Abstract
In modern datacenter networks (DCNs), load balancing mechanisms are widely deployed to enhance link utilization and alleviate congestion. Recently, a large number of load balancing algorithms have been proposed to spread traffic among the multiple parallel paths. The existing solutions make rerouting decisions for all flows once they experience congestion on a path. They are unable to distinguish between the flows that really need to be rerouted and the flows that potentially have negative effects due to rerouting, resulting in frequently ineffective rerouting and performance degradation. To address the above issues, we present a traffic-differentiated load balancing (TDLB) mechanism, which focuses on distinguishing flows that necessarily to be rerouted and employing corresponding measures to make optimize routing decisions. Specifically, TDLB detects path congestion based on queue length at the switches, and distinguishes the traffic that must be rerouted through the host pair information in the packet header, and selects an optimal path for rerouting. The remaining traffic remains on the original path and relies on congestion control protocols to slow down to alleviate congestion. The NS-2 simulation results show that TDLB effectively reduces tailing latency and average flow completion time (FCT) for short flows by up to 45% and 46%, respectively, compared to the state-of-the-art load balancing schemes.
This work is supported by the National Natural Science Foundation of China (62102046, 62072056), the Natural Science Foundation of Hunan Province (2023JJ50331, 2022JJ30618, 2020JJ2029), the Hunan Provincial Key Research and Development Program (2022GK2019), the Scientific Research Fund of Hunan Provincial Education Department (22B0300), the Changsha University of Science and Technology Graduate Innovation Project (CLSJCX23101).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Li, W., Chen, S., Li, K., Qi, H., Xu, R., Zhang, S.: Efficient online scheduling for coflow-aware machine learning clusters. IEEE Trans. Cloud Comput. 10(4), 2564–2579 (2020)
Wang, J., Liu, Y., Rao, S., Zhou, X., Hu, J.: A novel self-adaptive multi-strategy artificial Bee Colony algorithm for coverage optimization in wireless sensor networks. Ad Hoc Netw. 150, 103284 (2023)
Li, H., Zhang, Y., Li, D., et al.: URSA: hybrid block storage for cloud-scale virtual disks. In: Proceedings of the Fourteenth EuroSys Conference, pp. 1–17 (2019)
Wang, J., Liu, Y., Rao, S., et al.: Enhancing security by using GIFT and ECC encryption method in multi-tenant datacenters. Comput. Mater. Continua 75(2), 3849–3865 (2023)
Wang, Y., Wang, W., Liu, D., et al.: Enabling edge-cloud video analytics for robotics applications. IEEE Trans. Cloud Comput. 11(2), 1500–1513 (2023)
Wang J., Rao S., Liu Y., et al.: Load balancing for heterogeneous traffic in datacenter networks. J. Netw. Comput. Appl. 217 (2023)
Hu, J., Zeng, C., Wang, Z., et al.: Enabling load balancing for lossless datacenters. In: Proceedings of IEEE ICNP (2023)
Xu, R., Li, W., Li, K., Zhou, X., Qi, H.: DarkTE: towards dark traffic engineering in data center networks with ensemble learning. In: Proceedings of IEEE/ACM IWQOS, pp. 1–10 (2021)
Li, W., Yuan, X., Li, K., Qi, H., Zhou, X.: Leveraging endpoint flexibility when scheduling coflows across geo-distributed datacenters. In: Proceedings of IEEE INFOCOM, pp. 873–881 (2018)
Bai, W., Chen, K., Hu, S., Tan, K., Xiong, Y.: Congestion control for high-speed extremely shallow-buffered datacenter networks. In: Proceedings of ACM APNet, pp. 29–35 (2017)
Hopps, C.E.: Analysis of an equal-cost multi-path algorithm (2000)
Alizadeh, M., et al.: CONGA: distributed congestion-aware load balancing for datacenters. In Proceedings of ACM Conference on SIGCOMM, pp. 503–514 (2014)
Ghorbani, S., Yang, Z., Godfrey, P.B., Ganjali, Y., Firoozshahian, A.: DRILL: micro load balancing for low-latency data center networks. In: Proceedings of ACM SIGCOMM, pp. 225–238 (2017)
Vanini, E., Pan, R., Alizadeh, M., Taheri, P., Edsall, T.: Let it flow: resilient asymmetric load balancing with flowlet switching. In: Proceedings of USENIX NSDI, pp. 407–420 (2017)
Zhang, H., Zhang, J., Bai, W., Chen, K., Chowdhury, M.: Resilient datacenter load balancing in the wild. In: Proceedings of ACM SIGCOMM, pp. 253–266 (2017)
Dixit, A., Prakash, P., Hu, Y.C., Kompella, R.R.: On the impact of packet spraying in data center networks. In: Proceedings of IEEE INFOCOM, pp. 2130–2138 (2013)
Hu, J., Huang, J., Li, Z., Wang, J., He, T.: A receiver-driven transport protocol with high link utilization using anti-ECN marking in data center networks. IEEE Trans. Netw. Serv. Manag. 20(2), 1898–1912 (2023)
He, X., Li, W., Zhang, S., Li, K.: Efficient control of unscheduled packets for credit-based proactive transport. In: Proceedings of ICPADS, pp. 593–600 (2023)
Kabbani, A., Vamanan, B., Hasan, J., Duchene, F.: FlowBender: flow-level adaptive routing for improved latency and throughput in datacenter networks. In: Proceedings of CoNEXT, pp. 149–160 (2014)
Wang, J., Yuan, D., Luo, W., et al.: Congestion control using in-network telemetry for lossless datacenters. Comput. Mater. Continua 75(1), 1195–1212 (2023)
Wen, K., Qian, Z., Zhang, S., Lu, S.: OmniFlow: coupling load balancing with flow control in datacenter networks. In: Proceedings of ICDCS, pp. 725–726 (2016)
Shafiee, M., Ghaderi, J.: A simple congestion-aware algorithm for load balancing in datacenter networks. In: Proceedings of INFOCOM, pp. 1–9 (2016)
Alizadeh, M., Greenberg, A. et al.: Data center TCP (DCTCP). In: Proceedings of ACM SIGCOMM, pp. 63–74 (2010)
Munir, A., et al.: Minimizing flow completion times in data centers. In: Proceedings of INFOCOM, pp. 2157–2165 (2013)
Li, Z., Bai, W., Chen, K., et al.: Rate-aware flow scheduling for commodity data center networks. In: Proceedings of IEEE INFOCOM, pp. 1–9 (2017)
David, Z., Tathagata, D., Prashanth, M., Dhruba, B., Randy, K.: DeTail: reducing the flow completion time tail in datacenter networks. In: Proceedings of the ACM SIGCOMM, pp. 139–150 (2012)
Benson, T., Akella, A., Maltz, D.: Network traffic characteristics of data centers in the wild. In: Proceedings of ACM IMC, pp. 267–280 (2010)
Hu, C., Liu, B., Zhao, H., et al.: Discount counting for fast flow statistics on flow size and flow volume. IEEE/ACM Trans. Network. 22(3), 970–981 (2013)
The NS-2 network simulator. http://www.isi.edu/nsnam/ns
Bai, W., Hu, S., Chen, K., Tan, K., Xiong, Y.: One more config is enough: saving (DC) TCP for high-speed extremely shallow-buffered datacenters. IEEE/ACM Trans. Network. 29(2), 489–502 (2020)
Liu, Z., et al.: Enabling work-conserving bandwidth guarantees for multi-tenant datacenters via dynamic tenant-queue binding. In: IEEE INFOCOM 2018-IEEE Conference on Computer Communications, pp. 1–9 (2018)
Hu, C., Liu, B., Zhao, H., Chen, K., et al.: Disco: memory efficient and accurate flow statistics for network measurement. In: Proceedings of IEEE ICDCS, pp. 665–674 (2010)
Wei, W., Gu, H., Deng, W., Xiao, Z., Ren, X.: ABL-TC: a lightweight design for network traffic classification empowered by deep learning. Neurocomputing 489, 333–344 (2022)
Wei, W., et al.: GRL-PS: graph embedding-based DRL approach for adaptive path selection. IEEE Trans. Netw. Serv. Manag. (2023)
Hu, J., He, Y., Wang, J., et al.: RLB: reordering-robust load balancing in lossless datacenter network. In: Proceedings of ACM ICPP (2023)
Hu, J., Zeng, C., Wang, Z., Xu, H., Huang, J., Chen, K.: Load balancing in PFC-enabled datacenter networks. In: Proceedings of ACM APNet (2022). Wang, J., Rao, S., Liu, Y., et al.: Load balancing for heterogeneous traffic in datacenter networks. J. Netw. Comput. Appl. 217 (2023)
Zhao, Y., Huang, Y., Chen, K., Yu, M., et al.: Joint VM placement and topology optimization for traffic scalability in dynamic datacenter networks. Comput. Netw. 80, 109–123 (2015)
Zheng, J., Du, Z., Zha, Z., et al.: Learning to configure converters in hybrid switching data center networks. IEEE/ACM Trans. Network. 1–15 (2023)
Liu, Y., Li, W., Qu, W., Qi, H.: BULB: lightweight and automated load balancing for fast datacenter networks. In: Proceedings of ACM ICPP, pp. 1–11 (2022)
Katta, N., Hira, M., Kim, C., Sivaraman, A., Rexford, J.: HULA: scalable load balancing using programmable data planes. In: Proceedings of the Symposium on SDN Research, pp. 1–12 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Hu, J., Liu, Y., Rao, S., Wang, J., Zhang, D. (2024). Enabling Traffic-Differentiated Load Balancing for Datacenter Networks. In: Tari, Z., Li, K., Wu, H. (eds) Algorithms and Architectures for Parallel Processing. ICA3PP 2023. Lecture Notes in Computer Science, vol 14489. Springer, Singapore. https://doi.org/10.1007/978-981-97-0798-0_15
Download citation
DOI: https://doi.org/10.1007/978-981-97-0798-0_15
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-0797-3
Online ISBN: 978-981-97-0798-0
eBook Packages: Computer ScienceComputer Science (R0)