Analytical performance modeling for computer systems / Y.C. Tay.

Format:

Book

Author/Creator:

Tay, Y. C., author.

Series:

Synthesis digital library of engineering and computer science.

Synthesis lectures on computer science, 1932-1686 ; # 7.

Synthesis lectures on computer science, 1932-1686 ; # 7

Language:

English

Subjects (All):

Computer systems--Reliability--Mathematical models.

Computer systems.

Physical Description:

1 online resource (149 p.)

Edition:

Second edition.

Place of Publication:

San Rafael, California (1537 Fourth Street, San Rafael, CA 94901 USA) : Morgan & Claypool, 2014.

Language Note:

English

Summary:

This book is an introduction to analytical performance modeling for computer systems, i.e., writing equations to describe their performance behavior. It is accessible to readers who have taken college-level courses in calculus and probability, networking and operating systems. This is not a training manual for becoming an expert performance analyst. Rather, the objective is to help the reader construct simple models for analyzing and understanding the systems that they are interested in. Describing a complicated system abstractly with mathematical equations requires a careful choice of assumptions and approximations. They make the model tractable, but they must not remove essential characteristics of the system, nor introduce spurious properties. To help the reader understand the choices and their implications, this book discusses the analytical models for 30 research papers. These papers cover a broad range of topics: processors and disks, routers and crawling, databases and multimedia, worms and wireless, multicore and cloud, etc. An appendix provides many questions for readers to exercise their understanding of the models in these papers.

Contents:

0. Preliminaries

1. Concepts and Little's law

Concepts

Open and closed systems

Little's law

Discussion of papers

2. Single queues

Applying Little's law to a 1-server queue

Queue specification

Pollaczek-Khinchin formula

Discussionof papers

3. Open systems

Residual life

Birth-death process

Open queueing networks: Jackson networks

4. Markov chains

Markov chain for a closed network

Markov chain for a multi-class network

State aggregation

5. Closed systems

PASTA

Arrival theorem

Mean value analysis (MVA)

6. Bottlenecks and flow equivalence

Bottleneck analysis

Flow equivalence

Equivalence between open and closed

7. Deterministic approximations

Average value approximation (AVA)

Fluid approximation

8. Transient analysis

Decomposing an equilibrium

Epidemic models

9. Experimental validation and analysis

Case study: database transaction locking

Model validation and experimental analysis

The need for validation

Data presentation

Real systems and workloads

Simulation

Parameter space reduction

Uninteresting regions of parameter space

Quantitative prediction vs. qualitative understanding

Analytic validation

10. Analysis with an analytical model

The science & art in performance modeling

Power

Technique

Assumptions and approximations

Metrics

Science and technology

Intuition and contradiction

A. Exercises

Bibliography

Author's biography.

Notes:

Part of: Synthesis digital library of engineering and computer science.

Series from website.

Includes bibliographical references (pages 119-123).

Title from PDF title page (viewed on November 12, 2013).

Cited in:

Compendex

INSPEC

Google scholar

Google book search

ISBN:

1-62705-270-4

OCLC:

861559698