Guerrilla Manifesto Online Updated

Those of you who own a copy of Guerrilla Capacity Planning, know about the little manual included in the back jacket (my editor's idea, btw). The intent is to use it as a weapon of mass instruction in your Tiger Team meetings or whatever. As my Aussie colleague, Steve Jenkin, pointed out to me at the time I was writing that book, those of you in the trenches often run into resistance when trying to propose some capacity or performance approach because you lack the authority; even if your argument is an excellent one.

The role of the Guerrilla Manifesto is to provide you with more authoritative support via the various mantras listed there. Hardcopy is good, but online is better; especially for use with your mobile phone. The most recent updates are now available and have been indexed for easier reference. Let me know how this works for you.

CMG 2008 Boot Camp Sessions

Those of you who attended my Capacity Planning Boot Camp sessions at CMG 2008, may have noticed that something got lost in the translation between my original notes and what landed on your CMG CD. The corrected slides, including updated hyperlinks, are now available as PDFs from my CMG Materials page.

If you didn't attend CMG 2008, but you'd like to know more about capacity management techniques, consider coming to my 2-day Guerrilla Boot Camp class in 2009.

Gunther Receives A.A. Michelson Award

At the annual CMG International Conference in Las Vegas last week, Dr. Neil Gunther was the recipient of the prestigious A.A. Michelson Award; the industry's highest honor for computer performance analysis and capacity planning. As he said in his acceptance speech, it was the fulfillment of a dream he had entertained at his first CMG Conference in 1993.

Linux Meets Zipf's Law

It's amazing how power laws seem to be seen in everything these days:

A team of researchers from ETH Zürich (Einstein's alma mater) in Switzerland used four decades of data detailing the evolution of open source software applications created for a Linux operating system to confirm the adherence to Zipf's law. The team studied Debian Linux, as it is continuously being developed by more than 1,000 volunteers from around the world. Beginning with 474 packages in 1996, Debian has expanded to include more than 18,000 packages today. The packages form an intricate network, with some packages having greater connectivity than others, as defined by how many other packages depend on a given package.

It's also amazing what passes for physics these days:

T. Maillart.; D. Sornette; S. Spaeth, and G. von Krogh. “Empircal Tests of Zipf’s Law Mechanism in Open Source Linux Distribution.” Physical Review Letters 101 218701 (2008).

Is the Internet Green?

Research at the University of Melbourne in Australia, presented to the Symposium on Sustainability of the Internet and ICT, claims that a surge in energy consumption caused by the increased adoption of broadband will continue to slow the Internet. The study is the first to model Internet power consumption due to services like video on demand (VOD) and will enable MU researchers to identify the major contributors to Internet power consumption as the adoption of broadband services grows in the coming years.

Worldwide Supercomputer Ratings

Interesting visualization of worldwide supercomputer performance. These Flash bubble-charts seem to be de rigueur for the NYT now. Bubble diameters are proportional to their TFLOPS rating and the location of each bubble cluster is topologically correct with respect to geographical location, but not by Euclidean distance; which is probably why it wasn't superimposed on a map.

The breakdown of these top-100 machines by processor family (not shown there) looks like this:

1. Intel: 75.6%
   
2. IBM: 12%
   
3. AMD: 12%
   
4. NEC: 0.2%
   
5. SPARC: 0.2%

However, the number 1 machine (at 1.1 petaFLOPs) is based on the IBM Cell processor.

What the Harmonic Mean Means

As I discuss in Chapter 1 of The Practical Performance Analyst, time is the fundamental performance metric. Computer system performance metrics are therefore either direct measures of time, e.g, seconds, hours, minutes, or they are rates. All rate metrics have their units of time in the denominator, e.g., GB/s, MIPS, TPS, IOPS.

A conceptual difficulty can arise when we try to summarize a set of performance numbers as a single number; especially if they're rates.