A GSPN model for the analysis of DNS-based redirection in distributed Web systems

• Main Authors: Gaeta, R., Gribaudo, M., Manini, D., Sereno, M.
• Format: Conference Proceeding
• Language: English
• Subjects: Access methods and protocols, osi model; Analytical models; Applied sciences; Computational modeling; Computer simulation; Exact sciences and technology; Interconnected networks; Networks and services in france and abroad; Systems, networks and services of telecommunications; Telecommunication computing; Telecommunications; Telecommunications and information theory; Teleprocessing networks. Isdn; Teletraffic
• ISSN: 1526-7539; 2375-0227
• DOI: 10.1109/MASCOT.2004.1348180

The rapid growth of the Internet, in both user numbers and Web content, has fueled extensive efforts to improve the user's overall Internet experience. A growing number of providers deliver content from multiple servers or proxies to reduce response time by moving content closer to end users. An increasingly popular mechanism to direct client requests towards one of the replica servers is DNS-based redirection. In this mechanism, the authoritative domain name server (ADNS) of the Web site takes the request dispatcher role by mapping the URL host name into the IP address of one of the replica servers (both locally and geographically distributed). However, the ADNS controls only a very small fraction of the requests reaching the Web site because the address mapping is not requested for each client access. Indeed, to reduce Internet traffic due to DNS requests, address resolution is cached at various name servers for a time-to-live (TTL) period, opening a new set of problems not addressed in classical centralized schedulers of parallel and/or distributed systems. We present an approximate generalized stochastic Petri nets (GSPN) model for the analysis of the workload offered to replica servers in a DNS based redirection architecture. Different dispatching algorithms, as well as different strategies to manage TTL assignment at the ADNS, are considered to show the potential of the GSPN based analysis.