COUDER: Robust Topology Engineering for Optical Circuit Switched Data Center Networks

Many optical circuit switched data center networks (DCN) have been proposed in the past to attain higher capacity and topology reconfigurability, though commercial adoption of these architectures have been minimal. One major challenge these architectures face is the difficulty of handling uncertain traffic demands using commercial optical circuit switches (OCS) with high switching latency. Prior works have generally focused on developing fast-switching OCS prototypes to quickly react to traffic changes through frequent reconfigurations. This approach, however, adds tremendous complexity to the control plane, and raises the barrier for commercial adoption of optical circuit switched data center networks. We propose COUDER, a robust topology and routing optimization framework for reconfigurable optical circuit switched data centers. COUDER optimizes topology and routing based on a convex set of traffic matrices, and offers strict throughput guarantees for any future traffic matrices bounded by the convex set. For the bursty traffic demands that are unbounded by the convex set, we employ a desensitization technique to reduce performance hit. This enables COUDER to generate topology and routing solutions capable of handling unexpected traffic changes without relying on frequent topology reconfigurations. Our extensive evaluations based on Facebook's production DCN traces show that, even with daily reconfiguration, COUDER achieves about 20\% higher throughput, and about 32\% lower average hop count compared to cost-equivalent static topologies. Our work shows that adoption of reconfigurable topologies in commercial DCNs is feasible even without fast OCSs.

[1]  Ye Yu,et al.  N I ] 2 6 A ug 2 01 4 Space Shuffle : A Scalable , Flexible , and High-Bandwidth Data Center Network , 2014 .

[2]  Ramesh Govindan,et al.  Understanding Lifecycle Management Complexity of Datacenter Topologies , 2019, NSDI.

[3]  Thomas E. Anderson,et al.  F10: A Fault-Tolerant Engineered Network , 2013, NSDI.

[4]  Albert G. Greenberg,et al.  The nature of data center traffic: measurements & analysis , 2009, IMC '09.

[5]  Stephen P. Boyd,et al.  Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers , 2011, Found. Trends Mach. Learn..

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

[7]  Ryohei Urata,et al.  Datacenter optics: requirements, technologies, and trends (Invited Paper) , 2017 .

[8]  Atul Singh,et al.  Proteus: a topology malleable data center network , 2010, Hotnets-IX.

[9]  Mark Jerrum,et al.  Three-Dimensional Statistical Data Security Problems , 1994, SIAM J. Comput..

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

[11]  Paramvir Bahl,et al.  Flyways To De-Congest Data Center Networks , 2009, HotNets.

[12]  Albert G. Greenberg,et al.  COPE: traffic engineering in dynamic networks , 2006, SIGCOMM.

[13]  Hong Liu,et al.  The emerging optical data center , 2011, 2011 Optical Fiber Communication Conference and Exposition and the National Fiber Optic Engineers Conference.

[14]  J. Y. Yen,et al.  Finding the K Shortest Loopless Paths in a Network , 2007 .

[15]  He Liu,et al.  Circuit Switching Under the Radar with REACToR , 2014, NSDI.

[16]  Donald F. Towsley,et al.  Optimal routing with multiple traffic matrices tradeoff between average and worst case performance , 2005, 13TH IEEE International Conference on Network Protocols (ICNP'05).

[17]  Andrew V. Goldberg,et al.  A new approach to the maximum flow problem , 1986, STOC '86.

[18]  Hong Liu,et al.  Scaling Optical Interconnects in Datacenter Networks Opportunities and Challenges for WDM , 2010, 2010 18th IEEE Symposium on High Performance Interconnects.

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

[20]  Jeffrey C. Mogul,et al.  Thinking about Availability in Large Service Infrastructures , 2017, HotOS.

[21]  Nick McKeown,et al.  Why flow-completion time is the right metric for congestion control , 2006, CCRV.

[22]  Ben Y. Zhao,et al.  Mirror mirror on the ceiling: flexible wireless links for data centers , 2012, CCRV.

[23]  Albert G. Greenberg,et al.  Data center TCP (DCTCP) , 2010, SIGCOMM '10.

[24]  Nathan Farrington,et al.  Facebook's data center network architecture , 2013, 2013 Optical Interconnects Conference.

[25]  Rajdeep Das,et al.  Expanding across time to deliver bandwidth efficiency and low latency , 2019, NSDI.

[26]  Yin Zhang,et al.  Finding critical traffic matrices , 2005, 2005 International Conference on Dependable Systems and Networks (DSN'05).

[27]  Charles E. Leiserson,et al.  Fat-trees: Universal networks for hardware-efficient supercomputing , 1985, IEEE Transactions on Computers.

[28]  Ankit Singla,et al.  Jellyfish: Networking Data Centers Randomly , 2011, NSDI.

[29]  Alex C. Snoeren,et al.  RotorNet: A Scalable, Low-complexity, Optical Datacenter Network , 2017, SIGCOMM.

[30]  Stephen P. Boyd,et al.  Convex Optimization , 2004, Algorithms and Theory of Computation Handbook.

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

[32]  Nick McKeown,et al.  Designing a Fault-Tolerant Network Using Valiant Load-Balancing , 2008, IEEE INFOCOM 2008 - The 27th Conference on Computer Communications.

[33]  Himanshu Shah,et al.  FireFly , 2014, SIGCOMM.

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

[35]  Amin Vahdat,et al.  Hedera: Dynamic Flow Scheduling for Data Center Networks , 2010, NSDI.

[36]  Xin Wang,et al.  Neural Network Meets DCN: Traffic-driven Topology Adaptation with Deep Learning , 2018, SIGMETRICS.

[37]  Franziska Wulf,et al.  Minimization Methods For Non Differentiable Functions , 2016 .

[38]  Gal Shahaf,et al.  Beyond fat-trees without antennae, mirrors, and disco-balls , 2017, SIGCOMM.

[39]  Richard M. Karp,et al.  Theoretical Improvements in Algorithmic Efficiency for Network Flow Problems , 1972, Combinatorial Optimization.

[40]  Michael Dinitz,et al.  Xpander: Unveiling the Secrets of High-Performance Datacenters , 2015, HotNets.

[41]  Christina Delimitrou,et al.  ECHO: Recreating network traffic maps for datacenters with tens of thousands of servers , 2012, 2012 IEEE International Symposium on Workload Characterization (IISWC).

[42]  Jens Vygen,et al.  Efficient implementation of the Goldberg–Tarjan minimum-cost flow algorithm , 1998 .

[43]  Nikhil R. Devanur,et al.  ProjecToR: Agile Reconfigurable Data Center Interconnect , 2016, SIGCOMM.

[44]  Paramvir Bahl,et al.  Augmenting data center networks with multi-gigabit wireless links , 2011, SIGCOMM.

[45]  Hong Liu,et al.  Jupiter Rising: A Decade of Clos Topologies and Centralized Control in Google's Datacenter Network , 2015, Comput. Commun. Rev..

[46]  Pramod Viswanath,et al.  Costly circuits, submodular schedules and approximate Carathéodory Theorems , 2016, Queueing Syst. Theory Appl..

[47]  Mohit Tawarmalani,et al.  Robust Validation of Network Designs under Uncertain Demands and Failures , 2017, NSDI.

[48]  Rui Wang,et al.  Minimal Rewiring: Efficient Live Expansion for Clos Data Center Networks , 2019, NSDI.

[49]  Hui Xu,et al.  Transceivers and optical engines for computer and datacenter interconnects , 2010, 2010 Conference on Optical Fiber Communication (OFC/NFOEC), collocated National Fiber Optic Engineers Conference.

[50]  Ramesh Govindan,et al.  Evolve or Die: High-Availability Design Principles Drawn from Googles Network Infrastructure , 2016, SIGCOMM.

[51]  Alex C. Snoeren,et al.  Inside the Social Network's (Datacenter) Network , 2015, Comput. Commun. Rev..

[52]  Srinivasan Seshan,et al.  Scheduling techniques for hybrid circuit/packet networks , 2015, CoNEXT.

[53]  Amin Vahdat,et al.  Integrating microsecond circuit switching into the data center , 2013, SIGCOMM.

[54]  Yin Zhang,et al.  COPE: traffic engineering in dynamic networks , 2006, SIGCOMM 2006.