面向全可编程网络数据平面的资源优化方法

doi:10.3969/j.issn.0372-2112.2018.10.016

PDF(1450 KB)

电子学报 ›› 2018, Vol. 46 ›› Issue (10) : 2423-2429. DOI: 10.3969/j.issn.0372-2112.2018.10.016

学术论文

面向全可编程网络数据平面的资源优化方法

申涓, 段通, 兰巨龙

作者信息 +

The Resource Optimization Towards Fully-Programmable Network Dataplane

SHEN Juan, DUAN Tong, LAN Ju-long

Author information +

文章历史 +

摘要

现有数据平面无法在整体上支持网络功能的创新和演进，因此面向用户可编程的新型网络数据平面技术发展迅速.针对现有可编程数据平面硬件开销过大且缺乏资源优化的问题，从解析器、匹配表、动作执行器三个方面建立了资源开销模型，并分别提出了类型域合并、匹配域偏移量合并、"域-字"拆分合并映射等资源优化方法.基于NetFPGA的仿真结果表明，与现有机制相比，所提方法减小了38%左右的资源开销.

Abstract

The existing network data plane could not support the evolution and innovation of network functions, thus the new data plane technology for user-programmability is developing rapidly. For the huge amount of hardware resource costs and the lack of responsible resource optimization, a resource cost model combining parser, match table, and action processor is built, and the corresponding resource optimization methods like type field combination, match field offset combination and "field-to-word" mapping are proposed. The NetFPGA-based experimental results show that the proposed mechanism can reduce hardware resource cost by 38% compared to existing mechanisms.

导出引用

申涓, 段通, 兰巨龙. 面向全可编程网络数据平面的资源优化方法[J]. 电子学报, 2018, 46(10): 2423-2429. https://doi.org/10.3969/j.issn.0372-2112.2018.10.016

SHEN Juan, DUAN Tong, LAN Ju-long. The Resource Optimization Towards Fully-Programmable Network Dataplane[J]. Acta Electronica Sinica, 2018, 46(10): 2423-2429. https://doi.org/10.3969/j.issn.0372-2112.2018.10.016

中图分类号： TP393

参考文献

[1] SCHAFFRATH G,WERLE C,PAPADIMITRIOU P,et al.Network virtualization architecture:proposal and initial prototype[A].Proceedings of ACM Workshop on Virtualized Infrastructure Systems and Architectures[C].Barcelona:ACM,2009.63-72.
[2] CHIOSI M,CLARKE D,et al.Network Functions Virtualisation-Introductory White Paper[OL].http://portal.etsi.org/NFV/NFV_White_Paper.pdf,2012-12-22.
[3] MCKEOWN N.Keynote talk:software-defined networking[A].IEEE International Conference on Computer Communications[C].Rio de Janeiro:IEEE,2009.1-11.
[4] JACOBSON V,SMETTERS D K,THORNTON J D,et al.Networking named content[J].Communications of the ACM,2012,55(1):117-124.
[5] MCKEOWN N,ANDERSON T,BALAKRISHNAN H N,et al.Openflow:enabling innovation in campus networks[J].ACM SIGCOMM Computer Communication Review,2008,38(2):69-74.
[6] BOSSHART P,GIBB G,KIM H S,et al.Forwarding metamorphosis:fast programmable match-action processing in hardware for SDN[J].ACM SIGCOMM Computer Communication Review,2013,43(4):99-110.
[7] BOSSHART P,DALY D,GIBB G,et al.P4:programming protocol-independent packet processors[J].ACM SIGCOMM Computer Communication Review,2014,44(3):87-95.
[8] SONG H.Protocol oblivious forwarding:unleash the power of SDN through a future-proof forwarding plane[A].Proceedings of ACM SIGCOMM Workshop on Hot Topics in Software Defined Networking (HotSDN)[C].Hong Kong:ACM,2013.127-132.
[9] CHOLE S,FINGERHUT A,MA S,et al.dRMT:disaggregated programmable switching[A].Proceedings of ACM SIGCOMM'17[C].Los Angeles:ACM,2017.1-14.
[10] KOZANITIS K,HUBER J,SINGH S,et al.Leaping multiple headers in a single bound:wire-speed parsing using the Kangaroo system[A].Proceedings of IEEE International Conference on Computer Communications[C].San Diego:IEEE,2010.1-9.
[11] LU G,SHI Y,GUO C,et al.CAFE:a configurable packet forwarding engine for data center networks[A].Proceedings of ACM SIGCOMM workshop on programmable routers for extensible services of tomorrow (PRESTO)[C].Barcelona:ACM,2009.25-30.
[12] LI B,TAN K,LUO L,et al.ClickNP:highly flexible and high performance network processing with reconfigurable hardware[A].Proceedings of ACM SIGCOMM[C].Florianopolis:ACM,2016.1-14.
[13] GIBB G,VARGHESE G,HOROWITZ M,et al.Design principles for packet parsers[A].Proceedings of the 9th ACM/IEEE Symposium on Architectures for Networking and Communications Systems[C].NJ:ACM,2013.13-24.
[14] 段通,兰巨龙,胡宇翔,等.一种支持网络功能演进的可重构数据平面[J].电子学报,2016,44(7):1721-1727. DUAN Tong,LAN Ju-long,HU Yu-xiang,et al.A reconfigurable dataplane enabling network function evolution[J].Acta Electronica Sinica,2016,44(7):1721-1727.(in Chinese)
[15] JOSE L,YAN L,VARGHESE G,et al.Compiling packet programs to reconfigurable switches[A].Proceedings ofUsenix Conference on Networked Systems Design and Implementation[C].Oakland:USENIX Association,2015.103-115.
[16] MONSANTO C,REICH J,FOSTER N,et al.Composing software-defined networks[A].Proceedings of Usenix Conference on Networked Systems Design and Implementation[C].LOMBARD:USENIX Association,2013.1-14.
[17] 段通,兰巨龙,胡宇翔,等.SDN中一种基于多级流表的功能组合方法[J].电子学报,2016,44(11):2682-2687. DUAN Tong,LAN Ju-long,HU Yu-xiang,et al.A function composition method of software-defined network based on multiple tables[J].Acta Electronica Sinica,2016,44(11):2682-2687.(in Chinese)
[18] Stanford University.NetFPGA-10G project[OL].https://github.com/NetFPGA/NetFPGA-public/wiki/Home_NetFPGA-10G,2014-11-09.
[19] YABE T.OpenFlow implementation on NetFPGA-10G Design Document[OL].https://docs.google.com/document/d/1ZwHXQZocKwQls6Ted8VZO8h9MjBtu9WxV2fAY44eOgE/edit,2014-12-09.