在軟體定義網路中三位元可定址內容記憶體(Ternary Content Access Memory, TCAM) 是一個重要的有限資源，現今的交換機安置的TCAM大小，大約只有幾千行規則位址，成了軟體定義網路(Software Define Network, SDN) 在提供多功能的網路應用和更多的網路需求時的主要阻礙。在這篇論文中我們提出一個在規則位址分配架構(Rule Distribution)下的演算法，使網路上的交換機TCAM資源更有效率的共享。規則位址分配架構將網路上所有的規則收集後、分割，然後分到網路上不同的交換機上。我們所提出的演算法探討如何平均分割規則位址同時達到最少量的額外規則位址產出。這樣的問題是一個NP-hard的問題，因此我們提出異質(heuristic)演算法，並且運用規則覆蓋方法和Fiduccia-Matheyses圖形分割演算法。然後使用Classbench 規則位址模擬器來模擬實際網路規則位址狀況。我們所提出的演算法能有效的減少額外規則位址，同時也使分割後的規則位址群更加平均。

In Software-Defined Networking (SDN), Ternary Content Access Memory (TCAM) is a scarce and expensive resource, providing only a few thousands of rule entries on a network switch. In this paper, we propose an algorithm under rule distribution scheme which allows switches in the network to share their TCAM resources in order to achieve better TCAM space utilization. Rule distribution scheme collects rules from network switches and redistributes the rule sets to network switches after partition the overall rules to rule sets. Our proposed algorithm mainly deals with the balanced rule partition problem, which is an NP-hard problem. We design a heuristic algorithm utilizing cover-set graph dependency and Fiduccia-Matheyses graph partition concept. We evaluate our algorithm by real world synthetic routing policy provided by ClassBench packet classification simulator. The result shows that our algorithm efficiently reduces the overall rule space overhead and balances the decomposed rule sets.

I. Introduction 1
II. Related Work 3
2.1. Packet Classifications Compression 3
2.2. Rules Caching 4
2.3. Rule Distribution 6
III. Algorithms 10
3.1. Dependency Tree Builds Up& Rule Sets Separation 10
3.2. Rule Partition 13
3.3. Assign Sub-sets to Switches 21
3.4. Rule Distribution Scheme & Update Mechanism 22
IV. Simulation 23
4.1. Simulation Environment 23
4.2. Simulation Results 24
V. Conclusion 30

References 31

[1] N. McKeown, T. Anderson, H. Balakrishan, G. Parulkar, L. Peterson, J. Rexford, S. Shenker, and J. Turner, “Openflow: Enabling Innovation in Campus Networks,” ACM SIGCOMM Computer Communication Review, Vol. 38 Issue 2, pp. 69-74, 2008.
[2] K. Nanxi, L. Zhenming, R. Jennifer, and D.Walker, “Optimizing the“ One Big Switch” Abstraction in Software Defined Networks,” Proceedings of the Ninth ACM Conference on
Emerging Networking Experiments and Technologies CoNEXT, pp 13-24, Santa Barbara, California, USA, December 2013.
[3] Z. Ying, N. Sriram, H. Xin, B. Neda, and M. Ravi, “A Compressive Method for Maintaining Forwarding States in SDN Controller,” HotSDN, pp. 139-144, Chicago, IL, USA, August 2014.
[4] K. Naga, A. Omid, R. Jennifer, and W. David, “Rule-Caching Algorithms for Software-Defined Networks,” HotSDN, pp. 175-180, Chicago, IL, USA, August 2014.
[5] C. Andrew R, M. Jeffrey C, T. Jean, Y. Praveen, S. Puneet, and B. Sujata, “DevoFlow: Scaling Flow Management for High-Performance Networks,” ACM SIGCOMM Computer Communication Review, Volume 41 Issue 4, pp254-265, Toronto, Ontario, Canada, August 2011.
[6] N. Yukihiro, H. Kazuki, L. Chunghan, K. Shinji, S. Osamu, and S. Takeshi, “DomainFlow: Practical Flow Management Method using Multiple Flow Tables in Commodity Switches,” Proceedings of the Ninth ACM Conference on Emerging Networking Experiments and Technologies CoNEXT, pp 399-404, Santa Barbara, California, USA, December 2013.
[7] Y. Minlan, R. Jennifer, F. Michael J, and W. Jia, “ Scalable Flow-Based Networking with DIFANE,” ACM SIGCOMM Computer Communication Review, Vol. 40 Issue 4, pp. 351-362, New Delhi, India, October 2010.
[8] K. Yossi, H. David, and K. Isaac, “Palette: Distributing Tables in Software-Defined Networks,” Proceedings of IEEE INFOCOM, pp 545-549, April 2013.
[9] C. M. Fiduccia and R. M. Matheyses, “A Linear-Time Heuristic for Improving Network Partitions,” Proceedings of the 19th IEEE Design Automation Conference, pp 175-181, 1982.
[10] A. X. Liu, C. R. Meiners, and E. Torng, “TCAM Razor: A Systematic Approach Towards Minimizing Packet Classifiers in TCAMs,” IEEE Transactions on Networking, vol. 18, no. 2, pp. 490-500, April 2010.
[11] C. H. Lin, and G. Y. Cheng, “Flow-table Distribution in Software-Defined Networks,” 2014.
[12] M. Moshref, M. Yu, A. Sharma, and R. Govindan, “VCRIB: Virtualized Rule Management in the Cloud,” Proceedings of the 4th USENIX Conference on Hot Topics in Cloud Computing HotCloud, pp 23, 2012.
[13] G. Karypis and V. Kumar, “A Fast and High Quality Multilevel Scheme for Partitioning Irregular Graphs,” SIAM Journal on Scientific Computing, vol. 20, no. 1, pp. 359–392, 1998.
[14] T. David E, and T. Jonathan S, “ClassBench: A Packet Classification Benchmark,” IEEE Transactions on Networking, Vol. 15, No. 3, June 2007
[15] C. R. Meiner, A.X. Liu, E. Torng, and J. Patel, “SPliT: Optimizing Space, Power, and Throughput for TCAM-Based Classification,” IEEE Symposium on Seventh Architectures for Networking and Communications Systems (ANCS), 2011.
[16] Y. Liu, S. O. Amin, and L. Wang, “Efficient FIB Caching using Minimal Non-overlapping Prefixes,” ACM SIGCOMM Computer Communication Review, Vol. 43 Issue 1, pp. 14-21, New York, USA, January 2013.
[17] N. Shelly, E. J. Jackson, T. Koponen, N. Mckeown, and J. Rajahalme, “Flow Caching for High Entropy Packet Fields,” HotSDN, pp. 151-156, Chicago, IL, USA, August 2014.