Managing RAID on Linux - Derek Vadala [3]
* * *
* * *
Warning
These icons indicate a warning or caution.
* * *
Comments and Questions
Please address comments and questions concerning this book to the publisher:
O'Reilly & Associates, Inc.
1005 Gravenstein Highway North
Sebastopol, CA 95472
(800) 998-9938 (in the U.S. or Canada)
(707) 829-0515 (international/local)
(707) 829-0104 (fax)
To comment or ask technical questions about this book, send email to:
bookquestions@oreilly.com
O'Reilly has a web site for this book, where they'll list examples, errata, and any plans for future editions. The site also includes a link to a forum where you can discuss the book with the author and other readers. You can access this site at:
http://www.oreilly.com/catalog/mraidlinux/
For more information about books, conferences, Resource Centers, and the O'Reilly Network, see the O'Reilly web site at:
http://www.oreilly.com
Acknowledgments
Many people helped with the writing of this book, but the greatest credit is owed to Andy Oram, my editor. It was his early interest in my original proposal that started this project, and his suggestions, criticism, and raw editorial work turned this text from a draft into an O'Reilly book. I'm also indebted to many people at O'Reilly, for all their hard work on the numerous tasks involved in producing a book.
Neil Brown, Nick Moffitt, Jakob Oestergaard, and Levy Vargas reviewed the final draft for technical errors and provided me with essential feedback. Their insight and expertise helped make this book stronger. Many others helped review various bits of material along the way, including Joel Becker, Martin Bene, Danny Cox, Jim Ford, Corin Hartland-Swann, Dan Jones, Eyal Lebedinsky, Greg Lehey, Ingo Molnar, and Benjamin Turner.
Thanks to all the filesystem developers who offered me feedback on Chapter 6: Stephen C. Tweedie, Seth Mos, Steve Lord, Steve Best, Theodore Ts'o, Vladimir V. Saveliev, and Hans Reiser. My appreciation also goes out to all the vendors who provided me with software, equipment, and comments: Thomas Bayens, Chin-Tien Chu, and Thomas Hall at IBM; Angelina Lu and Deanna Bonds at Adaptec; Craig Lyons and Daron Keith at Promise; James Evans at LSI Logic; Pete Kisich, Kathleen Paulus, and Adam Radford at 3ware; Joey Lai at Highpoint Technologies; Mathilde Kraskovetz at Mandrake; and Harshit Mehta at SuSE.
Thanks to my family and friends, who provided support and countless favors while I was writing this book, especially Dallas Wisehaupt, Philippe Stephan, Stephen Fisher, Trevor Noonan, Carolyn Keddy, Erynne Simpson, David Perry, Benjamin Richards, Matthew Williams, Peter Pacheco, Eric Bronnimann, Al Lenderink, Ben Feltz, and Erich Bechtel.
I owe special thanks to Craig Newmark, Jim Buckmaster, Jeff Green, and the entire staff of Craigslist.org for graciously providing me with office space and Internet access during my many excursions to San Francisco. Their hospitality directly resulted in the writing of Chapter 2. And finally, thanks especially to Eric Scheide, who encouraged me to write the original proposal for this book, gave me my first job as a Unix system administrator, and didn't argue as I slowly retired Ultrix and Solaris machines in favor of Linux.
Chapter 1. Introduction
Every system administrator sooner or later realizes that the most elusive foe in sustaining reliable system performance is bandwidth. On one hand, network connectivity provides a crucial connection to the outside world through which your servers deliver data to users. This type of bandwidth, and its associated issues, is well documented and well studied by virtually all system and network administrators. It is at the forefront of modern computing, and the topic most often addressed by both non-technical managers and the mainstream media. A multitude of software and documentation has been written to address network and bandwidth issues. Most administrators, however, don't realize that similar bandwidth problems exist at the bus level in each system you manage.