BCDC: A High-Performance, Server-Centric Data Center Network
The capability of the data center network largely decides the performance of cloud computing. However, the number of servers in the data center network becomes increasingly huge, because of the continuous growth of the application requirements. The performance improvement of cloud computing faces great challenges of how to connect a large number of servers in building a data center network with promising performance. Traditional tree-based data center networks have issues of bandwidth bottleneck, failure of single switch, etc. Recently proposed data center networks such as DCell, FiConn, and BCube, have larger bandwidth and better fault-tolerance with respect to traditional tree-based data center networks. Nonetheless, for DCell and FiConn, the fault-tolerant length of path between servers increases in case of failure of switches; BCube requires higher performance in switches when its scale is enlarged. Based on the above considerations, we propose a new server-centric data center network, called BCDC, based on crossed cube with excellent performance. Then, we study the connectivity of BCDC networks. Furthermore, we propose communication algorithms and fault-tolerant routing algorithm of BCDC networks. Moreover, we analyze the performance and time complexities of the proposed algorithms in BCDC networks. Our research will provide the basis for design and implementation of a new family of data center networks.
Keywordsdata center network interconnection network crossed cube server-centric fault-tolerant
Unable to display preview. Download preview PDF.
We thank the anonymous reviewers and editors for their valuable suggestions that help to improve the presentation of the paper.
- 1.Harris D. Ballmer’s millionserver claim doesn’t seem so crazy. https://gigaom.com/2013/07/17/ballmers-million-server-claim-doesnt-seem-so-crazy/#comments, July 2013.
- 2.Dignan L. AWS financials on deck: The road to 3 million servers in operation. http://www.zdnet.com/article/aws-financials-on-deck-the-road-to-3-million-servers-in-operation/, April 2015.
- 3.Al-Fares M, Loukissas A, Vahdat A. A scalable, commodity data center network architecture. In Proc. the ACM SIGCOMM Conf. Data Communication, August 2008, pp.63-74.Google Scholar
- 4.Guo C X, Wu H T, Tan K, Shi L, Zhang Y G, Lu S W. DCell: A scalable and fault-tolerant network structure for data centers. In Proc. the ACM SIGCOMM Conf. Data Communication, August 2008, pp.75-86.Google Scholar
- 5.Li D, Guo C X, Wu H T, Tan K, Zhang Y G, Lu S W. Fi-Conn: Using backup port for server interconnection in data centers. In Proc. IEEE INFOCOM, April 2009, pp.2276-2285.Google Scholar
- 6.Guo C X, Lu G H, Li D, Wu H T, Zhang X, Shi Y F, Tian C, Zhang Y G, Lu S W. BCube: A high performance, server-centric network architecture for modular data centers. In Proc. the ACM SIGCOMM Conf. Data Communication, August 2009, pp.63-74.Google Scholar
- 7.Greenberg A, Hamilton J R, Jain N, Kandula S, Kim C, Lahiri P, Maltz D A, Patel P, Sengupta S. VL2: A scalable and flexible data center network. In Proc. the ACM SIGCOMM Conf. Data Communication, August 2009, pp.51-62.Google Scholar
- 8.Abu-Libdeh H, Costa P, Rowstron A, O’Shea G, Donnelly A. Symbiotic routing in future data centers. In Proc. ACM SIGCOMM, Aug.30-Sept.3, 2010, pp.51-62.Google Scholar
- 16.Lin D, Liu Y, Hamdi M, Muppala J. FlatNet: Towards a flatter data center network. In Proc. IEEE Global Communications Conf., December 2012, pp.2499-2504.Google Scholar
- 17.Wang T, Su Z Y, Xia Y, Qin B, Hamdi M. NovaCube: A low latency Torus-based network architecture for data centers. In Proc. IEEE Global Communications Conf., December 2014, pp.2252-2257.Google Scholar
- 18.Wang T, Su Z Y, Xia Y, Liu Y, Muppala J, Hamdi M. SprintNet: A high performance servercentric network architecture for data centers. In Proc. IEEE Int. Conf. Communications, June 2014, pp.4005-4010.Google Scholar
- 20.Wang T, Su Z Y, Xia Y, Hamdi M. CLOT: A cost-effective low-latency overlaid Torus-based network architecture for data centers. In Proc. IEEE Int. Conf. Communications, June 2015, pp.5479-5484.Google Scholar
- 21.Li D W, Wu J, Liu Z Y, Zhang F. Towards the tradeoffs in designing data center network architectures. IEEE Trans. Parallel and Distributed Systems, 2017, 28(1): 260-273.Google Scholar
- 23.Cull P, Larson S M. The Möbius cubes. IEEE Trans. Computers, 1995, 44(5): 647-659.Google Scholar
- 31.Efe K, Blackwell P K, Slough W, Shiau T. Topological properties of the crossed cube architecture. Parallel Computing, 1994, 20(12): 1763-1775.Google Scholar
- 42.Diestel R. Graph Theory (4th edition). Springer, 2010.Google Scholar
- 43.Ghemawat S, Gobioff H, Leung S T. The Google file system. In Proc. the 19th ACM Symp. Operating Systems Principles, October 2003, pp.29-43.Google Scholar