軟件定義網絡（SDN）將傳統網路的控制區塊從分散式網絡設備中抽離。在本篇論文中，我們基於目前SDN中的白牌交換機，利用佇列搭配非阻塞式的快取，加快交換機的速度。我們使用NetFPGA網路卡和Open vSwitch軟件來實作白牌交換機。我們將我們的原型與阻塞式設計的快取進行比較。最後實驗結果表明，我們所提出的設計實現了較好的封包處理能力。

Software-Defined Networking (SDN) separates control planes from distributed network devices. For the popular white box SDN platforms, we propose a Queue-based Non- blocking Per-Port Cache design to increase switch throughput. We implement it with the NetFPGA Network Interface Card and the Open vSwitch software search engine. We compare our prototype with a blocking cache design. Experiment results show that the proposed design achieves high throughput.

Abstract i
Contents ii
List of Figures iii
List of Tables iv
1 Introduction 1
2 Related Work 4
2.1 OpenvSwitch.................................. 4
2.2 NetworkTrafficLocality............................ 5
2.3 WhiteBoxSwitch ............................... 6
2.4 Control-MessageQuenching.......................... 8
2.5 Accelerating OpenFlow Switches with Per-port Blocking Cache . . . . . . 9
3 Proposed Methodology 10
3.1 NonblockingCacheProblems ......................... 10
3.2 SwitchDesignFramework ........................... 11
3.3 Q-NPPC Implementation ........................... 13
4 Evaluation 19
4.1 Experiment Considerations .......................... 19
4.2 Experiment Environment ............................ 20
4.3 Results and Analysis................................. 21
4.3.1 Cache hit rate ........................................ 22
4.3.2 Switch throughput ................................. 27
5 Conclusion And Future Work ....................... 36
References ...................................................... 37

[1] N. McKeown, “Software-defined networking,” INFOCOM keynote talk, vol. 17, no. 2, pp. 30–32, 2009.
[2] “L. foundation, opendaylight: an open source community and meritocracy for software-defined networking, a linux foundation collaborative project,” 2016, avail- able at https://www.opendaylight.org,.
[3] “Floodlight.” [Online]. Available: http://www.projectfloodlight.org/
[4] “Pox.” [Online]. Available: http://www.noxrepo.org/pox/about-pox/
[5] N. McKeown, T. Anderson, H. Balakrishnan, G. Parulkar, L. Peterson, J. Rexford, S. Shenker, and J. Turner, “Openflow: enabling innovation in campus networks,” ACM SIGCOMM Computer Communication Review, vol. 38, no. 2, pp. 69–74, 2008.
[6] J. H. Han, P. Mundkur, C. Rotsos, G. Antichi, N. H. Dave, A. W. Moore, and P. G. Neumann, “Blueswitch: Enabling provably consistent configuration of net- work switches,” in Proceedings of the Eleventh ACM/IEEE Symposium on Archi- tectures for networking and communications systems, ser. SIGCOMM ’15. ACM, 2015, pp. 363–364.
[7] P. Bosshart, G. Gibb, K. Hun-Seok, G. Varghese, N. McKeown, M. Izzard, F. Mu- jica, and M. Horowitz, “Forwarding metamorphosis: Fast programmable match- action processing in hardware for sdn,” in Proceedings of the ACM SIGCOMM 2013 conference on SIGCOMM, ser. SIGCOMM’13. ACM, 2013, pp. 99–110.
[8] “Tcam.” [Online]. Available: https://en.wikipedia.org/wiki/Content-addressable memory#Ternary CAMs
[9] “Ram.” [Online]. Available: https://en.wikipedia.org/wiki/Random-access memory
[10] “L. foundation, openswitch, community-based, open source, full-featured network operating system,” 2016. [Online]. Available: http://www.openswitch.net/
[11] “O. community. source code of open vswitch. open virtual switch.” 2014, available at
https://www.openvswitch.org.
[12] “What is white box switching and white box switches?” 2016, available at
https://www.sdxcentral.com/cloud/converged-datacenter/whitebox/definitions/ what-is-white-box-networking/.
[13] “Netfpga 1g cml reference nic projects,” 2015. [Online]. Available: https: //github.com/NetFPGA/NetFPGA-public/wiki/NetFPGA-1G-CML-Projects
[14] C. Y. Lin, “Accelerating OpenFlow switches with per-port cache,” 2015. [On- line]. Available: http://140.113.39.130/cgi-bin/gs32/hugsweb.cgi?o=dnthucdr&s= %22GH02102062501%22.id.&
[15] “The apache license.” [Online]. Available: http://www.apache.org/licenses/ LICENSE-2.0
[16] T. Chiueh and P. Pradhan, “Cache memory design for network processors,” in
Proceedings of the 6th International Symposium on High-Performance Computer Architecture, ser. HPCA-6, 2000, pp. 409–418.
[17] A. Siddiqui, “Whitebox switches deployment experien,” 2016, available at https: //conference.apnic.net/data/41/white-box-switching 1456262714.pdf.
[18] “Introduction to pci protocol,” available at http://electrofriends.com/articles/ computer-science/protocol/introduction-to-pci-protocol/.
[19] T. Luo, H.-P. Tan, P. C. Quan, Y. W. Law, and J. Jin, “Enhancing responsiveness and scalability for openflow networks via control-message quenching,” in Proceedings of Int. Conf. CT Convergence (ICTC). IEEE, 2012, pp. 348–353.
[20] D. Kroft, “Lockup-free instruction fetch/prefetch cache organization,” in Proceed- ings of the 8th annual symposium on Computer Architecture. ACM, May 12-14, 1981, pp. p.81–87.
[21] T. Benson, A. Anand, A. Akell, and M. Zhang, “Understanding data center tra c characteristics,” in ACM SIGCOMM Computer Communication, 2010.
[22] S. Kandula, S. Sengupta, A. Greenberg, P. Patel, and R. Chaiken, “The nature of data center tra c: measurements and analysis,” in Proceedings of the 9th ACM SIGCOMM conference on Internet measurement conference, ser. ANCS ’09. ACM, 2009.
[23] “Erfc,” available at http://mathworld.wolfram.com/Erfc.html.
[24] “Cumulative distribution function,” available at https://en.wikipedia.org/wiki/
Cumulative distribution function.
[25] “Modelsim,” available at http://www.mentor.com/products/fv/modelsim/.
[26] B. Lantz, B. Heller, and N. McKeown, “A network in a laptop: Rapid prototyping for software-defined networks,” in Proceedings of the 9th ACM SIGCOMM Workshop on Hot Topics in Networks, ser. Hotnets-IX. New York, NY, USA: ACM, 2010, pp. 19:1–19:6. [Online]. Available: http: //doi.acm.org/10.1145/1868447.1868466
[27] “Ubuntu,” available at http://www.ubuntu.com/download/desktop.
[28] “Ripcord-lite for pox: A simple network controller for openflow-based data centers.”
available at https://github.com/brandonheller/riplpox.
[29] M. Al-Fares, S. Radhakrishnan, B. Raghavan, N. Huang, and A. Vahdat, “Hedera: Dynamic flow scheduling for data center networks,” in Proceedings of the 7th USENIX Conference on Networked Systems Design and Implementation, ser. NSDI’10. Berkeley, CA, USA: USENIX Association, 2010, pp. 19–19. [Online]. Available: http://dl.acm.org/citation.cfm?id=1855711.1855730
[30] “Iperf,” available at https://iperf.fr/.
[31] “Numpy v1.11,” available at http://docs.scipy.org/doc/numpy/index.html.
[32] Broadcom, “Engineered elephant ows for boosting application performance in large-scale clos networks,” 2014. [Online]. Available: https://www.broadcom.com/ collateral/wp/OF-DPA-WP102-R.pdf
[33] “Design compiler,” available at http://www.synopsys.com/Tools/Implementation/ RTLSynthesis/DesignCompiler/Pages/default.aspx.