Mitigating elephant flows in SDN-based IXP networks

Internet Exchange Points (IXPs) play a key role in the Internet architecture, enabling cost-effective connections among multiple autonomous systems (ASes). The management of IXP networks includes the activity of taking care of elephant flows; they represent a small number of the total flows of an IXP, but have high impact on the overall network traffic. Managing elephant flows involves adequate identification and eventually rerouting of such flows to more appropriate locations, to minimize the possible negative impact on the other (mice) flows. Elephant flow management becomes even more important in SDN-based IXPs that require controllers to have a consistent view of the underlying network to allow fine-grained adjustment. In this paper, we propose, develop, and evaluate a recommendation system to suggest alternative configurations to previously identified elephant flows in an SDN-based IXP network. In our solution, the IXP operator can define templates that ultimately define how elephant flows can be rerouted to achieve a specific objective. We demonstrate that our system can help IXP operators to mitigate the impact of elephant flows on the IXP network.

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

[2]  Rodrigo Fonseca Datacenter Network Large Flow Detection and Scheduling from the Edge Rui ( Ray ) , 2014 .

[3]  Yonggang Wen,et al.  “ A Survey of Software Defined Networking , 2020 .

[4]  Lisandro Zambenedetti Granville,et al.  Software-defined networking: management requirements and challenges , 2015, IEEE Communications Magazine.

[5]  Lisandro Zambenedetti Granville,et al.  SDEFIX - Identifying elephant flows in SDN-based IXP networks , 2016, NOMS.

[6]  Martín Casado,et al.  Software-defined internet architecture: decoupling architecture from infrastructure , 2012, HotNets-XI.

[7]  Ted Taekyoung Kwon,et al.  OpenSample: A Low-Latency, Sampling-Based Measurement Platform for Commodity SDN , 2014, 2014 IEEE 34th International Conference on Distributed Computing Systems.

[8]  Geng Lin,et al.  Macroflows and Microflows: Enabling Rapid Network Innovation through a Split SDN Data Plane , 2012, 2012 European Workshop on Software Defined Networking.

[9]  Liang Guo,et al.  The war between mice and elephants , 2001, Proceedings Ninth International Conference on Network Protocols. ICNP 2001.

[10]  Wang-Cheol Song,et al.  Visualization of elephant flows and QoS provisioning in SDN-based networks , 2015, 2015 17th Asia-Pacific Network Operations and Management Symposium (APNOMS).

[11]  Brice Augustin,et al.  IXPs: mapped? , 2009, IMC '09.

[12]  Chun-Yu Lin,et al.  Elephant flow detection in datacenters using OpenFlow-based Hierarchical Statistics Pulling , 2014, 2014 IEEE Global Communications Conference.

[13]  Ian F. Akyildiz,et al.  A roadmap for traffic engineering in SDN-OpenFlow networks , 2014, Comput. Networks.

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

[15]  Christian E. Hopps,et al.  Analysis of an Equal-Cost Multi-Path Algorithm , 2000, RFC.

[16]  Lisandro Zambenedetti Granville,et al.  On the management of virtual networks , 2013, IEEE Communications Magazine.

[17]  Praveen Yalagandula,et al.  Mahout: Low-overhead datacenter traffic management using end-host-based elephant detection , 2011, 2011 Proceedings IEEE INFOCOM.

[18]  Basil S. Maglaris,et al.  Combining OpenFlow and sFlow for an effective and scalable anomaly detection and mitigation mechanism on SDN environments , 2014, Comput. Networks.

[19]  Daniel O. Awduche,et al.  Requirements for Traffic Engineering Over MPLS , 1999, RFC.

[20]  Qiang Fu,et al.  Cardigan: SDN distributed routing fabric going live at an Internet exchange , 2014, 2014 IEEE Symposium on Computers and Communications (ISCC).