Reliable performance evaluations require the use of representative workloads. This is no easy task since modern computer systems and their workloads are complex, with many interrelated attributes and complicated structures. Experts often use sophisticated mathematics to analyze and describe workload models, making these models difficult for practitioners to grasp. This book aims to close this gap by emphasizing the intuition and the reasoning behind the definitions and derivations related to the workload models. It provides numerous examples from real production systems, with hundreds of graphs. Using this book, readers will be able to analyze collected workload data and clean it if necessary, derive statistical models that include skewed marginal distributions and correlations, and consider the need for generative models and feedback from the system. The descriptive statistics techniques covered are also useful for other domains.
|Publisher:||Cambridge University Press|
|Product dimensions:||7.17(w) x 10.24(h) x 1.18(d)|
About the Author
Dror G. Feitelson is a Professor of Computer Science at the Hebrew University of Jerusalem. He is a founding co-organizer of a series of international workshops on job-scheduling strategies for parallel processing and of the ACM Experimental Computer Science Workshop. He maintains the Parallel Workloads Archive, a widely used community resource with logs of activity on parallel supercomputers.
Table of Contents
1. Introduction; 2. Workload data; 3. Statistical distributions; 4. Fitting distributions to data; 5. Heavy tails; 6. Correlations in workloads; 7. Self-similarity and long-range dependence; 8. Hierarchical generative models; 9. Case studies; 10. Summary and outlook.