Local area networks (LANs) are important for an enterprise to hold a competitive edge. Many companies have therefore converted terminal-based computing systems to LAN-based distributed data processing systems. This paper proposes a design methodology for distributed databases connected by a LAN. Two primary objectives of the methodology are: (i) to allocate data files and workload among heterogeneous servers; and (ii) to determine the number of servers to satisfy the response time required for processing each transaction. The file and workload allocation decision is formulated as a nonlinear zero-one integer programming problem. This problem is proven to be NP-complete. A heuristic is developed to solve this problem effectively. A decision support system is implemented and an example is solved to illustrate the practical usefulness of the system. (C) 2000 Elsevier Science B.V. All rights reserved.