在現在的資料中心有相當大比例的流量是小流量的資料傳遞。在
許多資料中心當中大流量和小流量的資料傳遞有著相同的權重，但即
使小流量完成資料傳輸的時間較短，相同的權重仍會讓小流量的資料
傳輸花費較多時間來傳遞單一封包，也因此相同權重的負載平衡的策
略會不公平的對待小流量的資料傳遞。在我們的方法當中透過觀察
Flowlet 大小的特性代表著傳輸路線的壅塞情形及流量大小，來鎖定部
分大流量的資料傳遞，並且透過負載平衡策略的改變，將占用不壅塞
路徑的大流量的資料傳遞改由較為壅塞的路徑傳輸，保留更多的資源
給小流量的資料傳遞，同時部過度剝削大流量資掉傳遞的資源，來改
善大流量和小流量資料傳遞之間的不公平，並且進一步的提升小流量
資料傳遞的效能

In modern datacenter network, mice flows are big part in overall traffic. Most load balancing algorithm give the same priority to mice flow and elephant flow while making load balance decision. Even mice flow have small
flow completion time. Such equal priority strategy let mice flow take more time to transmit a single packet than elephant flow. In this paper, we propose a fast mice and slow elephant load balancing algorithm which can first
locate elephant flow overuse uncongested route by factors affect flowlet size and elephant flows are abusing uncongested path are routed to congested path
to improve the imbalance between mice flow and elephant flow and further increase the throughput of mice flow.

[1] Z. Han and L. Yu, “A survey of of the bcube data center network topology,” 2018
IEEE 4th International Conference on Big Data Security on Cloud (BigDataSecurity), IEEE International Conference on High Performance and Smart Computing,
(HPSC) and IEEE International Conference on Intelligent Data and Security (IDS),
2018.
[2] J. Srinivas and B. Eswara Reddy, “Exploiting geo distributed datacenters of a
cloud for load balancing,” 2015 IEEE International Advance Computing Conference
(IACC), 2015.
[3] M. Alizadeh, T. Edsall, S. Dharmapurikar, et al., “Conga: Distributed congestionaware load balancing for datacenters,” ACM SIGCOMM Computer Communication
Review, vol. 44, no. 4, pp. 503–514, 2014.
[4] C. Hopps, “Analysis of an equal-cost path alogrithm,” RFC2992, IETF, 2000.
[5] S. Kandula, D. Katabi, S. Sinha, and A. Berger, “Dynamic load balancing without
packet reordering,” ACM SIGCOMM Computer Communication Review, vol. 37,
no. 2, pp. 51–62, 2007.
[6] P. Hurtig and A. Brunstrom, “Packet reordering in tcp,” IEEE GLOBECOM Worksops, 2011.
[7] M. Al-Fares, S. Radhakrishnan, B. Raghavan, N. Huang, and A. Vahdat, “Hedera:
Dynamic flow scheduling for data center networks,” Proceedings of the 7th USENIX
Conference on Networked Systems Design and Implementation, vol. 10, pp. 19–19,
2010.
[8] K. He, E. Rozner, K. Agarwal, et al., “Presto: Edge-based load balancing for fast
datacenter networks,” SIGCOMM ’15 Proceedings of the 2015 ACM Conference on
Special Interest Group on Data Communication, 2015.
[9] T. Benson, A. Anand, A. Akella, et al., “Microte: Fine grained traffic engineering
for data centers,” CoNEXT ’11 Proceedings of the Seventh Conference on emerging
Networking Experiments and Technologies, 2011.
[10] H. Xu and B. Li, “Repflow: Minimizing flow completion times with replicated flows
in data centers,” IEEE INFOCOM 2014-IEEE Conference on Computer Communications, pp. 1581–1589, 2014.
[11] D. Zats, T. Das, P. Mohan, D. Borthakur, and R. Katz, “Detail: reducing the flow
completion time tail in datacenter networks,” ACM SIGCOMM Computer Communication Review, vol. 42, no. 4, pp. 139–150, 2012.
[12] J. Cao, R. Xia, P. Yang, C. Guo, G. Lu, L. Yuan, Y. Zheng, H. Wu, Y. Xiong, and
D. Maltz, “Per-packet load-balanced, low-latency routing for clos-based data center networks,” Proceedings of the Ninth ACM Conference on Emerging Networking
Experiments and Technologies, pp. 49–60, 2013.
[13] S. Qiu, X. Yu, K. Wang, et al., “Miflo: A scheduling algorithm based on mice flows
optimization in hybrid data center network,” 2017 16th International Conference on
Optical Communications and Networks (ICOCN), 2017.
[14] W. Wang, Y. Sun, K. Salamatian, et al., “Adaptive path isolation for elephant and
mice flows by exploiting path diversity in datacenters,” IEEE Transactions on Network and Service Management, 2016.
[15] H. Xu and B. Li, “Tinyflow: Breaking elephants down into mice in data center networks,” 2014 IEEE 20th International Workshop on Local Metropolitan Area Networks (LANMAN), 2014.
[16] R. Trestian, G.-M. Muntean, and K. Katrinis, “Micetrap: Scalable traffic engineering
of datacenter mice flows using openflow,” 2013 IFIP/IEEE International Symposium
on Integrated Network Management (IM 2013), 2013.
[17] D. Carra, “Controlling the delay of small flows in datacenters,” 2014 IEEE 34th
International Conference on Distributed Computing Systems Workshops (ICDCSW),
2014.
[18] C. Wang, G. Zhang, H. Chen, et al., “An aco-based elephant and mice flow scheduling system in sdn,” 2017 IEEE 2nd International Conference on Big Data Analysis
(ICBDA), 2017.
[19] D. F. Pellegrini, L. Maggi, A. Massaro, et al., “Blind, adaptive and robust flow segmentation in datacenters,” IEEE INFOCOM 2018 - IEEE Conference on Computer
Communications, 2018.
[20] M. Al-Fares, A. Loukissas, and A. Vahdat, “A scalable, commodity data center network architecture,” ACM SIGCOMM conference on Data communication, 2008.
[21] K. Kumar and B. Annappa, “Load balancing strategy for optimal peak hour performance in cloud datacenters,” IEEE International Conference on Signal Processing,
Informatics, Communication and Energy Systems (SPICES), 2015.
[22] Z. Guo, X. Dong, S. Chen, et al., “How to set timeout: Achieving adaptive load balance in asymmetric topology based on flowlet switching,” IEEE 37th International
Performance Computing and Communications Conference (IPCCC), 2018.
[23] T. Benson, A. Akella, and D. A. Maltz, “Network traffic characteristics of data centers in the wild,” IMC ’10 Proceedings of the 10th ACM SIGCOMM conference on
Internet measurement, 2010.
[24] S. Kandula, S. Sengupta, A. Greenberg, et al., “The nature of data center traffic measurements & analysis,” IMC ’09 Proceedings of the 9th ACM SIGCOMM conference
on Internet measurement, 2009.
[25] N. Dukkipati and N. McKeown, “Why flow-completion time is the right metric for
congestion control,” ACM SIGCOMM Computer Communication Review, vol. 36,
no. 1, pp. 59–62, 2006.