Measurements and Analysis of M/M/1 and M/M/c Queuing Models of the SIP Proxy Server

In recent years, Internet Protocol (IP) telephony has been a real alternative to the traditional Public Switched Telephone Networks (PSTN). IP telephony offers more flexibility in the implementation of new features and services. The Session Initiation Protocol (SIP) is becoming a popular signaling protocol for Voice over IP (VoIP) based applications. The SIP Proxy server is a software application that provides call routing services by parsing and forwarding all the incoming SIP packets in an IP telephony network. The efficiency of this process can create large scale, highly reliable packet voice networks for service providers and enterprises. We established that the efficient design and implementation of the SIP Proxy server architecture can enhance the performance characteristics of a SIP Proxy server significantly. Since SIP Proxy server performance can be characterized by its transaction states of each SIP session, we emulated the M/M/1 performance model of the SIP Proxy Server and studied some of the key performance benchmarks such as average response time to process the SIP calls and mean number of SIP calls in the system. We showed its limitations, and then studied an alternative M/M/c based SIP Proxy Server performance model with enhanced performance and predictable results. Index Terms—SIP, Performance, M/M/1,M/M/c in the SIP Proxy Server software, which forms a central part of the control plane corresponding to the VoIP data plane. Our key contribution in this paper is obtaining a better understanding of the performance of the SIP Proxy system. We emulated the M/M/1 queuing model proposed in (7), obtained the analytical results and compared them with exper- iments performed on a real SIP Proxy Server. Motivated by our understanding of the SIP Proxy Server software architecture, we proposed a less complex, more predictable, and more realistic SIP Proxy Server based on M/M/c queuing model. Current trends in server architecture make this model more suitable than the M/D/1 model we proposed in (18). In M/M/cmodel, we considered a single proxy server with mul- tiple threads to process all the incoming SIP calls generated from SIP endpoints. To avoid the propagation delay between the proxy servers, we considered a single proxy server in this model. This paper is organized as follows: Section II addresses the background information on SIP and SIP Proxy Server; Section III provides the motivation for this research; Section IV defines the actual M/M/cbased modeling of the SIP Proxy Server, followed by the analytical and experimental results of the M/M/1 and M/M/c models in Section V; Section VI details the comparative study of the results of the SIP Proxy Server models.