» » Analyzing Computer System Performance with Perl::PDQ
Download Analyzing Computer System Performance with Perl::PDQ epub book
ISBN:3642225829
Author: Neil J. Gunther
ISBN13: 978-3642225826
Title: Analyzing Computer System Performance with Perl::PDQ
Format: rtf lit lrf mbr
ePUB size: 1270 kb
FB2 size: 1887 kb
DJVU size: 1474 kb
Language: English
Category: Programming
Publisher: Springer; 2nd ed. 2011 edition (August 4, 2011)
Pages: 474

Analyzing Computer System Performance with Perl::PDQ by Neil J. Gunther



Analyzing computer system performance is often regarded by most system administrators, IT professionals and software engineers as a black art that is too time consuming to learn and apply. is a leading industry computer performance consultant who founded Performance Dynamics Company (ww. erfdynamics. His performance and capacity planning classes have been presented at such organizations as Boeing, Fedex, Motorola, Stanford University, and Sun Microsystems.

Analyzing computer system performance is often regarded by most system administrators, IT professionals and software engineers as a black art that is too time consuming to learn and apply. Finally, this book by acclaimed performance analyst Dr. Neil Gunther makes this subject understandable and applicable through programmatic examples.

Analyzing Computer System. has been added to your Cart. The book is written to be a field manual for enlightened practitioners of performance analysis, or possibly a school textbook. As the epigraph in this book points out, Common sense is the pitfall of performance.

Start by marking Analyzing Computer System Performance with Perl: : PDQ as Want to Read: Want to Read savin. ant to Read. Presents the practical application of these concepts in the context of modern, distributed, computer system designs.

Описание: To solve performance problems in modern computing infrastructures, often comprising thousands of servers running hundreds of applications, spanning multiple tiers, you need tools that go beyond mere reporting. You need tools that enable performance analysis of application workflow across the entire enterprise. The PDQ manual has been relegated to an appendix in Part IV, along with solutions to the exercises contained in each chapter. Throughout, the Perl code listings have been newly formatted to improve readability.

PDQ is an open-source performance analyzer based on the paradigm of queues. Queues are ubiquitous in every computing environment as buffers, and since any application architecture can be represented as a circuit of queueing delays, PDQ is a natural fit for analyzing system performance.

To solve performance problems in modern computing infrastructures, often comprising thousands of servers running hundreds of applications, spanning multiple tiers, you need tools that go beyond mere reporting. You need tools that enable performance analysis of application workflow across the entire enterprise. That's what PDQ (Pretty Damn Quick) provides. PDQ is an open-source performance analyzer based on the paradigm of queues. Queues are ubiquitous in every computing environment as buffers, and since any application architecture can be represented as a circuit of queueing delays, PDQ is a natural fit for analyzing system performance.

 

Building on the success of the first edition, this considerably expanded second edition now comprises four parts. Part I contains the foundational concepts, as well as a new first chapter that explains the central role of queues in successful performance analysis. Part II provides the basics of queueing theory in a highly intelligible style for the non-mathematician; little more than high-school algebra being required. Part III presents many practical examples of how PDQ can be applied. The PDQ manual has been relegated to an appendix in Part IV, along with solutions to the exercises contained in each chapter.

Throughout, the Perl code listings have been newly formatted to improve readability. The PDQ code and updates to the PDQ manual are available from the author's web site at www.perfdynamics.com
Reviews: 3
Ausstan
My review of the 1st edition is below so I won't repeat it again.

http://www.amazon.com/Analyzing-Computer-System-Performance-Perl/dp/3642058833/

The 2nd edition has several newly written introductory chapters to provide the needed
context for someone new to performance analysis, for example, the new introduction
to queueing theory is an wonderful exposition for a newbie. I only wished I had the
2nd edition when I bought the 1st edition.

Here is the link to more details on Dr. Gunther's site.

[...]

Now all we need is a Kindle edition.
Quamar
In this book and its predecessor, "Guerrilla Capacity Planning", Dr. Neil Gunther provides a useful introduction to the topic of measuring and modeling the scalability of parallel computer systems. The model that he advocates in his books is a useful starting point; however, this model fails to provide a sufficiently general basis for modeling the behavior of the wide variety of current parallel computer systems.

The "universal scalability law" to which he refers on p. 5 extends Amdahl's Law via the addition of a "queuing" term that models effects such as data exchange between parallel processes. And although Dr. Gunther suggests that this queuing term ought to grow linearly with the number of parallel processes, this queuing term depends on the specific communication architecture of the computer system and can grow non-linearly, for example, as log to the base two of the number of processes.

This logarithmic growth law can occur because one processor may not communicate directly with all other processors. Instead, one processor may send information to two other processors, and each of those two processors may send information to two more processors, and so forth. Therefore, in order to model the communication that occurs in such a communication cascade, the queuing term should grow as log(n).

Moreover, performance data that are obtained from current parallel computer systems do not always conform to Dr. Gunther's "universal" scalability "law" under other conditions. For example, a large volume of data that exceeds the capacity of the total cache memory when distributed across a few processors may well fit into total cache memory when distributed across a larger number of processors. Under these conditions, the scalability for the larger number of processors appears to grow "super-linearly" relative to the scalability of a few processors. However, on p. 5 of his book, Dr. Gunther states that "the data showed efficiencies of greater than 100%, which is simply not possible." Efficiencies of greater than 100% are not only possible, they are commonly observed due to cache memory effects. Thus, although Dr. Gunther's book is a useful introduction to the subject of measuring and modeling the behavior of parallel computer architectures, his universal scalability law should not be considered to be universal.
Yanthyr
For me this book is way too wordy. There are lots of useless long winded anecdotes and asides. I appreciate the author trying to not be dry to an extent but its too much for me and gets annoying when you just want to get straight into it. Some of the technical content is presented well but still in a long winded and imprecise fashion. I get the feeling the author can't help himself.