Abstract
Recent datacenter load balancing designs make full use of all available multiple paths to achieve high bisection bandwidth and support the increasing traffic demands. However, a multitude of uncertainties, such as congestion and asymmetry, easily leads to long tailed latencies for unlucky flows on bad paths. In this paper, we aim at adjusting the maximum number of multiple paths used by existing load balancing designs to achieve good tradeoff between the tailed latency and link utilization. Specifically, we propose a packet-level load balancing called scheme Adaptively Adjusting Concurrency (AAC) to spread packets across the multiple paths, which are adaptively selected according to path diversity. AAC is deployed at switch, without any modifications on end-hosts. The experimental results of NS2 simulation and Mininet implementation show that AAC significantly reduces the flow completion time by \(\sim\)21–56% over the state-of-the-art datacenter load balancing designs including MPTCP, LetFlow and RPS.
Similar content being viewed by others
References
Huang, Q., Jin, X., Lee, P.P.C., et al.: Setchvisor: Robust network measurement for software packet processing. In: Proc. ACM Special Interest Group on Data Communication, pp. 113–126 (2015)
Bredel, M., Bozakov, Z., Barczyk, A., et al.: low-based load balancing in multipathed layer-2 networks using OpenFlow and multipath-TCP. In: Proc. Hot Topics in Software Defined Networking, pp. 213–214 (2014)
Hopps, C.: Analysis of an equal-cost multi-path algorithm. RFC 2992, November, (2000). http://www.ietf.org/rfc/rfc2992.txt
Raiciu, C., Barre, S., Pluntke, C., et al.: Improving datacenter performance and robustness with multipath TCP. ACM SIGCOMM Comput. Commun. Rev. 41(4), 266–277 (2011)
Dixit, A., Prakash, P., Hu, Y. C., et al.: On the impact of packet spraying in data center networks. In Proc. IEEE INFOCOM, pp. 2130–2138 (2013)
Ghorbani, S., Yang, Z., Godfrey, P. B., et al.: Drill: Micro load balancing for low-latency data center networks. In: Proc. ACM Special Interest Group on Data Communication, pp. 225–238 (2017)
Zhang, H., Zhang, J., Bai, W., et al.: Resilient datacenter load balancing in the wild. In: Proc. ACM Special Interest Group on Data Communication, pp. 253–266 (2017)
Vanini, E., Pan, R., Alizadeh, M., et al.: Let it flow: Resilient asymmetric load balancing with flowlet switching. In: Proc. USENIX Symposium on Networked Systems Design and Implementation, pp. 407–420 (2017)
Chen, G., Lu, Y., Meng, Y., et al.: Fast and cautious: Leveraging multi-path diversity for transport loss recovery in data centers. In: Proc. USENIX Annual Technical Conference, pp. 29–42 (2016)
Tso, F. P., Hamilton, G., Weber, R., et al.: Longer is better: exploiting path diversity in data center networks. In: Proc. International Conference on Distributed Computing Systems, pp. 430–439 (2013)
Alizadeh, M., Edsall, T., Dharmapurikar, S., et al.: CONGA: distributed congestion-aware load balancing for datacenters. In: Proc. ACM Conference on SIGCOMM, pp. 503–514 (2014)
Cao, Y., Xu, M., Fu, X., et al.: Explicit multipath congestion control for data center networks. In Proc. ACM Conference on Emerging Networking Experiments and Technologies, pp. 73–84 (2013)
Zats, D., Das, T., Mohan, P., et al.: DeTail: reducing the flow completion time tail in datacenter networks. In: Proc. ACM SIGCOMM on Applications, Technologies, Architectures, and Protocols for Computer Communication, pp. 139–150 (2012)
Zhang, J., Zhang, D., Huang, K.: Improving datacenter throughput and robustness with Lazy TCP over packet spraying. Comput. Commun. 62, 23–33 (2015)
Wang, W., Sun, Y., Salamatian, K., et al.: Adaptive path isolation for elephant and mice flows by exploiting path diversity in datacenters. IEEE Trans. Netw. Serv. Manag. 13(1), 5–18 (2016)
Alizadeh, M., Kabbani, A., Edsall, T., et al.: Less is more: trading a little bandwidth for ultra-low latency in the data center. In: Proc. USENIX Symposium on Networked Systems Design and Implementation, pp. 253–266 (2012)
Carpio, F., Engelmann, A., Jukan, A.: DiffFlow: differentiating short and long flows for load balancing in data center networks. In: Proc. IEEE Global Communications Conference, pp. 1–6 (2016)
Lee, C., Park, C., Jang, K., et al.: Accurate latency-based congestion feedback for datacenters. In: Proc. USENIX, pp. 403–415 (2015)
Mittal, R., Lam, V.T., Dukkipati, N., et al.: TIMELY: RTT-based congestion control for the datacenter. ACM SIGCOMM Comput. Commun. Rev. 45(4), 537–550 (2015)
Zou, S., Huang, J., Wang, J., et al.: Improving TCP Robustness over asymmetry with reordering marking and coding in data centers. In: Proc. International Conference on Distributed Computing Systems, pp. 57–67 (2019)
Alizadeh, M., Yang, S., Sharif, M., et al.: Pfabric: minimal near-optimal datacenter transport. ACM SIGCOMM Comput. Commun. Rev. 43(4), 435–446 (2013)
Munir, A., Qazi, I.A., Uzmi, Z.A., et al.: Minimizing flow completion times in data centers. In: Proc. IEEE INFOCOM, pp. 2157–2165 (2013)
Noormohammadpour, M., Raghavendra, C.S.: Datacenter traffic control: understanding techniques and tradeoffs. IEEE Commun. Surv. Tutor. 20(2), 1492–1525 (2017)
Alizadeh, M., Greenberg, A., Maltz, D. A., et al.: Data center TCP (DCTCP). In: Proc. ACM SIGCOMM, pp. 63–74 (2010)
Hu, J., Huang, J., Lv, W., et al.: CAPS: coding-based adaptive packet spraying to reduce flow completion time in data center. IEEE/ACM Trans. Netw. 27(6), 2338–2353 (2019)
Kheirkhah, M., Wakeman, I., Parisis, G.: MMPTCP: a multipath transport protocol for data centers. In: Proc. IEEE INFOCOM, pp.1–9 (2016)
Zhangy, W., Lingy, D., Zhangy, Y., et al.: Achieving optimal edge-based congestion-aware load balancing in data center networks. In: Proc. IEEE Networking Conference, pp. 109–117 (2020)
Sen, S., Shue, D., Ihm, S., et al.: Scalable, “Optimal flow routing in datacenters via local link balancing”. In: Proc. ACM Conference on Emerging Networking Experiments and Technologies, pp. 151–162 (2013)
Serfozo, R.F.: An equivalence between continuous and discrete time Markov decision processes. Oper. Res. 27(3), 616–620 (1979)
Kabbani, A., Sharif, M.: Flier: flow-level congestion-aware routing for direct-connect data centers. In: Proc. IEEE INFOCOM, pp. 1–9 (2017)
Katta, N., Hira, M., Ghag, A., et al.: CLOVE: How I learned to stop worrying about the core and love the edge. In: Proc. the 15th ACM Workshop on Hot Topics in Networks, pp. 155–161 (2016)
Huang, J., Li, W., Li, Q., et al.: Tuning high flow concurrency for MPTCP in data center networks. J. Cloud Comput. 9(1), 1–15 (2020)
Liu, J., Huang, J., Li, W., et al.: AG: adaptive switching granularity for load balancing with asymmetric topology in data center network. In: Proc. International Conference on Network Protocols, pp. 1–11 (2019)
Shi, Q., Wang, F., Feng, D.: IntFlow: integrating per-packet and per-flowlet switching strategy for load balancing in datacenter networks. IEEE Trans. Netw. Serv. Manag. 17(3), 1377–1388 (2020)
Wang, P., Trimponias, G., Xu, H., et al.: Luopan: sampling-based load balancing in data center networks. IEEE Trans. Parallel Distrib. Syst. 30(1), 133–145 (2018)
Floyd, S., Jacobson, V.: Random early detection gateways for congestion avoidance. IEEE/ACM Trans. Netw. 1(4), 397–413 (1993)
Zou, S., Huang, J., Jiang, W., et al.: Achieving high utilization of flowlet-based load balancing in data center networks. Future Gener. Comput. Syst. 108, 546–559 (2020)
Xu, C., Yuan, T., Zhang, H., et al.: Dual channel per-packet load balancing for datacenters. In: Proc. IEEE INFOCOM, pp. 157–164 (2020)
He, B., Zhang, D., Zhao, C.: Hidden Markov Model-based Load Balancing in Data Center Networks. Comput. J. 63(10), 449–1462 (2020)
Xu, H., Li, B.: RepFlow: minimizing flow completion times with replicated flows in data centers. In: Proc. IEEE INFOCOM on Computer Communications, pp. 1581–1589 (2014)
Huang, J., Lv, W., Li, W., et al.: QDAPS: queueing delay aware packet spraying for load balancing in data center. In: Proc. International Conference on Network Protocols, pp. 66–76 (2018)
Perry, J., Ousterhout, A., Balakrishnan, H., et al.: “Fastpass: a centralized” zero-queue “datacenter network”. In: Proc. SIGCOMM, pp. 307–318 (2014)
Hu, J., Huang, J., Lv, W., et al.: TLB: Traffic-aware load balancing with adaptive granularity in data center networks. In: ICPP 2019: Proceedings of the 48th International Conference on Parallel Processing, pp. 1–10 (2019)
Katta, N., Ghag, A., Hira, M., et al.: Clove: congestion-aware load balancing at the virtual edge. In: Proc. the 13th International Conference on Emerging Networking Experiments and Technologies (2017)
Acknowledgements
This work is supported by the Natural Science Foundation of Hunan Province, China (No. 2018JJ2084), National Natural Science Foundation of China (No. 61872387), and Project of Foreign Cultural and Educational Expert (No. G20190018003).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Gao, W., Huang, J., Zou, S. et al. AAC: Adaptively Adjusting Concurrency by Exploiting Path Diversity in Datacenter Networks. J Netw Syst Manage 29, 26 (2021). https://doi.org/10.1007/s10922-021-09590-z
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10922-021-09590-z