Slashdot Mirror
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.
Well, I blame Al Gore ... for inventing the Internet in the first place.
There's a Gizoogle new machines on line!
"Flyin' in just a sweet place,
Never been known to fail..."
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...
Starmen.net
By definition the 0.6% increase in the fraction of electricity used by servers was matched by a 0.6% decrease in the fraction used by everything else, so everything is good.
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.
Another day closer to redwood heaven
Maybe, if they are sending out data. The standby power use of TVs and such is greater.
a s_sun.pdf.
This site has more (mainly corporate) musings on energy efficiency: http://www.ase.org/content/article/detail/3531.
s -selling-solar.html
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/dougl
--
Get abundant, get solar. http://mdsolar.blogspot.com/2007/01/slashdot-user
How dare you blame the man who has ridden the mighty moon worm!
There are two types of people in the world: those who divide people into two types and those who don't.
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
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.)
Two wrongs don't make a right, but three lefts do.
In the average home, the refrigerator had been the biggest power consumer for a long time. Now this place had been taken by the computer. Computers at home can be switched off when not in use, but for a server this is hardly possible. I'm not a computer hardware designer but I am curious in what ways the power consumtion of computers can be reduced. Using better cooling equipment? 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?
-- Cheers!
This guy actually wrote:
"Virtualization and consolidation of servers will work against this trend, though, and it's difficult to predict what will happen"
Instead of just taking the current trend, projecting it into the future as an infinite progression, therefore concluding that the human race will end sometime near the end of the 21st century?
I think this guys just destroyed any career as a media pundit he may have been planning.
Better start checking out some of those Medical Billing or "Massage Therapy" classes that have taken over at former computer-tech trade schools.
One is lead to believe that individual servers are using more power whereas the article indicates that more servers are being deployed.
I wonder if anyone has bothered to do a study of server power consumption per teraflop or web page served? In the same time frame, how much has the number of servers increased and how many transactions per second do each server perform?
Unlike cars which have decreased gas consumption per vehicle on average of only about 20% while carying the same number of passangers per vehicle, I think servers on average provide a lot more performance on a lot less power. There is just enough more of them (guessing a 10X increase) to increase the total electrical load (2X).
The truth shall set you free!
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.
Don't worry everyone, this problem was fixed yesterday: http://ask.slashdot.org/article.pl?sid=07/02/15/18 25230
No bandwidth, No servers, No problem
Your ad here. Ask me how!
"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.
I don't need no instructions to know how to rock!!!!
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!
I've always argued among my tech friends that the technology and computer industry, whether is it the manufacturing of the iPod (Green's agree with me here) or the world servers (Google etc..), they will be the biggest cause of greenhouse gases besides autos in the future.
I always tease them that it is Google and Apple that are destroying the environment...:)
One aspect that nobody seems to be talking about here is server room growth. Without actually looking up the numbers I would say I've added 2 or 3 servers for every 1 server removed from the racks.
My point being that the MHz/Watt (or whatever metric of computer power to electrical draw you want to use) is increasing but NOT at the rate that technology improves. We continue with each generation to hold on to and use older and older equipment.
Of course perhaps other shops have the type of budget to always replace older stuff with newer or more power efficient equipment.
Those who can, do.
Do you think they have to water cool those?
Seriously, though, here's a great article on power consumption, though in this case in the home. This was linked from another recent slashdot article on power consumption.
Of course, I am biased.
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.
We got served.
With DC-DC downconverters, which also generate heat (and potentially EMI).
Expect to see local government force data centers to get more efficient. Right new there are many moves afoot to reduce the amount of AC (that is air conditioning, not alternating current) that can be provided to buildings. It will not take much of a push in this direction to make us start talking about "cooling bound' data centers. For example, in Washington State and other states there are already limits on the amount of heating capacity (BTUs) per square foot so this is a logical extension.
Server deployments these days are placed into laterally expandable environments serving up Windows based .NET server architectures or *nix based AMP solutions which are basically highly inefficient in terms of processing power. But everyone is happy because it's reasonably easy to develop solutions ontop of these frameworks. Here's some observed data as I hit my home computer with about one page refresh every one or two seconds:
The font chopped up the nice fixed formatting, but what is seen is that on my reasonably fast single core machine it used approximately 25% of the system's CPU power to serve up a small number of pages per second. This is with an installation of a MediaWiki on Linux with Mysql, so it's possible that other solutions are worse especially when having to render up more complex HTML. I am not an expert in this field though, so feel free to add to or correct my statements.
"but money is the God of Algiers & Mahomet their prophet." - Rich. O'Bryen June 8th 1786
Won't heat become a much bigger problem before we get to the point that electricity in constrained? Rack servers are very dense from a BTU/sq ft perspective. Wont we bump against an inability to handle the cooling requirements if we double our power density per sq ft?
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.
Letter To Iran
Most companies seem to be using 5 year old equipment anyway.
"No, no, no, don't tug on that! You never know what it might be attached to."
When the machines in their lust for power exhaust the conventional sources... they will turn to the only source left... mankind.
Then we'll all have that inconvenient blue/red pill choice thingy.
You can't talk about Wikipedia's flaws on Wikipedia
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.
I can attest to this personally.
I have several white-box servers in a co-lo that together with a good stiff tailwind draw about 4 amps total.
I also have several Dell 1950 and 2950 servers in a data center for my day job. Each one by itself draws about 3 amps (dual supply, 1.5 amps per supply, surging to 3 amps when one of the supplies is turned off for whatever reason). Granted, there are many more fans in the Dell servers than in my whitebox servers, but I have more storage in my whitebox servers.
Ron Gage - Westland, MI
"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!"
sic transit gloria mundi
...but how much did performance increase by?
the RBOCS have been doing this forever with a number of their equipment. I wonder how many more insane patents will be granted.
I prefer the "u" in honour as it seems to be missing these days.
If you use water to cool electricity-based computing, wouldn't it make sense to use electricity to cool water-based computing? Where's your head, man?!
...following the principles of Heisenburger's Uncertain Cat...
The article is the usual tabloid trash which confuses the issues and has some strange tie-ins to Chernobyl in the hopes of spreading panic. Exactly what I've come to expect on /.
The story everywhere is that servers are getting more efficient, smaller, and more dense. This means that data centres all over Europe are at their capacity for supplying electricity and cooling, with lots of empty space they can't rent out. Even the newer centres designed a few years ago are having problems. I hear the same thing about centers in the U.S. The electricity companies are struggling to keep up for the data centres not directly on the main distribution grid, requiring the replacement of transformers and transmission lines. The smarter data centres build right next to major sub-stations/switching stations. Google got smart and are building a massive data centre right next to a hydro-electric dam at one of the main crossroads of the western US power grid.
Currently, customers with dense server racks are asking for 2.5KVA per square metre, but there aren't any centres that can supply more than 1.5KVA/m2. There are newer racks coming out that will require 3KVA/m2 or more. With every watt (or BTU if you count that way), there needs to be an equal amount of cooling, which is always slightly less efficient.
Many server farm companies are turning to hiring case modding "tuning" specialists who can build water cooled equipment, and lashing up entire floors full of servers that use more efficient cooling so they can put their cooling energy budget into powering the servers. Interesting to see a whole floor of servers without all the fan noise.
On the other side of the equation, consumers want more and more content. Broadband is taking off (well, except in some places), carrier bandwidth is keeping pace with more capacity at ever lower costs, but the content providers are running into a wall with being able to grow their server farms fast enough. As server capacity grows, the energy costs will grow, but the amount of content served will be significantly higher.
the AC
Hemos is like...sci-fi fans;he thinks technology is cool, but he hasn't bothered to understand the science it's based on
This was some years ago so things are probably different now, but at the time this was a big selling point. Same computing power, lower electrical bill.
You are not entitled to your opinion. You are entitled to your informed opinion. -- Harlan Ellison
Total XBox 360 power consumption has gone up inf% since 2000.
I used to bulls-eye womp-rats in my pants
OK, so the input has increased by 2x. In terms of output, how do current servers compare to five years ago? If the output is only 1.5 and the power consumption doubles, that sucks. If you're getting 5-10x the power output, then perhaps it's not really such a big deal. Through refining and better engineering most things can be made smaller, faster, and more efficient over time, but there is still a point where efficiency and output diverge.
"The 2005 estimate shows that servers and associated equipment burned through 5 million kW of power"
Watts is a measure of power, which they correctly state, but it's odd to say that something "burned through 5 million kW" since, being power, that's a rate of energy use rather than the amount of energy itself (which should be in Killowatt-hours or Joules).
There's no problem in the world that can't be made better the simple stroke of the pen, right?
A sickening thought, actually. Reminds me when the Sudbury nickle smelter belched out 2% of the world's SO2.
I come here for the love
- 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.Find free books.
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.]
This issue is a bit more complicated than you think.
If you post with your REAL login, we might listen...
....or not....
Don't tell me to get a life. I'm a gamer; I have LOTS of lives!
Well, that makes sense. As ISPs services return lower and lower margins, more ISPs will turn to setting up grow rooms where the heat and power consumption is hidden by that of the servers. You need a lot of hi-wattage lights for that kind of operation. They probably would have gone into meth (as it uses less space for the same dollar volume), but the feds are watching the pseudoephedrine too closely.
That is all.
Alrigty, show me where I can sign up to get 48V DC power delivered to a data center. Since my rack right now has over 2KW of 1U, mult-CPU hotness, that means that *one rack* will need 50 amps. There are 10 racks in a row, and at least 10 rows in that particular room (there are others), so this power company will have to be able to deliver 5,000 amps just for that one room. Think of the conductors you need... and wish for a pink unicorn, too.
Sure, I can put some solar panels up with a huge charge controller/regulator, and hook up a ton of submarine batteries, but I don't think that I'm going to find room on the roof for 240kw of solar panels... and rememer, that's just *one room* in the data center. Pink unicorns, man, pink unicorns. At best, you can move the AC->DC conversion and *some* of the regulation out of the air-conditioned room, but that's about all you're going to gain.
The idea of putting DC->DC converters close to a chip is interesting, but would still only take a tiny shaving off of the energy budget of a server.
Oh, you're not stuck, you're just unable to let go of the onion rings.
I'm not sure if it is new, but I've noticed that a lot of software vendors totally bloat the hardware requirements for their software. For example, our small college (300+ enrolled students) is looking to purchase PowerCampus. The "recommended" specs for this is like 4 servers, 3 database and one application, each with multiple RAID arrays. To a total of some 20+ disks. The actual data storage requirements are somewhere around 4 GB total. Though I'd be surprised if it was even that much. I mean, how much data can your store about several hundred students? What the fuck? I guess they just have a "one size fits all" approach to hardware recommendation, but geez. We're not talking about a high traffic website here. Just student data management. Maybe 5 staff on it at any given time and perhaps a few students hitting it now and then to check stuff.
I did find a "consolidated" recommendation and got it down to 2 servers. But they still wanted like 3 separate RAID arrays. I guess we can do whatever we want, but it makes me wonder if their software is any good (efficient/effective) with these kinds of specs.
Yeah, it is based on Microsoft, so what what you will about bloat, but this is just silly. I can only assume that other companies are doing stuff like this.... get a little cash and throw hardware at a solution and hope that preempts any performance problems.
-matthew
"THERE IS NO JUSTICE, THERE IS ONLY ME." -Death
"One is lead to believe that individual servers are using more power whereas the article indicates that more servers are being deployed."
You fucking moron..."One is LED to believe"...unless you are made of a very heavy element.
I reserve the right to think for myself. Others' opinions are optional. Puppy on lap = typos...not illiteracy.
Welcome to Wikipedia's world.
Wikipedia says you won the lotto and you're sending us all your money, too.
+++OK ATH
Alrigty, show me where I can sign up to get 48V DC power delivered to a data center.
As you explained, that would be silly. What would NOT be silly is 400V DC or perhaps 15kV DC for a large data center.
Finally! A year of moderation! Ready for 2019?
Blizzard is already doing this. My company uses colo space in two facilities that also house Blizzard servers. I don't know the voltage, but all of their World of Warcraft server farms (~1000 blades each, around a dozen sites) run HP blades on DC power. The data centers have serious AC power distribution systems, but they've built custom DC power distribution in their floor space. The grounding wires - they're not small.
Cooling is provided by the facility's HVAC system, it's paid for (it's hard to bill each customer for hvac when they're all in a room the size of a football field). So Blizzard seems to be using DC to reduce total power consumption. The other benefit, as the parent suggested, is reduced wear on servers when they're not dealing with heat produced by inefficient AC/DC conversion. Of course, high-end power supplies are getting more and more efficient, but there's always some power loss/heat generation.
At that point, we still have to convert down to lower voltage, and probably wouldn't be able to do it any more efficiently than we already convert AC power... so where, exactly, is the huge advantage that would make it worth it?
Oh, you're not stuck, you're just unable to let go of the onion rings.
At that point, we still have to convert down to lower voltage, and probably wouldn't be able to do it any more efficiently than we already convert AC power... so where, exactly, is the huge advantage that would make it worth it?
It is significantly more efficient to transform DC than AC at relatively low voltages. That is the whole point. Power supplies today have to smooth the output because of the fluctuating nature of the AC input, and they also have to do Power Factor Correction on the input. DC-to-DC has no power factor to correct and it is trivial to smooth the output at a typical switch frequency of 1MHz.
Finally! A year of moderation! Ready for 2019?
Unlike cars which have decreased gas consumption per vehicle on average of only about 20% while carying the same number of passangers per vehicle [...]
Is this a statistic referring to vehicles in the US, or some other country ?