Options
Optimal allocation of clients to file servers
Date Issued
25-09-1997
Author(s)
Ammaiyar, D. Vasuki
Raghavan, S. V.
Abstract
The transparent way in which the remote resources are shared with improved performance justify the rapid replacement of single Large Computer Systems by Local Area Networks (LANs). Information (data) sharing is one of the major goals of LANs and file servers are one of the means of supporting data sharing in LAN environments. A typical LAN might have one or more file servers and in a network consisting of multiple file servers making effective use of them is an important design issue. One of the means of effectively utilizing the file servers is to restrict the number of clients using the server (Client Server Allocation Problem). The existing techniques for solving the client server allocation problem either treat the clients on the network as statistically identical or treat them as entirely independent. However, the evaluation studies conducted in the context of computer networks show that clients on a network are neither identical nor entirely independent, but can be grouped into different classes based on their workload generation pattern. Thus, an algorithm which solves the client server allocation problem taking care of the workload generation pattern is required. In this paper, we propose a new iterative algorithm for solving such problems based on the concept of demand inflation. The time and space complexities of the proposed algorithm are compared with that of the existing algorithms. The application of the proposed algorithm is illustrated with an example. © 1997 Elsevier Science B.V.
Volume
20