Network Flow Avoidance Method Based on Service Satisfaction in Data Center

doi:10.3778/j.issn.1002-8331.2009-0507

Abstract

Abstract:

More and more industries are starting to utilize the cloud to reduce costs and improve productivity. Supporting diversified service raises higher requirements on the network performance of data centers, which is critical to ensure the quality of various services under high load. Cloud service providers also pay attention to improving the utilization of network resources and reducing energy consumption of data centers. A method for scheduling non-service network flows based on service satisfaction is proposed to solve the problems mentioned above. Firstly, the concept of service satisfaction is introduced to assess whether the network status can meet the service needs, and then it is classified according to the different services supported by the network flow. When the network load surges, the network flow that is not dependent on user services will be adjusted based on service satisfaction to reduce network load and alleviate congestion. The simulation results show that the active avoidance method can give priority to ensuring the quality of service when the network is suffering heavy load and improve network performance at the same time.

Key words: network flow, service satisfaction, active avoidance, network congestion, service classification

摘要：

越来越多的行业开始利用云以降低成本提高生产力，支撑多样化的服务对数据中心的网络性能提出了更高的要求，如何高负载下优先保证各项服务的质量变得至关重要，云服务提供商同时也关注如何提高数据中心的网络资源利用率并降低能耗。结合上述问题，提出一种基于服务满足度对非服务网络流进行调度的方法。引入服务满足度这一概念，评估网络状态能否满足服务需要，然后依据网络流所支撑的不同服务将其分类，网络负载激增时基于服务满足度调整非用户服务依赖的网络流，降低网络负载缓解拥塞。仿真结果表明，主动避让方法在网络高负载时能优先保证服务的质量，同时提高网络性能。

关键词: 网络流, 服务满足度, 主动避让, 网络拥塞, 服务分类

WU Ziqiang, ZHOU Jiantao, ZHAO Daming, LIU Lin. Network Flow Avoidance Method Based on Service Satisfaction in Data Center[J]. Computer Engineering and Applications, 2021, 57(19): 116-122.

武自强，周建涛，赵大明，柳林. 数据中心基于服务满足度的网络流避让方法[J]. 计算机工程与应用, 2021, 57(19): 116-122.

References

[1] China Research Institute of Information and Communication.Cloud computing White Paper（2019）[EB/OL].（2019-07）[2019-08-31].http：//www.caict.ac.cn/kxyj/qwfb/bps/201907/t20190702_202162.htm.
[2] 殷波.面向云环境的资源分配关键技术研究[D].北京：北京邮电大学，2013.
YIN B.Research on key technology of resource allocation for cloud environments[D].Beijing：Beijing University of Posts and Telecommunications，2013.
[3] MATHEW P.Self-benchmarking guide for data centers：Metrics，benchmarks，actions：LBNL-3393E[R].Lawrence Berkeley National Laboratory，2010.
[4] CHIARAVIGLIO L，D"ANDREAGIOVANNI F，LANCELLOTTI R，et al.An approach to balance maintenance costs and electricity consumption in cloud data centers[J].IEEE Transactions on Sustainable Computing，2018，3（4）：274-288.
[5] 杨光.网络设备功耗管理架构与节能策略研究[D].北京：北京邮电大学，2016.
YANG G.Network device power consumption and energy saving strategy of the management structure[D].Beijing：Beijing University of Posts and Telecommunications，2016.
[6] 陈琳，南洋.一种面向大规模系统域网络性能管理系统[J].计算机工程与科学，2017，39（9）：1588-1593.
CHEN L，NAN Y.A mass-oriented system area network performance management system[J].Computer Engineering and Science，2017，39（9）：1588-1593.
[7] ZHOU B，WU J，WANG L，et al.Joint optimization of server and network resource utilization in cloud data centers[C]//Proceedings of Global Communications Conference，2017：1-6.
[8] LI D，SHANG Y，CHEN C.Software defined green data center network with exclusive routing[C]//Proceedings of IEEE Infocom，2014.
[9] WANG T，XIA Y，MUPPALA J，et al.Achieving energy efficiency in data centers using an artificial intelligence abstraction model[J].IEEE Transactions on Cloud Computing，2018，6（3）：612-624.
[10] ZHANG H，XIAO Y，BU S，et al.Distributed resource allocation for data center networks：A hierarchical game approach[J].IEEE Transactions on Cloud Computing，2018，8：778-789.
[11] XU G，DAI B，HUANG B，et al.Bandwidth-aware energy efficient routing with SDN in data center networks[C]//Proceedings of the 17th International Conference on High Performance Computing and Communications，2015：766-771.
[12] CHOWDHURY M，STOICA I.Efficient coflow scheduling without prior knowledge[J].ACM Special Interest Group on Data Communication，2015，45（4）：393-406
[13] Cisco global cloud index：Methods for predicting and 2015—2020 White Papers[EB/OL].（2016）[2020-08-31].https：//www.cisco.com/c/m/zh_cn/express/case_center/vertical/wprdc001408.html.
[14] TAN L Z，SU W，CHENG P，et al.Sonum：Software-defined synergetic sampling approach and optimal network utilization mechanism for long flow in a data center network[J].Applied Science，2019，10（1）：171.
[15] GUO Z，HUI S，XU Y，et al.Dynamic flow scheduling for power-efficient data center networks[C]//Proceedings of International Workshop on Quality of Service，2016：1-10.
[16] LUO S，YU H，ZHAO Y，et al.Towards practical and near-optimal coflow scheduling for data center networks[J].IEEE Transactions on Parallel & Distributed Systems，2016，27（11）：1.
[17] CAO Z Z，KODIALAM M，LAKSHMAN T V.Joint static and dynamic traffic scheduling in data center networks[M].[S.l.]：IEEE Press，2016.
[18] XIA W，ZHAO P，WEN Y，et al.A survey on Data Center Networking（DCN）：Infrastructure and operations[J].IEEE Communications Surveys & Tutorials，2017，19（1）：640-656.
[19] WANG T，XU H，LIU F.Aemon：Information-agnostic mix-flow scheduling in data center networks[C]//Proceedings of Asia-Pacific Workshop on Networking，2017.
[20] ZHANG H，TANG F，BAROLLI L.Efficient flow detection and scheduling for SDN-based big data centers[J].Journal of Ambient Intelligence and Humanized Computing，2019，10（4）：1915-1926.
[21] PIETRI I，CHRONIS Y，IOANNIDIS Y.Multi-objective optimization of scheduling dataflows on heterogeneous cloud resources[C]//Proceedings of 2017 IEEE International Conference on Big Data，2017.
[22] PERRY J，OUSTERHOUT A E，BALAKRISHNAN H，et al.Fastpass：A centralized “Zero-Queue” datacenter network[J].ACM SIGCOMM Computer Communication Review，2014，44（4）：1-12.
[23] GAO P X，NARAYAN A，KUMAR G，et al.pHost：Distributed near-optimal datacenter transport over commodity network fabric[C]//Proceedings of Conference on Emerging Network Experiment and Technology，2015.
[24] GROSVENOR M P，SCHWARZKOPF M，GOG I，et al.Queues don’t matter when you can JUMP them![C]//Proceedings of the 12th USENIX Conference on Networked Systems Design and Implementation，2015：1-14.
[25] ZHANG X Y.Adaptive flow scheduling for modular datacenter networks[J].Peer-to-Peer Networking and Applications，2017，10：1142-1151.
[26] KHEIRKHAH M，WAKEMAN I，PARISIS G.Multipath transport and packet spraying for efficient data delivery in data centres[J].Computer Networks，2019，162：1-14.
[27] ABBASLOO S，XU Y，CHAO H J，et al.To schedule or not to schedule：when no-scheduling can beat the best-known flow scheduling algorithm in datacenter networks[J].arXiv：2001.08253，2020.
[28] 胡智尧，李东升，李紫阳.数据中心网络流调度技术前沿进展[J].计算机研究与发展，2018，55（9）：1920-1930.
HU Z Y，LI D S，LI Z Y，et al.Recent advances in datacenter flow scheduling[J].Journal of Computer Research and Development，2018，55（9）：1920-1930.
[29] ALIZADEH M，EDSALL T.On the data path performance of leaf-spine datacenter fabrics[C]//Proceedings of IEEE 21st Annual Symposium on High-Performance Interconnects，2013.