This document summarizes a research paper presented at the 1st Workshop on Multimedia-Aware Networking 2011 that proposes a preliminary design for a content-aware network node. The design aims to classify multimedia traffic based on deep packet inspection and apply specific routing policies. An experimental testbed was implemented to validate the concept, which demonstrated that the content-aware node was able to identify traffic and route differently compared to a traditional agnostic node, without affecting delay.

1. !st Workshop on Multimedia-Aware Networking 2011 (WoMAN ‘11) A PRELIMINARY IMPLEMENTATION OF A CONTENT–AWARE NETWORK NODE N. Vorniotakis, G. Xilouris, G. Gardikis, N. Zotos, E. Palis, A. Kourtis

2. Contents Introduction Scope Content-Awareness Enablers Design Experimental Testbed Validation and experimental results Acknowledgments - Conclusions 2 ICME 2011 Conference, WOMAN Workshop July 11 2011, Barcelona

3. Introduction Multimedia content is anticipated to be increased at least by a factor of 6 in 2012 Network nodes are currently agnostic to the content they deliver In order for future network architectures to cope with this environment continue to provide fast switching and forwarding at the core push the intelligence to the edge Given the constant evolution in hardware capabilities — in terms of CPU power and memory availability there is the capability to: Provide new functionalities to the network nodes in order to make the network aware of the content being transferred hence applying specific policies or routing respectively 3 ICME 2011 Conference, WOMAN Workshop July 11 2011, Barcelona

4. Scope This work presents a preliminary design of a content-aware network node Discusses the main concepts and principles governing this design Presents an preliminary implementation of an algorithm for identification of multimedia streams over RTP protocol Validates the proof-of-concept through experimental results 4 ICME 2011 Conference, WOMAN Workshop July 11 2011, Barcelona

5. Content-Awareness Enablers Flow awareness content-awareness should be performed per-flow of network data Use of hash tables where every active flow record, is maintained by the network node Mechanisms for removal of idle or zombie flows are mandatory in order to be detected and removed, and free memory Enables the processing of the minimum required amount of packets Resulting Smaller processing delays Better scalability 5 ICME 2011 Conference, WOMAN Workshop July 11 2011, Barcelona

6. Content-Awareness Enablers Traffic Classification Current techniques exploit information taken from OSI Layer 3 to Layer 7 Many techniques combine multilayer information with application data inspection (DPI) for accurate traffic identification Less invasive to privacy methods involve statistical analysis of the flow dynamics Methods used to classify traffic at application level include Exact Matching Prefix Matching Heuristics methods Machine learning based on statistical features 6 ICME 2011 Conference, WOMAN Workshop July 11 2011, Barcelona

8. Policer Module is in charge of applying the desired policies at the respective flows. This module includes also the queue schedulers that are used for traffic control (shaping, differentiation, prioritization)

9. C-A functions were designed to be modular and scalable

10. Flow Handling module comprises of

11. the Packet Capturer module that captures incoming network packets

12. Flow Handler that organizes incoming packets to network flows.

13. Routing module comprises of:

14. Packet Marker and the Routing Tables Handler7 ICME 2011 Conference, WOMAN Workshop July 11 2011, Barcelona

16. for every incoming flow, after the content is identified three main decisions need to be made.

17. how to police the traffic at the ingress interface

18. how to route the flow

19. how to handle (shaping, conditioning, prioritization) the flow at the egress.

20. This module exploits functionalities provided by the Linux OS kernel and User Space utilities (i.e. iptables, traffic control

21. Content Mapping Table that contains information on how to police and condition the flows depend- ing on content type

22. A number of alternative local RIBs is used that are statically pre-assigned8 ICME 2011 Conference, WOMAN Workshop July 11 2011, Barcelona

24. The actual detection algorithm is much more complex so it can be accurate on most cases since it has more passes and also takes into account RTCP data.9 ICME 2011 Conference, WOMAN Workshop July 11 2011, Barcelona

26. The actual detection algorithm is much more complex so it can be accurate on most cases since it has more passes and also takes into account RTCP data.10 ICME 2011 Conference, WOMAN Workshop July 11 2011, Barcelona

28. traffic generator is used to create a gradually increasing source of background traffic11 ICME 2011 Conference, WOMAN Workshop July 11 2011, Barcelona

29. Experimental - Cases Testing Scenarios Case1 - content agnostic network Case2 - traffic classification based on policies and HTB Case3 - traffic classification based on content identification 12 ICME 2011 Conference, WOMAN Workshop July 11 2011, Barcelona

31. In case3 the content aware features of the ingress node allow the selection of different path in the network

32. The one way delay is not affected by the operation of the C-A algorithmCase2 13 ICME 2011 Conference, WOMAN Workshop July 11 2011, Barcelona

33. Acknowledgments This work has been supported by the European Research Project FP7 “MediA Ecosystem Deployment Through Ubiquitous Content-Aware Network Environments”ICT-ALICANTE Project No. 2010-2013. http://www.ict-alicante.eu 14 ICME 2011 Conference, WOMAN Workshop July 11 2011, Barcelona

34. Thank you for your attention Questions ? Contact information NikolaosVorniotakis (nkvorn@iit.demorkritos.gr) George Xilouris (xilouris@iit.demokritos.gr) 15 ICME 2011 Conference, WOMAN Workshop July 11 2011, Barcelona

35. 16 ICME 2011 Conference, WOMAN Workshop July 11 2011, Barcelona