Usage based topology for DCNs

Many data center network topologies are designed to provide full bisection bandwidth for tens of thousands of servers in order to achieve high network throughput and server agility. However, the utilization rate of DCNs on average is below 10%, which results in a significant waste of network resources and energy. Many researchers propose consolidating network traffic flows to maximize the set of idle network equipment and switching them to low power mode to save energy. In this paper, we propose using skinnier network topologies to meet performance requirements of realistic loads thus saving not only energy but capital cost as well. We undertake a comprehensive study of the sub-graphs of fat-trees for different traffic characteristics and present an analytical model for the number of switches required in each layer of the topology. Furthermore, we examine the potential energy savings of utilizing higher-port-count switches at the edge layer and evaluate the reduced energy consumption using the power data of Cisco modular switches.

[1]  Sujata Banerjee,et al.  ElasticTree: Saving Energy in Data Center Networks , 2010, NSDI.

[2]  Hong Liu,et al.  Energy proportional datacenter networks , 2010, ISCA.

[3]  Randy H. Katz,et al.  Greening the Switch , 2008, HotPower.

[4]  Rajesh Gupta,et al.  Path Consolidation for Dynamic Right-Sizing of Data Center Networks , 2013, 2013 IEEE Sixth International Conference on Cloud Computing.

[5]  Charles Clos,et al.  A study of non-blocking switching networks , 1953 .

[6]  Amin Vahdat,et al.  A scalable, commodity data center network architecture , 2008, SIGCOMM '08.

[7]  Sujata Banerjee,et al.  A Power Benchmarking Framework for Network Devices , 2009, Networking.

[8]  William J. Dally,et al.  Flattened butterfly: a cost-efficient topology for high-radix networks , 2007, ISCA '07.

[9]  H. Jonathan Chao,et al.  Switch sizing for energy-efficient datacenter networks , 2014, PERV.

[10]  Sujata Banerjee,et al.  Networks of Tiny Switches ( NoTS ) : In search of network power efficiency and proportionality , 2013 .

[11]  Xiaodong Wang,et al.  CARPO: Correlation-aware power optimization in data center networks , 2012, 2012 Proceedings IEEE INFOCOM.

[12]  Haitao Wu,et al.  BCube: a high performance, server-centric network architecture for modular data centers , 2009, SIGCOMM '09.

[13]  Suresh Singh,et al.  Greening of the internet , 2003, SIGCOMM '03.

[14]  Lei Shi,et al.  Dcell: a scalable and fault-tolerant network structure for data centers , 2008, SIGCOMM '08.

[15]  David A. Maltz,et al.  Network traffic characteristics of data centers in the wild , 2010, IMC '10.