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.
|Using tshark to Watch and Inspect Network Traffic||Aug 31, 2015|
|Where's That Pesky Hidden Word?||Aug 28, 2015|
|A Project to Guarantee Better Security for Open-Source Projects||Aug 27, 2015|
|Concerning Containers' Connections: on Docker Networking||Aug 26, 2015|
|My Network Go-Bag||Aug 24, 2015|
|Doing Astronomy with Python||Aug 19, 2015|
- Problems with Ubuntu's Software Center and How Canonical Plans to Fix Them
- Concerning Containers' Connections: on Docker Networking
- A Project to Guarantee Better Security for Open-Source Projects
- Where's That Pesky Hidden Word?
- Firefox Security Exploit Targets Linux Users and Web Developers
- My Network Go-Bag
- Doing Astronomy with Python
- Build a “Virtual SuperComputer” with Process Virtualization
- Three More Lessons
- diff -u: What's New in Kernel Development