Intel pushes the limits of free cooling to 90 degrees

Chipmaker's air-economizer experiment reveals that servers can weather relatively harsh conditions while delivering huge savings on cooling

If your organization is facing tough economic times, take heart: Some of the best things in life aren't just free; they can even save you money. One such example is the air we breathe. Not only does it have laudable health benefits; outside air can be used to cool datacenters for a fraction of the cost of power-guzzling CRAC units -- and perhaps with fewer drawbacks than you might imagine.

Intel has released a report detailing a recent, impressive experiment in "free cooling" using air-side economization. An air-side economizer can draw on outside air to cool the inside a datacenter, then push the hot air that exits the machines back outdoors.

In conducting its proof-of-concept experiment, Intel sought not only to test the limits of air-side economization by allowing machines to be cooled by air temperatures as high as 90 degrees Fahrenheit; the company also aimed to challenge the perceptions that using outside air can be harmful to servers in that it subjects them to excessive humidity and contaminants.

Can this approach save money over using traditional chillers? Intel says yes: By using air economizers 91 percent of the time (accounting for times when outside air might not be adequate), the company says it could enjoy an estimated 67 percent in power savings at a 10MW datacenter, which would total a very cool $2.87 million.

Intel Air-Side Economization
Intel orchestrated its proof of concept at a datacenter location in New Mexico thusly: It set up about 900 heavily utilized production servers in a 1,000 square foot trailer, which was split into two 500 foot compartments. One compartment was cooled 24-7 by a relatively low-cost, warehouse-grade DX (direct expansion) air-conditioning unit; the other was cooled almost exclusively by outside air, though it was also equipped to be cooled by the DX chiller if the need arose.

As explained by Intel's report on the proof of concept test, "We designed the system to use only the economizer until the supply air exceeded the 90 degree maximum, at which point we began using the chiller to cool the air to 90 degrees . If the temperature dropped below 65 degrees , we warmed the supply air by mixing it with hot return air from the servers."

Ninety degrees is an unusually high temperature for a server room. Intel says in the report that it traditionally sets its chiller temperature to 68 degrees in its datacenters. Conventional wisdom dictates that air-side economization is better for mild, temperate climates, not regions where temperatures can hit the 80s, 90s, and beyond. There was method to Intel's seeming madness, however: "We reasoned that this might be feasible because server manufacturers specify that their products can operate in temperatures as high as 98 degrees."

Not content with simply pushing the temperature boundaries, Intel wanted to gauge how resilient the machines could be to humidity and air contaminants. To that end, Intel used no humidity controls whatsoever and installed just a standard household air filter "that removed only large particles from the incoming air but permitted fine dust to pass through."

Intel didn't go easy on its machines as it conducted this experiment. The chipmaker says that the servers were working at 90 percent utilization during the testing, crunching large production batch silicon design workloads.

As for the type of servers, Intel says they were standard, single-core, dual-socket, Intel-based machines that were roughly two years old. In other words, Intel didn't enlist specially hardened or ruggedized equipment but instead used the same type of machines found in the company's other datacenters.

During the 10-month test, Intel found that the machines cooled by outside air experienced humidity variations from four percent to more than 90 percent, and that it changed rapidly at times. Moreover, "the servers and the interior of the compartment became covered in a layer of dust."

Once the experiment was complete, Intel calculated that the air-economized trailer required 74 percent fewer KWh to keep cool then the air-conditioned trailer. Based on the testing, Intel concluded that in this particular region, at least, it could rely on air-side economizers 91 percent of the time and save $2.87 million on cooling at 10MW datacenter.

Cost savings aside, the other big question, of course, is how well did the server weather the unusually harsh conditions? After all, a datacenter full of fried or dust-clogged machines is pretty much worthless, no matter how inexpensive it is to cool. The answer: surprisingly well. "Despite the dust and variation in humidity and temperature, there was only a minimal difference between the 4.46 percent failure rate in the economizer compartment and the 3.83 percent failure rate in our main datacenter over the same period," Intel reports. "The failure rate in the trailer compartment with DX cooling was 2.45 percent, actually lower than in the main datacenter."

These results may be cause for some concern among anyone worried about server uptime: As you can see, the failure rates are relatively low across the board -- but the servers in the air-side economization trailer failed nearly twice as much as those in the room where traditional cooling was employed. On the other hand, it's notable that Intel made the conditions in the "free cooling" section unusually harsh.

Intel is certainly not dismissing the potential ill-effects of outside air on the machines entirely. "We plan to further test for possible hardware degradation using a server-aging analysis that compares systems used in the economizer compartment, in the air-conditioned compartment, and in our main datacenter," Intel reports.

One remedy to the problems posed by humidity and contaminants could be ruggedized chasses, such as the IBM BladeCenter T and HT. As described by Big Blue, these chasses comply with both NEBS (Network Equipment-Building System) Level 3 and ETSI (European Telecommunications Standards Institute) standards and are "ideal harsh environments and running applications under the most demanding conditions." The hardened design "enables performance across broader range of temperatures and humidity," according to Alex Yost, VP for IBM BladeCenter at IBM, and "enables airborne contaminant filtration" to boot.

One of these chasses, loaded, would run around $5,000 more than a standard chassis, according to Yost. Still, it amounts to a smart investment if you're contemplating exposing your machines to free outside air under harsher-than-normal conditions.

You can download Intel's white paper on its air-economizer experiment, titled "Reducing Data Center Cost with an Air Economizer"; there's also a video available on how the air economizer works.


Copyright © 2008 IDG Communications, Inc.

How to choose a low-code development platform