Abstract
The problem of TCP incast in data centers attracts a lot of attention in our research community. TCP incast is a catastrophic throughput collapse that occurs when multiple senders transmitting TCP data simultaneously to a single aggregator. Based on several experiments, researchers found that TCP timeouts are the primary cause of incast problem. Particularly, timeouts due to insufficient duplicate acknowledgments is unavoidable when at least one of the last three segments is lost from the tail of a window. As a result, this type of timeouts should be avoided to improve the goodput of TCP in data center networks. A few attempts have been made to reduce timeouts, but still the problem is not completely solved especially in the case of timeouts due to insufficient duplicate acknowledgments. In this paper, we present an efficient TCP fast retransmission approach, called TCP-EFR, which is capable to reduce TCP timeouts due to lack of duplicate acknowledgments which is caused by the loss of packets from the tail of a window in data center networks. TCP-EFR makes changes in the fast retransmission and recovery algorithm of TCP by using the congestion signal mechanism of DCTCP based on instantaneous queue length. In addition, TCP-EFR controls the sending rate for avoiding the overflow of switch buffer in order to reduce the loss of packets. The results of a series of simulations in single as well as multiple bottleneck topologies using qualnet 4.5 demonstrates that TCP-EFR can significantly reduce the timeouts due to inadequate duplicate acknowledgments and noticeably improves the performance compared to DCTCP, ICTCP and TCP in terms of goodput, accuracy and stability under various network conditions.
Similar content being viewed by others
References
Kant, K.: Data center evolution: a tutorial on state of the art, issues, and challenges. Comput. Netw. 53(17), 2939–2965 (2009). doi:10.1016/j.comnet.2009.10.004. ISSN 1389–1286
Ren, Y., Zhao, Y., Liu, P., Dou, K., Li, J.: A survey on TCP incast in data center networks. Int. J. Commun. Syst. 27, 1160–1172 (2012)
Bari, M.F., Boutaba, R., Esteves, R., Granville, L.Z., Podlesny, M., Rabbani, M.G., Qi, Z., Zhani, M.F.: Data center network virtualization: a survey. IEEE Commun. Surv. Tutor. 15(2), 909–928 (2013). Second Quarter 2013
Kiriha, Y., Nishihara, M.: Survey on data center networking technologies. IEICE Trans. Commun. E96–B(3), 713–721 (2013)
Shang, Y., Li, D., Xu, M.: Energy-aware routing in data center network. In: Proceedings of the First ACM SIGCOMM Workshop on Green networking (Green Networking ’10), pp. 1–8. ACM, New York (2010). doi:10.1145/1851290.1851292
Li, D., Xu, M., Liu, Y., Xie, X., Cui, Y., Wang, J., Chen, G.: Reliable multicast in data center networks. IEEE Trans. Comput. 63(8), 2011–2014 (2014). doi:10.1109/TC.2013.91
Chen, K., Guo, C., Wu, H., Yuan, J., Feng, Z., Chen, Y., Lu, S., Wu, W.: DAC: generic and automatic address configuration for data center networks. IEEE/ACM Trans. Netw. 20(1), 84–99 (2012). doi:10.1109/TNET.2011.2157520
Yu, Y., Fang, S., Aung, K.M.M., Foh, C.H., Li, H., Zhu, Y.: A layer 2 multipath solution and its performance evaluation for Data Center Ethernets. Int. J. Commun. Syst. 27, 2555 (2013). doi:10.1002/dac.2488
Zhang, Y., Ansari, N.: On architecture design, congestion notification, TCP incast and power consumption in data center. IEEE Commun. Surv. Tutor. 15(1), 39–64 (2013)
Zhang, J., Ren, F., Yue, X., Shu, R., Lin, C.: Sharing bandwidth by allocating switch buffer in data center networks. IEEE J. Sel. Areas Commun. 32(1), 39–51 (2014). doi:10.1109/JSAC.2014.140105
Wu, W., Crawford, M.: Potential performance bottleneck in Linux TCP. Int. J. Commun. Syst. 20, 1263–1283 (2007). doi:10.1002/dac.872
Liu, C.H., Kind, A., Liu, T.: Summarizing data center network traffic by partitioned conservative update. IEEE Commun. Lett. 17(11), 2168–2171 (2013). doi:10.1109/LCOMM.2013.091913.130094
Qin, Y., Shi, Y., Sun, Q., Zhao, L.: Analysis for unfairness of TCP outcast problem in data center networks. In: 2013 25th International Teletraffic Congress (ITC), pp. 1–4 (2013). doi:10.1109/ITC.2013.6662965
Tahiliani, R.P., Tahiliani, M.P., Sekaran, K.C.: TCP variants for data center networks: a comparative study. In: Proceedings of the 2012 International Symposium on Cloud and Services Computing (ISCOS ’12), pp. 57–62. IEEE Computer Society, Washington (2012). doi:10.1109/ISCOS.2012.38
Chen, Y., Griffith, R., Liu, J., Katz, R.H., Joseph, A.D.: Understanding TCP incast throughput collapse in datacenter networks. In: Proceedings of the 1st ACM Workshop on Research on Enterprise Networking (WREN ’09), pp. 73–82. ACM, New York (2009). doi:10.1145/1592681.1592693. http://doi.acm.org/10.1145/1592681.1592693
Phanishayee, A., Krevat, E., Vasudevan, V., Andersen, D.G., Ganger, G.R., Gibson, G.A., Seshan, S.: Measurement and analysis of TCP throughput collapse in cluster-based storage systems. In: Baker, M., Riedel, E. (eds.) Proceedings of the 6th USENIX Conference on File and Storage Technologies (FAST’08), p. 14. USENIX Association, Berkeley (2008). Article 12
Lee, J., Cha, H., Ha, R.: A time-dominated TCP congestion control over heterogeneous networks. Int. J. Commun. Syst. 21, 1325–1345 (2008). doi:10.1002/dac.957
Zhang, J., Ren, F., Tang, L., Lin, C.: Taming TCP incast throughput collapse in data center networks. In: Proceedings of 21\(^{st}\) International Conference on Network Protocols (2013)
Zhang, J., Wen, J., Wang, J., Zhao, W.: TCP-FITDC: an adaptive approach to TCP incast avoidance for data center applications. 2013 International Conference on Computing, Networking and Communications (ICNC), pp. 1048–1052 (2013)
Shukla, S., Chan, S., Tam, A.S.W., Gupta, A., Yang, X., Chao, H.J.: TCP PLATO: packet labelling to alleviate time-out. IEEE J. Sel. Areas Commun. 32(1), 65–76 (2014). doi:10.1109/JSAC.2014.140107
Zhang, J., Ren, F., Tang, L., Lin, C.: Modeling and solving TCP incast problem in data center networks. IEEE Trans. Parallel Distrib. Syst. 99, 1 (2015). doi:10.1109/TPDS.2014.2310210
Wu, H., Feng, W., Guo, C., Zhang, Y.: ICTCP: incast congestion control for TCP in data-center networks. IEEE/ACM Transactions on Networking 21(2), 345–358 (2013). doi:10.1109/TNET.2012.2197411
Ming, L., Lukyanenko, A., Tarkoma, S., Yla-Jaaski, A.: MPTCP incast in data center networks. Communications 11(4), 25–37 (2014). doi:10.1109/CC.2014.6827566
Wang, G., Ren, Y., Dou, K., Li, J.: IDTCP: an effective approach to mitigating the TCP incast problem in data center networks. Inf. Syst. Front. 16(1), 35–44 (2014). doi:10.1007/s10796-013-9463-4
Alizadeh, M., Greenberg, A., Maltz, D.A., Padhye, J., Patel, P., Prabhakar, B., Sengupta, S., Sridharan, M.: Data center TCP (DCTCP). SIGCOMM Comput. Commun. Rev. 40(4), 63–74 (2010). doi:10.1145/1851275.1851192. http://doi.acm.org/10.1145/1851275.1851192
Hwang, J., Yoo, J., Choi, N.: IA-TCP: a rate based incast-avoidance algorithm for TCP in data center networks. In: 2012 IEEE International Conference on Communications (ICC), pp. 1292–1296 (2012)
Ko, E., An, D., Yeom, I., Yoon, H.: Congestion control for sudden bandwidth changes in TCP. Int. J. Commun. Syst. 25, 1550–1567 (2012). doi:10.1002/dac.1322
Hashimoto, M., Hasegawa, G., Murata, M.: An analysis of energy consumption for TCP data transfer with burst transmission over a wireless LAN. Int. J. Commun. Syst. (2014). doi:10.1002/dac.2832
Hou, T.-C., Hsu, C.-W., Wu, C.-S.: A delay-based transport layer mechanism for fair TCP throughput over 802.11 multihop wireless mesh networks. Int. J. Commun. Syst. 24, 1015–1032 (2011). doi:10.1002/dac.1207
Vasudevan, V., Phanishayee, A., Shah, H., Krevat, E., Andersen, D.G., Ganger, G.R., Gibson, G.A., Mueller, B.: Safe and effective fine-grained TCP retransmissions for datacenter communication. In: Proceedings of the ACM SIGCOMM 2009 Conference on Data Communication (SIGCOMM ’09), pp. 303–314. ACM, New York (2009). doi:10.1145/1592568.1592604
Das, T., Sivalingam, K.M.: TCP improvements for data center networks. 2013 Fifth International Conference on Communication Systems and Networks (COMSNETS), pp. 1–10 (2013)
Tam, A.S.W., Xi, K., Xu, Y., Chao, H.J.: Preventing TCP incast throughput collapse at the initiation, continuation, and termination. In: Proceedings of the 2012 IEEE 20th International Workshop on Quality of Service (IWQoS ’12), p. 9. IEEE Press, Piscataway (2012). Article 29
Sreekumari, Prasanthi, Chung, Sang-Hwa: TCP NCE: a unified solution for non-congestion events to improve the performance of TCP over wireless networks. EURASIP J. Wirel. Commun. Netw. 2011, 23 (2011)
Dixit, A., Prakash, P., Hu, Y.C., Kompella, R.R.: On the impact of packet spraying in data center networks. 2013 Proceedings IEEE INFOCOM, pp. 2130–2138 (2013). doi:10.1109/INFCOM.2013.6567015
Dixit, A., Prakash, P., Kompella, R.R.: On the efficacy of fine-grained traffic splitting protocolsin data center networks. SIGCOMM Comput. Commun. Rev. 41(4), 430–431 (2011). doi:10.1145/2043164.2018504. http://doi.acm.org/10.1145/2043164.2018504
Gill, P., Jain, N., Nagappan, N.: Understanding network failures in data centers: measurement, analysis, and implications. Proceedings of the ACM SIGCOMM 2011 Conference (SIGCOMM ’11). ACM, New York (2011). doi:10.1145/2018436.2018477. http://doi.acm.org/10.1145/2018436.2018477
Vamanan, B., Hasan, J., Vijaykumar, T.N.: Deadline-aware datacenter TCP (D2TCP). In: Proceedings of the ACM SIGCOMM 2012 Conference on Applications, Technologies, Architectures, and Protocols for Computer Communication (SIGCOMM ’12), pp. 115–126. ACM, New York (2012)
Park, Mi-Young: Chung, Sang-Hwa: TCP’s dynamic adjustment of transmission rate to packet losses in wireless networks. EURASIP J. Wirel. Commun. Netw. 2012, 304 (2012)
Jiang, C., Li, D., Xu, M.: LTTP: an LT-code based transport protocol for many-to-one communication in data centers. IEEE J. Sel. Areas Commun. 32(1), 52–64 (2014). doi:10.1109/JSAC.2014.140106
Acknowledgments
This research was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Science, ICT and future Planning (NRF-2015R1A2A1A15056298) and also supported by the ICT R&D program of MSIP/IITP. [B0126-15-1051, A Study on Hyper Connected Self-Organizing Network Infrastructure Technologies for IoT Service].
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Sreekumari, P., Jung, Ji. & Lee, M. A simple and efficient approach for reducing TCP timeouts due to lack of duplicate acknowledgments in data center networks. Cluster Comput 19, 633–645 (2016). https://doi.org/10.1007/s10586-016-0555-z
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10586-016-0555-z