Server Power Consumption Doubled Over Past 5 years

Watt's up writes "A new study shows an alarming increase in server power consumption over the past five years. In the US, servers (including cooling equipment) consumes 1.2% of all the electricity in 2005, up from 0.6% in 2000. The trend is similar worldwide. 'If current trends continue, server electricity usage will jump 40 percent by 2010, driven in part by the rise of cheap blade servers, which increase overall power use faster than larger ones. Virtualization and consolidation of servers will work against this trend, though, and it's difficult to predict what will happen as data centers increasingly standardize on power-efficient chips." We also had a recent discussion of power consumption in consumer PCs that you might find interesting.

Comments

Inconvenient Truth

[JusticeISaid]

Well, I blame Al Gore ... for inventing the Internet in the first place.

Solution

[Ziest]

48 volt DC. Why the hell are we still putting 110 AC into the power supply and steping it down to 24 volt DC. And what do you get when you do that? HEAT. And to compensate for not having a better power system you then get to spend a fortune on HVAC to cool the room that you heat by stepping down the voltage. 110 power supplies make sense in the home but in a data center it is stupid.

Re:Solution

[Ungrounded Lightning]

So how do you get 12 volt, 5 volt, 3.3 volt, and 1.5 volt DC from that?

High-efficiency switching regulators on the blades. (They're actually getting so good that you have less heat loss by putting a local switcher near a power-hungry chip than by bringing its high current in at its low voltages through the PC-board power planes.)

Getting the raw AC->DC conversion out of the way outside the air-conditioned environment saves you a bunch of heat load, as does distributing at a relatively high voltage (such as "relay-rack" standard 48VDC) to reduce I-squared-R losses. And switchers are more efficient with higher raw DC supplies, so going to 48V (about the highest you can while avoiding touch-it-and-die shock hazard - which is why Bell standardized on it) is much better than 12 or 24.

Re:Solution

[Wesley Felter]

As one of the founders of Google pointed out about 3 months ago, most if not all the compnents in a PC could be designed to run off a common voltage. The only reasons they don't are historical.

That's not what the Google paper said. It proposed that power supplies should output only 12V and motherboards should contain many DC-DC converters to generate voltages needed by chips. As chip fabrication technology changes, newer chips need lower voltages to operate optimally (not to mention that lower voltage = lower power); since different chips in a computer are made with different technologies, they need different voltages ranging from 1.8V down to 1.0V.

Re:Solution

[NerveGas]

      Get a grip on reality.

      Even if you switch to 48V DC, you still have to convert 120 VAC to 48 V DC, then down to 12/5/3.3/1.x volts for motors and logic, so all you're doing is moving the conversion from a decentralized setup (a power supply in each computer) to a centralized one (a single large power supply). In the end, however, you still have to get from 120 down to around 1 volt for the CPU, and you're not going to suddenly make an order-of-magnitude change in the efficiency of that - or even near a doubling.

    To keep it in perspective, though, there are vastly overshadowing losses which make the small differences in centralized/decentralized conversion efficiency moot. Your 120 VAC leg is probably coming from a 440 VAC lead coming into the building, and going through a very large transformer to get 120 VAC - and the 440 VAC that comes in is coming from a much higher voltage that was converted down at least once (and perhaps more) after being transmitted very long distances. The losses in all of that are much, much higher than the losses in conversion that you mention.

    Sure, if you could generate and transmit a nice, smooth, regulated 48V DC from the power station to your computer, that would be great - but that's so unfeasable that you might as well wish for a pink unicorn while you're at it.

Re:Solution

[hackstraw]

I didn't read the Google paper (or the FA for that matter), but while we are on the subject, this is something that I don't understand.

Why do servers have AC to DC power supplies at all? I don't know about you, but I have my servers on UPSes. So the whole thing goes AC from wall to DC in the UPS to the batteries then from DC to AC to the computer where it converts it back to DC.

I'm not an EE, but why cant AC come from the wall into the UPS and then the UPS spits out DC to the computer?

Granted the UPS power supply needs to be redundant because they are the 2nd most likely thing to fail in servers after disks, but what am I missing here? I know there are telco grade computers that take DC, but these are not available in many options and are typically lower end boxes. But to me, none of these additional conversions to AC and DC an back again with the added likelihood of a failure anywhere in the chain seems a bit non-optimal.

Re:Solution

[Wesley Felter]

You got it; that's how telco central offices work and a few companies are proposing that other data centers should switch to DC. But there are many problems: low-voltage DC requires thicker cables than high-voltage AC, I've heard that high-voltage DC can only be plugged in by licensed electricians, and AFAIK there is no standard DC connector. And industry intertia, of course.

Moore's law

[k3v0]

Considering that the processing power has more than doubled over that amount of time it would seem that we are still getting more bang per watt than before

"Alarming" increase in "alarming" statistics

[G4from128k]

Why does this alarm anyone and is it even really true? Several factors conspire to make this statistic both bogus and unalarming.

1. More computers are classed as "servers." I'd bet that before many of the workgroup and corporate IT computers and mainframes weren't classed as "servers." It's the trend toward hosted services, web farms, ASPs, etc. that is moving more computers from dispersed offices to concentrated server farms.

2. More of the economy runs on servers - this would be like issuing a report during the industrial revolution that power consumption by factories increased at an "alarming" rate. Moreover, I'd wager that a good chunk of that server power is paid for by exporting internet and IT-related services.

3. Electricity is only a small fraction of U.S. energy consumption. Most of the energy (about 2/3) goes into transportation (of atoms, not bits).

It's only natural and proper that server power consumption should rise with the increasing use of the internet in global commerce. This report should be cause for celebration, not cause for alarm. (but then celebration does sell news, does it.)

Re:"Alarming" increase in "alarming" statistics

[fred fleenblat]

more to the point energy-wise, people using those servers (for on-line shopping, telecommuting, etc) are saving tons of enegy by not driving to the store, the mall, or the office to accomplish everything.

Calibrate your BS detectors..

[stratjakt]

"If current trends continue" is almost always followed by a fallacious argument. Current trends rarely continue. Be it world population, transistor density, climatology, and especially at the blackjack table.

Just pointing that out.

And how much energy did those computers save?

[WoTG]

It's not like we plug in computers to sit around idling all day. They're doing stuff. I can send an email to anywhere on the planet instead of stuffing and envelope to have it carried by truck, boat, or plane. Cars have better power plants than ever before... they didn't get that way with back of the envelope calculations! A lot of forms that I used to submit by fax or snail mail? All gone electronic.

So, computers are using more power than 5 years ago? Who cares? If it bothers you, then get off the grid and fun in your cave.

Trends

[glwtta]

"This baby is only six months old and she already has one head and two arms; if these trends continue, she'll have 4 heads and 8 arms by the time she's two!"

Ok, so power use doubled...

[Aphrika]

...but how much did performance increase by?