روش مدیریت توزیع جریان‌ها در سیستم‌های مبتنی بر OpenFlow
الموضوعات :مهشید صالحی 1 , مسعودرضا هاشمی 2
1 - دانشگاه صنعتی اصفهان
2 - دانشکده مهندسی برق و کامپیوتر
الکلمات المفتاحية: سوئیچ شبکه مرکز داده OpenFlow ECMP,
ملخص المقالة :
معماری فعلی شبکه‌های مرکز داده ترکیبی از سوئیچ‌های اترنت و روترها است اما این معماری نمی‌تواند نیازهای این شبکه‌ها را برآورده کند. سوئیچ‌های اترنت انعطاف‌پذیر و تنظیماتشان ساده است اما گسترش‌پذیر نیستند. روترها گسترش‌پذیری بهتر و استفاده کارامد از پهنای باند را فراهم می‌کنند اما هزینه آنها زیاد است. این معماری ترکیبی سربارهای تنظیمات و نگهداری قابل توجهی را به وجود می‌آورد و بنابراین اگر بتوان شبکه‌های لایه دو را بزرگ‌تر کرد تعداد روترها و در نتیجه هزینه‌ها کمتر می‌شود. برای این منظور روش‌های زیادی ارائه شده است. در این مقاله برخی از نیازهای اصلی شبکه‌های مرکز داده و ویژگی‌های تعدادی از روش‌های پیشنهادی بیان شده و از بین روش‌ها، OpenFlow ترجیح داده می‌شود اما سربار کنترلی OpenFlow زیاد است. یک روش برای کم‌کردن سربار کنترلی جداکردن جریان‌های بزرگ و کوچک است که مدیریت جریان‌های بزرگ به کنترل‌کننده داده می‌شود و برای مسیریابی جریان‌های کوچک از مسیریابی ECMP استفاده می‌شود. OpenFlow از ECMP پشتیبانی نمی‌کند. در این مقاله روشی مبتنی بر OpenFlow برای جایگزینی ECMP ارائه شده که کارایی آن معادل ECMP است و در مقابل خطا تحمل‌پذیر است.
[1] N. McKeown, et al., "OpenFlow: enabling innovation in campus networks," ACM SIGCOMM Computer Communication Review, vol. 38, no. 2, pp. 69-74, Apr. 2008.
[2] M. Casado, T. Koponen, D. Moon, and S. Shenker, "Rethinking packet forwarding hardware," in Proc. 7th ACM SIGCOMM HotNets Workshop, 6 pp., 6-7 Oct. 2008.
[3] A. R. Curtis, et al., "DevoFlow: scaling flow management for high-performance networks," SIGCOMM Computer Communication Review, vol. 41, no. 4, pp. 254-265, Aug. 2011.
[4] A. Greenberg, et al., "VL2: a scalable and flexible data center network," SIGCOMM Computer Communication Review, vol. 39, no. 4, pp. 51-62, Oct. 2009.
[5] S. Kandula, S. Sengupta, A. Greenberg, P. Patel, and R. Chaiken, "The nature of data center traffic: measurements & analysis," in Proc. of the 9th ACM SIGCOMM Conf. on Internet Measurement Conf., pp. 202-208, Chicago, 4-6 Nov. 2009.
[6] M. Al-Fares, S. Radhakrishnan, B. Raghavan, N. Huang, and A. Vahdat, "Hedera: dynamic flow scheduling for data center networks," in Proc. of the 7th USENIX Conf. on Networked Systems Design and Implementation, NSDI'10, p. 19, 2010.
[7] A. R. Curtis, K. Wonho, and P. Yalagandula, "Mahout: low-overhead datacenter traffic management using end-host-based elephant detection," in Proc IEEE INFOCOM, pp. 1629-1637, 10-15 Apr. 2011.
[8] C. E. Hopps, Analysis of an Equal-Cost Multi-Path Algorithm, RFC 2992, 2000.
[9] Cisco Data Center Infrastructure 2.5 Design Guide, 2007, Available from: www.cisco.com/application/pdf/en/us/guest/netsol/ ns107/c649/ccmigration_09186a008073377d.pdf.
[10] R. Perlman, "Rbridges: transparent routing," in Proc IEEE INFOCOM, vol. 2, pp. 1211-1218, 2004.
[11] J. Touch and R. Perlman, Transparent Interconnection of Lots of Links (TRILL): Problem and Applicability Statement, RFC 5556, 2009.
[12] Cisco, Scaling Data Centers with FabricPath and the Cisco FabricPath Switching System, 2010.
[13] C. Kim, M. Caesar, and J. Rexford, "Floodless in seattle: a scalable ethernet architecture for large enterprises," SIGCOMM Computer Communication Review, vol. 38, no. 4, pp. 3-14, Feb. 2008.
[14] M. Scott, A. Moore, and J. Crowcroft, "Addressing the scalability of ethernet with MOOSE," in Proc. of DC CAVES Workshop, 8 pp., 17-18 Mar. 2009.
[15] C. Clos, "A study of non-blocking switching networks," Bell System Technical J., vol. 32, no. 2, pp. 406-424, Mar. 1953.
[16] R. Zhang-Shen and N. McKeown, "Designing a predictable Internet backbone network," in Proc. of 3rd Workshop on Hot Topics in Networks, HotNets-III, pp. 58-64, Nov. 2004.
[17] M. Kodialam, T. Lakshman, and S. Sengupta, "Efficient and robust routing of highly variable traffic," in Proc. of 3rd Workshop on Hot Topics in Networks, HotNets-III, 15-16 Nov. 2004.
[18] B. Stephens, A. L. Cox, S. Rixner, and T. S. E. Ng, "A scalability study of enterprise network architectures," in Proc. of the 2011 ACM/IEEE 7th Symp. on Architectures for Networking and Communications Systems, pp. 111-121, Oct. 2011.
[19] B. Stephens, et al., "PAST: scalable ethernet for data centers," in Proc. of the 8th Int. Conf. on Emerging Networking Experiments and Technologies, pp. 49-60, Nice, Dec. 2012.
[20] R. N. Mysore, et al., "PortLand: a scalable fault-tolerant layer 2 data center network fabric," SIGCOMM Computer Communication Review, vol. 39, no. 4, pp. 39-50, Aug. 2009.
[21] J. Mudigonda, P. Yalagandula, M. Al-Fares, and J. C. Mogul, "SPAIN: COTS data-center ethernet for multipathing over arbitrary topologies," in Proc. of the 7th USENIX Conf. on Networked Systems Design and Implementation, NSDI'10, pp. 265-280, Apr. 2010.
[22] J. Mudigonda, P. Yalagandula, J. Mogul, B. Stiekes, and Y. Pouffary, "NetLord: a scalable multi-tenant network architecture for virtualized datacenters," SIGCOMM Computer Communication Review, vol. 41, no. 4, pp. 62-73, Aug. 2011.
[23] J. Shafer, B. Stephens, M. Foss, S. Rixner, and A. L. Cox, "Axon: a flexible substrate for source-routed ethernet," in Proc. of the 6th ACM/IEEE Symp. on Architectures for Networking and Communications Systems, 11 pp., California, Oct. 2010.
[24] C. Guo, et al., "SecondNet: a data center network virtualization architecture with bandwidth guarantees," in Proc. of the 6th Int. Conf., ACM, 12 pp., Philadelphia, Nov. 2010.
[25] C. Guo, H. Wu, K. Tan, L. Shi, Y. Zhang, and S. Lu, "Dcell: a scalable and fault-tolerant network structure for data centers," SIGCOMM Computer Communication Review, vol. 38, no. 4, pp. 75-86, Oct. 2008.
[26] C. Guo, et al., "BCube: a high performance, server-centric network architecture for modular data centers," SIGCOMM Computer Communication Review, vol. 39, no. 4, pp. 63-74, Oct. 2009.
[27] A. Jung Ho, et al., "HyperX: topology, routing, and packaging of efficient large-scale networks," in Proc. of the Conf. on High Performance Computing Networking, Storage, and Analysis, 11 pp., 14-20 Nov. 2009. 2009.
[28] A. Singla, C. Y. Hong, L. Popa, and P. B. Godfrey, "Jellyfish: networking data centers randomly," in Proc. of the 9th USENIX Conf. on Networked Systems Design and Implementation, pp. 17-17, 25-27 Apr. 2012.
[29] M. Al-Fares, A. Loukissas, and A. Vahdat, "A scalable, commodity data center network architecture," SIGCOMM Computer Communication Review, vol. 38, no. 4, pp. 63-74, Oct. 2008.
[30] J. Dean and S. Ghemawat, "MapReduce: simplified data processing on large clusters," Commun. ACM, vol. 51, no. 1, pp. 107-113, Jan. 2008.
[31] S. R. Ohring, M. Ibel, S. K. Das, and M. J. Kumar, "On generalized fat trees," in Proc. IEEE 9th Int. Parallel Processing Symp., pp. 37-44, Apr. 1995.
[32] N. Farrington, E. Rubow, and A. Vahdat, "Data center switch architecture in the age of merchant silicon," in Proc. IEEE 17th Symp. on High Performance Interconnects, pp. 93-102, Aug. 2009.
[33] D. Abts and J. Kim, High Performance Datacenter Networks: Architectures, Algorithms, and Opportunities, Morgan & Claypool Publishers, 2011.
