Abstract
A fundamental goal of data-center networking is to efficiently interconnect a large number of servers with the low equipment cost. Several server-centric network topologies for data centers have been proposed. They, however, are not truly expandable and suffer a low degree of regularity and symmetry. Inspired by the commodity servers in today’s data centers that come with dual-port, we consider how to build expandable and cost-effective topologies without expensive high-end switches and additional hardware on servers except the two NIC ports. In this chapter, two such network topologies, called HCN and BCN, are designed based on the compound graph theory. The two topologies can achieve hierarchical expansion by only adding a small number of links among servers. Although the server degree is only 2, HCN can be expanded very easily to encompass hundreds of thousands servers with the low diameter and high bisection width. HCN also offers high degree of regularity, scalability and symmetry, which conform to the modular design of data centers. BCN is the largest known network topology for data centers with the server degree 2 and network diameter 7. BCN has many attractive features, including the low diameter, high bisection width, large number of node-disjoint paths for the one- to-one traffic, and good fault-tolerant ability. Mathematical analysis and comprehensive simulations show that HCN and BCN possess excellent topological properties.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Al-Fares M, Loukissas A, Vahdat A. A scalable, commodity data center network architecture [J]. ACM SIGCOMM Computer Communication Review, 2008, 38(4): 63–74.
Greenberg A, Hamilton J R, Jain N, et al. VL2: a scalable and flexible data center network [J]. ACM SIGCOMM Computer Communication Review, 2009, 39(4): 51–62.
Guo C, Wu H, Tan K, et al. Dcell: a scalable and fault-tolerant network structure for data centers [J]. ACM SIGCOMM Computer Communication Review, 2008, 38(4): 75–86.
Li D, Guo C, Wu H, et al. FiConn: Using backup port for server interconnection in data centers [C]. In Proc. of 28th IEEE INFOCOM, Rio de Janeiro, Brazil, 2009: 2276–2285.
Li D, Guo C, Wu H, et al. Scalable and cost-effective interconnection of data-center servers using dual server ports [J]. IEEE/ACM Transactions on Networking, 2011, 19(1): 102–114.
Guo C, Lu G, Li D, et al. BCube: a high performance, server-centric network architecture for modular data centers [J]. ACM SIGCOMM Computer Communication Review, 2009, 39(4): 63–74.
Wu H, Lu G, Li D, et al. MDCube: a high performance network structure for modular data center interconnection [C]. In Proc. of 5th ACM CoNEXT, Rome, Italy, 2009: 25–36.
Alon N, Hoory S, Linial N. The Moore bound for irregular graphs [J]. Graphs and Combinatorics, 2002, 18(1): 53–57.
Damerell R M. On Moore graphs [C]. In Proc. of Cambridge Philosophical Society, Cambridge, UK, 1973:227–236.
Imase M and Itoh M. A design for directed graphs with minimum diameter [J]. IEEE Transactions on Computers, 1983, 32(8): 782–784.
Agrawal D P, Chen C, Burke J R. Hybrid graph-based networks for multiprocessing [J]. Telecommunication system, 1998, 10:107–134.
Breznay P T, Lopez M A. Tightly connected hierarchical interconnection networks for parallel processors [C]. In Proc. of 22th IEEE ICPP, NY, USA, 1993, 1: 307–310.
Breznay P T, Lopez M A. A class of static and dynamic hierarchical interconnection networks [C]. In Proc. of 23th IEEE ICCP, Raleigh, USA, 1994, 1:59–62.
Agrawal D P, Chen C, Burke J R. Hybrid graph-based networks for multiprocessing [J]. Telecommunication Systems, 1998, 10(1-2): 107–134.
Lu G, Shi Y, Guo C, et al. CAFE: a configurable packet forwarding engine for data center networks [C]. In Proc. of 2nd ACM SIGCOMM workshop on Programmable routers for extensible services of tomorrow, 2009: 25–30.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2022 Springer Nature Singapore Pte Ltd.
About this chapter
Cite this chapter
Guo, D. (2022). HCN: A Server-Centric Network Topology for Data Centers. In: Data Center Networking. Springer, Singapore. https://doi.org/10.1007/978-981-16-9368-7_3
Download citation
DOI: https://doi.org/10.1007/978-981-16-9368-7_3
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-9367-0
Online ISBN: 978-981-16-9368-7
eBook Packages: Computer ScienceComputer Science (R0)