Rule Selector: A Novel Scalable Model for High-Performance Flow Recognition

When OpenFlow is initially put forward in academia, the performance and scalability issues in OpenFlow switches are gaining increasing attention. Currently, almost all of the software-based OpenFlow switches, such as Open vSwitch, usually use linear search algorithm on the wildcard rule tables. In recent years, many improved models and algorithms have been presented, but most of them haven't pay more attention to solving the scalability issues. In this paper, we propose a novel scalable model for high-performance flow recognition called Rule Selector, and implement it in the Open vSwitch. Based on our evaluation, we can say that our model achieves fast and scalable flow recognition. In our experiments, the performance of the Rule Selector is 4 times better than that of LightFlow and 3 times better than that of GFlow while its memory overhead is lower than the others.

[1]  Michiaki Hayashi,et al.  GPU-accelerated hash and wildcard hybrid flow switching for tackling massive flow entries , 2013, 2013 IEEE 14th International Conference on High Performance Switching and Routing (HPSR).

[2]  Jin Zhao,et al.  GFlow: Towards GPU-based high-performance table matching in OpenFlow switches , 2015, 2015 International Conference on Information Networking (ICOIN).

[3]  T. N. Vijaykumar,et al.  EffiCuts: optimizing packet classification for memory and throughput , 2010, SIGCOMM '10.

[4]  Minyi Guo,et al.  LABERIO: Dynamic load-balanced Routing in OpenFlow-enabled Networks , 2013, 2013 IEEE 27th International Conference on Advanced Information Networking and Applications (AINA).

[5]  Giuseppe Monteleone,et al.  Session Border Controller Virtualization Towards "Service-Defined" Networks Based on NFV and SDN , 2013, 2013 IEEE SDN for Future Networks and Services (SDN4FNS).

[6]  Michiaki Hayashi,et al.  LightFlow: Speeding up GPU-based flow switching and facilitating maintenance of flow table , 2012, 2012 IEEE 13th International Conference on High Performance Switching and Routing.

[7]  Tiejun J. Xia,et al.  Technologies and protocols for data center and cloud networking , 2013, IEEE Communications Magazine.

[8]  F. Richard Yu,et al.  Resource sharing for software defined D2D communications in virtual wireless networks with imperfect NSI , 2014, 2014 IEEE Global Communications Conference.

[9]  George Varghese,et al.  Packet classification using multidimensional cutting , 2003, SIGCOMM '03.

[10]  George Varghese,et al.  Scalable packet classification , 2001, SIGCOMM 2001.

[11]  Nick McKeown,et al.  Packet classification on multiple fields , 1999, SIGCOMM '99.

[12]  Guido Appenzeller,et al.  Implementing an OpenFlow switch on the NetFPGA platform , 2008, ANCS '08.

[13]  Victor C. M. Leung,et al.  Enabling technologies for future data center networking: a primer , 2013, IEEE Network.

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

[15]  Hui Chen,et al.  Research on TCAM-based Openflow switch platform , 2012, 2012 International Conference on Systems and Informatics (ICSAI2012).

[16]  Yuefeng Ji,et al.  First demonstration of enhanced software defined networking (eSDN) over elastic grid (eGrid) optical networks for data center service migration , 2013 .

[17]  Pankaj Gupta,et al.  Packet Classification using Hierarchical Intelligent Cuttings , 1999 .

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

[19]  Victor C. Valgenti,et al.  OpenFlow Accelerator: A Decomposition-Based Hashing Approach for Flow Processing , 2015, 2015 24th International Conference on Computer Communication and Networks (ICCCN).

[20]  Wolfgang Kellerer,et al.  Demonstration of SDN Based Optical Network Virtualization and Multidomain Service Orchestration , 2014, 2014 Third European Workshop on Software Defined Networks.