AN ADAPTIVE PSEUDOSERVING BASED INTERNET SERVER LOAD SHARING SCHEME

Abstract

For the past few years. surveys continue to report long download times, as the number one reason users are dissatisfied with the Internet [2]. The different bottlenecks suffered by data on the Internet can be categorized according to the location of the problem. These are identified as client side congestion, network congestion and server congestion. Server-side congestion arises when a large number of users wish to retrieve files from a server over a short period of time. Under such conditions, the users who have obtained popular files from a busy server are in possession of a valuable resource. These users are in a unique position to benefit enormously by sharing retrieved files. Pseudoserving. a new paradigm for Internet access, provides incentives for users to contribute to the speedy dissemination of server files, through a contract set by a superserver. Under this contract, the superserver grants a user, a referral, to where a copy of the requested file may be retrieved, in exchange for the user's assurance to serve other users for a specified period of time. In this thesis a simulation study, that considers only congestion occurring near the server has been done. It demonstrates the benefit of pseudoserving in reducing download times and network traffic. Simulations have shown that: 1. Pseudoserving scales itself to handle very high request rates. 2. Users, who participate as pseudoservers, benefit enormously in return for a relatively small contribution of their resources. 3. Pseudoserving is robust under realistic conditions, because it can tolerate a large number of dishonest users. The simulation program is written in Java 2 and is tested on a Pentium under Linux environment.