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.

Server consumption doubles?

[bilbravo]

Nah... the figure doubled. I'm sure the overall power consumption in the US (or elsewhere) has not lessened while servers have doubled.
 
Nitpicking, I know...

Re:Server consumption doubles?

[bilbravo]

Hit submit, not preview...

I wanted to add, I'm sure that means the number has more than doubled; I'm sure power consumption has grown, so if the percentage doubled, that needs to be multiplied by whatever factor energy consumption OVERALL has increased.

I got too excited about my nitpicking to post my actual though.

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

[Anonymous Coward]

The frustrating part is that some of the equpiment has that ability built in, it's just not standardized enough to be used. A bunch of our cisco gear has a plug for backup power, and we had some DEC equipment years back that did, but they were different plugs and different voltages. If it were standardized, life would be good.
I think what it would take is for UPS manufacturers to standardize a set of voltages (12, 5, 3.3 perhaps) and a plug so that it would be very easy to replace standard power supplies with a standard DC in power supply.

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

[NerveGas]

I wasn't aware that operating systems really cared which voltage was powering the hardware... :-)

While individual systems may vary, I've noticed that the older the facility where I was working, the more likely they were to have DC power - since the facilities were "telco" before they were "telecom", and most telco stuff is DC. Even in newer datacenters, it's only the small outfits that haven't had DC, most of the larger ones have had DC available.

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.

Re:Solution

[the_womble]

So the disadvantage of using low voltage DC is that the morons are more likely to be able to steal it, thus slowing down the removal of their genes from the population?

The servers are actually doing something

[mdsolar]

Maybe, if they are sending out data. The standby power use of TVs and such is greater.

Sun's David Douglas, VP Eco Responsibility, estimates that the cost of running computers (power use) will exceed the cost of buying computers in about 5 years: http://www.ase.org/uploaded_files/geed_2007/dougla s_sun.pdf. This site has more (mainly corporate) musings on energy efficiency: http://www.ase.org/content/article/detail/3531.
--
Get abundant, get solar. http://mdsolar.blogspot.com/2007/01/slashdot-users -selling-solar.html

Re:The servers are actually doing something

[fred fleenblat]

>> Sun's David Douglas, VP Eco Responsibility, estimates that the
>> cost of running computers (power use) will exceed the cost of
>> buying computers in about 5 years

i think if you're running linux/intel it's already the case.
maybe the cost of sun's hardware is so high that the problem is still 5 years out for them.

Blasphemy!

[dextromulous]

How dare you blame the man who has ridden the mighty moon worm!

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.

Re:"Alarming" increase in "alarming" statistics

[AusIV]

I agree. Server power consumption may have doubled over the past 5 years, but what has the increase in data throughput been? Using a mutilated version of Moore's law, I'll assume that each server is doubling it's throughput every 18 months. 5 years is 60 months, so each server should have doubled 3 and 1/3 times, meaning each server is over 8 times more productive than they were 5 years ago (it's closer to 10, but we'll round down, as I'm trying to make this a conservative estimate).

It's also safe to say that there are "more" servers than there were 5 years ago, but I'm not even going to venture a guess on how many more. Assuming we have the exact same number of servers we did 5 years ago, we'd be processing 8 times more data per kilowatt-hour, meaning the cost of processing data has fallen by 75%. My estimates of data throughput may be high, and my server quantity estimate is definitely low, but I'm guessing 75% is a low end estimate.

Even if we are using more energy, we're getting more bang for our buck. I'd rather have data traveling through servers than on planes and trucks in the form of mail. I'd rather have documents be stored in mass on hard drives than have millions of pages of paper going to waste. Suggesting that this increase of power consumption is alarming is absurd.

cheap blade servers...

[gavint]

driven in part by the rise of cheap blade servers

Rubbish. One of the biggest myths in server sales today is that blades consume more power. If you fill racks full of them they consume more power per square metre of floor space, not per server. If you need the same number of servers they should consume less power, largely due to the centralised AC/DC conversion.

HP especially are working to make blades some of the most efficient servers on the market.

Re:cheap blade servers...

[timeOday]

But compared to other computers, blade servers have a higher density of processors to other expenses (especially if you include server space), so your $100K buys more CPUs. I know it's certainly arguable which is the most relevant metric, but look at it this way: the Eniac pulled 150,000 watts. Since computers are so much more efficient now, the total burden from computers must have fallen, right? Wrong. Because the economics now allow google to run 200K computers (a guess, since it's a secret). Sure, if google had to run on Enacs, it would have to be plugged straight into the sun. But the total amount of computation "required" is not fixed after all.

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.

Did you know disco record sales were up 300%?

[Phanatic1a]

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 ...then by the year 2100, server rooms and cooling equipment will consume over 300,000% of all the electricity!

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.

Re:Computers are powerhogs

[Technician]

Using another semiconductor than silicon for the CPU? Or a radical change in the design of the CPU or orther components? Are there experts here who can elaborate on this?

Performance per watt is a biggie for chip manufactures. Having a less than 10 watt server chip is possible, but who wants to use a Palm Pilot for a transaction server?

Having the performance to handle a slashdotting is what is needed in many servers. Performance is first, power consumption is second. That is why the performance per watt is an important part of the chip design. Low power chips is not the main design item. High performance is the most important. Providing that performance at the lowest power possible is the sweet spot chip designers aim for.

Here is additional reading. Look at what the Core 2 Duo and quad is bringing to the server market.
Please note the Woodcrest and Operon is now obsolete. The Operon was leading, but the new multi-core chips are a new race in the performance per watt race.

http://www.computerworld.com/blogs/node/2160

http://www.intel.com/performance/server/xeon/ppw.h tm

http://www.supermicro.com/newsroom/pressreleases/2 006/press081406.cfm

http://news.com.com/Chipmakers+admit+Your+power+ma y+vary/2100-1006_3-6082352.html

But Other Efficiencies Are Gained

[DumbSwede]

This tends to be the trend with any useful technology. As technologies become more cost effective and energy efficient the rise in demand outpaces the energy savings as the economic advantage they offer is more fully utilized. This happened first with steam powered devices, then automotive, then air travel.

While it may seem disturbing that computers are consuming a larger percentage of energy usage, one has to realize they probably more than offset their own energy use -- this by allowing other resources to either be used more efficiently or by enabling other economic activity that discovers and distributes resources, energy among them.

Bullshit

[MindStalker]

Trend continues. Thats like saying people have been using more 120W bulbs than when they used to use 60W bulbs, if this trend continues everyone will be using 500W bulbs by 2015.

Yea as computing has gotten cheaper and people are using more of it, but thats because the relative cost of powering them have remained cheap. Don't expect the trend to continue once it becomes expensive compared to other things.

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?

And say one-third of that is for spam filtering

[justthinkit]

A sickening thought, actually. Reminds me when the Sudbury nickle smelter belched out 2% of the world's SO2.

overcapacity, spam, botnets

[bcrowell]

Personally, I use an insanely wasteful server because I don't have any choice. 99% of the time its cpu is 99% idle. However:

• You can't get webhosting with good support and reliability unless you pay for the level of webhosting that gets you your own box.
• I need my server to be able to stand up to a spike in demand caused by ten thousand spams hitting it in three seconds...
• ... or 1000 ssh login requests in one minute from a bot searching for weak pasword...
• ... or a brain-dead bot requesting the same 5 Mb pdf file 10,000 times in one hour, and sucking down 60 Mb worth of partial-content responses.

Similar deal with multi-core CPUs. People are talking about making desktop machines into the equivalent of 1980 supercomputer, and one of the main justifications seems to be that anti-virus software can run all the time without affecting responsiveness. This is nuts. The internet and its protocols weren't designed for a world infested by Windows machines controlled by malware.

Don't you see the looming crisis?

[NotQuiteReal]

computers are using more power than 5 years ago

There's your problem, right there. You are thinking on such a short time scale. If you look back 100 years, the amount of electricity being used by computers is INFINITELY more than before. In no time at all, COMPUTERS WILL USE ALL THE ELECTRICITY IN THE UNIVERSE.

Clearly this is a problem. Think about it - those electrical cords have two wires. Electricity comes in one side, swirls around your computer for a bit, heating things up and showing you devil images, then it goes out the other wire, "to the ground", where SATAN lives. I am sure all that electricity "juice" is polluting our groundwater and causing all the hideous mutations we see today. Wasn't one of earliest large-scale electric projects the TVA, and isn't Tennessee where Al Gore, the ARCHITECT of Global Warming, is from?

And who would benefit from Warm Weather - that's right, SATAN. And Nashville is the home of country music, associated with BANJO MUSIC, need I say more? Sure Al says he is against global warming, but that is just reverse psychology. There is a reason why clueless Tonight Show "Jaywalkers" didn't recognize his photo, but knew he was up to no good.

All the juice in the universe must be a lot - so... when it all seeps into the ground, WHAMO, the whole thing will burst open, unleashing the daemons of the netherworld (which has nothing to do with Netherlands, it's cold there, right now)!

Disclaimers:

All facts taken out of context on purpose.

Two animals were harmed making this post, well, just one, but I kicked it twice.

[omg, I will be SO modded down for this post, but damn, it is scary how easy it is to think like a loon.]