Analisis Kinerja Algoritme TCP Congestion Control Berdasarkan Single dan Multiple Flow pada Multi-Path Routing

Penulis

  • Bayu Sutawijaya Fakultas Ilmu Komputer - Universitas Brawijaya
  • Achmad Basuki Fakultas Ilmu Komputer - Universitas Brawijaya
  • Fitra Abdurrachman Bachtiar Fakultas Ilmu Komputer - Universitas Brawijaya

DOI:

https://doi.org/10.25126/jtiik.2020752402

Abstrak

Teknik multi-path routing merupakan solusi efektif untuk menambah kapasitas bandwidth jaringan. Namun, TCP menggunakan multiple paths sama dengan di single path. Penelitian ini melakukan analisis kinerja algoritme TCP congestion control Reno, BIC, CUBIC, dan BBR pada multi-path routing dengan setiap multiple paths menggunakan cost yang sama. Analisis yang dilakukan meliputi perbandingan antara single path routing dengan multi-path routing, single flow, dan multiple flow. Analisis single flow meliputi link delay dan loss rate. Sedangkan analisis multiple flow meliputi inter TCP protocol fairness dan fairness antara TCP dengan UDP. Semua evaluasi dilakukan berdasarkan emulasi pada VirtualBox. Berdasarkan hasil emulasi, multi-path routing dapat berdampak pada packet reordering, tetapi tidak mengakibatkan penurunan rata-rata throughput yang signifikan. Pada single flow, BBR merupakan algoritme TCP congestion control terbaik pada multi-path routing. Namun, pada multiple flow, CUBIC merupakan algoritme TCP congestion control terbaik pada multi-path routing. Pada evaluasi link delay, rata-rata RTT BBR lebih rendah hingga 58 ms dibandingkan dengan Reno, BIC, dan CUBIC. Sedangkan pada evaluasi loss rate, rata-rata throughput BBR lebih tinggi hingga 12 Mbps dibandingkan dengan Reno, BIC, dan CUBIC. Pada evaluasi inter TCP protocol fairness dan fairness antara TCP dengan UDP, fairness CUBIC paling mendekati 1 dibandingkan dengan Reno, BIC, dan BBR.

 

Abstract

The multi-path routing technique is an effective solution to increase network bandwidth capacity. However, TCP uses multiple paths similar to a single path. This study analyzes the performance of TCP congestion control algorithms Reno, BIC, CUBIC, and BBR on multi-path routing with each multiple paths using the same cost. The analysis includes a comparison between single path routing and multi-path routing, single flow, and multiple flows. In a single flow, the analysis includes link delay and loss rate. Whereas in multiple flows, the analysis includes inter TCP protocol fairness and fairness between TCP and UDP. All evaluations are based on emulation in VirtualBox. Based on the results from emulation, multi-path routing can have an impact on packet reordering but does not result in a significant degrade in average throughput. In a single flow, BBR is the best TCP congestion control algorithm on multi-path routing. However, in multiple flows, CUBIC is the best TCP congestion control algorithm on multi-path routing. In the link delay evaluations, the average RTT on BBR up to 58 ms lower than Reno, BIC, and CUBIC. Whereas in the loss rate evaluations, the average throughput on BBR up to 12 Mbps higher than Reno, BIC, and CUBIC. In the evaluation of inter TCP protocol fairness and fairness between TCP and UDP, fairness on CUBIC is closest to 1 than Reno, BIC, and BBR.


Downloads

Download data is not yet available.

Biografi Penulis

  • Bayu Sutawijaya, Fakultas Ilmu Komputer - Universitas Brawijaya
    mahasiswa magister FILKOM UB

Referensi

ARROKKIAM, J. A., WU, X., BROWN, K. N. dan SREENAN, C. J., 2014. Experimental Evaluation of TCP Performance over 10Gb/s Passive Optical Networks (XG-PON). In: IEEE Global Communications Conference, pp. 2223–2228.

BENNETT, J. C. R., PARTRIDGE, C. dan SHECTMAN, N., 1999. Packet Reordering is Not Pathological Network Behavior. IEEE/ACM Transactions on Networking, 7(6), pp. 789–798.

CARDWELL, N., CHENG, Y., GUNN, C. S., YEGANEH, S. H. dan JACOBSON, V., 2016a. BBR Congestion-Based Congestion Control. ACM Queue, 14(5), pp. 20–53.

CARDWELL, N., CHENG, Y., GUNN, C. S., YEGANEH, S. H. dan JACOBSON, V., 2016b. BBR Congestion Control, IETF 97. [online] Tersedia di: <https://www.ietf.org/proceedings/97/slides/slides-97-iccrg-bbr-congestion-control-02.pdf> [Diakses 23 Juli 2019].

CARDWELL, N., CHENG, Y., YEGANEH, S. H. dan JACOBSON, V., 2017. BBR Congestion Control. Internet Congestion Control Research Group - Internet Draft.

CARPA, R., DIAS DE ASSUNCAO, M., GLUCK, O., LEFEVRE, L. dan MIGNOT, J. -C., 2017. Evaluating the Impact of SDN-Induced Frequent Route Changes on TCP Flows. In: 13th International Conference on Network and Service Management.

CHENG, Y. dan CARDWELL, N., 2016. Making Linux TCP Fast, In: Netdev 1.2.

DIXIT, A., PRAKASH, P., HU, Y. C. dan KOMPELLA, R. R., 2013. On the Impact of Packet Spraying in Data Center Networks. In: IEEE INFOCOM, pp. 2130–2138.

HA, S. dan RHEE, I., 2008. Hybrid Slow Start for High-Bandwidth and Long-Distance Networks. In: PFLDNet.

HA, S., RHEE, I. dan XU, L., 2008. CUBIC : A New TCP-Friendly High-Speed TCP Variant. ACM SIGOPS Operating Systems Review - Research and developments in the Linux kernel, 42(5), pp. 64–74.

HASEGAWA, G. dan MURATA, M., 2001. Survey on Fairness Issues in TCP Congestion Control Mechanisms. IEICE Transactions on Communications, E84-B(6), pp. 1461–1472.

HE, J. dan REXFORD, J., 2008. Toward Internet-Wide Multipath Routing. IEEE Network, 22(2), pp. 16–21.

HOCK, M., BLESS, R. and ZITTERBART, M., 2017. Experimental Evaluation of BBR Congestion Control. In: IEEE 25th International Conference on Network Protocols (ICNP).

HUBERT, B., MAXWELL, G., MOOK, R., OOSTERHOUT, M., SCHROEDER, P. B. dan SPAANS, J., 2002. Linux Advanced Routing & Traffic Control HOWTO. [online] Tersedia di: <https://www.tldp.org/HOWTO/Adv-Routing-HOWTO/lartc.loadshare.html> [Diakses 23 Juli 2019].

iPerf - The ultimate speed test tool for TCP, UDP and SCTP, n.d. [online] Tersedia di: <https://iperf.fr/> [Diakses 23 Juli 2019.

JACOBSON, V., 1990. modified TCP congestion avoidance algorithm. End2end-interest mailing list.

JAIN, R. K., CHIU, D.-M. dan HAWE, W. R., 1984. A Quantitative Measure of Fairness and Discrimination for Resource Allocation in Shared Computer System. Technical Report TR-301, Digital Equipment Corporation.

KANAGEVLU, R. dan AUNG, K. M. M., 2015. SDN controlled Local re-routing to reduce congestion in cloud Data Centers. In: International Conference on Cloud Computing Research and Innovation, pp. 80–88.

KARLSSON, J., HURTIG, P., BRUNSTROM, A., KASSLER, A. dan STASI, G. D., 2012. Impact of Multi-path Routing on TCP Performance. In: IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks.

KUROSE, J. F. dan ROSS, K. W., 2017. Computer Networking: A Top-Down Approach. 7th ed. New Jersey: Pearson.

KUZNETSOV, A. N., n.d. TBF - Token Bucket Filter. [online] Tersedia di: <https://linux.die.net/man/8/tc-tbf> [Diakses 23 Juli 2019].

LEUNG, K.-C., LI, V. O. K. dan YANG, D., 2007. An Overview of Packet Reordering in Transmission Control Protocol (TCP): Problems, Solutions, and Challenges. IEEE Transactions on Parallel and Distributed Systems, 18(4), pp. 522–535.

LIU, J., LI, J., SHOU, G., HU, Y., GUO, Z. dan DAI, W., 2014. SDN Based Load Balancing Mechanism for Elephant Flow in Data Center Networks. In: International Symposium on Wireless Personal Multimedia Communications, pp. 486–490.

LUKASEDER, T., BRADATSCH, L., ERB, B., HEIJDEN, R. W. V. D. dan KARGL, F., 2016. A Comparison of TCP Congestion Control Algorithms in 10G Networks. In: IEEE 41st Conference on Local Computer Networks, pp. 706–714.

NetEM, n.d. [online] Tersedia di: <https://wiki.linuxfoundation.org/networking/netem> [Diakses 23 Juli 2019].

ROS, D. dan WELZL, M., 2013. Less-than-Best-Effort Service: A Survey of End-to-End Approaches. IEEE Communications Surveys and Tutorials, 15(2), pp. 898–908.

SINGH, S. K., DAS, T. dan JUKAN, A., 2015. A Survey on Internet Multipath Routing and Provisioning. IEEE Communications Surveys and Tutorials, 17(4), pp. 2157–2175.

Tcpdump, n.d. [online] Tersedia di: <https://www.tcpdump.org> [Diakses 23 Juli 2019].

VirtualBox, n.d. [online] Tersedia di: <https://www.virtualbox.org/> [Diakses 23 Juli 2019].

XU, L., HARFOUSH, K. dan RHEE, I., 2004. Binary Increase Congestion Control (BIC) for Fast, Long-Distance Networks. In: INFOCOM, pp. 2514–2524.

YUE, Z., ZHANG, X., REN, Y., LI, J. dan ZHONG, Q., 2012. The Performance Evaluation and Comparison of TCP-based High-speed Transport Protocols. In: IEEE 3rd International Conference on Software Engineering and Service Science, pp. 509–512.

Diterbitkan

08-10-2020

Terbitan

Bagian

Ilmu Komputer

Cara Mengutip

Analisis Kinerja Algoritme TCP Congestion Control Berdasarkan Single dan Multiple Flow pada Multi-Path Routing. (2020). Jurnal Teknologi Informasi Dan Ilmu Komputer, 7(5), 961-970. https://doi.org/10.25126/jtiik.2020752402