The Red Shift TheoryThe Red Shift Theory
It's Sun's thesis about the explosive growth in demand for raw computing power--but is it more than the utility computing model warmed over?
August 17, 2007
Earlier this summer, a truck pulled up to Building 50 on the grounds of the Stanford Linear Accelerator Center at Stanford University and delivered a jet-black shipping container. Prefabricated, equipped with a built-in cooling system, and crammed with 252 Sun servers, it's one of the first of Sun's so-called Blackboxes. The unit will sift data for physicists examining the effects of subatomic particles colliding at nearly the speed of light. The containerized data center let Stanford add nearly a third more computing power without the cost of new construction, says Randy Melen, the head of high-performance storage and computing for Stanford's department of scientific computing and computing services.
Red Shift Redefined
• Red shift refers to companies experiencing exponential growth in demand for raw computing power
• Red-shift companies tend to be Web 2.0-focused like YouTube and MySpace, or big financial, energy, and pharmaceutical companies
• Those companies, Sun CTO Greg Papadopoulos says, will experience similarly high levels of growth in users, revenue, etc., while blue-shift companies will grow relative to GDP
• Along with the cost of powering and cooling in-house data centers, the red shift is driving a surge in utility computing and software as a serviceDatabase calls have gone from millions to billions, says Salesforce's Fisher Red-shifting companies will experience explosive growth, predicts Sun's Papadopoulos
Designed for customers that face massive computing requirements but aren't ready to shift all their infrastructure to the Internet cloud, the Blackbox epitomizes Sun's approach to the red-shift challenge. In the future, as Papadopoulos sees it, "the Google model"--massive server farms running hundreds of low-end machines--will give way to high-end, extremely dense units like Blackbox and Sun's Constellation, a highly efficient, low-power system based on interconnected Sun Blade 6000 servers. Designed to run complex applications, such as climate, weather, and ocean modeling, the first Constellation will go online at the Texas Advanced Computing Center at the University of Texas, in Austin, later this summer.
Referring again to the power grid, Papadopoulos uses the analogy of a massive, very hot power plant that produces multiple megawatts of energy versus an array of portable Honda generators.
But the jury is still out on whether the big iron from Sun will win out over arrays of dozens or hundreds of commodity boxes. "We'll see [an exponential] increase in the number of servers sold, yes," says technology pundit Mark Anderson, author of the Strategic News Service newsletter. "Will they be Sun servers, running Solaris? I'm not so sure. Everything is headed toward open systems, mostly Linux on commodity servers."
So far, though, Papadopoulos' bet on big over small seems to be paying off. After five years of losses following the pop of the dot-com bubble, Sun's fortunes have changed for the better since the appointment of Jonathan Schwartz, Sun's former chief software architect and a big red-shift proponent, as CEO in April 2006. Last month, the company reported its first full-year profit in half a decade. In its latest earnings report, Sun said its gross margins also rose, to more than 47%, though revenue was essentially flat. (A week later, Sun said it would go through another round of restructuring, cutting an unspecified number of jobs.)
So, after years of contraction, Sun's universe is expanding once more. The question is the same one facing theoretical physicists: Will the red shift go on forever?
About the Author(s)
You May Also Like