Sameer Agarwal and Mosharaf Chowdhury and Dilip Joseph and Ion Stoica

EECS Department, University of California, Berkeley

Technical Report No. UCB/EECS-2011-96

August 24, 2011

http://www2.eecs.berkeley.edu/Pubs/TechRpts/2011/EECS-2011-96.pdf

Despite widespread application, packet classification is implemented and deployed in an ad-hoc manner at different layers of the protocol stack. Moreover, high speed packet classification, in presence of a large number of classification rules, is both resource and computation intensive. We propose a scalable layer-agnostic packet classification framework (Lattice) that generalizes classifier design and enables offloading part of computation and memory requirements to collaborators (e.g., end hosts). Lattice eliminates per-packet classification and per-flow states in classifiers to increase scalability and decreases vulnerability to state-based DoS attacks. Furthermore, Lattice is incentive compatible in that collaborators cannot get better service by lying, and it incentivizes deployment by giving preferential treatment to packets carrying Lattice-related information. Finally, Lattice-enabled classifiers remain semantically equivalent to their unmodified counterparts. To evaluate Lattice, we have built a prototype using the Click software router and implemented multiple Lattice-enabled classifiers. Lattice-enabled firewalls perform at least 2X faster than unmodified counterparts and scale well with the increasing number of classification rules.

---

BibTeX citation:

@techreport{Agarwal:EECS-2011-96,
    Author= {Agarwal, Sameer and Chowdhury, Mosharaf and Joseph, Dilip and Stoica, Ion},
    Title= {Lattice: A Scalable Layer-Agnostic Packet Classification Framework},
    Year= {2011},
    Month= {Aug},
    Url= {http://www2.eecs.berkeley.edu/Pubs/TechRpts/2011/EECS-2011-96.html},
    Number= {UCB/EECS-2011-96},
    Abstract= {Despite widespread application, packet classification is implemented and deployed in an ad-hoc manner at different layers of the protocol stack. Moreover, high speed packet classification, in presence of a large number of classification rules, is both resource and computation intensive. We propose a scalable layer-agnostic packet classification framework (Lattice) that generalizes classifier design and enables offloading part of computation and memory requirements to collaborators (e.g., end hosts). Lattice eliminates per-packet classification and per-flow states in classifiers to increase scalability and decreases vulnerability to state-based DoS attacks. Furthermore, Lattice is incentive compatible in that collaborators cannot get better service by lying, and it incentivizes deployment by giving preferential treatment to packets carrying Lattice-related information. Finally, Lattice-enabled classifiers remain semantically equivalent to their unmodified counterparts. To evaluate Lattice, we have built a prototype using the Click software router and implemented multiple Lattice-enabled classifiers. Lattice-enabled firewalls perform at least 2X faster than unmodified counterparts and scale well with the increasing number of classification rules.},
}

EndNote citation:

%0 Report
%A Agarwal, Sameer 
%A Chowdhury, Mosharaf 
%A Joseph, Dilip 
%A Stoica, Ion 
%T Lattice: A Scalable Layer-Agnostic Packet Classification Framework
%I EECS Department, University of California, Berkeley
%D 2011
%8 August 24
%@ UCB/EECS-2011-96
%U http://www2.eecs.berkeley.edu/Pubs/TechRpts/2011/EECS-2011-96.html
%F Agarwal:EECS-2011-96