Abstract
With the growing of cloud computing, the need of computing power no longer can be satisfied with a few powerful servers or small scale parallel computer systems. More and more servers are connected together as a data center network. Then, fault tolerance becomes an import issue when building a massive data center network. Currently, many researches focus on building fat-tree data center networks. In this paper, we propose a load balanced fat-tree architecture with uniform mapping connection patterns to provide higher fault tolerance capability for heavy traffic load networks. Two fault tolerated 4 × 4 banyan type switch designs are introduced to improve the fault tolerance capability of fat-tree networks. Finally, fault tolerance capability evaluations of link or switch faults in fat-tree network are given to support our idea, and a 4 × 4 banyan type switch IC is demonstrated as the commodity switch for building the fault tolerant fat-tree data center networks. The 4 × 4 banyan type switch IC is fabricated in 90 nm CMOS technology, and the maximum operation rate of the IC is 5.8 Gbps per channel or 23.2 Gbps total data rate with only 23 ps peak-to-peak jitter.
















Similar content being viewed by others
References
Cisco Data Center Infrastructure 2.5 Design Guide. Available online: http://www.cisco.com/application/pdf/en/us/guest/netsol/ns107/c649/ccmigratio_09186a008073377d.pdf. Accessed Dec 2007.
Al-Fares, M., Loukissas, A., Vahdat, A. (2008). A scalable, commodity, data center network architecture. In Proceedings of ACM SIGCOMM (pp. 63–74).
Guo, C., Wu, H., Tan, K., Shi, L., Zhang, Y., Lu, S. (2008). DCell a scalable and fault-tolerant network structure for data centers. In Proceedings of ACM SIGCOMM (pp. 75–86).
Kliegl, M., Lee, J., Li, J., Zhang, X., Guo, C., Rincon, D. (2010). Generalized DCell structure for load-balanced data center networks. In Proceedings of IEEE INFOCOM (pp. 1–5).
Li, D., Guo, C., Wu, H., Tan, K., Zhang, Y., Lu, S. (2009). FiConn: Using backup port for server interconnection in data centers. In Proceedings of IEEE INFOCOM (pp. 2276–2285).
Guo, C., Lu, G., Li, D., Wu, H., Zhang, X., Shi, Y., Tian, C., Zhang, Y., Lu, S. (2009). BCube: a high performance, server-centric network architecture for modular data centers. In Proceedings of ACM SIGCOMM (pp. 63–74).
Farrington, N., Rubow, E., Vahdat, A. (2009). Data center switch architecture in the age of merchant silicon. In Proceedings of 17th IEEE symposium on high performance interconnects (pp. 93–102).
Chueh, H.S., Lien, C.M., Chang, C.S., Cheng, J., Lee, D.S. (2011). Implementing load-balanced switches with fat-tree networks (pp. 1–9). Available online: http://www.ee.nthu.edu.tw/cschang/LB-fat-tree-networks-TR.pdf. Accessed June 2011.
Requena, C.G., Requena, M.E.G., Rodriguez, P.J.L., Marin, J.F.D. (2009). FT2EI: a dynamic fault-tolerant routing methodology for fat trees with exclusion intervals. IEEE Transactions on Parallel and Distributed Systems, 20(6), 802–817.
Sem-Jacobsen, F.O., Skeie, T., Lysne, O., Duato, J. (2011). Dynamic fault tolerance in fat trees. IEEE Transactions on Computers, 60(4), 508–525.
Chang, C.S., Lee, D.S., Jou, Y.S. (2002). Load balanced Birkhoff–von Neumann switches, part I: one-stage buffering. Computer Communications, 25, 611–622.
Chang, C.S., Lee, D.S., Shih, Y.J., Yu, C.L. (2008). Mailbox switch: a scalable two-stage switch architecture for conflict resolution of ordered packets. IEEE Transactions on Communications, 56(1), 136–149.
Yu, C.L., Chang, C.S., Lee, D.S. (2009). CR switch: a load-balanced switch with contention and reservation. IEEE Transactions on Networking, 17(5), 1659–1671.
Hu, B., & Yeung, K.L. (2010). Feedback-based scheduling for load-balanced two-stage switches. IEEE Transactions on Networking, 18(4), 1077–1090.
Clos, C. (1953). A study of non-blocking switching networks. Bell System Technical Journal, 32, 406–424.
Leiserson, C.E. (1985). Fat-Trees: universal network for hardware-efficient supercomputing. IEEE Transactions on Computers, 34(10), 892–901.
Wu, C.L., & Feng, S.Y. (1980). The reverse-exchange interconnection network. IEEE Transaction on Computers, c-29(9), 801–811.
Data Center CEE/DCB Switch Chip Family, FM 6000 (2010). IEEE Transactions on Communications (pp. 136–149). Available online: http://www.fulcrummicro.com/product/FM6000_Product_Brief.pdf. Accessed Feb 2011.
Chrysos, N., & Dimitrakopoulos, G. (2009). Practical high-throughput crossbar scheduling. In IEEE Micro (pp. 23–35).
Chang, C.S., Lee, D.S., Shih, Y.J. (2008). Mailbox switch: a scalable two-stage switch architecture for conflict resolution of ordered packets. IEEE Transactions on Communications, 56(1), 136–149.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Lai, WC., Chiu, CT. Data Center Switch for Load Balanced Fat-Trees. J Sign Process Syst 71, 173–187 (2013). https://doi.org/10.1007/s11265-012-0710-6
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11265-012-0710-6