Design and Implementation of a Consolidated Middlebox Architecture

Vyas Sekar, Norbert Egi, Sylvia Ratnasamy, Michael Reiter and Guangyu Shi

EECS Department
University of California, Berkeley
Technical Report No. UCB/EECS-2011-110
October 6, 2011

http://www2.eecs.berkeley.edu/Pubs/TechRpts/2011/EECS-2011-110.pdf

Most network deployments respond to changing application, workload, and policy requirements via the deployment of specialized network appliances or “middle- boxes”. Today, however, middlebox platforms are ex- pensive and closed systems, with little/no hooks for extensibility. Furthermore, they are acquired from independent vendors and deployed as standalone devices with little cohesiveness in how the ensemble of middleboxes is managed. As network requirements continue to grow in both scale and variety, this bottom-up approach leads middlebox deployments on a trajectory of growing device sprawl with corresponding escalation in capital and management costs.

To address this challenge, we present CoMb, a new architecture for middlebox deployments that systematically applies the design principle of consolidation, both at the level of building individual middleboxes and managing a network of middleboxes. This paper addresses key resource management and implementation challenges that arise in exploiting the benefits of con- solidation in middlebox deployments. Using a prototype implementation in Click, we show that CoMb can reduce the network provisioning cost by up to 2.5× and reduce the load imbalance in a network by up to 25×.


BibTeX citation:

@techreport{Sekar:EECS-2011-110,
    Author = {Sekar, Vyas and Egi, Norbert and Ratnasamy, Sylvia and Reiter, Michael and Shi, Guangyu},
    Title = {Design and Implementation of a Consolidated Middlebox Architecture},
    Institution = {EECS Department, University of California, Berkeley},
    Year = {2011},
    Month = {Oct},
    URL = {http://www2.eecs.berkeley.edu/Pubs/TechRpts/2011/EECS-2011-110.html},
    Number = {UCB/EECS-2011-110},
    Abstract = {Most network deployments respond to changing application, workload, and policy requirements via the deployment of specialized network appliances or “middle- boxes”. Today, however, middlebox platforms are ex- pensive and closed systems, with little/no hooks for extensibility. Furthermore, they are acquired from independent vendors and deployed as standalone devices with little cohesiveness in how the ensemble of middleboxes is managed. As network requirements continue to grow in both scale and variety, this bottom-up approach leads middlebox deployments on a trajectory of growing device sprawl with corresponding escalation in capital and management costs.

To address this challenge, we present CoMb, a new architecture for middlebox deployments that systematically applies the design principle of consolidation, both at the level of building individual middleboxes and managing a network of middleboxes. This paper addresses key resource management and implementation challenges that arise in exploiting the benefits of con- solidation in middlebox deployments. Using a prototype implementation in Click, we show that CoMb can reduce the network provisioning cost by up to 2.5× and reduce the load imbalance in a network by up to 25×.}
}

EndNote citation:

%0 Report
%A Sekar, Vyas
%A Egi, Norbert
%A Ratnasamy, Sylvia
%A Reiter, Michael
%A Shi, Guangyu
%T Design and Implementation of a Consolidated Middlebox Architecture
%I EECS Department, University of California, Berkeley
%D 2011
%8 October 6
%@ UCB/EECS-2011-110
%U http://www2.eecs.berkeley.edu/Pubs/TechRpts/2011/EECS-2011-110.html
%F Sekar:EECS-2011-110