Brachman, A. (2010). Performance of AQM routers in the presence of new TCP variants. In: Proceedings of the second international conference on advances in future internet. pp. 88–93.
[2]CRON, (2011). CRON Project: Cyberinfrastructure for Reconfigurable Optical Networking Environment. Retrieved from: http://www.cron.loni.org/.
[3]Eshete, A., Jiang, Y.,Landmark, L. (2012). Fairness among high speed and traditional TCP under different queue management mechanisms. In: Proceedings of the ACM asian internet engineering conference. pp. 39–46.
[4]Floyd, S. (2003). Highspeed TCP for large congestion windows, RFC3649.
[5]Floyd, S., Jacobson, V. (1993). Random early detection gateways for congestion avoidance.IEEE/ACM Transactions on Networking, Vol.1(4), pp: 397–413.
[6]Gettys, J., Nichols, K. (2012). Bufferbloat: dark buffers in the internet. Communications of the ACM, Vol.55(1), pp:57-65.
[7]Hoeiland-Joergensen, T., McKenney, P. et al. (2014). Flowqueue-Codel (draft-hoeilandjoergensen-aqm-fq-codel-00). Retrieved from: https://tools.ietf.org/html/draft-hoeiland-joergensen-aqm-fq-codel-00.
[8]Hollot, C., Misra, V., Towsley, D., Gong, W. (2002). Analysis and design of controllers for AQM routers supporting TCP flows. IEEE Transactions of Automatic Control, Vol.47, pp: 945–959.
[9]Kelly, T. (2003). Scalable TCP: improving performance in high speed wide area networks. Computer Communication Review, Vol.33(2), pp: 83–91.
[10]Kuhn, N., Lochin, E. et al. (2014). Revisiting old friends: Is codel really achieving what red cannot? In: ACM
SIGCOMM Capacity Sharing Workshop. ACM, Chicago, IL, USA.
[11]Kunniyur, S., Srikant, R. (2001). Analysis and design of an adaptive virtual queue (AVQ) algorithm for active queue management. Computer Communication Review, Vol. 31(4), pp:123–134.
[12]Kushwaha V, Gupta R. Congestion control for high-speed wired network: a systematic literaturereview. Journal of Network and Computer Applications, Vol.45, pp: 62–78, 2014.
[13]Lapsley, D., Low, S. (1999). Random early marking: an optimization approach to internet congestion control. In: Proceedings of the IEEE ICON.
[14]Leith, D., Shorten, R. (2004). H-TCP: TCP for high-speed and long distance networks. In: Proceedings of the PFLDnet. 2004.
[15]Nichols, K., Jacobson, V. (2012). Controlling queue delay. Communications of the ACM, Vol.55(7), pp:42-50.
[16]Ns-2 Network Simulator. (n. d.). Retrieved from: (http://www.isi.edu/nsnam/ns/).
[17]Rao, V. P., Tahiliani, M. P. et al. (2014). Analysis of sfqCoDel for Active Queue Management, Applications of Digital Information and Web Technologies (ICADIWT).
[18]Rhee, I., Xu, L. (2008). CUBIC: a new TCP-friendly high-speed TCP variant. SIGOPS Operating System Review, Vol.42(5), pp:64–74.
[19]Tan, K., Song, J. (2006). Compound TCP: a scalable and TCP-friendly congestion control for high-speed networks. In Proc. 4th International Workshop on Protocols for FAST Long-Distance Networks, March 2006.
[20]Xue, L., Cui, C. et al. (2012). Experimental evaluation of the effect of queue management schemes on the performance of high speed tcps in 10gbps network environment. In proceeding of International Conference on Computing, Networking and Communications (ICNC), pp: 315-319, IEEE.