Systems Performance: Enterprise and the Cloud

Long ago, the prerequisite UNIX performance book was Adrian Cockcroft's 1994 classic, Sun Performance and Tuning: Sparc & Solaris, later updated in 1998 as Java and the Internet. As Solaris evolved to include the invaluable DTrace observability features, new essential performance references have been published, such as Solaris Performance and Tools: DTrace and MDB Techniques for Solaris 10 and OpenSolaris (2006) by McDougal, Mauro, and Gregg, and DTrace: Dynamic Tracing in Oracle Solaris, Mac OS X and FreeBSD (2011), also by Mauro and Gregg.Much has occurred in Solaris Land since those books appeared, notably Oracle's acquisition of Sun Microsystems in 2010 and the demise of the OpenSolaris community. But operating system technologies have continued to improve markedly in recent years, driven by stunning advances in multicore processor architecture, virtualization, and the massive scalability requirements of cloud computing.A new performance reference was needed, and I eagerly waited for something that thoroughly covered modern, distributed computing performance issues from the ground up. Well, there's a new classic now, authored yet again by Brendan Gregg, former Solaris kernel engineer at Sun and now Lead Performance Engineer at Joyent.Systems Performance: Enterprise and the Cloud is a modern, very comprehensive guide to general system performance principles and practices, as well as a highly detailed reference for specific UNIX and Linux observability tools used to examine and diagnose operating system behaviour. It provides thorough definitions of terms, explains performance diagnostic Best Practices and "Worst Practices" (called "anti-methods"), and covers key observability tools including DTrace, SystemTap, and all the traditional UNIX utilities like vmstat, ps, iostat, and many others.The book focuses on operating system performance principles and expands on these with respect to Linux (Ubuntu, Fedora, and CentOS are cited), and to Solaris and its derivatives [1]; it is not directed at any one OS so it is extremely useful as a broad performance reference.The author goes beyond the intricacies of performance analysis and shows how to interpret and visualize statistical information gathered from the observability tools. It's often difficult to extract understanding from voluminous rows of text output, and techniques are provided to assist with summarizing, visualizing, and interpreting the performance data.Gregg includes myriad useful references from the system performance literature, including a "Who's Who" of contributors to this great body of diagnostic tools and methods.This outstanding book should be required reading for UNIX and Linux system administrators as well as anyone charged with diagnosing OS performance issues. Moreover, the book can easily serve as a textbook for a graduate level course in operating systems [2].[1] Solaris 11, of course, and Joyent's SmartOS (developed from OpenSolaris)[2] Gregg has taught system performance seminars for many years; I have also taught such courses...this book would be perfect for the OS component of an advanced CS curriculum.

As expected, this book is primarily for the Linux or Solaris System Administrators. But, I found it very useful in understanding how to measure and diagnose issues with CPU, memory, storage, and networking.Gregg promotes his USE methodology for investigating performance issues: Utilisation—how much of a resource is being used? Saturation—is the resource fully utilised? Errors—are there errors concerning the resource? Some resource managers fail requests rather than queue themHe provides a whole chapter on how he solved a difficult performance problem through the use of this method.Gregg also covers benchmarking: "Benchmarking is surprisingly difficult to do well, with many opportunities for mistakes and oversights."Gregg is a big fan of dtrace and provides numerous scripts throughout the book, and in the appendix.I will have to read the book again sometime soon in order to pick more ideas about performance tuning and diagnosis.

I can still remember when i was downloading Brendan Gregg webinars about disk I/Os. It was obvious, this guy knew a lot about it and could explain it in most efficient way. I was just getting frustrated that all this knowledge was not put into a book. A few years later the "precious" is here ! This book is simply amazing, covering all possible aspects of system performance. You will not be overwhelmed : Brendan knows how to find a good balance between over simplification and too much details. You will learn what you really need to know (the internals), the good methods, the right tools. I can't thank enough Brendan Gregg to bring this new master piece i was waiting for so long.If you're a system administration, a developper, a "true" database administrator trying to understand how your database is likely to interact with the operating system & hardware, here you are. You can't afford to miss this book.

I found this to be an excellent resource. I've been reading it slowly in my spare time and on plane rides and it's a big book, I'm about half way now.The book is well written and I enjoy the breadth and depth of the topics. Each of which is covert from a near beginner to an almost expert level. Which is good for me because my understanding of the topics Brendan covers spans the same range, some I've barely heard of others I use almost every week.He does cover both Linux and Solaris which make some of the procedure descriptions a bit repetititve but we do have a 90-10 split of Linux and Solaris machines and I may get stuck on a Solaris box one of these days.My only criticism so far is the glossary could be more complete, I would like to have had EVERY acronym he uses in there because of the slow pace, I'm reading I don't remember the ones we don't use. Very common problem.I'm using it to increase my skills in tracking down performance problems in software I develop and deploy for an international scientific collaboration. Fortunately for me, I haven't had a hard performance problem since I started reading the book, but I'm not sure how quickly I could use such a tome to solve a specific problem. On the other hand I have used many things I've learned to gain a better understanding of things that are working.I like most of the reviewers so far would recommend it for anyone with even basic skills who is interested in understanding the issues affecting System Performance.I gave it 4 stars instead of 5 because of how broad an audience it addresses. While that's a good thing in that people can find what they need it also means there is a lot they don't need. Nobody would write a book like this that only had what I need on the topic but I'm saving the 5 star rating for something that knocks my socks off. This is well worth the price if you take the time to not only read it but become familiar with the techniques presented.

Este libro es una referencia indispensable si trabajas en IT y eres SysAdmin. No es requisito saber programar en el ambiente Linux pero es deseable tener fundamentos de arquitectura del kernel y haber programado en algún lenguage de bajo nivel para sacarle el máximo provecho a todo el material que se presenta.

The book is full of valuable knowledge and experience. Don't get distracted by the fact it is a bit older, it worths the money.

Lettura utile per chiunque lavori nel settore IT, non solo per chi è interessato al tema delle performance. Da tenere a portata di mano sempre.

The material covers the details of “why” without being a pure theoretical explanation, very pragmatic.Books should more be written with such an approach.Congrats to the author!

It's an amazing book. If you're a system administrator, you should read this book!