TCP for Data Centers: Short Flows and Incast
Abstract views: 10
/ 
PDF downloads: 6
Keywords:
TCP Incast, Data Centers, Short Flows, Bandwidth Utilization, Server Concurrency, Load Balancing, Congestion Control, Traffic Scheduling, Low Latency, High ThroughputAbstract
Data center network challenges include meeting modern application demands due to limits of the
traditional Transmission Control Protocol (TCP). This study evaluates the TCP Incast phenomenon, a common
issue in data center environments where multiple servers respond simultaneously, leading to network
congestion, packet loss, and retransmission delays. To explore the impact of TCP Incast on data center
performance, the paper investigates key performance indicators including bandwidth utilization, server
concurrency, and load balancing effectiveness. By modeling scenarios and evaluating mitigation strategies, the
research proposes practical solutions to enhance TCP efficiency in high-bandwidth, low-latency data center
environments. Results highlight the importance of bandwidth scaling, advanced load distribution algorithms,
and optimized traffic scheduling mechanisms to mitigate the adverse effects of TCP Incast, thereby improving
overall system performance.
Downloads
References
J. Ousterhout, "It’s Time to Replace TCP in the Datacenter," Stanford University, Jan. 18, 2023. [Online]. Available: https://homa-transport.atlassian.net/wiki/spaces/HOMA/overview
C. Raiciu, S. Barre, C. Pluntke, A. Greenhalgh, D. Wischik, and M. Handley, "Improving Datacenter Performance and Robustness with Multipath TCP," in Proceedings of the ACM SIGCOMM 2011 Conference, Toronto, Canada, Aug. 2011, pp. 265–276. [Online]. Available: https://doi.org/10.1145/2018436.2018472
Liu, J. Huang, Y. Zhou, J. Wang, and T. He, "Task-aware TCP in Data Center Networks," in 2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS), Atlanta, GA, USA, Jun. 2017, pp. 1417–1424. [Online]. Available: https://doi.org/10.1109/ICDCS.2017.175
T. Yu and X. Qiu, "STCC: A SDN-oriented TCP congestion control mechanism for datacenter network," IET Networks, vol. 10, no. 1, pp. 13–23, Jan. 2021. [Online]. Available: https://doi.org/10.1049/ntw2
Q. I. Ali, "Design and implementation of an embedded intrusion detection system for wireless applications," IET Information Security, vol. 6, no. 3, pp. 171–182, 2012, doi: 10.1049/iet-ifs.2011.0152.
Q. I. Ali, "Performance Evaluation of WLAN Internet Sharing Using DCF & PCF Modes," International Arab Journal of e-Technologies (IAJET), vol. 1, no. 1, pp. 38–45, 2009.
S. L. Qaddoori and Q. I. Ali, "An embedded and intelligent anomaly power consumption detection system based on smart metering," IET Wireless Sensor Systems, vol. 13, no. 2, pp. 75–90, 2023, doi: 10.1049/wss2.12054.
H. M. Mohammed and Q. I. Ali, "E-proctoring systems: A review of design techniques, features, and abilities against threats and attacks," Quantum Journal of Engineering, Science, and Technology, vol. 3, no. 2, pp. 14–30, 2022.
H. Lim, W. Bai, Y. Zhu, Y. Jung, and D. Han, "Towards Timeout-less Transport in Commodity Datacenter Networks," in Proc. of the 16th European Conf. on Computer Systems (EuroSys '21), 2021, pp. 1–16. [Online]. Available: https://doi.org/10.1145/3447786.3456227
T. Zhang et al., "Rethinking Fast and Friendly Transport in Data Center Networks," IEEE/ACM Transactions on Networking, vol. 29, no. 2, pp. 1–13, Apr. 2021. [Online]. Available: https://doi.org/10.1109/TNET.2020.3012556
M. K. Mukerjee, C. Canel, W. Wang, D. Kim, S. Seshan, and A. C. Snoeren, "Adapting TCP for Reconfigurable Datacenter Networks," in Proceedings of the 17th USENIX Symposium on Networked Systems Design and Implementation (NSDI '20), Santa Clara, CA, USA, Feb. 2020, pp. 651–666. [Online]. Available: https://www.usenix.org/conference/nsdi20/presentation/mukerjee
A. M. Abdelmoniem, B. Bensaou, and A. J. Abu, "Mitigating incast-TCP congestion in data centers with SDN," Annals of Telecommunications, 2017. [Online]. Available: https://doi.org/10.1007/s12243-017-0608-1
J. Huang, Y. Huang, J. Wang, and T. He, "Adjusting Packet Size to Mitigate TCP Incast in Data Center Networks with COTS Switches," IEEE Transactions on Cloud Computing, 2018. [Online]. Available: https://doi.org/10.1109/TCC.2018.2810870
W. Bai, S. Hu, K. Chen, K. Tan, and Y. Xiong, "One More Config Is Enough: Saving (DC)TCP for High-Speed Extremely Shallow-Buffered Datacenters," IEEE/ACM Transactions on Networking, vol. 29, no. 2, pp. 1–10, Apr. 2021. [Online]. Available: https://doi.org/10.1109/TNET.2020.3032999
S. Zou, J. Huang, J. Wang, and T. He, "Flow-Aware Adaptive Pacing to Mitigate TCP Incast in Data Center Networks," IEEE/ACM Transactions on Networking, vol. 29, no. 2, pp. 1–14, Apr. 2021. [Online]. Available: https://doi.org/10.1109/TNET.2020.3027749
A. M. Abdelmoniem and B. Bensaou, "T-RACKs: A Faster Recovery Mechanism for TCP in Data Center Networks," IEEE/ACM Transactions on Networking, vol. 29, no. 2, pp. 1–16, Apr. 2021. [Online]. Available: https://doi.org/10.1109/TNET.2021.3059913
R. Alshahrani and H. Peyravi, "Modeling and Simulation of Data Center Networks," in Proc. of SIGSIM-PADS '14, Denver, CO, USA, 2014, pp. 1–7. [Online]. Available: https://doi.org/10.1145/2601381.2601389
