A high-performance Two-Phase Multipath scheme for data-center networks

Multipath forwarding has been recently proposed to improve utilization in data centers leveraged by its redundant network design. However, most multipath proposals require significant modifications to the tenants network stack and therefore are only feasible in private clouds. In this paper, we propose the Two-Phase Multipath (TPM) forwarding scheme for public clouds. The proposal improves tenants network throughput, whereas keeping unmodified network stack on tenants. Our scheme is composed of a smart offline configuration phase that discover optimal disjoint paths, and a fast online path selection phase that improves flow throughput at run time. A logically centralized manager uses a genetic algorithm to generate and install sets of paths, summarized into trees, during multipath configuration, and a local controller performs the multipath selection based on network usage. We analyze TPM for different workloads and topologies under several scenarios of usage database locations and update policies. The results show that our proposal yields up to 77% throughput gains over previously proposed approaches.

[1]  Amin Vahdat,et al.  Less Is More: Trading a Little Bandwidth for Ultra-Low Latency in the Data Center , 2012, NSDI.

[2]  Elisa Rojas,et al.  All-Path bridging: Path exploration protocols for data center and campus networks , 2015, Comput. Networks.

[3]  Srikanth Kandula,et al.  Dynamic load balancing without packet reordering , 2007, CCRV.

[4]  Deep Medhi,et al.  Opportunistic resilience embedding (ORE): Toward cost-efficient resilient virtual networks , 2015, Comput. Networks.

[5]  David Mazières,et al.  EyeQ: Practical Network Performance Isolation for the Multi-tenant Cloud , 2012, HotCloud.

[6]  Günter Rudolph,et al.  Convergence analysis of canonical genetic algorithms , 1994, IEEE Trans. Neural Networks.

[7]  Jeffrey C. Mogul,et al.  SPAIN: COTS Data-Center Ethernet for Multipathing over Arbitrary Topologies , 2010, NSDI.

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

[9]  Wu Chou,et al.  An adaptive multi-path computation framework for centrally controlled networks , 2015, Comput. Networks.

[10]  Amin Vahdat,et al.  PortLand: a scalable fault-tolerant layer 2 data center network fabric , 2009, SIGCOMM '09.

[11]  David W. Coit,et al.  Solving the redundancy allocation problem using a combined neural network/genetic algorithm approach , 1996, Comput. Oper. Res..

[12]  Ali Sajassi,et al.  VXLAN DCI Using EVPN , 2014 .

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

[15]  D. Zats,et al.  DeTail: reducing the flow completion time tail in datacenter networks , 2012, CCRV.

[16]  Reuven Cohen,et al.  Optimizing Data Plane Resources for Multipath Flows , 2015, IEEE/ACM Transactions on Networking.

[17]  Otto Carlos Muniz Bandeira Duarte,et al.  XenFlow: Seamless migration primitive and quality of service for virtual networks , 2014, GLOBECOM.

[18]  Otto Carlos Muniz Bandeira Duarte,et al.  An efficient energy-aware mechanism for virtual machine migration , 2015, 2015 Global Information Infrastructure and Networking Symposium (GIIS).

[19]  Lisandro Zambenedetti Granville,et al.  Data Center Network Virtualization: A Survey , 2013, IEEE Communications Surveys & Tutorials.

[20]  Benny Rochwerger,et al.  A case for overlays in DCN virtualization , 2011 .

[21]  Otto Carlos Muniz Bandeira Duarte,et al.  Virtual Machine Migration , 2015 .

[22]  Antony I. T. Rowstron,et al.  Better never than late: meeting deadlines in datacenter networks , 2011, SIGCOMM.

[23]  George Varghese,et al.  CONGA: distributed congestion-aware load balancing for datacenters , 2015, SIGCOMM.

[24]  Marcelo G. Rubinstein,et al.  FITS: A flexible virtual network testbed architecture , 2014, Comput. Networks.

[25]  Radia J. Perlman,et al.  An algorithm for distributed computation of a spanningtree in an extended LAN , 1985, SIGCOMM '85.

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

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

[28]  Pankaj Garg,et al.  NVGRE: Network Virtualization Using Generic Routing Encapsulation , 2015, RFC.

[29]  Nick McKeown,et al.  OpenFlow: enabling innovation in campus networks , 2008, CCRV.

[30]  Sujata Banerjee,et al.  DevoFlow: scaling flow management for high-performance networks , 2011, SIGCOMM.

[31]  Mark Handley,et al.  Improving datacenter performance and robustness with multipath TCP , 2011, SIGCOMM.

[32]  David S. Johnson,et al.  Computers and Intractability: A Guide to the Theory of NP-Completeness , 1978 .

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

[34]  János Farkas,et al.  Shortest path bridging: Efficient control of larger ethernet networks , 2010, IEEE Communications Magazine.

[35]  David A. Maltz,et al.  Surviving failures in bandwidth-constrained datacenters , 2012, CCRV.

[36]  Jeffrey C. Mogul,et al.  NetLord: a scalable multi-tenant network architecture for virtualized datacenters , 2011, SIGCOMM.

[37]  Otto Carlos Muniz Bandeira Duarte,et al.  A two-phase multipathing scheme based on genetic algorithm for data center networking , 2014, GLOBECOM.

[38]  Jussara M. Almeida,et al.  SpaDeS: Detecting spammers at the source network , 2013, Comput. Networks.

[39]  Deep Medhi,et al.  Impact of Ethernet Multipath Routing on Data Center Network Consolidations , 2014, 2014 IEEE 34th International Conference on Distributed Computing Systems Workshops (ICDCSW).

[40]  Fan Yao,et al.  A comparative analysis of data center network architectures , 2014, 2014 IEEE International Conference on Communications (ICC).

[41]  Stefano Secci,et al.  Latency versus survivability in geo-distributed data center design , 2014, 2014 IEEE Global Communications Conference.

[42]  Martín Casado,et al.  Extending Networking into the Virtualization Layer , 2009, HotNets.

[43]  Minghua Chen,et al.  Joint VM placement and routing for data center traffic engineering , 2012, 2012 Proceedings IEEE INFOCOM.

[44]  Benjamin Doerr,et al.  Optimal Parameter Choices Through Self-Adjustment: Applying the 1/5-th Rule in Discrete Settings , 2015, GECCO.

[45]  Murat Yuksel,et al.  Large-scale network parameter configuration using an on-line simulation framework , 2008, TNET.

[46]  Ayan Banerjee,et al.  Transparent Interconnection of Lots of Links (TRILL): Clarifications, Corrections, and Updates , 2016, RFC.

[47]  Aniruddha S. Gokhale,et al.  Software-Defined Networking: Challenges and research opportunities for Future Internet , 2014, Comput. Networks.

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

[49]  Luís Henrique Maciel Kosmalski Costa,et al.  Online traffic-aware virtual machine placement in data center networks , 2012, 2012 Global Information Infrastructure and Networking Symposium (GIIS).

[50]  James Won-Ki Hong,et al.  SNMP-based enterprise IP network topology discovery , 2011, Int. J. Netw. Manag..