Enhanced inferencing: estimation of a workload dependent performance model

  • Authors:
  • Dinesh Kumar;Li Zhang;Asser Tantawi

  • Affiliations:
  • IBM T.J. Watson Research Center, Hawthorne, NY;IBM T.J. Watson Research Center, Hawthorne, NY;IBM T.J. Watson Research Center, Hawthorne, NY

  • Venue:
  • Proceedings of the Fourth International ICST Conference on Performance Evaluation Methodologies and Tools
  • Year:
  • 2009

Quantified Score

Hi-index 0.00



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.