IBCube: An Economical and Incremental Datacenter Network

Datacenternetworkshaveattractedalotofresearchinterestinthepastfewyears.BCubeisproved tobeapromisingschemedue to its lowcost.Byusingarecursiveconstructionscheme,BCube can exponentially scale a datacenter. Industry experiences, however, articulate the importance of incrementalexpansionofdatacenter.In thisarticle, theauthorsshowthatBCube’sexpanding schemesufferslowutilizationofswitchports.TheyproposeIBCube,anoveleconomicaldesignfor incrementallybuildingdatacenternetworks.Theinsightisthat:bylettingthenumberofswitchesin eachBCubelayerequalthenumberofthebuildingblocks,theauthorscanenabletheswitchportsto befullyutilizedtosupportthetotalnumberofnetworkinterfacecardsofthedeployedserversinthe datacenters.Accordingly,theirIBCubedesignsanovelautomaticportallocationscheme.Simulation resultsshowthattheIBCubedesignreducesthebudgetforthedatacenternetworksby94%aswell asimprovesthepacketdelayandthroughputby10.3%and11.5%,respectively,comparedtothe previouspartialBCubedesign. KEyWoRDS Data Center, Data Center Networks, Incremental Data Center Networks, Routing, Topology

[1]  Ben Y. Zhao,et al.  Packet-Level Telemetry in Large Datacenter Networks , 2015, SIGCOMM.

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

[3]  Hakim Weatherspoon,et al.  Globally Synchronized Time via Datacenter Networks , 2016, SIGCOMM.

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

[5]  Kaishun Wu,et al.  TiM: Fine-Grained Rate Adaptation in WLANs , 2016, IEEE Trans. Mob. Comput..

[6]  Xingming Sun,et al.  Achieving Efficient Cloud Search Services: Multi-Keyword Ranked Search over Encrypted Cloud Data Supporting Parallel Computing , 2015, IEICE Trans. Commun..

[7]  Richard W. Hamming,et al.  Error detecting and error correcting codes , 1950 .

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

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

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

[11]  Ion Stoica,et al.  A cost comparison of datacenter network architectures , 2010, CoNEXT.

[12]  Ming Zhang,et al.  Understanding data center traffic characteristics , 2010, CCRV.

[13]  Minjie Zhang,et al.  A belief propagation-based method for task allocation in open and dynamic cloud environments , 2017, Knowl. Based Syst..

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

[15]  Xiaodong Liu,et al.  A speculative approach to spatial-temporal efficiency with multi-objective optimization in a heterogeneous cloud environment , 2016, Secur. Commun. Networks.

[16]  Devavrat Shah,et al.  Fastpass: a centralized "zero-queue" datacenter network , 2015, SIGCOMM 2015.

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

[18]  Enhua Wu,et al.  Robust dense reconstruction by range merging based on confidence estimation , 2016, Science China Information Sciences.

[19]  Hong-Fang Yu,et al.  Pricing the spare bandwidth: towards maximizing data center’s profit , 2016, Science China Information Sciences.

[20]  Jialin Li,et al.  Designing Distributed Systems Using Approximate Synchrony in Data Center Networks , 2015, NSDI.

[21]  Balázs Sonkoly,et al.  Free-scaling your data center , 2013, Comput. Networks.