TCP Skyline: A High-Throughput Transport for Data Center Networks

被引:0
|
作者
Wang J. [1 ]
Xia Y. [1 ]
机构
[1] Department of Computer Science, Sichuan Normal University, Chengdu
来源
Tien Tzu Hsueh Pao/Acta Electronica Sinica | 2020年 / 48卷 / 12期
关键词
Data center; Delay ACK; Multi-turn transmission; Retransmission timeout; TCP Incast; Transmission protocol;
D O I
10.3969/j.issn.0372-2112.2020.12.019
中图分类号
学科分类号
摘要
In the "many-to-one" concurrent traffic pattern of the data center networks, TCP(Transmission Control Protocol) and its existing improvements have low throughput in single-round and multi-round of data transmission scenarios. Hence, a strategy called TSL(TCP SkyLine) is proposed for fast discovering and retransmitting the lost packets through packet labelling and adjusting the initial size of the congestion window dynamically. TSL solves the traditional TCP Incast problem and the TCP Incast problem caused by the legacy window in multi-round of data transmission. Through extensive experiments we show that TSL can achieve more than 90% goodput regardless of single or multiple rounds of data transmission. In a 10Gbps network, the number of concurrent connections supported by TSL has increased by 5 times and once respectively compared to the traditional TCP and DCTCP, and the goodput has increased by 18 times and 8.6 times respectively. In a 1Gbps network, the number of concurrent connections supported by TSL has increased by 5.8 times and once respectively compared to the traditional TCP and DCTCP. © 2020, Chinese Institute of Electronics. All right reserved.
引用
收藏
页码:2425 / 2433
页数:8
相关论文
共 20 条
  • [1] SONG Jie, SUN Zong-zhe, Et al., Research advance on MapReduce based big data processing platforms and algorithms, Journal of Software, 28, 3, pp. 514-543, (2017)
  • [2] LIANG Jun-jie, LI Feng-hua, Et al., Optimized high-dimensional index and KNN query in MapReduce, Acta Electronica Sinica, 44, 8, pp. 1873-1880, (2016)
  • [3] Vasudevan V, Phanishayee A, Shah H, Et al., Safe and effective fine-grained TCP retransmissions for data center communication, ACM SIGCOMM Computer Communication Review, 39, 4, pp. 303-314, (2009)
  • [4] Yadav G H K, Madhavi K., Response time-based resource allocation according to service level agreements in cloud computing, International Journal of Internet Technology and Secured Transactions, 9, 4, pp. 537-546, (2019)
  • [5] YEJin, LI Tao-shen, Ge Zhi-hui, Priority-based congestion control scheme for deadline-aware TCP in data center networks, Journal of Software, 26, S2, pp. 61-70, (2015)
  • [6] GUO Li-na, Simulation analysis of TCP Incast in data center networks, Computer Engineering and Design, 36, pp. 60-64, (2015)
  • [7] HUANG Jia-wei, XU Wen-xi, Et al., An ECN-based slow-start of TCP congestion control in data center networks, Journal of University of Electronic Science and Technology of China, 47, pp. 169-177, (2018)
  • [8] Li Dan, Chen Gui-hai, Et al., Data center network research progress and trends, Chinese Journal of Computers, 37, 2, pp. 259-274, (2014)
  • [9] Alipio M, Tiglao N M, Et al., TCP Incast solutions in data center networks: A classification and survey, Journal of Network and Computer Applications, 146, (2019)
  • [10] Alizadeh M, Greenberg A, Maltz D A, Et al., Data center TCP (DCTCP), ACM SIGCOMM 2010 Conference, pp. 63-74, (2010)