Enhanced Inferencing: Estimation of a Workload Dependent Performance Model

Performance modeling of software systems is vital for predictive analysis of their performance and capacity planning of the host environment. Robust performance prediction and efficient capacity planning highly depend on an accurate estimation of the underlying model parameters. AMBIENCE, which is a prototype tool developed at IBM Research, makes use of the powerful Inferencing technique to generate a workload-independent parameters based performance model. However, modern software systems are quite complex in design and may exhibit variable service times and overheads at changing workloads. In this work, we extend the Inferencing technique for generating workload-dependent service time and CPU overhead based performance models. We call this extended form as Enhanced Inferencing. Implementation of Enhanced Inferencing in AMBIENCE shows significant improvement of the order of 26 times over Inferencing. We further present a case study where Enhanced Inferencing provides a quantitative performance difference between consolidated and partitioned software system installations. Ability to carry out such evaluations can have significant impact on capacity planning of software systems that are characterized by workload-dependent model parameters.

By: Dinesh Kumar; Li Zhang; Asser Tantawi

Published in: RC24894 in 2009

LIMITED DISTRIBUTION NOTICE:

This Research Report is available. This report has been submitted for publication outside of IBM and will probably be copyrighted if accepted for publication. It has been issued as a Research Report for early dissemination of its contents. In view of the transfer of copyright to the outside publisher, its distribution outside of IBM prior to publication should be limited to peer communications and specific requests. After outside publication, requests should be filled only by reprints or legally obtained copies of the article (e.g., payment of royalties). I have read and understand this notice and am a member of the scientific community outside or inside of IBM seeking a single copy only.

rc24894.pdf

Questions about this service can be mailed to reports@us.ibm.com .