Netography: Troubleshoot your network with packet behavior in SDN

Network troubleshooting is always a tough and daunting task for network operators to struggle with, due to difficultly observed network state, large network size and limited tools such as ping and traceroute. Software-defined networking (SDN) brings us the centralized network control and the customized network management over the entire network, which enables new ways of network troubleshooting. Previous efforts focus on static checking, passive monitoring and active probing, which rely on scraping rules from either controller or network devices. Since those rules describe the actions supposed to be performed on packets, the actions having been performed on packets can be different. We propose the concept of packet behavior to describe the real changes of packets and highlight its importance towards network troubleshooting. Based on the novel approach of exporting packet behavior and flow rules via copies triggered by probes being actively sent, we present the design of Netography system and illustrate the procedures of troubleshooting tasks regarding forwarding errors as well as performance degradation caused by non-tenant-contention reasons. We implement a prototype and verify our system on a small deployment with three typical use cases.

[1]  Marco Canini,et al.  A NICE Way to Test OpenFlow Applications , 2012, NSDI.

[2]  Samuel T. King,et al.  Debugging the data plane with anteater , 2011, SIGCOMM 2011.

[3]  John B. Carter,et al.  SDN traceroute: tracing SDN forwarding without changing network behavior , 2014, HotSDN.

[4]  Chen-Nee Chuah,et al.  Characterization of Failures in an Operational IP Backbone Network , 2008, IEEE/ACM Transactions on Networking.

[5]  Alan L. Cox,et al.  PAST: scalable ethernet for data centers , 2012, CoNEXT '12.

[6]  Nick McKeown,et al.  Where is the debugger for my software-defined network? , 2012, HotSDN '12.

[7]  George Varghese,et al.  Automatic Test Packet Generation , 2012, IEEE/ACM Transactions on Networking.

[8]  Donald F. Towsley,et al.  Inferring link loss using striped unicast probes , 2001, Proceedings IEEE INFOCOM 2001. Conference on Computer Communications. Twentieth Annual Joint Conference of the IEEE Computer and Communications Society (Cat. No.01CH37213).

[9]  Brighten Godfrey,et al.  VeriFlow: verifying network-wide invariants in real time , 2012, HotSDN '12.

[10]  J. Carter,et al.  OpenSample : A Low-Latency , Sampling-Based Measurement Platform for SDN , 2013 .

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

[12]  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.

[13]  Nick McKeown,et al.  I Know What Your Packet Did Last Hop: Using Packet Histories to Troubleshoot Networks , 2014, NSDI.

[14]  Nick G. Duffield,et al.  Network Tomography of Binary Network Performance Characteristics , 2006, IEEE Transactions on Information Theory.

[15]  George Varghese,et al.  Real Time Network Policy Checking Using Header Space Analysis , 2013, NSDI.

[16]  George Varghese,et al.  Header Space Analysis: Static Checking for Networks , 2012, NSDI.

[17]  IEEE/IFIP Network Operations and Management Symposium, NOMS 2010, 19-23 April 2010, Osaka, Japan , 2010, IEEE/IFIP Network Operations and Management Symposium.

[18]  Rodrigo Fonseca,et al.  Planck , 2014, SIGCOMM.

[19]  Renata Teixeira,et al.  NetDiagnoser: troubleshooting network unreachabilities using end-to-end probes and routing data , 2007, CoNEXT '07.