Slashdot is powered by your submissions, so send in your scoop

 


Forgot your password?
Close
typodupeerror
×
Power IT

EPA Sends Data Center Power Study to Congress 127

Posted by CmdrTaco from the turns-out-we-use-a-lot-of-juice dept.
BDPrime writes "We've all been hearing ad nauseum about power and cooling issues in the data center. Now the EPA has issued a final report to Congress detailing the problem and what might be done to fix it. Most likely what will happen is the EPA will add servers and data centers into its Energy Star program. If you don't feel like reading the entire 133-page report, the 14-page executive summary is a little easier to get through."
This discussion has been archived. No new comments can be posted.

EPA Sends Data Center Power Study to Congress More

EPA Sends Data Center Power Study to Congress

Comments Filter:

  • Summery (Score:3, Funny)

    by Average_Joe_Sixpack ( 534373 ) on Monday August 06, 2007 @12:04PM (#20130989)
    If you don't feel like reading the entire 133-page report, the 14-page executive summary is a little easier to get through.

    Still too long. Can anyone reduce it to a single phrase or word? Thanks in advance

    • Re: (Score:1, Insightful)

      by Anonymous Coward

      These forecasts indicate that unless energy efficiency is improved beyond current trends, the federal government's electricity cost for servers and data centers could be nearly $740 million annually by 2011, with a peak load of approximately 1.2 GW.

      It then goes on to describe three scenarios that decrease this to various extents but require work and preparation.

      Essentially, we're going to end up building 10 more power plants in the next 4 years because we're so fucking stupid that we can't take simple measures on our current data centers to make them even a little bit more efficient. If you ask me, energy is just too cheap. Put a cap limit on energy use and everything over goes up in price exponentially for a facility. Then you'll see them st

      • Unfortunately, virtualization could probably help out here: I have a feeling a lot of the servers mentioned (although I admit I havent rtfa) have windows...Ive seen govt policies that say 1 app per windows server because they[widnows apps] "don't play nicely" together. Wasn't there an article recently on this, containerization or whatever they called it?

        • Virtualization has put the super smack down on our datacenter. From 250 physical servers to 20...how's that for power savings?

    • Great scott! (Score:5, Interesting)

      by Bacon Bits ( 926911 ) on Monday August 06, 2007 @12:10PM (#20131061)
      Snipped from page 5:

      These forecasts indicate that unless energy efficiency is improved beyond current trends, the federal government's electricity cost for servers and data centers could be nearly $740 million annually by 2011, with a peak load of approximately 1.2 GW.

      • Re:Great scott! (Score:5, Funny)

        by nharmon ( 97591 ) on Monday August 06, 2007 @12:29PM (#20131249)
        That amount of power can be easily generated with one DeLorean. I'm going back to sleep...

      • Re:Great scott! (Score:4, Insightful)

        by Frank T. Lofaro Jr. ( 142215 ) on Monday August 06, 2007 @12:38PM (#20131331) Homepage
        $740 million? That's like 4.2 days of the Iraq war!
        ($177M/day for Iraq http://www.usatoday.com/news/politicselections/nat ion/president/2004-08-26-iraq-war-clock_x.htm [usatoday.com]

        That sounds like a big number, and is for most of us, but not for the Federal government. About 29 cents more in taxes off each paycheck (assuming 100 M taxpayers, and paychecks every 2 weeks).

        There are much bigger fish to fry.

        Also, there is only so much one can cut the energy use, and thus that cost down, and still get the business of the government done. And the improvements in efficiency will require hardware, software, and personnel which have their own costs. Eventually you will hit a point where there is no longer a return on investment to make it worthwhile.

        • Re: (Score:2)

          by Burz ( 138833 )
          Notice that the report was issued by the EPA, and what seems like a trifling amount of money for the federal gov't could represent a very significant impact to the environment. On page 8 of the summary it projects the CO2 emissions that could be avoided under the different scenarios.

        • Re: (Score:3, Insightful)

          by aaarrrgggh ( 9205 )

          Also, there is only so much one can cut the energy use, and thus that cost down, and still get the business of the government done. And the improvements in efficiency will require hardware, software, and personnel which have their own costs. Eventually you will hit a point where there is no longer a return on investment to make it worthwhile.

          The same thing was said for many other things over the years; lighting pops to mind. Offices used to consume about 3 watts per square foot of office area in the 70's.

      • 1.21 gigawatts? 1.21 gigawatts? Great Scott!

        The only power source capable of generating 1.21 gigawatts of electricity is a bolt of lightning.

        (Just reinforcing the reference. heh)

    • Maybe in a sentence.. "Individual Server power usage is embarrassing and it should be more efficient"...

      So what happens now?? Now we wait for a congressional committee meeting broadcasted on c-span where politicians can grand stand and talk about how it needs to change... Fortunately most politicians will consider this typical as a "black box", so they will not touch on technical details, but rather just complain.. Maybe talk about a special "colo server" tax.... Maybe throw in some global warming comments.
    • Reduced to a single word...

      Whirrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrr.....

      That help you out?
    • Google for that and see what you get.
  • "... EPA!!! EPA!!!"

  • Mandatory Madonna reference (Score:3, Funny)

    by Ancient_Hacker ( 751168 ) on Monday August 06, 2007 @12:08PM (#20131041)
    Having any Govt investigate efficiency is about as practical as the Madonna Commission On Chastity and Modesty. Computers are doing just fine at reducing their power consumption by many percent a year without the govt's "help".

  • wow (Score:3, Informative)

    by thatskinnyguy ( 1129515 ) on Monday August 06, 2007 @12:09PM (#20131051)

    n 2006, U.S. data centers consumed an estimated 61 billion kilowatt-hours (kWh) of energy, which accounted for about 1.5% of the total electricity consumed in the U.S. that year.


    Is that it? Seems like small potatoes to me.

    • Re:wow (Score:5, Interesting)

      by jandrese ( 485 ) <kensama@vt.edu> on Monday August 06, 2007 @12:21PM (#20131173) Homepage Journal
      1.5% of the total electricity used in the US per year is a huge number. It's like when politicians talk about something really expensive and they say "oh, it's only 1% of our GDP" to make it sound not so bad, except to people who know just how enormous the GDP of this country is.

      More importantly, this could probably be reduced considerably without major disruptions or reduction in quality of service by just embracing higher efficiency components in our datacenter equipment (especially servers).

    • Re:wow (Score:5, Informative)

      by Bacon Bits ( 926911 ) on Monday August 06, 2007 @12:32PM (#20131277)
      It's an estimated 11,000,000 servers in everything from 2 server closets to thousand server enterprise centers. These 11 million systems consume more power than all the TV sets in the US combined, and there are more TV sets in the US today than people.

      Or lets do it this way. Hoover Dam at peak output produces 2 Gigawatts of power per hour. 11 million servers consume 61 billion KW hours annually. It takes Hoover Dam 30,000 hours (about 3.5 years) to produce that much power. So you need four Hoover Dams just to power all the data centers in the US.

      • Re: (Score:3, Informative)

        by miller60 ( 554835 )
        Actually, dams are serving as magnets for data center development, since hydro power is cheaper than other sources and provides the public relations advantage of being "greener" than coal or nuke power. That's why more than 2 million square feet of data center space [datacenterknowledge.com] is being planned in and around Quincy, Washington, a farm town of 5,000. Meanwhile, in northern NY state, HSBC is locating a $1 billion data center project [datacenterknowledge.com] in Cambria (another farm town of 5,000), where it will use hydro power from the Niagara r

      • Re: (Score:2)

        by Himring ( 646324 )
        That doesn't include the energy needed to support the nation of wow, now numbering over 9 million....

      • Units -arghhhh! (Score:3, Informative)

        by IvyKing ( 732111 )

        Or lets do it this way. Hoover Dam at peak output produces 2 Gigawatts of power per hour.


        What you meant to say is "Hoover Dam at peak output produces 2 Gigawatts." What does make more sense is saying 48 million KWH per day or a bit over 17 billion KWH per year - assuming that there is enough water behind the dam to allow for continuous peak output, which is certainly not the case this year.
        • I'm sorry, is my math wrong? Or are you just irritated by the fact that I didn't show my work?

          • Re: (Score:2)

            by IvyKing ( 732111 )
            I was barfing at the use of 'gigawatts per hour' when the correct term is simply gigawatts, a unit of power. Running at full output, Hoover Dam will produce 2 gigawatt hours (2 million KWH) in one hour - which is now referring to units of energy. Remember power=(energy/time) and energy=(power*time), so saying Hoover Dam puts out 2GJ/s would also be correct (and 7.2TJ/hr).

            'Gigawatts per hour' would be the correct term/phrase to use when describing how power production or demand changes with time and impli

            • Ah, Gigawatt-hours of energy vs Gigawatt/hour of power. Gotcha. Sorry about that, been too long since I've really done anything with it.

      • Re: (Score:3, Funny)

        by wcspxyx ( 120207 )
        Can you please state that in units us Slashdotters can understand? Like how many Libraries of Congress would we have to burn to get that much energy?

      • Re: (Score:2)

        by Shishak ( 12540 )
        Um, If the hoover dam produces 2 Gigawatts then over an hour it would produce 2 Gigawatt hours. If the Government servers consume 1.2 Gigawatts then over an hour they would consume 1.2Gigawatt hours (GwH) So, 1 hoover damn can support all the servers. Still an ass load of power, no doubt but you don't need 4 hoover dams. That is by 2011, not today, they are expecting some growth over the next 4 years.

  • cogeneration (Score:3, Funny)

    by MonorailCat ( 1104823 ) on Monday August 06, 2007 @12:14PM (#20131101)
    Move all the data centers to Minnesota or Canada and use them to heat people's houses.

    Or better yet! DatacenterBurgerKing with CPU-broiled whoppers.
    • I'll take a Mushroom and Swiss Intel with chips, please. Oh, and I'll also have floating point errors on the side.

    • Re:cogeneration (Score:4, Interesting)

      by misleb ( 129952 ) on Monday August 06, 2007 @12:43PM (#20131389)
      Ya know, I always wondered why most places weren't more efficient about the cooling of their datacenters... particularly in the winter. Like it'll be 20 degrees F outside and they're STILL running A/C for the computers. WTF? Just vent a small amount of the outside air into the datacenter and you're done. Or better yet, just blow in the air from the offices and send them warm, data center heated air.

      Another question, why do we vent the exhaust from our refrigerators into the house during the summer? Just seems like there's a lot you could do to save energy just by moving what would outerwise be waste heat to places where it can either be used or at least not cause a larger cooling problem.

      • Guessing (Score:4, Interesting)

        by iknownuttin ( 1099999 ) on Monday August 06, 2007 @12:52PM (#20131473)
        Like it'll be 20 degrees F outside and they're STILL running A/C for the computers.

        Climate controlled. There's this element among building planners that think any outside air is bad(TM). That's why, even in small buildings where you don't have to worry about pressure differentials blowing windows out like you do in skyscrapers, you can't open a frick'n window in the Fall or Spring when the air smells wonderful and there's this perfect chill in the air the just stimulates the brain.

        I'm drenched in sweat here in Hotlanta (it's 82F and 66% humidity and climbing to 94) and I really miss New England's Spring and Fall.

        • Re: (Score:2)

          by misleb ( 129952 )

          I'm drenched in sweat here in Hotlanta (it's 82F and 66% humidity and climbing to 94) and I really miss New England's Spring and Fall.


          Haha, it is almost chilly here today in Portland. Well, cool, anyway. Portland summers are the mildest I've ever experienced in the lower 48. Though I imagine Seattle is similar.

          -matthew
        • Actually, if I remember right I heard a story once of a data center in a northern climate that tried to pump in cool outside air to cool their data center. Apparently while the air was cool, it was also somewhat damp, which wasn't good for the electronics. So eventually, they just got tired of the condensation and corrosion and switched back to A/C.

          It can't be too bad though, I would think that an A/C unit cooling off a building with an outside temp below freezing would be very efficient.
          • Speaking as one who knows a little about this subject, humidity is exactly why you can't always use outdoor air. Yes, outdoor air often is used, but not always. Hot air can hold more water, which itself can hold a lot of heat. The HVAC industry uses the term "enthalpy" for the amount of heat in the air. Bring in arctic cold from outdoors, and even though that outdoor air can be bone dry, you'll get massive condensation because the indoor air started with more than enough water to saturate the combined a
      • The concept of "free cooling" is gaining significant momentum in the data center space. I don't have any free or public information, but rest assured that leveraging winter air and other technique are being looked at very hard. Of course, this is not altruism or "green" thinking. It's our old friend financial greed. Reduction in capital expenditures for chiller plants and reduction in utility bills.
      • I once worked in a shop where the mainframe's waste heat was captured to help heat the building.

        When they upgraded the mainframe (double the MIPS, half the size, 1/4 the watts) the mainframe didn't throwing enough heat to do any good.

        I haven't worked there for ages, I'm guessing they've got rows of Intel boxes beside the mainframe these days and probably recycle as much heat as the bad old serial terminal days.
    • Gervase Markham from the Mozilla Foundation suggests using excess heat to power data center jacuzzis [mozillazine.org].
    • Scientific American had an article about containerized data centers; basically a server center built into a standard 20 foot shipping container. I was reading it while at the pool where my daughter was taking swimming lessons. And the thought di occur to me that hooking up the cooling system to the pool would be a great idea.

      And of course in winter, all you would need around here is to open the doors, but since there is a school only 75 yards from the pool, it would not be hard to run the water over there.

      P

  • great news for Sun (Score:3, Informative)

    by toby ( 759 ) * on Monday August 06, 2007 @12:24PM (#20131205) Homepage Journal
    ...whose servers are among [sun.com] the most power-efficient [sun.com] available, and even more so with Niagara 2. [sun.com]

    Disclaimer: I own a tiny bit of Sun stock. (But I bought it because I believe in them, not vice versa!)

  • Simple Solution (Score:5, Insightful)

    by evilviper ( 135110 ) on Monday August 06, 2007 @12:30PM (#20131257) Journal
    I've long been dumbfounded by the way datacenters charge. They seemingly all charge a hell of a lot for physical space, and then almost completely ignore power requirements. This seems incredibly strange, since datacenter operating costs are pretty much tied directly to power consumption (monthly electricity fees, UPSes, electrical generators, cooling, etc.), and only incidentally to physical space.

    Further, the cost to handle each extra watt is multiplied thanks to cooling, power back-up, wiring, etc., while increasing the physical size of the building, constructing more datacenters, etc. is just a flat (linear) cost, and mostly just a one-time expenditure at that.

    This strange arrangement is what has led us here. It's not the natural evolution of technology to cram as much power consumption into as tiny a box as possible. It's an artificial need, created by the idiotic distribution of fees common to datacenters.

    If a few large datacenters declared their fees as a small $$$ value for each unit of space, and additionally a few dollars, per watt of power consumption, you'd see the problem naturally fix itself, through normal economic forces. As soon as watts are the defining factor, companies won't pay more for a cramped 1U server rather than an (inexpensive) 2U or 3U server. You will also see companies happy to pay more for lower-powered server hardware, as having them directly bear the energy cost will make buying efficient servers a significant savings to them.

    • Re: (Score:2)

      by Renraku ( 518261 )
      People good with numbers will usually take the usable floor space of a data center and put a watts per square foot estimate with it based on average or projected power consumption. If you say every square foot costs an average of $5 in power usage, you can figure that in with maintainance per square foot, cooling per square foot, etc, etc.

      Combine these all into a neat little sum on someone's bill.

      Try to think of data center 'floor space' as the main stage. Everything is built around maintaining and supply

      • Re: (Score:3, Interesting)

        by evilviper ( 135110 )

        People good with numbers will usually take the usable floor space of a data center and put a watts per square foot estimate with it based on average or projected power consumption.

        Of course the (average) price of electricity is figured into it. That is the PROBLEM.

        It is a (self-perpetuating) prisoner's dilemma. The more power consumption you can squeeze into the smallest space, the better of a deal you get. Since it's all averaged out, those using more power than average are getting subsidized by those w

    • Re: (Score:2)

      by jsailor ( 255868 )
      Very few, if any providers charge solely by square footage anymore.
      Like shipping packages where the fees are combination of volume, weight, distance, etc. Data center pricing is typically priced based on a combination of space, power, power density, circuits, contract length, continguous space, etc.

    • Re:Simple Solution (Score:4, Informative)

      by fm6 ( 162816 ) on Monday August 06, 2007 @01:59PM (#20132207) Homepage Journal

      If a few large datacenters declared their fees as a small $$ value for each unit of space, and additionally a few dollars, per watt of power consumption, you'd see the problem naturally fix itself, through normal economic forces
      How on earth do you track individual power consumption? Putting a meter on each system is hardly practical. I suppose you get away with one on each rack, but many customers (the vast majority in the one data center I worked in) don't rent whole racks.
      • They don't need to track power consumption; they track capacity. So if you pay for a 30A circuit they assume that you will use all of it all the time.

      • Re: (Score:2)

        by mosch ( 204 )
        How on earth do you track individual power consumption? Putting a meter on each system is hardly practical. I suppose you get away with one on each rack, but many customers (the vast majority in the one data center I worked in) don't rent whole racks.

        PDUs that can track per-outlet power distribution, and spew the data over serial or SNMP are widely available, and deployed widely.

        The problem is also solved for larger (per-rack) situations.

      • Putting a meter on each system is hardly practical.

        I can't see any reason why not. An induction coil costs a few cents, and you could easily feed a rack worth into a single cheap meter.

        But more to the point, I really wasn't suggesting live monitoring. Just have them select from a range of power levels and charge them as appropriate.
      • It would be very easy to measure the current in a wire. I could build a cheap device that could be built into an AC power cord. Almost any engineer could. To that you add a small 8-bit micro controller to send the measurement via Ethernet. You don't need 100% stable accuracy like you do with a meter that is read once per month. This little instrument would be read out once a minute or every five minutes.
        This is NOT a KWH meter you are simply sampling the instantaneous current in the AC line and logging

        • Re: (Score:2)

          by fm6 ( 162816 )
          Well, your first concept I have to accept, since you clearly know the tech better than I do. But you couldn't charge somebody for "how much power each kind of equipment draws" because that varies with usage. That was true even before manufacturers started making chips that turn off a lot of transistors when they're in idle state.
        • How about a cheap thermometer and a plastic bag? Put a plastic bag over the exhaust vent of the server, and see how long it takes to fill it. Next, measure the ambient temperature of the room, and the temperature of the exhaust coming from the server. Now you know a volume of air that the server heats a specific amount in a certain period of time. Apply your physics and you know how much power the server drew to do that.

          Before you laugh too much, that's basically how the EPA figures out the mileage of c

    • Re: (Score:2, Insightful)

      by ICLKennyG ( 899257 )
      This is already happening to a functional point. Navisite, the host we use here at this company, charges by the square foot, however you only get so many watts per square foot. We have (2) 19" racks about half full of hardware with a total physical footprint of under 9 square feet; we could even get it under 5. However due to the power density we have 100 square feet of space that we rent. Because we use hyper dense blade servers for the management efficiency we fill a "racks" space of power with aproxa

    • Re: (Score:2)

      by guruevi ( 827432 )
      Having worked in a datacenter and I have even set up one, let me make it simple to you:

      The cost of 1U space = ((power + people + space + loan + hardware + software) / avg. used U's by customers) * profit rate

      Somebody can simply do that using an Excel sheet and the customer will know that his server costs $1000/year.

      The way you propose would increase that cost with development time, read-out infrastructure and the extra support to handle those things. Next to that, the customer would get a random bill every

      • Somebody can simply do that using an Excel sheet and the customer will know that his server costs $1000/year.

        You have an interesting point at least. It is simpler billing, but charging by size is the worst possible thing you can do. It has lead to many problems over time, a few of which I've already mentioned.

        A thought experiment:
        What if you were to price based purely on number of servers, using average server size?
        What if you were to price based on the WEIGHT of the server instead of U size?
        What if you b

    • This is definitely happening, at least in the UK anyway. It seems to be quite a recent thing, I suspect that power companies have been jacking up the prices for datacentres. As little as a couple of years ago, if you wanted to get some colocation, the cost was all about how much bandwidth you were using. I've been trying to get quotes for colocation recently and the message I've been getting from almost every company I've spoken to is that bandwidth and rack space is relatively abundant, but power consumpti

    • If a few large datacenters declared their fees as a small $$$ value for each unit of space, and additionally a few dollars, per watt of power consumption, you'd see the problem naturally fix itself, through normal economic forces. As soon as watts are the defining factor, companies won't pay more for a cramped 1U server rather than an (inexpensive) 2U or 3U server. You will also see companies happy to pay more for lower-powered server hardware, as having them directly bear the energy cost will make buying efficient servers a significant savings to them.

      Yes, that would be a great solution. Unfortunately, real estate space is getting higher day by day. Building an extension to a datacenter isn't always feasible, and any physical space extension requires quite some investment (such as for cooling, you'd need more coolers to cover more space).

      • Unfortunately, real estate space is getting higher day by day.

        Fortunately, the speed of light is very fast. Even in areas with the highest priced real estate around, it's just a few dozen miles (or a couple milliseconds delay) to get to the middle of nowhere, where the same land is dirt cheap.

        and any physical space extension requires quite some investment (such as for cooling, you'd need more coolers to cover more space).

        If you have an empty building, you don't need a cooler (more accurately, a very very t

    • Except for mom-and-pop customers, all large facilities (365 Main, Savvis, Equinix) charge clients directly or indirectly for power consumption. They might price the cost in ways to obscure it, but if you work it hard enough you can get it down to $/SF plus $/kW. They will often give you a price break for redundant circuits over normal circuits if you are persistent enough.

      The problem with the equation as you suggest is that installed capacity is more expensive than consumption-- The lifetime cost of the i

  • Congress will act (Score:5, Funny)

    by MobyDisk ( 75490 ) on Monday August 06, 2007 @12:31PM (#20131269) Homepage
    No doubt our congress will act swiftly by moving daylight savings time to conserve power.

  • Virtualization? (Score:3, Insightful)

    by tji ( 74570 ) on Monday August 06, 2007 @12:35PM (#20131309)
    I just grabbed the executive summary version, and didn't see any mention of virtualization..

    To me, this seems like one of the more important aspects of power efficiency. Individual server efficiency is important, but the gains from higher utilization could be even more significant. Adding another core to a hypervisor will always be more efficient than adding a new system (CPU, Power Supply, disks, video, etc..). The energy efficient hardware can also be applied to the hypervisor hosts. Build efficient servers, and use as few of them as practical.

    Many data centers are already greatly decreasing their server count using virtualization. This should be part of any data center energy efficiency discussion.
    • Virtualization is great for some things, but security concerns are substantial - PCI compliance generally means that all of the guests on a host have to be at the same security level. Also, some of the virtual environments don't handle IPv6 properly (and a few other things). These aren't showstoppers, but they can reduce some of the benefit.
      • Also, in most current virtualization environments, performance under heavy load on the guest has shown to suffer from 10-40% (depending on which virtualization product you're using). Not quite ready for prime time yet.

    • Re: (Score:3, Informative)

      by necro81 ( 917438 )
      Table ES-1 in the executive summary suggests server consolidation at various levels (moderate, aggressive, etc.). Server consolidation can be done in a number of ways, with virtualization being one of the most effective and popular.

    • Re: (Score:3, Informative)

      by 1sockchuck ( 826398 )
      The report addresses virtualization only indirectly when it refers to electric utilities offering incentive programs. PG&E offers financial incentives to encourage the use of virtualization in data center consolidations [datacenterknowledge.com], with qualifying customers able to earn a rebate of up to $4 million per project site. Other utilities are looking at adapting similar incentives based on virtualization.

      I'm not sure EPA is the right party to be advocating virtualization. The EnergyStar ratings and utility-level programs

  • With a lot of these massive datacenters residing in sunny california you tihnk they could offset a large chunk of their power needs with solar panels covering the roofs Like the FedEx hub in Oakland.

    • Re: (Score:2)

      by Dan Ost ( 415913 )
      Wouldn't it make more sense to simply build data centers in cooler climes?

      • Re: (Score:2)

        by SolusSD ( 680489 )
        cool climate with some sunshine would be best i guess. you could leave the windows open *and* benefit from solar power to help power the servers. :)
  • Get rid of the AC DC power supplys and replace them with bigger ones that power more then one system also this will work better with back up power.
    • -48VDC is standard for some kinds of telecom equipment, so there's plenty of server gear that will work in -48VDC data centers, and it's very efficient. Unfortunately, using this niche gear requires very large economies of scale, on the order of tens of millions of dollars to be cost-effective.

      For mere mortals, blade servers are a better compromise. When you have 4 power supplies per 10 servers, instead of 20, you can afford to invest in more efficient equipment. It's still not as efficient as the rectif
      • also a dc set will give off less heat leading to less need for AC

        • Re: (Score:3, Informative)

          by Chris Snook ( 872473 )
          Yes, but how much less heat? DC rectifiers waste heat too. 3-phase power supplies on blade chassis are considerably more efficient than typical 1-phase pizza box power supplies. The blade system has an efficient entry cost an order of magnitude more than the pizza box, and 3 orders of magnitude less than the DC data center, but is closer to the DC data center in AC conversion efficiency. This makes it a very good compromise for the vast majority of enterprises that do not buy their data centers by the a
  • OK, so I am a desktop/notebook guy. So this stuff may already exist for servers - but:

    1) With multiple front-end servers behind NLB, make the NLB smart enough to put some servers to sleep when their processing isn't needed and wake-on-lan those servers (or the equivalent) when they are needed again?

    2) Do servers do "speedstep" like desktops/notebooks where the processors and other components go to lower power level modes when they are not being fully utilized? If not, they should enable that.
    • Most servers run 24/7, so sleep mode would do more harm than good.
      • Most servers are also overpowered for the workload they perform. Just getting people to stop running 3GHz processors when a 1Ghz Sempron would do, would be a nice start.

        • Replacing old boxes with blade servers are a nice touch. In mose cases they use far less energy then the previous box, but yes if you have a file server connected to a SANs and its only real reason is for OS there's no need for dual quad cores. But, in the case of say a SQL or IIS/WEB server, you need both horsepower and 24/7 response times. So, a sleep mode wouldn't help you in that case.
    • AMD processors "speedstep" (it's why we purchased AMD boxes for our hosting operation). We've saved a huge amount on power (our datacenter does metered power, not flat rate power) due to this.

  • Federal Guidelines for Clock Speed Limits (Score:4, Funny)

    by infonography ( 566403 ) on Monday August 06, 2007 @01:30PM (#20131903) Homepage
    55 Mhz that's the law, exceed it and your looking at a speeding ticket.
  • http://www.eweek.com/article2/0,1895,2000867,00.as p [eweek.com]

    Also reduces a major cost and greenness problem: all those little redundant ac/dc power supplies in those rackmount machines. Further, it allosw you to take the heat generated by the power conversion to another nearby location, reducing the CFM reqs for your cooling system.

    • Yup...You replace all your AC->DC power supplies with DC->DC power supplies in the servers. It seems like the real benefit of the setup you linked to is the fact that it operates at 380v to the servers, which most likely allows for more efficient power supplies. You would probably see a lot of these benefits by switching to a higher voltage of AC, but you wouldn't want to run 5vdc and 12vdc through the whole data center, not without running copper wires the size of small tree trunks.
  • We've all been hearing ad nauseum about power and cooling issues in the data center.

    Whose data center? Mine? Yours? The EPA's?

    Please don't butcher the English language like that. Throwing random articles around is a sign of laziness (similar in magnitude to "They said...").

    Brought to you by SIAA (Society against the Indiscriminant Abuse of Articles)
  • Does this mean an Energy Star computer would be Sales Tax Free in Connecticut like appliances are?

  • Higher voltage (Score:3, Informative)

    by Skapare ( 16644 ) on Monday August 06, 2007 @06:09PM (#20135261) Homepage

    I have found that stock switching power supplies as found in common computers are slightly more efficient when powered with 240 volts rather than 120 volts. Some more so and some less so. And virtually all of them can be changed over to 240 volts (having the correct 2-pole switching).

    And by using 240 volts instead of 120 volts, you can run twice as many computers on the same power loss in the building wiring (same current, same size wire, same power loss due to heat, serving twice the load).

    Direct DC fed power systems may or may not provide realistic savings. DC introduces new electrical safety challenges and costs (electrical arcs inside switches, circuit breakers, and fuses, cannot be cut off by AC's zero voltage crossing that DC does not have). This requires lower voltages for equivalent interruption safety. But if power supplies end up losing less power than the building wiring at the higher current, then DC may be the better choice.

    We will need more in-depth study to determine if DC will save power or not at a given installation (it may at some and not at others). But for most installations, going from 120 volts up to 208 or 240 volts (depending in which is available) is as simple as rewiring the system (using 2-pole breakers ... requiring double size power panels) and verifying the computer power supplies are ready for the higher voltage.

    208 volts is the likely line-to-line voltage in data centers powered by 3-phase (208Y/120) power in North America. Future data centers could be designed for a 416Y/240 volt power system which can also be used to power fluorescent lighting.

  • FFS (Score:2)

    by 1u3hr ( 530656 )
    We've all been hearing ad nauseum

    "ad nauseam"

    Yeah, it's an obscure word. Is it really such an imposition to ask "editors" to use a fucking dictionary? Took me 5 seconds to confirm my suspicion.

Slashdot Top Deals

He has not acquired a fortune; the fortune has acquired him. -- Bion

Close