AnOpenFlow-based performance-orientedmultipath forwarding scheme in datacenters<FootNote> Project supported by the National Basic Research Program (973) of China (No. 2012CB315806), the National Natural Science Foundation of China (Nos. 61103225 and 61379149), the Jiangsu Provincial Natural Science Foundation (No. BK20140070), and the Jiangsu Future Networks Innovation Institute Prospective Research Project on Future Networks, China (No. BY2013095-1-06) </FootNote>

Bo LIU, Ming CHEN, Bo XU, Hui HU, Chao HU, Qing-yun ZUO, Chang-you XING

PDF(578 KB)
PDF(578 KB)
Front. Inform. Technol. Electron. Eng ›› 2016, Vol. 17 ›› Issue (7) : 647-660. DOI: 10.1631/FITEE.1601059
Article
Article

AnOpenFlow-based performance-orientedmultipath forwarding scheme in datacenters<FootNote> Project supported by the National Basic Research Program (973) of China (No. 2012CB315806), the National Natural Science Foundation of China (Nos. 61103225 and 61379149), the Jiangsu Provincial Natural Science Foundation (No. BK20140070), and the Jiangsu Future Networks Innovation Institute Prospective Research Project on Future Networks, China (No. BY2013095-1-06) </FootNote>

Author information +
History +

Abstract

Although dense interconnection datacenter networks (DCNs) (e.g., FatTree) provide multiple paths and high bisection bandwidth for each server pair, the widely used single-path Transmission Control Protocol (TCP) and equal-cost multipath (ECMP) transport protocols cannot achieve high resource utilization due to poor resource excavation and allocation. In this paper, we present LESSOR, a performance-oriented multipath forwarding scheme to improve DCNs’ resource utilization. By adopting an OpenFlow-based centralized control mechanism, LESSOR computes near-optimal transmission path and bandwidth provision for each flow according to the global network view while maintaining nearly real-time network view with the performance-oriented flow observing mechanism. Deployments and comprehensive simulations show that LESSOR can efficiently improve the network throughput, which is higher than ECMP by 4.9%–38.3% under different loads. LESSOR also provides 2%–27.7% improvement of throughput compared with Hedera. Besides, LESSOR decreases the average flow completion time significantly.

Keywords

Datacenter network / Traffic engineering / OpenFlow / Multipath transmission

Cite this article

Download citation ▾
Bo LIU, Ming CHEN, Bo XU, Hui HU, Chao HU, Qing-yun ZUO, Chang-you XING. AnOpenFlow-based performance-orientedmultipath forwarding scheme in datacenters<FootNote> Project supported by the National Basic Research Program (973) of China (No. 2012CB315806), the National Natural Science Foundation of China (Nos. 61103225 and 61379149), the Jiangsu Provincial Natural Science Foundation (No. BK20140070), and the Jiangsu Future Networks Innovation Institute Prospective Research Project on Future Networks, China (No. BY2013095-1-06) </FootNote>. Front. Inform. Technol. Electron. Eng, 2016, 17(7): 647‒660 https://doi.org/10.1631/FITEE.1601059

References

[1]
Al-Fares, M., Loukissas, A., Vahdat, A., 2008. A scalable, commodity data center network architecture. ACM SIGCOMM Comput. Commun. Rev., 38(4):63–74. http://dx.doi.org/10.1145/1402946.1402967
[2]
Al-Fares, M., Radhakrishnan, S., Raghavan, B., et al., 2010. Hedera: dynamic flow scheduling for data center networks. Proc. 7th USENIX Conf. on Networked Systems Design and Implementation, p.1–15.
[3]
Alizadeh, M., Greenberg, A., Maltz, D.A., et al., 2010. Data center TCP (DCTCP). ACM SIGCOMM Comput. Commun. Rev., 41(4):63–74. http://dx.doi.org/10.1145/1851182.1851192
[4]
Alizadeh, M., Edsall, T., Dharmapurikar, S., et al., 2014. CONGA: distributed congestion-aware load balancing for datacenters. ACM SIGCOMM Comput. Commun. Rev., 44(4):503–514. http://dx.doi.org/10.1145/2619239.2626316
[5]
Benson, T., Akella, A., Maltz, D.A., 2010. Network traffic characteristics of data centers in the wild. Proc. 10th ACM SIGCOMM Conf. on Internet Measurement, p.267–280. http://dx.doi.org/10.1145/1879141.1879175
[6]
Benson, T., Anand, A., Akella, A., et al., 2011. MicroTE: fine grained traffic engineering for data centers. Proc. 7th Conf. on Emerging Networking EXperiments and Technologies, Article 8. http://dx.doi.org/10.1145/2079296.2079304
[7]
Bredel, M., Bozakov, Z., Barczyk, A., et al., 2014. Flowbased load balancing in multipathed layer-2 networks using OpenFlow and multipath-TCP. Proc. 3rd Workshop on Hot Topics in Software Defined Networking, p.213–214. http://dx.doi.org/10.1145/2620728.2620770
[8]
Cao, J., Xia, R., Yang, P., et al., 2013. Per-packet loadbalanced, low-latency routing for Clos-based data center networks. Proc. 9th ACM Conf. on Emerging Networking EXperiments and Technologies, p.49–60. http://dx.doi.org/10.1145/2535372.2535375
[9]
Chen, Y., Jain, S., Adhikari, V.K., et al., 2011. A first look at inter-data center traffic characteristics via Yahoo! datasets. Proc. IEEE INFOCOM, p.1620–1628. http://dx.doi.org/10.1109/INFCOM.2011.5934955
[10]
Chiesa, M., Kindler, G., Schapira, M., 2014. Traffic engineering with equal-cost-multipath: an algorithmic perspective. Proc. IEEE Conf. on Computer Communications, p.1590–1598. http://dx.doi.org/10.1109/INFOCOM.2014.6848095
[11]
Curtis, A.R., Mogul, J.C., Tourrilhes, J., et al., 2011a. DevoFlow: scaling flow management for high-performance networks. ACM SIGCOMM Comput. Commun. Rev., 41(4):254-265. http://dx.doi.org/10.1145/2043164.2018466
[12]
Curtis, A.R., Kim, W., Yalagandula, P., 2011b. Mahout: low-overhead datacenter traffic management using endhost-based elephant detection. Proc. IEEE INFOCOM, p.1629–1637. http://dx.doi.org/10.1109/INFCOM.2011.5934956
[13]
Dixit, A., Prakash, P., Hu, Y.C., et al., 2013. On the impact of packet spraying in data center networks. Proc. IEEE INFOCOM, p.2130–2138. http://dx.doi.org/10.1109/INFCOM.2013.6567015
[14]
Ford, A., Raiciu, C., Handley, M., et al., 2013. TCP Extensions for Multipath Operation with Multiple Addresses. RFC 6824. http://dx.doi.org/10.17487/RFC6824
[15]
Greenberg, A., Hamilton, J.R., Jain, N., et al., 2011. VL2: a scalable and flexible data center network. Commun. ACM, 54(3):95–104. http://dx.doi.org/10.1145/1897852.1897877
[16]
Handigol, N., Heller, B., Jeyakumar, V., et al., 2012. Reproducible network experiments using container-based emulation. Proc. 8th Int. Conf. on Emerging Networking EXperiments and Technologies, p.253–264. http://dx.doi.org/10.1145/2413176.2413206
[17]
Hong, C.Y., Caesar, M., Godfrey, P.B., 2012. Finishing flows quickly with preemptive scheduling. ACM SIGCOMM Comput. Commun. Rev., 42(4):127–138. http://dx.doi.org/10.1145/2377677.2377710
[18]
Hopps, C.E., 2000. Analysis of an Equal-Cost Multi-path Algorithm. RFC 2992. Available fromhttp://www.ietf. org/rfc/rfc2992.txt.
[19]
Jain, S., Kumar, A., Mandal, S., et al., 2013. B4: experience with a globally-deployed software defined WAN. ACM SIGCOMM Comput. Commun. Rev., 43(4):3–14. http://dx.doi.org/10.1145/2534169.2486019
[20]
Kabbani, A., Vamanan, B., Hasan, J., et al., 2014. FlowBender: flow-level adaptive routing for improved latency and throughput in datacenter networks. Proc. 10th ACM Int. Conf. on Emerging Networking EXperiments and Technologies, p.149–160. http://dx.doi.org/10.1145/2674005.2674985
[21]
Le, Q.Q., Yang, G.W., Hung, W.N.N., et al., 2014. Performance-driven assignment and mapping for reliable networks-on-chips. J. Zhejiang Univ.-Sci. C (Comput. & Electron.), 15(11):1009–1020. http://dx.doi.org/10.1631/jzus.C1400055
[22]
Li, X.L., Wang, H.M., Guo, C.G., et al., 2012. Topology awareness algorithm for virtual network mapping. J. Zhejiang Univ.-Sci. C (Comput. & Electron.), 13(3): 178–186. http://dx.doi.org/10.1631/jzus.C1100282
[23]
Madry, A., 2010. Faster approximation schemes for fractional multicommodity flow problems via dynamic graph algorithms. Proc. 42nd ACM Symp. on Theory of Computing, p.121–130. http://dx.doi.org/10.1145/1806689.1806708
[24]
McKeown, N., Anderson, T., Balakrishnan, H., et al., 2008. OpenFlow: enabling innovation in campus networks. ACM SIGCOMM Comput. Commun. Rev., 38(2):69–74. http://dx.doi.org/10.1145/1355734.1355746
[25]
Mudigonda, J., Yalagandula, P., Al-Fares, M., et al., 2010. SPAIN: COTS data-center Ethernet for multipathing over arbitrary topologies. Proc. 7th USENIX Conf. on Networked Systems Design and Implementation, p.18–33.
[26]
Peng, Y., Chen, K., Wang, G., et al., 2014. HadoopWatch: a first step towards comprehensive traffic forecasting in cloud computing. Proc. IEEE Conf. on Computer Communications, p.19–27. http://dx.doi.org/10.1109/INFOCOM.2014.6847920
[27]
Qi, H., Shiraz, M., Liu, J.Y., et al., 2014. Data center network architecture in cloud computing: review, taxonomy, and open research issues. J. Zhejiang Univ.-Sci. C (Comput. & Electron.), 15(9):776–793. http://dx.doi.org/10.1631/jzus.C1400013
[28]
Raiciu, C., Handley, M., Wischik, D., 2011a. Coupled Congestion Control for Multipath Transport Protocols. RFC 6356. http://dx.doi.org/10.17487/RFC6356
[29]
Raiciu, C., Barre, S., Pluntke, C., et al., 2011b. Improving datacenter performance and robustness with multipath TCP. ACM SIGCOMM Comput. Commun. Rev., 41(4):266–277. http://dx.doi.org/10.1145/2043164.2018467
[30]
Rotsos, C., Sarrar, N., Uhlig, S., et al., 2012. OFLOPS: an open framework for OpenFlow switch evaluation. Proc. 13th Int. Conf. on Passive and Active Measurement, p.85–95. http://dx.doi.org/10.1007/978-3-642-28537-0_9
[31]
Wilson, C., Ballani, H., Karagiannis, T., et al., 2011. Better never than late: meeting deadlines in datacenter networks. ACM SIGCOMM Comput. Commun. Rev., 41(4):50–61. http://dx.doi.org/10.1145/2018436.2018443
[32]
Yu, C., Lumezanu, C., Zhang, Y., et al., 2013. FlowSense: monitoring network utilization with zero measurement cost. Proc. 14th Int. Conf. on Passive and Active Measurement, p.31–41. http://dx.doi.org/10.1007/978-3-642-36516-4_4
[33]
Zats, D., Das, T., Mohan, P., et al., 2012. DeTail: reducing the flow completion time tail in datacenter networks. ACM SIGCOMM Comput. Commun. Rev., 42(4):139–150. http://dx.doi.org/10.1145/2377677.2377711

RIGHTS & PERMISSIONS

2016 Zhejiang University and Springer-Verlag Berlin Heidelberg
PDF(578 KB)

Accesses

Citations

Detail

Sections
Recommended

/