IDEAFIX: Identifying Elephant Flows in P4-Based IXP Networks

Internet Exchange Points (IXPs) are high-performance networks that allow multiple autonomous systems to exchange traffic, with benefits ranging from cost reductions to performance improvements. In addition, performance requirements and a number of players involved in such networks bring out several issues to management tasks, such as elephant flows identification. This kind of flows, with high size and substantial duration, can severely impact the performance of smaller flows. In this paper, we present IDEAFIX, a mechanism to identify elephant flows in P4-based IXP networks. Our approach consists in analyzing flows features for each ingress packet immediately in the edge switch. These features are then stored in P4 registers, indexed by hash keys, and compared to predefined thresholds for flow classification. Experimental evaluations show that IDEAFIX is significantly more efficient than the state-of-the-art approaches implemented with sFlow and traditional Software-Defined Networking (SDN) tools (e.g., OpenFlow). While state-of-the-art mechanisms add up to 17MB of monitoring data, our solution causes an overhead of only 25KB. Also, the implemented prototype takes less than 0.40ms to identify elephant flows with a 95% accuracy in scenarios with scarce memory resources.

[1]  Lisandro Zambenedetti Granville,et al.  Mitigating elephant flows in SDN-based IXP networks , 2017, 2017 IEEE Symposium on Computers and Communications (ISCC).

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

[3]  Chiara Orsini,et al.  C Consiglio Nazionale delle Ricerche The Impact of IXPs on the AS-level Topology Structure of the Internet , 2010 .

[4]  Roy Friedman,et al.  Constant Time Updates in Hierarchical Heavy Hitters , 2017, SIGCOMM.

[5]  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).

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

[7]  S. Muthukrishnan,et al.  Heavy-Hitter Detection Entirely in the Data Plane , 2016 .

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

[9]  Mahmood Ahmadi,et al.  Bloom filter applications in network security: A state-of-the-art survey , 2013, Comput. Networks.

[10]  Rade Stanojevic,et al.  IXP traffic: a macroscopic view , 2012, LANC.

[11]  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.

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

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

[14]  Luciano Paschoal Gaspary,et al.  Identificação de Fluxos Elefantes em Redes de Ponto de Troca de Tráfego com Suporte à Programabilidade P4 , 2018, SBRC.

[15]  George Varghese,et al.  P4: programming protocol-independent packet processors , 2013, CCRV.