The Ultimate Linux Box 2001: How to Design Your Dream Machine
Editor's Note: The following article is the unabridged version of an article by the same title that appears in the November 2001 issue of Linux Journal.
Five years ago, in a Linux Journal article I wrote during 1996, I developed a recipe for an elegant and economical Linux box. I used this as motivation for a discussion of what makes a good balanced system design. The article became one of the most popular in LJ's history, so the editors have invited me back for a second round.
This time, however, we're going to involve more people than just me. LJ recruited Rick Moen, author of some well-known FAQs on modems and other hardware topics, to assist with this article. Daryll Strauss, the man behind the famous all-Linux rendering farm used in the movie “Titanic”, also contributed sage advice coming from his background in graphics and extreme data crunching.
Also, we're going to examine system architecture from a different perspective. Instead of going for economy we're going to go for the balls-out maximum crunching power. This time, we're going to ask not what the most cost-effective plan is, but how to get the absolute highest performance out of hardware we can live with.
“Hardware you can live with” means a machine that is stable, easy to troubleshoot and inexpensive to maintain after the original money-is-no-object build phase. It should be small and low-maintainance enough enough to live beside your desk, as opposed to (say) some liquid-cooled monstrosity that needs to be nursed by a full-time technician. It should be, in short, a PC—an extraordinary gold-plated hand-tuned hotrod of a PC but a PC nevertheless. Another important aspect of liveability is level of emitted acoustic noise and heat; we'll be paying attention to minimizing both as we design.
We'll stick with Intel hardware. Alphas are fast and have that wonderful sexy 64-bit architecture with enough symmetrical registers to make an old compiler jock like me drool copiously, but the line has just been sold to Intel and seems all too likely to be end-of-lifed in favor of the Itanium before long. The PowerPC has earned its fans, too—considered in isolation, I like that chip a lot better than any Intel architecture. But PC hardware has all the advantages of the biggest market; it's the easiest to get serviced and least expensive to upgrade, and thus scores high on the hardware-you-can-live-with scale.
The “ultimate Linux box” that we showcase as a result will, of course, inevitably fall behind the leading edge within months. But walking through the process of developing the ULB should will teach you things about system design and troubleshooting that you can continue applying long after the hardware in this article has become obsolete.
|Non-Linux FOSS: libnotify, OS X Style||Jun 18, 2013|
|Containers—Not Virtual Machines—Are the Future Cloud||Jun 17, 2013|
|Lock-Free Multi-Producer Multi-Consumer Queue on Ring Buffer||Jun 12, 2013|
|Weechat, Irssi's Little Brother||Jun 11, 2013|
|One Tail Just Isn't Enough||Jun 07, 2013|
|Introduction to MapReduce with Hadoop on Linux||Jun 05, 2013|
- Containers—Not Virtual Machines—Are the Future Cloud
- Non-Linux FOSS: libnotify, OS X Style
- Linux Systems Administrator
- Validate an E-Mail Address with PHP, the Right Way
- Lock-Free Multi-Producer Multi-Consumer Queue on Ring Buffer
- Technical Support Rep
- Senior Perl Developer
- UX Designer
- Introduction to MapReduce with Hadoop on Linux
- Weechat, Irssi's Little Brother
Free Webinar: Hadoop
How to Build an Optimal Hadoop Cluster to Store and Maintain Unlimited Amounts of Data Using Microservers
Realizing the promise of Apache® Hadoop® requires the effective deployment of compute, memory, storage and networking to achieve optimal results. With its flexibility and multitude of options, it is easy to over or under provision the server infrastructure, resulting in poor performance and high TCO. Join us for an in depth, technical discussion with industry experts from leading Hadoop and server companies who will provide insights into the key considerations for designing and deploying an optimal Hadoop cluster.
Some of key questions to be discussed are:
- What is the “typical” Hadoop cluster and what should be installed on the different machine types?
- Why should you consider the typical workload patterns when making your hardware decisions?
- Are all microservers created equal for Hadoop deployments?
- How do I plan for expansion if I require more compute, memory, storage or networking?