© University of Kent - Contact | Feedback | Legal | FOI | Cookies
Permabase: predicting the performance of distributed systems at the design stage
G. Waters, P. Linington, D. Akehurst, P. Utton, and G. Martin
IEE Proceedings - Software, 148(4):182-196, August 2001.Abstract
The use of distributed systems is now critical to many organisations. Designing software for these systems can be complex and there are growing demands on the performance of systems as they become increasingly large-scale. Timeliness is no longer just a matter of response time, as there can be stringent delay requirements for real-time multimedia traffic. In this paper we describe the Permabase project funded by BT, which produced prototypes to predict software performance automatically at the systems design stage. The paper discusses the Permabase rationale and describes the architecture and details of the prototype systems and its validation using case studies. We discuss the use of UML as a mechanism for capturing the information needed for performance prediction modelling and show how translation enabled us to produce simulation models. We review the achievements of the project and look forward to ways in which the work could be enhanced and built upon to encompass a greater range of systems.
Bibtex Record
@article{1292,
author = {G. Waters and P. Linington and D. Akehurst and P. Utton and G. Martin},
title = {Permabase: predicting the performance of distributed systems at the design stage},
month = {August},
year = {2001},
pages = {182-196},
keywords = {determinacy analysis, Craig interpolants},
note = {},
doi = {},
url = {http://www.cs.kent.ac.uk/pubs/2001/1292},
publication_type = {article},
submission_id = {13076_1001080287},
journal = {IEE Proceedings - Software},
volume = {148},
number = {4},
publisher = {IEE},
ISSN = {1462-5970},
}