An adaptive scheduling scheme for dynamic service time allocation on a shared resource

Abstract

A scheduling scheme that allows a number of customers to share a common resource in an efficient and fair way is presented. Each customer is allowed to use the resource for an amount of time that does not exceed a certain limit, the limit being a function of the waiting time elapsed between the time of its last request and the time of access to the resource. After expiration of the service time allocated to a customer, if more service is still needed, the customer has to re-enter the request queue and issue a new service request. The scheme combines the advantages of both processor-sharing and first-come, first-served disciplines in a dynamic way. The applicability and the advantages of the scheme in both open and closed system environments are discussed.