Towards cost-effective and low latency data center network architecture

Abstract This paper presents the design, analysis, and implementation of a novel data center network architecture, named NovaCube. Based on regular Torus topology, NovaCube is constructed by adding a number of most beneficial jump-over links, which offers many distinct advantages and practical benefits. Moreover, in order to enable NovaCube to achieve its maximum theoretical performance, a probabilistic oblivious routing algorithm PORA is carefully designed. PORA is a both deadlock and livelock free routing algorithm, which achieves near-optimal performance in terms of average routing path length with better load balancing thus leading to higher throughput. Theoretical derivation and mathematical analysis together with extensive simulations further prove the good performance of NovaCube and PORA.

[1]  H. Jonathan Chao,et al.  Cutting the Electricity Cost of Distributed Datacenters Through Smart Workload Dispatching , 2013, IEEE Communications Letters.

[2]  Mounir Hamdi,et al.  SprintNet: A high performance server-centric network architecture for data centers , 2014, 2014 IEEE International Conference on Communications (ICC).

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

[4]  Vijay Mann,et al.  VMFlow: Leveraging VM Mobility to Reduce Network Power Costs in Data Centers , 2011, Networking.

[5]  Sebti Foufou,et al.  A general framework for performance guaranteed green data center networking , 2014, 2014 IEEE Global Communications Conference.

[6]  Xue Liu,et al.  Minimizing Electricity Cost: Optimization of Distributed Internet Data Centers in a Multi-Electricity-Market Environment , 2010, 2010 Proceedings IEEE INFOCOM.

[7]  Amin Vahdat,et al.  Data Center Switch Architecture in the Age of Merchant Silicon , 2009, 2009 17th IEEE Symposium on High Performance Interconnects.

[8]  Yan Zhang,et al.  HERO: Hierarchical energy optimization for data center networks , 2012, 2012 IEEE International Conference on Communications (ICC).

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

[10]  Zhenhua Liu,et al.  Towards the design and operation of net-zero energy data centers , 2012, 13th InterSociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems.

[11]  Philip Heidelberger,et al.  Blue Gene/L torus interconnection network , 2005, IBM J. Res. Dev..

[12]  S. Lennart Johnsson,et al.  ROMM routing on mesh and torus networks , 1995, SPAA '95.

[13]  Mounir Hamdi,et al.  Fine-grained power control for combined input-crosspoint queued switches , 2014, 2014 IEEE Global Communications Conference.

[14]  H. T. Kung,et al.  Credit-Based Flow Control for ATM Networks , 1994, SIGCOMM 1994.

[15]  Albert G. Greenberg,et al.  VL2: a scalable and flexible data center network , 2009, SIGCOMM '09.

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

[17]  Emin Gün Sirer,et al.  Small-world datacenters , 2011, SoCC.

[18]  Hannes Hartenstein,et al.  Confidential database-as-a-service approaches: taxonomy and survey , 2014, Journal of Cloud Computing.

[19]  Burkhard D. Steinmacher-Burow,et al.  The IBM Blue Gene/Q Interconnection Fabric , 2012, IEEE Micro.

[20]  Bo Qin,et al.  NovaCube: A low latency Torus-based network architecture for data centers , 2014, 2014 IEEE Global Communications Conference.

[21]  William J. Dally,et al.  Deadlock-Free Adaptive Routing in Multicomputer Networks Using Virtual Channels , 1993, IEEE Trans. Parallel Distributed Syst..

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

[23]  Larry Kaplan,et al.  The Gemini System Interconnect , 2010, 2010 18th IEEE Symposium on High Performance Interconnects.

[24]  William J. Dally,et al.  Locality-preserving randomized oblivious routing on torus networks , 2002, SPAA '02.

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

[26]  Daniel C. Kilper,et al.  On the Energy Efficiency of Content Delivery Architectures , 2011, 2011 IEEE International Conference on Communications Workshops (ICC).

[27]  Thomas F. Wenisch,et al.  PowerNap: eliminating server idle power , 2009, ASPLOS.

[28]  Sebti Foufou,et al.  Towards bandwidth guaranteed energy efficient data center networking , 2015, Journal of Cloud Computing.

[29]  Vanish Talwar,et al.  Power Management of Datacenter Workloads Using Per-Core Power Gating , 2009, IEEE Computer Architecture Letters.

[30]  Antony I. T. Rowstron,et al.  Symbiotic routing in future data centers , 2010, SIGCOMM '10.

[31]  Mounir Hamdi,et al.  Designing efficient high performance server-centric data center network architecture , 2015, Comput. Networks.

[32]  Chris Fallin,et al.  Memory power management via dynamic voltage/frequency scaling , 2011, ICAC '11.

[33]  Konstantina Papagiannaki,et al.  c-Through: part-time optics in data centers , 2010, SIGCOMM '10.

[34]  Keith D. Underwood,et al.  Initial performance evaluation of the Cray SeaStar interconnect , 2005, 13th Symposium on High Performance Interconnects (HOTI'05).

[35]  Mounir Hamdi,et al.  CLOT: A cost-effective low-latency overlaid torus-based network architecture for data centers , 2015, 2015 IEEE International Conference on Communications (ICC).

[36]  H. Jonathan Chao,et al.  JET: Electricity cost-aware dynamic workload management in geographically distributed datacenters , 2014, Comput. Commun..

[37]  Zhiyang Su,et al.  Rethinking the Data Center Networking: Architecture, Network Protocols, and Resource Sharing , 2014, IEEE Access.

[38]  Uichin Lee,et al.  Greening the internet with content-centric networking , 2010, e-Energy.

[39]  Amin Vahdat,et al.  Helios: a hybrid electrical/optical switch architecture for modular data centers , 2010, SIGCOMM '10.

[40]  Luis Gravano,et al.  Adaptive Deadlock- and Livelock-Free Routing with All Minimal Paths in Torus Networks , 1994, IEEE Trans. Parallel Distributed Syst..

[41]  Jordi Torres,et al.  GreenHadoop: leveraging green energy in data-processing frameworks , 2012, EuroSys '12.

[42]  Albert G. Greenberg,et al.  The cost of a cloud: research problems in data center networks , 2008, CCRV.

[43]  Leslie G. Valiant,et al.  Universal schemes for parallel communication , 1981, STOC '81.

[44]  Yan Zhang,et al.  On Architecture Design, Congestion Notification, TCP Incast and Power Consumption in Data Centers , 2013, IEEE Communications Surveys & Tutorials.