Skip to main content

Wired 14.10: The Information Factories

Popularity Report

Total Popularity Score: 0
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...

Rank

Bookmark History

Saved by 5 people (1 private), first by anonymouse user on 2006-11-27


Public Sticky notes

Google's Hölzle noticed the high electric bills after taking his post in 1999. At 15 cents per kilowatt-hour, power dominated his calculus of costs. "A power company could give away PCs and make a substantial profit selling power," he says. (At The Dalles, the huge protuberances on top are not giant disk drives, climbing to the rooftop for a smoke while the RAM below does the work, but an array of eight hulking cooling towers.)

Highlighted by smpark

Although the evergreen mazes, mountain majesties, and always-on skiing surely play a role, two amenities in particular make this the perfect site for a next-gen data center. One is a fiber-optic hub linked to Harbour Pointe, Washington, the coastal landing base of PC-1, a fiber-optic artery built to handle 640 Gbps that connects Asia to the US. A glassy extension cord snakes through all the town's major buildings, tapping into the greater Internet though NoaNet, a node of the experimental Internet2. The other attraction is The Dalles Dam and its 1.8‑gigawatt power station. The half-mile-long dam is a crucial source of cheap electrical power – once essential to aluminum smelting, now a strategic resource in the next phase in the digital revolution. Indeed, Google and other Silicon Valley titans are looking to the Columbia River to supply ceaseless cycles of electricity at about a fifth of what they would cost in the San Francisco Bay Area. Why? To feed the ravenous appetite of a new breed of computer.

Highlighted by b3zx313

According to Bell's law, every decade a new class of computer emerges from a hundredfold drop in the price of processing power. As we approach a billionth of a cent per byte of storage, and pennies per gigabit per second of bandwidth, what kind of machine labors to be born?

Highlighted by b3zx313

Groove Networks.

Highlighted by b3zx313

BACK IN 1993, in a midnight email to me from his office at Sun Microsystems, CTO Eric Schmidt envisioned the future: "When the network becomes as fast as the processor, the computer hollows out and spreads across the network." His then-employer publicized this notion in a compact phrase: The network is the computer. But Sun's hardware honchos failed to absorb Schmidt's CEO-in-the-making punch line. In which direction would the profits from that transformation flow? "Not to the companies making the fastest processors or best operating systems," he prophesied, "but to the companies with the best networks and the best search and sort algorithms."

Schmidt wasn't just talking. He left Sun and, after a stint as CEO of Novell, joined Google, where he found himself engulfed by the future he had predicted. While competitors like Excite, Inktomi, and Yahoo were building out their networks with SPARCstations and IBM mainframes, Google designed and manufactured its own servers from commodity components made by Intel and Seagate. In a 2005 technical article, operations chief Urs Hölzle explained why. The price of high-end processors "goes up nonlinearly with performance," he observed. Connecting innumerable cheap processors in parallel offered at least a theoretical chance for a scalable system, in which bang for the buck didn't erode as the system grew.

Highlighted by b3zx313

"In this architecture, the data is mostly resident on servers 'somewhere on the Internet' and the application runs on both the 'cloud servers' and the user's browser. When you use Google Gmail, Maps, Yahoo's services, many of eBay's services, you are using this architecture." He added: "The consequence of this 'architectural shift' is the return of massive data centers."

Highlighted by b3zx313

By the byte, RAM is some 100 times more costly than disk storage. Engineers normally conserve it obsessively, using all kinds of tricks to fool processors into treating disk drives as though they were RAM. But Google understands that the most precious resource is not money but time. Search users, it turns out, are sorely impatient. Research shows that they're satisfied with results delivered within a twentieth of a second. RAM can be accessed some 10,000 times faster than disks. So, measured by access time, RAM is 100 times cheaper than disk storage.

Highlighted by b3zx313

In the last decade, the speed of backbone traffic has accelerated from 45 Mbps to roughly a terabit per second. That's a rise of more than 20,000 times. Google interconnects its hundreds of thousands of processors with gigabit Ethernet lines. The expense of placing gigantic data centers near major fiber-optic nodes is well worth the expense.

Highlighted by b3zx313

The facility is run by telco giant Verizon. It was designed not for supercomputing but for communications, steering photons through glass threads and mostly copper switches toward their telephonic destinations. MCI, a Verizon acquisition, built it to accommodate UUNet, the premier high-end Internet service provider.

Highlighted by b3zx313

ese cabinets once held as many as eight UUNet routers apiece. Now each 10-foot frame houses 42 black Dell PowerEdge servers, interconnected by a Rastafarian tangle of wires – tens of thousands of computers in total. Hovering above the cabinets like a midday emanation over Death Valley, a shimmering haze of heat signifies an awesome consumption of power.

If it's necessary to waste memory and bandwidth to dominate the petascale era, gorging on energy is an inescapable cost of doing business. Ask.com operations VP Dayne Sampson estimates that the five leading search companies together have some 2 million servers, each shedding 300 watts of heat annually, a total of 600 megawatts. These are linked to hard drives that dissipate perhaps another gigawatt. Fifty percent again as much power is required to cool this searing heat, for a total of 2.4 gigawatts. With a third of the incoming power already lost to the grid's inefficiencies, and half of what's left lost to power supplies, transformers, and converters, the total of electricity consumed by major search engines in 2006 approaches 5 gigawatts.

Highlighted by b3zx313

The next wave of innovation will compress today's parallel solutions in an evolutionary convergence of electronics and optics: 3-D and even holographic memory cells; lasers inscribed on the tops of chips, replacing copper pins with streams of photons; and all-optical networks in which thousands of colors of light travel along a single fiber. As these advances find their way into an increasing variety of devices, the petascale computer will shrink from a dinosaur to a teleputer

Highlighted by b3zx313

UNTIL HUMANKIND devises an inexhaustible font of electricity that can be situated wherever it's most convenient, the best hope for cooling overheated data centers is to make computers themselves more efficient. The dire state of data center economics (as well as customer demand for portable computers with a reasonable battery life) has driven chipmakers to throw all their weight behind efforts to design low-power chips. AMD's Opteron CPU, debuted in 2003, consumed significantly less power than its predecessors, reversing the trend toward higher speed and greater power consumption that had held since the microprocessor was invented. The Opteron upgrade this past summer brought an additional 30 percent reduction in power usage. Intel, introducing its competing Core architecture, recently acknowledged that the market now values energy efficiency over clock speed. But with the Internet's expansion and the migration of desktop applications online, these improvements won't be enough to avert a meltdown.

An even more daunting roadblock stands ahead: Further dramatic gains in efficiency may be physically impossible without radical breakthroughs in chip design. Microsoft's Craig Mundie bluntly describes the predicament. "We have now run into a brick wall," he says. "What brought all of us faster computing was raising the CPU's clock rate, which increased power consumption. Raising the clock rate without consuming more power was only possible because we could lower the voltage. We can't do that anymore because we're down into electron volts. If you can't lower the voltage, you can't raise the clock rate without using a lot more power."

Highlighted by b3zx313

But reliance on massively parallel computing may come to define the limits of what can be accomplished by a computer-on-a-planet.

Highlighted by b3zx313

We ran out of power before we ran out of space,

Highlighted by b3zx313

The desktop is dead. Welcome to the Internet cloud, where massive facilities across the globe will store all the data you'll ever use. George Gilder on the dawning of the petabyte age.

Highlighted by wroush

The desktop is dead. Welcome to the Internet cloud, where massive facilities across the globe will store all the data you'll ever use. George Gilder on the dawning of the petabyte age.

Highlighted by eyalnow

For it's here that Google has chosen to build its new 30‑acre campus, the base for a server farm of unprecedented proportion.

Highlighted by eyalnow

One is a fiber-optic hub linked to Harbour Pointe, Washington, the coastal landing base of PC-1, a fiber-optic artery built to handle 640 Gbps that connects Asia to the US.

Highlighted by eyalnow

Indeed, Google and other Silicon Valley titans are looking to the Columbia River to supply ceaseless cycles of electricity at about a fifth of what they would cost in the San Francisco Bay Area. Why? To feed the ravenous appetite of a new breed of computer.

Highlighted by eyalnow

According to Bell's law, every decade a new class of computer emerges from a hundredfold drop in the price of processing power. As we approach a billionth of a cent per byte of storage, and pennies per gigabit per second of bandwidth, what kind of machine labors to be born?

How will we feed it?

How will it be tamed?

And how soon will it, in its inevitable turn, become a dinosaur?

Highlighted by eyalnow

One characteristic of this new machine is clear. It arises from a world measured in the prefix giga, but its operating environment is the petascale. We're all petaphiles now, plugged into a world of petabytes, petaops, petaflops. Mouthing the prefix peta (signifying numbers of the magnitude 10 to the 15th power, a million billion) and the Latin verb petere (to search)

Highlighted by eyalnow

Yawn. Today Google rules a total database of hundreds of petabytes, swelled every 24 hours by terabytes of Gmails, MySpace pages, and dancing-doggy videos – a relentless march of daily deltas, each larger than the whole Web of a decade ago. To make sense of it all, Page and Brin – with Microsoft, Yahoo, and Barry "QVC" Diller's Ask.com hot on their heels – are frantically taking the computer-on-a-chip and multiplying it, in massively parallel arrays, into a computer-on-a-planet.

Highlighted by eyalnow

Eric Schmidt envisioned the future: "When the network becomes as fast as the processor, the computer hollows out and spreads across the network." His then-employer publicized this notion in a compact phrase: The network is the computer.

Highlighted by eyalnow

In a 2005 technical article, operations chief Urs Hölzle explained why. The price of high-end processors "goes up nonlinearly with performance," he observed. Connecting innumerable cheap processors in parallel offered at least a theoretical chance for a scalable system, in which bang for the buck didn't erode as the system grew.

Highlighted by eyalnow

The extended Googleplex comprises an estimated 200 petabytes of hard disk storage – enough to copy the Net's entire sprawling cornucopia dozens of times – and four petabytes of RAM. To handle the current load of 100 million queries a day, its collective input-output bandwidth must be in the neighborhood of 3 petabits per second.

Highlighted by eyalnow

Cloud computing, he confirmed, has indeed succeeded the old high-performance staples: mainframes and client-server, both of which require local-area networks. This is very much last year's news. "In this architecture, the data is mostly resident on servers 'somewhere on the Internet' and the application runs on both the 'cloud servers' and the user's browser. When you use Google Gmail, Maps, Yahoo's services, many of eBay's services, you are using this architecture." He added: "The consequence of this 'architectural shift' is the return of massive data centers."

Highlighted by eyalnow

Google appears to have attained one of the holy grails of computer science: a scalable massively parallel architecture that can readily accommodate diverse software.

Highlighted by eyalnow

In every era, the winning companies are those that waste what is abundant – as signalled by precipitously declining prices – in order to save what is scarce. Google has been profligate with the surfeits of data storage and backbone bandwidth. Conversely, it has been parsimonious with that most precious of resources, users' patience.

Highlighted by eyalnow

The recent explosion of hard disk storage capacity makes Moore's law look like a cockroach race. In 1991, a 100-megabyte drive cost $500, and a 50-megahertz Intel 486 processor cost about the same. In 2006, $500 buys a 750-gigabyte drive or a 3-gigahertz processor. Over 15 years, that's an advance of 7,500 times for the hard drive and 60 times for the processor. By this crude metric, the cost-effectiveness of hard drives grew 125 times faster than that of processors.

Highlighted by eyalnow

But the miraculous advance of disk storage concealed a problem: The larger and denser the individual disks, the longer it takes to scan them for information.

Highlighted by eyalnow

The solution is to deploy huge amounts of random access memory. By the byte, RAM is some 100 times more costly than disk storage. Engineers normally conserve it obsessively, using all kinds of tricks to fool processors into treating disk drives as though they were RAM. But Google understands that the most precious resource is not money but time.

Highlighted by eyalnow

THE FASTEST-GROWING search engine – besides Google – isn't Microsoft or Yahoo or AOL. It's Ask.com, which has seen its total searches grow 20 percent this year.

Highlighted by eyalnow

If it's necessary to waste memory and bandwidth to dominate the petascale era, gorging on energy is an inescapable cost of doing business. Ask.com operations VP Dayne Sampson estimates that the five leading search companies together have some 2 million servers, each shedding 300 watts of heat annually, a total of 600 megawatts. These are linked to hard drives that dissipate perhaps another gigawatt. Fifty percent again as much power is required to cool this searing heat, for a total of 2.4 gigawatts. With a third of the incoming power already lost to the grid's inefficiencies, and half of what's left lost to power supplies, transformers, and converters, the total of electricity consumed by major search engines in 2006 approaches 5 gigawatts.

Highlighted by eyalnow

As energy analysts Peter Huber and Mark Mills projected in 1999, the planetary machine is on track to be consuming half of all the world's output of electricity by the end of this decade.

Highlighted by eyalnow

The struggle to find an adequate supply of electricity explains the curious emptiness that afflicts some 30 percent of Ask.com's square footage. Why is the second-fastest-growing search engine one-third empty? "We ran out of power before we ran out of space," says search operations manager James Snow,

Highlighted by eyalnow

As Microsoft Live operations chief Debra Chrapaty tells me, her company "added a Google" last year in search capability.

Highlighted by eyalnow

China is moving forward with plans to build as many as 30 new nuclear plants; perhaps the next wave of data centers will be sited in Shenzhen.

Highlighted by eyalnow

FOR THE MOMENT, at least, the power of massive parallelism has far outstripped the promise of alternative computing architectures. But reliance on massively parallel computing may come to define the limits of what can be accomplished by a computer-on-a-planet. Two decades ago, Carver Mead, the former head of computer science at Caltech and key contributor to several generations of chip technology, pointed out that a collection of chips arrayed in parallel can't do everything a computer might be called upon to do. "Parallel architectures," he noted, "are inherently special-purpose."

Highlighted by eyalnow

The problem has an acronym – NUMA, for nonuniform memory access – and it has never been solved.

Highlighted by eyalnow

Google's magical ability to distribute a search query among untold numbers of processors and integrate the results for delivery to a specific user demands the utmost central control. This triumph of centralization is a strange, belated vindication of Grosch's law, the claim by IBM's Herbert Grosch in 1953 that computer power rises by the square of the price. That is, the more costly the computer, the better its price-performance ratio. Low-cost computers could not compete. In the end, a few huge machines would serve all the world's computing needs. Such thinking supposedly prompted Grosch's colleague Thomas Watson to predict a total global computing market of five mainframes.

The advent of personal computers dealt Grosch's law a decisive defeat. Suddenly, inexpensive commodity desktop PCs were thousands of times more cost-effective than mainframes.

Highlighted by eyalnow

The next wave of innovation will compress today's parallel solutions in an evolutionary convergence of electronics and optics: 3-D and even holographic memory cells; lasers inscribed on the tops of chips, replacing copper pins with streams of photons; and all-optical networks in which thousands of colors of light travel along a single fiber. As these advances find their way into an increasing variety of devices, the petascale computer will shrink from a dinosaur to a teleputer – the successor to today's handhelds – in your ear or in your signal path. It will access a variety of searchers and servers, enabling participation in metaverses beyond the ken of even Ray Kurzweil's prophetic imagination. Moreover, it will link to trillions of sensors around the globe, giving it a constant knowledge of the physical state of the world, from traffic conditions to the workings of your own biomachine.

Highlighted by eyalnow

Andy Kessler tells me, "It's sure to happen. It always has. Because all the creativity, customer whims, long tails, and money are at the network's edge.

Highlighted by eyalnow

The test of the new global ganglia of computers and cables, worldwide webs of glass and light and air, is how readily they take advantage of unexpected contributions from free human minds, in all their creativity and diversity. Search and you shall find.

Highlighted by eyalnow