Analytic response time model for distributed systems

  • Authors:
  • Janice H. Cook;Leo H. Groner

  • Affiliations:
  • IBM Corporation, Dept. 848, Bldg. 2, Somers, NY;IBM Corporation, Dept. 33PA, Bldg. 962-l-3-37, Kingston, NY

  • Venue:
  • APL '90 Conference proceedings on APL 90: for the future
  • Year:
  • 1990

Quantified Score

Hi-index 0.00

Visualization

Abstract

Network designers are faced with a combinatorial explosion of choices not only among various vendors' workstations, hosts and servers, but also among application distribution strategies, communication media, communication protocols, and network topologies. To study performance trade-offs among various designs, the authors have developed a generic system thruput and response time model for distributed systems. We have applied the model to actual customer networks.The modeller describes the system in a language of model statements describing operations, resources, submodels, parameters and transactions flows. Model statements are “compiled” into arrays that form the input to the analytical queueing network model.The modeling package is written in APL2 and is based on an earlier VSAPL package developed for manufacturing planning. Since the package is designed with an open set of submodel types, and since APL2 is portable across many architectures and operating systems, we can easily integrate non-APL2 code.