The Community for Technology Leaders
Green Image
Issue No. 11 - November (2011 vol. 22)
ISSN: 1045-9219
pp: 1804-1812
Patrick Traynor , Georgia Institute of Technology, Atlanta
Vijay Balasubramaniyan , Georgia Institute of Technology, Atlanta
Italo Dacosta , Georgia Institute of Technology, Atlanta
Mustaque Ahamad , Georgia Institute of Technology, Atlanta
ABSTRACT
The performance of SIP proxies is critical for the robust operation of many applications. However, the use of even light-weight authentication schemes can significantly degrade throughput in these systems. In particular, systems in which multiple proxies share a remote authentication database can experience reduced performance due to latency. In this paper, we investigate how the application of parallel execution and batching can be used to maximize throughput while carefully balancing demands for bandwidth and call failure rates. Through the use of a modified version of OpenSER, a high-performance SIP proxy, we demonstrate that the traditional recommendation of simply launching a large number of parallel processes not only incurs substantial overhead and increases dropped calls, but can actually decrease call throughput. An alternative technique that we implement, request batching, similarly fails to achieve high proxy throughput. Through a carefully selected mix of batching and parallelization, we reduce the bandwidth required to maximize authenticated signaling throughput by the proxy by more than 75 percent. This mix also keeps the call loss rates below 1 percent at peak performance. In addition, we demonstrate that the delay introduced by batching is acceptable for VoIP applications. As a result, our technique significantly reduce the cost and increase the throughput of authentication for large-scale networks supporting SIP applications.
INDEX TERMS
SIP, VoIP, digest authentication, SIP proxy performance.
CITATION
Patrick Traynor, Vijay Balasubramaniyan, Italo Dacosta, Mustaque Ahamad, "Improving Authentication Performance of Distributed SIP Proxies", IEEE Transactions on Parallel & Distributed Systems, vol. 22, no. , pp. 1804-1812, November 2011, doi:10.1109/TPDS.2011.62
98 ms
(Ver 3.1 (10032016))