Modeling RPC performance

  • Authors:
  • J. A. Rolia;M. Starkey;G. Boersma

  • Affiliations:
  • Carleton University;Carnegie Mellon University;Carleton University

  • Venue:
  • CASCON '93 Proceedings of the 1993 conference of the Centre for Advanced Studies on Collaborative research: distributed computing - Volume 2
  • Year:
  • 1993

Quantified Score

Hi-index 0.00

Visualization

Abstract

Distributed computing applications are collections of processes allocated across a network that cooperate to accomplish common goals. The applications require the support of a distributed computing runtime environment that provides services to help manage process concurrency and interprocess communication. This support helps to hide much of the inherent complexity of distributed environments via industry standard interfaces and permits developers to create more portable applications. The resource requirements of the runtime services can be significant and may impact application performance and system throughput. This paper describes work done to study the performance behaviour of an application server executing within a distributed computing environment (DCE) on an AS/400 communicating with other processes via the remote procedure call (RPC) Mechanism. The results of the study provide insight into the potential benefits of redesigning some aspects of the current DCE RPC, its current implementation on the AS/400, and provide guidance to those developing DCE applications.