OpenQFlow: Scalable OpenFlow with Flow-Based QoS

SUMMARY OpenFlow, originally proposed for campus and enterprise network experimentation, has become a promising SDN architecture that is considered as a widely-deployable production network node recently. It is, in a consequence, pointed out that OpenFlow cannot scale and replace today’s versatile network devices due to its limited scalability and flexibility. In this paper, we propose OpenQFlow, a novel scalable and flexible variant of OpenFlow. OpenQFlow provides a fine-grained flow tracking while flow classification is decoupled from the tracking by separating the inefficiently coupled flow table to three different tables: flow state table, forwarding rule table, and QoS rule table. We also develop a two-tier flowbased QoS framework, derived from our new packet scheduling algorithm, which provides performance guarantee and fairness on both granularity levels of micro- and aggregate-flow at the same time. We have implemented OpenQFlow on an off-the-shelf microTCA chassis equipped with a commodity multicore processor, for which our architecture is suited, to achieve high-performance with carefully engineered software design and optimiza

[1]  Martín Casado,et al.  NOX: towards an operating system for networks , 2008, CCRV.

[2]  Sujata Banerjee,et al.  Automated and Scalable QoS Control for Network Convergence , 2010, INM/WREN.

[3]  Desmond P. Taylor,et al.  A Generalized Processor Sharing Approach to Flow Control in Integrated Services Networks: The SingleNode Case , 2007 .

[4]  Jean-Yves Le Boudec,et al.  Rate adaptation, Congestion Control and Fairness: A Tutorial , 2000 .

[5]  Mark Handley,et al.  XORP: an open platform for network research , 2003, CCRV.

[6]  Raj Jain,et al.  The art of computer systems performance analysis - techniques for experimental design, measurement, simulation, and modeling , 1991, Wiley professional computing.

[7]  Jia Wang,et al.  Scalable flow-based networking with DIFANE , 2010, SIGCOMM '10.

[8]  Jonathan S. Turner,et al.  Scalable packet classification using distributed crossproducing of field labels , 2005, Proceedings IEEE 24th Annual Joint Conference of the IEEE Computer and Communications Societies..

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

[10]  Robert Tappan Morris,et al.  Dynamics of random early detection , 1997, SIGCOMM '97.

[11]  Sartaj Sahni,et al.  Efficient construction of multibit tries for IP lookup , 2003, TNET.

[12]  Hao Wu,et al.  Tracking millions of flows in high speed networks for application identification , 2012, 2012 Proceedings IEEE INFOCOM.

[13]  Amin Vahdat,et al.  Hedera: Dynamic Flow Scheduling for Data Center Networks , 2010, NSDI.

[14]  Domenico Ferrari,et al.  Rate-controlled static-priority queueing , 1993, IEEE INFOCOM '93 The Conference on Computer Communications, Proceedings.

[15]  Abhay Parekh,et al.  A generalized processor sharing approach to flow control in integrated services networks: the single-node case , 1993, TNET.

[16]  Scott Shenker,et al.  Core-stateless fair queueing: achieving approximately fair bandwidth allocations in high speed networks , 1998, SIGCOMM '98.

[17]  Yin Zhang,et al.  On the characteristics and origins of internet flow rates , 2002, SIGCOMM '02.

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

[19]  Kyung Ho Lee,et al.  Quality‐of‐Service Mechanisms for Flow‐Based Routers , 2008 .