Slashdot Mirror


IBM Pushing Water-Cooled Servers, Meeting Resistance

judgecorp writes "IBM has said that water-cooled servers could become the norm in ten years. The company has lately been promoting wider user of the forty-year-old mainframe technology (e.g., here's a piece from April 2008), which allows faster clock speeds and higher processing power. But IBM now says water cooling is greener and more efficient, because it delivers waste heat in a form that's easier to re-use. They estimate that water can be up to 4,000 times more effective in cooling computer systems than air. However, most new data center designs tend to take the opposite approach, running warmer, and using free-air cooling to expend less energy in the first place. For instance, Dutch engineer Imtech sees no need for water cooling in its new multi-story approach which reduces piping and saves waste."

159 comments

  1. Any prediction over ten years is null and void by Meshach · · Score: 4, Insightful

    These kind of predictions always remind me of Bill Gates asserting that "640 K should be enough for anybody."

    Hardware and software faces change so fast; who has any idea what will be required or available in even ten years?

    --
    "Maybe this world is another planet's hell"
    Aldous Huxley
    1. Re:Any prediction over ten years is null and void by MrEricSir · · Score: 3, Informative

      I doubt Bill Gates ever said that. He's claimed the contrary on several occasions:
      http://www.usnews.com/usnews/biztech/gatesivu.htm
      http://www.wired.com/politics/law/news/1997/01/1484

      But yes, making predictions for the future is dumb. Unless you control the future, in which case it's not really a prediction *cough* Moore's Law *cough*

      --
      There's no -1 for "I don't get it."
    2. Re:Any prediction over ten years is null and void by Nefarious+Wheel · · Score: 2, Insightful

      It's much easier to predict the past, however, if you've been paying attention. Early computers blended their cooling system with the heating system of the surrounding building. They were sometimes designed together that way.

      --
      Do not mock my vision of impractical footwear
    3. Re:Any prediction over ten years is null and void by Anonymous Coward · · Score: 0, Flamebait

      I bet you're one of the luddites who thinks that bible is gods word, just because it says so...

      IBM was the evil empire before the evil empire. Yet they don't control much anything today.

      Have a nice day!

    4. Re:Any prediction over ten years is null and void by djdavetrouble · · Score: 1

      Early computers blended their cooling system with the heating system of the surrounding building. They were sometimes designed together that way.

      You know, one day a couple of years ago I saw something that really blew my mind. Our huge server room had an AC outage, and slowly things were starting to overheat.
      The server team dragged out fans and portable AC's and started shutting servers down, basically helpless. Meanwhile, less than 20 feet from the server room was a window
      that could not be opened, and the temperature outside that day was 20 degrees Fahrenheit. If only someone had thought to run a duct to the outside to use natures AC, they could have
      saved a lot of money and headache.

      --
      music lover since 1969
    5. Re:Any prediction over ten years is null and void by Myrimos · · Score: 1

      These kind of predictions always remind me of Bill Gates asserting that "640 K should be enough for anybody."

      I doubt Bill Gates ever said that. He's claimed the contrary on several occasions...

      Be that as it may, it's still fun to claim otherwise.

      --
      Internet scofflaw
    6. Re:Any prediction over ten years is null and void by corky842 · · Score: 1
      He did say that, but it was taken out of context:

      The full speech

    7. Re:Any prediction over ten years is null and void by Anonymous Coward · · Score: 0

      These kind of predictions always remind me of Bill Gates asserting that "640 K should be enough for anybody."

      [citation needed]

    8. Re:Any prediction over ten years is null and void by TheVision · · Score: 1

      ...and the temperature outside that day was 20 degrees Fahrenheit. If only someone had thought to run a duct to the outside to use natures AC, they could have saved a lot of money and headache.

      Desert-dry air and static sensitive devices. Brilliant!

    9. Re:Any prediction over ten years is null and void by jbengt · · Score: 1

      f only someone had thought to run a duct to the outside to use natures AC, they could have saved a lot of money and headache.

      Or, they could have, you know, put some A/C on the emergency back-up power.
      Backing up power to the servers without backing up power to the A/C really just allows for an orderly shutdown.

  2. What a waste of water! by failedlogic · · Score: 1, Funny

    The community in which a server farms is found surely has a need for what will be thousands of gallons a day. To the benefit of all, I'd suggest diverting a small amount of the heated water (hopefully near boiling) to another piping system in the building .... which would be routed to a building-wide coffee or espresso maker. Great for the employees and with an outside tap, the community can get free coffee to boot. If anyone from Greenpeace shows up to protest about the water wastage, avoid telling them about the coffee maker - it'll keep them up longer to protest.

    1. Re:What a waste of water! by Tablizer · · Score: 2, Funny

      would be routed to a building-wide coffee...the community can get free coffee to boot.

      Is that a pun?
         

    2. Re:What a waste of water! by Ed+Avis · · Score: 1

      Good idea! And the server farm can come ready-equipped with a camera and web server to show the status of the coffee maker.

      --
      -- Ed Avis ed@membled.com
    3. Re:What a waste of water! by More_Cowbell · · Score: 0, Troll

      I'm finding it hard to believe that someone with such a low /. UID would not know that water cooling systems for computers are self contained... (at least traditionally, TFA does not suggest otherwise).

      --
      Experience teaches only the teachable. -AH
    4. Re:What a waste of water! by seanadams.com · · Score: 5, Interesting

      The community in which a server farms is found surely has a need for what will be thousands of gallons a day. To the benefit of all, I'd suggest diverting a small amount of the heated water (hopefully near boiling) to another piping system in the building ....

      I'm sure it could be designed as a closed system with a heat exchange into the ground or outdoors. Indeed, it is the high temperature (relative to outdoors) at which the water is extracted straight off the CPU which makes this more efficient than air conditioning.

      However if you wanted to let it feed into the building's hot water system, it turns out there is already a really elegant way to do that: a tempering valve. It's a mechnical device which chooses the right amount of hot and cold water (each of arbitrary, variable temperatures) to produce some fixed output temperature. So to make moderately hot water you can combine some warm water from the servers and some super hot water from the boiler. The "free" server heat offsets the amount of water that needs to be heated by conventional means.

    5. Re:What a waste of water! by jcr · · Score: 1, Insightful

      Greenpeace is no better than PETA.

      I beg to differ. Greenpeace is sleazy, but PETA is a nut-cult.

      -jcr

      --
      The only title of honor that a tyrant can grant is "Enemy of the State."
    6. Re:What a waste of water! by DigiShaman · · Score: 1

      That's still quite a bit of hot water. I'm sure very little would be used in an office environment. Residential would be more like it if possible.

      Perhaps it would be better to engineer the hardware to run warm-hot. Having to chill the water down to outside ambient temp (no compressors needed) would save a lot of energy and cost.

      --
      Life is not for the lazy.
    7. Re:What a waste of water! by Hognoxious · · Score: 2, Funny

      Self contained would imply no radiation / conduction / convection of the waste heat generated by the CPU.

      I agree. Any alternative interpretation - such as that it recirculates the water - is clearly preposterous.

      --
      Confucius say, "Find worm in apple - bad. Find half a worm - worse."
    8. Re:What a waste of water! by Chrisq · · Score: 1

      That's still quite a bit of hot water. I'm sure very little would be used in an office environment. Residential would be more like it if possible.

      Perhaps it would be better to engineer the hardware to run warm-hot. Having to chill the water down to outside ambient temp (no compressors needed) would save a lot of energy and cost.

      Maybe google could get an environmental initiative grant to provide a staff swimming pool.

    9. Re:What a waste of water! by Chrisq · · Score: 1, Flamebait

      Greenpeace is no better than PETA.

      I beg to differ. Greenpeace is sleazy, but PETA is a nut-cult.

      -jcr

      Great pun - if you've ever been to a PETA buffer you will know that there are plenty of nuts around

    10. Re:What a waste of water! by jabithew · · Score: 1

      You're not going to get water hot enough to make coffee unless you run the servers at 90C+. There's that whole second law of thermodynamics thing. You also need a temperature gradient to drive heat transfer according to the basic heat exchanger design equation:

      Heat transfer=Heat transfer coefficient*area*mean temperature difference

      (You could use Fourier's law if you prefer).
      A better use would be a district heating across the building the server farm is in. How well that works depends a lot on where you are. But this scheme doesn't inherently waste either water or energy. It also allows you to run cooler, as most people won't want their rooms warmer than 30C. I think that a waste-free implementation would be very difficult to design though.

      --
      All intents and purposes. Not intensive purposes.
    11. Re:What a waste of water! by cdxta · · Score: 2, Interesting

      Why not just pipe the warm water from the servers in to the boiler and then the boiler has to heat the water less?

    12. Re:What a waste of water! by Anonymous Coward · · Score: 0

      you could always use excess warm water (in a closed loop) to "charge" a ground source heat pump therefore storing the heat for use later in the year underground (GSHP's don't always keep up with the heat required and can need additional heat input from a boiler or furnace). Given the temperature a few feet under ground is still fairly cool even in summer the returning water ought to be relatively cold. This would improve the efficiency of GSHP, other things like placing the pipes for the heat pump under a black-topped carpark (these can reach over 40C even in temperate climates) would further reduce heating costs. systems have been trialled ,in scotland (i think), to keep roads ice free during winter using heat gathered from beneath the road surface during summer and stored in insulated underground water tanks, mostly these just need a solar powered water pump and a thermostat and keep the road around 3C.

    13. Re:What a waste of water! by Anonymous Coward · · Score: 0

      Is that a pun?

      Yes, son. Puns are fun.

    14. Re:What a waste of water! by vtcodger · · Score: 1

      ***Given the temperature a few feet under ground is still fairly cool even in summer the returning water ought to be relatively cold.***

      Well, yeah. But isn't that because dirt is a lousy heat conductor? What's going to happen when you start trying to exchange a gazillion BTU per hour generated by your server farm into it? I'm not sure that you are wrong, but I think you might be. The ground just might not behave like an infinitely large heat sink/source?

      --
      You can't see ANYTHING from a car, You've got to get out of the goddamned contraption and walk...Edward Abbey
    15. Re:What a waste of water! by Sparky+McGruff · · Score: 0, Offtopic

      Greenpeace is sleazy, but PETA is a nut-cult.

      Are those nuts water cooled?

    16. Re:What a waste of water! by horza · · Score: 1

      You could force the techies to take a shower at least once a day, to drain off the excess hot water, though this scheme may find some staff resistance.

      Phillip.

    17. Re:What a waste of water! by Anonymous Coward · · Score: 0

      earth has a high thermal capacity and takes a long time to heat up, which is good. so it stores a lot of thermal energy without raising the temperature so much (there is a difference between heat and temperature), but if combined with some of the other suggestions(swimming pools, hot water, space heating etc) it could provide a means to put some waste heat to use, that would other wise require energy to return to a suitable temperature.If the area and amount of tubing was correctly calculated it could handle a gazzilion BTUs, it might not be a practical size but it could handle it if you could fit it.
      The millennium seed bank project on Svalbard used huge temporary chiller units to cool the surrounding rock to -18C during preparation and once the required temperature was reached these were replaced with far smaller units,just to maintain the temperature, (for centuries, as far as i understand the idea) using the ground for thermal storage is not so new, ground source heat pumps are well established but seem to work better when there is some means to return heat to the ground, summer cooling or other refrigeration systems (even heard of ice rinks!) these things use, i think, ~1/3 the energy to provide the same heat as generating the heat directly, since its just being moved rather than created.

    18. Re:What a waste of water! by 0racle · · Score: 1

      There is already a RFC defining a protocol for this, no need to reinvent the wheel.

      HTCPCP

      --
      "I use a Mac because I'm just better than you are."
    19. Re:What a waste of water! by jhw539 · · Score: 1

      Perhaps it would be better to engineer the hardware to run warm-hot. Having to chill the water down to outside ambient temp (no compressors needed) would save a lot of energy and cost.

      YES! This is exactly the approach being used currently in the most efficient (short of insane, no-cooling in a tent one-offs) datacenters today. Design the system to provide adequate space control at the typical outside ambient. Direct water cooling isn't even required, it can be done with large coils and evaporation cooling towers to take advantage of the wetbulb depression. As for energy savings, well on a typical 15 MW datacenter you can save about 6 MW for 8000 hours a year... That adds up fast.

    20. Re:What a waste of water! by drinkypoo · · Score: 1

      If you have more hot water than you can use, it seems like you could pipe it next door, and charge them some fraction of what they pay to heat water, or even simply trade it for cold water (which you need to cool your servers.)

      --
      "You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
    21. Re:What a waste of water! by gringofrijolero · · Score: 1

      ...water cooling systems for computers are self contained...

      Not always...

      --
      Todos mis movimientos están friamente calculados
    22. Re:What a waste of water! by adolf · · Score: 1

      What if you need more hot water (in terms of volume) than the loop through the server room(s) can provide? All the hot faucets on at once. Someone in the kitchen filling up a steam kettle. Power-washing the lot. (Or any combination of these things.)

      At that point, you'd still need some sort of relatively complicated valving to bypass the server room loop for these instances. And as long as you're adding complexity, one might as well just use a tempering valve and be done with it.

    23. Re:What a waste of water! by daveime · · Score: 1

      Yes, but there is something inherently wrong with worrying about "efficiency", when formerly the heat would have been simply wasted and dispersed into the atmosphere.

      *Any* system that takes waste heat and converts it, via Stirling Engine or whatever, to a useful form again is efficient ... at least *more* efficient than simply wasting it.

    24. Re:What a waste of water! by Anonymous Coward · · Score: 0

      (there is a difference between heat and temperature)

      I stopped reading at this bullshit.

  3. hmm.. by off1c3r · · Score: 1

    Seems like if one system goes bad, they have to shut down the whole array because of the water process? I guess when people complain about not having hot water, they won't call their utilities anymore, it would be the datacenter.

    1. Re:hmm.. by XDirtypunkX · · Score: 1

      A little piece of technology called an "isolation valve" helps with that one.

    2. Re:hmm.. by Anonymous Coward · · Score: 2, Insightful

      This is IBM... Do you _really_ think they'd design it in such a way that you'd have to take down the whole thing to fix a small section?

      You wouldn't have one long pipe running to all of them, with no way to shut off segments/individual nodes.

    3. Re:hmm.. by Chrisq · · Score: 1

      This is IBM... Do you _really_ think they'd design it in such a way that you'd have to take down the whole thing to fix a small section?

      You wouldn't have one long pipe running to all of them, with no way to shut off segments/individual nodes.

      No, but they might assume that the world will never need more than one hot water system.

    4. Re:hmm.. by Nefarious+Wheel · · Score: 2, Insightful
      Sort of depends on where the water's coming from, doesn't it? I remember once when the water piping in an old -- think it was a 360/95 or some such oddity -- failed (yes, it was a looong time ago) and the area under the false floor flooded. This was before Ethernet and the floor was a rats nest of individual terminal cables (not from the 360) -- hundreds of them, along with power cabling. The real problem surfaced (so to speak) some time later, when the actual rodents who did make a rats nest of it displayed the properties of dissolved urea and the effect of said resultant acid on the pre-teflon (I did say it was a while ago) cable insulation.

      Needless to say, it was a rat shit situation, and I was never more glad that I'd gone down the software track. Nobody wanted to get anywhere near the network guys for a while.

      --
      Do not mock my vision of impractical footwear
  4. Re:Frosty Piss by Tablizer · · Score: 0, Offtopic

    I like to water-cool my balls.

    I had a Japanese car that used to blow A/C down there. It was great; balls are on the outside of the body because they don't like body heat. Maybe Japan sells special water-cooled underwear. After all, they specialize in high-tech toiletries. (Just hope it doesn't spring a leak during a presentation.)

  5. When I come to office today by jigyasubalak · · Score: 1, Funny

    I attach the power cable and the network cord to my laptop.
    So, will I, now, need to connect a water pipe carrying cold water too?
    I wouldn't mind it if I can get my drink of water from it too :)

    --
    The best planning can be done after the project completes.
    1. Re:When I come to office today by Hurricane78 · · Score: 2, Interesting

      In case you didn't know: Water cooling must be in a closed loop. You should not ever need to replace that water. If you do, you can destroy your coolers, because growing crystals will burst them. I have seen pictures of that.

      --
      Any sufficiently advanced intelligence is indistinguishable from stupidity.
    2. Re:When I come to office today by miffo.swe · · Score: 4, Informative

      Problems with crystals comes with some types of water where there are a high degree of lime in it. While its simpler to just use heat exchangers you could also use waterfilters that separates the minerals from the water before use. Most places have water with low amounts of lime and minerals so deposits arent really a problem.

      I had a company that made solar panels (heating houses) and inverters for house warming. In some cases we took ground water and extracted heat directly from it and when taken apart those heat exchangers very rarely showed any deposits at all even after ten years of use.

      The easiest way to see what type of water you have is to look in your toilet and your sink. If there are much deposits there (not brown ones) you have water thats high with lime or other minerals.

      --
      HTTP/1.1 400
    3. Re:When I come to office today by sjames · · Score: 1

      They should have periodically flushed the system with a scale remover. However, it is better to keep the system closed. If evaporative cooling is wanted, that should be done in a secondary loop with a heat exchanger.

    4. Re:When I come to office today by Hurricane78 · · Score: 1

      I'm talking about crystals that you get with *distilled* water. ^^
      (Because it's never perfectly 100% pure.)

      --
      Any sufficiently advanced intelligence is indistinguishable from stupidity.
    5. Re:When I come to office today by miffo.swe · · Score: 1

      The problem is that something in contact with the water dissolves into the water and then build up at another place. Probably crappy aluminum or a completely wrong alloy for using in water.

      --
      HTTP/1.1 400
  6. Personally, I like the idea. by Anonymous Coward · · Score: 3, Interesting

    look at some of the newer blades or blade-ish solutions from supermicro, with 4 dual-socket boards in 2u. Dang near half the space is now taken up by ram slots. Suppose they switched to sodimms packed in like heatsink fins on one of those boards, and you could possibly cram in 2 more sockets with waterblocks.

    Similar re-arrangement with blade boards would likely also be possible.

    In a dedicated datacenter, I can't think of any real great money saving solutions for the waste heat, but it WOULD allow you to more easily cool everything with a large ground loop to get 50-55 degree water. Add a few more loops so you can melt the snow off the parking lot in the winter and bleed off heat there. Add a large tank of water and radiators to take advantage of cool nights to pre-cool the water before the chillers.

    Only chill the water with the chillers when needed. Seems to make a lot of sense to me.

    In smaller serverrooms in large office buildings, pre-heat the hot water, pipe the hot water to help heat the building in the winter, and depending on location and if its a mixed use building, you MIGHT be able to sell some of the heat to other building tenants.

    Personally, if I was building a new house, I'd have ground loop heat pump for cooling, heating, put a decent sized water tank on the top floor/attic that I could use to preheat hot water in the winter (also be good to hook into for solar hot water on the roof) and a water tank in the basement/crawl space as a source for cooling. Add some electronics to determine where to draw water source, and where to push water return for different devices depending on temperatures of each given tank, as well as when to run ground source heat pump or outside radiator and I think I could cut heating/cooling costs by a huge margin.

    Now if only we had a good way to pipe the light from all the blinking LED's to where its needed to remove the ugly florescent lighting. That or get everyone to work by the glow of their CRT/LCD

    1. Re:Personally, I like the idea. by jhw539 · · Score: 1

      A ground loop is not effective for a continuous cooling load - the ground loop is more a season heat storage medium than a heat sink. A cooling tower system is the traditional approach to achieving water at 55F for free cooling. Actually, we're using air to water coils that control datacenter temperature with 65F water, which can be achieved the majority of the time from cooling towers in many climates.

  7. Resistance by spectrokid · · Score: 5, Funny

    If they meet resistance, can't they just add some salt to the water?

    --

    10 ?"Hello World" life was simple then

    1. Re:Resistance by Korbeau · · Score: 1

      they should just use air, no?

    2. Re:Resistance by drunkenoafoffofb3ta · · Score: 1

      seems like if water is meeting resistance, then pressure's building up. Server explosion!

    3. Re:Resistance by jabithew · · Score: 1

      Is it bad that I actually winced when I read that?

      --
      All intents and purposes. Not intensive purposes.
    4. Re:Resistance by Antique+Geekmeister · · Score: 3, Funny

      That's because salt isn't the solution, it's the precipitate.

      _Ouch_. Please stop hitting me.

    5. Re:Resistance by Anonymous Coward · · Score: 0

      You've misinterpreted it.

      The servers they're pushing are bulky, and resist being pushed.

    6. Re:Resistance by GaryOlson · · Score: 1

      rimshot
      Hey, there's a crust on that rim.

      --
      Every mans' island needs an ocean; choose your ocean carefully.
    7. Re:Resistance by Anonymous Coward · · Score: 0

      Except that it dissociates in water. It _is_ part of the solution.

  8. Re:Frosty Piss by sigxcpu · · Score: 3, Informative

    Some tanks have air conditioning.
    Air conditioning the whole tank does not make sense because once you fire the cannon a few times the whole place is very hot.
    What they do is have a hose that hooks up to the special overall tankers wear and supplies you with cool air where you need it most.
    The hose connector is at the center of the suit.

    --
    As of Postgres v6.2, time travel is no longer supported.
  9. Not for all by __aarvde6843 · · Score: 5, Interesting

    I worked in several banks using IBM mainframes. The server room was always like a freezer.

    I think for now, many companies are perfectly ok with air cooling solutions. Besides, it's much safer to have air-conditioning and fans than some liquid flowing. The simpler the system, the less accidents occur within it...

    And believe me when I say that, if a company owns an IBM mainframe, they pay big bucks and they *don't* want any accidents.

    1. Re:Not for all by Hognoxious · · Score: 1

      I worked in several banks using IBM mainframes. The server room was always like a freezer. I think for now, many companies are perfectly ok with air cooling solutions.

      Me too. I didn't have to wear an aqualung and enter through an airlock, so they can't have been water cooled.

      And believe me when I say that, if a company owns an IBM mainframe, they pay big bucks and they *don't* want any accidents.

      Better steer clear of them there new-fangled 3090 models, then. It's a fad, I tell you.

      --
      Confucius say, "Find worm in apple - bad. Find half a worm - worse."
    2. Re:Not for all by stephanruby · · Score: 3, Insightful

      I think for now, many companies are perfectly ok with air cooling solutions. Besides, it's much safer to have air-conditioning and fans than some liquid flowing.

      If some companies can make fridges that do not leak coolant. I'm pretty sure IBM can make mainframes that do not leak their coolant either.

    3. Re:Not for all by __aarvde6843 · · Score: 1

      The servers are already inside a big freezer.

      But I believe you are right. It doesn't leak any coolant (at least not directly to the servers) he he

    4. Re:Not for all by Chris+Mattern · · Score: 1

      it's much safer to have air-conditioning and fans than some liquid flowing.

      Because, of course, if you have A/C, then you don't have any liquids flowing.

      You have obviously never had the joy of having to deal with a data center where one of the A/C condenser lines broke.

    5. Re:Not for all by Anonymous Coward · · Score: 0

      If some companies can make fridges that do not leak coolant. I'm pretty sure IBM can make mainframes that do not leak their coolant either.

      All depends. Are we talking about the *old* IBM, or the new, use-cheapass-components-and-jackass-design IBM?

    6. Re:Not for all by Hymer · · Score: 1

      I think for now, many companies are perfectly ok with air cooling solutions.
      Yes, yes we are... but there are a lot of new environment-aware politicians and they will start making rules (aka. laws) as soon they realize how much energy we use just to keep our servers cool.
      We may wait for them to make rules or we can buy new watercooled servers from IBM and reuse the energy to heat our building or to heat the corporate pool (that has been done when we used mainframes).

    7. Re:Not for all by cthulhu11 · · Score: 1

      The 3083 that IBM gave CMU (and which mostly idled) periodically leaked coolant, some sort of glycol, entailing an evacuation of the floor and/or building. ~1986.

  10. Takes me back... by jcr · · Score: 2, Informative

    I remember that IBM had an office building in Manassas, VA that was heated by the mainframes in the building. They got a lot of press at the time for that.

    -jcr

    --
    The only title of honor that a tyrant can grant is "Enemy of the State."
    1. Re:Takes me back... by JDub87 · · Score: 1

      I was born and raised in Manassas, VA - I never heard of or saw this IBM building... how long ago was this?

    2. Re:Takes me back... by jcr · · Score: 1

      I think it would have been around 1979 or so. It belonged to IBM's federal systems division.

      -jcr

      --
      The only title of honor that a tyrant can grant is "Enemy of the State."
  11. I watercooled my server years ago!!! by therufus · · Score: 0

    Try to keep up IBM. I built my computers years ago. I built a server/workstation 2 PC combo in a rack unit and used watercooling to cool both computers. In a server farm situation it makes sense too. You can recycle your water and I think it would be cheaper to cool water than air. Am I right?

    --
    You moved your mouse. Please restart Windows for changes to take effect.
    1. Re:I watercooled my server years ago!!! by f0dder · · Score: 1

      What was your server uptime? Are they still running?

    2. Re:I watercooled my server years ago!!! by Hurricane78 · · Score: 2, Informative

      You can recycle your water

      I'm not exactly sure what you mean by that, but either way you can't.
      In case you mean replacing the water: You're doing it wrong! ^^ The more often you replace the water, the more likely it is for your coolers to get some mineral crystals to grow. In two years, your CPU cooler might suddenly burst, killing your whole electronics.
      This even happens with distilled water, because there is no 100% in nature.
      There are even galleries out there of such bursts, including images of huge crystals inside the coolers.

      So usually, you use some protective fluid to mix with the water. And that stuff can't be recycled I think.

      --
      Any sufficiently advanced intelligence is indistinguishable from stupidity.
    3. Re:I watercooled my server years ago!!! by jcr · · Score: 4, Informative

      Try to keep up IBM.

      IBM was water-cooling machines at least as early as the 1970s.

      -jcr

      --
      The only title of honor that a tyrant can grant is "Enemy of the State."
    4. Re:I watercooled my server years ago!!! by Hognoxious · · Score: 2, Informative

      True, and everybody knows that.

      Or so I thought. Yet this assclown, who clearly doesn't know the difference between an IBM and a BMW, is at +5 insightful.

      --
      Confucius say, "Find worm in apple - bad. Find half a worm - worse."
    5. Re:I watercooled my server years ago!!! by Anonymous Coward · · Score: 0

      You keep repeating this. It's a legitimate issue - for hobbyists. I am guessing the photos you have seen were of hobbyist systems.

      Do you really think IBM is going to pour hard water into their reservoirs? Do you think they aren't going to put additives in the water and treat the plumbing to eliminate deposits? They are engineers who have thought about this problem for a long time, and they are supplying systems to companies who are paying a lot of money.

    6. Re:I watercooled my server years ago!!! by rackserverdeals · · Score: 1

      Pfft. You need to keep up. The future of data center cooling is oil.

      Personally, I prefer bacon fat for the extra flavor.

      --
      Dual Opteron < $600
    7. Re:I watercooled my server years ago!!! by iggymanz · · Score: 1

      1960s, and more vendors than just IBM.

  12. IBM needs a physics lesson by Saysys · · Score: 1

    We could save a lot of money by putting all that light-bulb heat to use.. to bad entropy makes these sorts of schemes uneconomical.

    1. Re:IBM needs a physics lesson by RsG · · Score: 3, Interesting

      We could save a lot of money by putting all that light-bulb heat to use.. to bad entropy makes these sorts of schemes uneconomical.

      Entropy doesn't make those situations uneconomical. It makes them quite literally impossible.

      However, define "use". Remember that you can use heat for more than electricity generation (made impossible in this case). You can't get net energy out of it, thermodynamically speaking. Entropy reigns. But you can still use it as heat.

      Hypothetical example: you build a cooling system for a server (water, air, it doesn't matter). You now have a radiator giving off waste heat. That waste heat can be used for some other, non power-generating purpose. What matters is that the heat is carried away from the radiator at a constant rate, or the cooling system will have to work harder to get the same result.

      You could use a water tank as a heat sink, then use the heated water for the usual purposes (washing, cooking, what have you). As the hot water heater/heat sink is drained, cool water is pumped in to replace it, allowing the radiator to continue functioning. In this instance the heat is used directly, as heat.

      The reason this doesn't run up against thermodynamics is that the hypothetical second use of the heat replaces an existing system you'd have to generate heat for (a conventional hot water heater). The system is still entropic and inefficient, it's just less inefficient than generating the same heat energy a second time. You go from the net waste being X% to the waste being X%. Whether this is worth the bother is a question of the circumstances.

      --
      Erotic is when you use a feather. Exotic is when you use the whole chicken.
    2. Re:IBM needs a physics lesson by Anonymous Coward · · Score: 0

      In reality that also depends of the scale, I know a clear case in a factory, the put a heat electric generator to reuse the wasted head from a ceramic oven, in the numbers efficiency can be seen low (between 10% to 20%) but if you put absolute numbers the feat is not low as they are generating more than 30kw for their electrical installation.

    3. Re:IBM needs a physics lesson by Anonymous Coward · · Score: 0

      One aspect of using heated water for other purposes that I don't see addressed so far is that no municipality will allow a computer's or server farm's cooling systems to tap into a potable supply. Pretty much everything that's done to move the heat away from electronics will involve some level of heat exchanger. It may be as close as individual device heatsinks connected to insulated lines to an exchanger that heats water, or it may be an air system cooling a bank of devices into a more central heatsink, etc. But the process involved is to carry heat away from devices to a remote location, where the heat (but not the water / other liquid itself) is used.

    4. Re:IBM needs a physics lesson by turbidostato · · Score: 1

      "I know a clear case in a factory, the put a heat electric generator to reuse the wasted head from a ceramic oven, in the numbers efficiency can be seen low"

      In the numbers it won't seem low, either: they went from a situation where they lost *all* that energy to a situation where they lose just a *part* of it. Clearly advantageous.

  13. Great working conditions... by yogibaer · · Score: 5, Funny

    From the article: "We can use that to heat offices, or water for a swimming pool". Job Ad: "Wanted: Sysadmin, we offer: all year heated office (20+ C), swimming pool, Jacuzzi (body temperature) integrated coffe mug wamer in tabletop and always a nice, warm breeze from our datacenter." IBM could even use the swimming pool as a cooling tank (or is it the other way round?).

  14. 4000 times? by Lord+Lode · · Score: 1

    Where do people always get these kinds of numbers. I dare to guess that in reality it's not even 2 times more effective :p

    1. Re:4000 times? by theheadlessrabbit · · Score: 4, Funny

      Where do people always get these kinds of numbers.

      this is a situation where a link to goatse would actually answer your question.

      --
      -I only code in BASIC.-
    2. Re:4000 times? by Chrisq · · Score: 4, Insightful

      Just try this. See how long you can stand naked (OK wear some running shorts) in air at 5 degrees centigrade. Probably fifteen minutes standing still or indefinitely if running.

      Now see how long you can stay in water at 5 degrees centigrade. For most people it would be less than a minute - you may not even be able to get in.

    3. Re:4000 times? by TheTurtlesMoves · · Score: 4, Interesting

      Water has a density of 1000kg per meter^3. Air is 1Kg per meter^3. Water has a much higher heat capacity than air. Current systems go from CPU->Air->Water and you need a thermal gradient for each, not to mention that blasting cold air through a server wastes quite a lot of air. Cut out the air and 4000 times seems quite likely, but I can't be bothered running the numbers.

      --
      The Grey Goo disaster happened 3 billion years ago. This rock is covered in self replicating machines!
    4. Re:4000 times? by tangent3 · · Score: 1

      http://en.wikipedia.org/wiki/Specific_heat_capacity#Table_of_specific_heat_capacities

      Water: 4.186 J/cm^3/K
      Air: 0.001297 J/cm^3/K

      3227 is closer to 3000 than 4000 I guess.. but at least he got the right orders of magnitude

    5. Re:4000 times? by Targon · · Score: 1

      These numbers are generated scientifically, not just by some "study". Liquid cooling works MUCH better than air cooling, but generally requires more maintenance in a single computer system. With a full building system where water is being pumped in from a larger system, there might not be as much maintenance needed, but the need to replace various components, like the tubes or fasteners for the tubes might require more maintenance than some people are familiar with.

    6. Re:4000 times? by MartinSchou · · Score: 1

      A much simpler explaination is a nice hot oven. Not a problem sticking your arm in there, even if it's 200 C (392F) as long as you don't touch the sides. Not really recomended doing that with water that's not quite boiling (say 93 C, 200F).

    7. Re:4000 times? by Anonymous Coward · · Score: 0

      Yeah, right.

      http://en.wikipedia.org/wiki/Ice_swimming

    8. Re:4000 times? by Anonymous Coward · · Score: 0

      Now see how long you can stay in water at 5 degrees centigrade. For most people it would be less than a minute - you may not even be able to get in.

      or get out once you're in :)

    9. Re:4000 times? by Anonymous Coward · · Score: 0

      Where do people always get these kinds of numbers.

      this is a situation where a link to goatse would actually answer your question.

      ROTFLMAO.....Though I am still a little traumatized from the first time I saw that.

  15. Ratio of specific heat capacities by NCamero · · Score: 5, Informative

    All IBM is saying is that water is a better heat conductor, and air is an insulator.

    http://en.wikipedia.org/wiki/Specific_heat_capacity

    Water ; 4 J /cm^3 K
    Air ; 0.001 J /cm^3 K

    Water/Air = 4000 times more heat transfer.

    So, given the choice, you would use water to transfer heat.

    1. Re:Ratio of specific heat capacities by SlashWombat · · Score: 2, Insightful

      Yes, but eventually, all that heat ends up in the air anyway ... the water is only the middleman. Water is actually probably the most efficient coolant around, however, the latent heat of evaporation means it works best when it is boiled off the surface to be cooled. This is not exactly ideal for a semiconductor, although it might be okay if the water was in direct contact with the silicon. (Silicon junction temperatures must be kept below 360 degrees Celsius.)

    2. Re:Ratio of specific heat capacities by shentino · · Score: 1

      then datacenters simply need nuclear plant style evaporative cooling towers.

    3. Re:Ratio of specific heat capacities by dbIII · · Score: 1

      Spot on, plus evaporative cooling consumes a bit of water. Unfortunately they would also need a power station quality water treatment plant so all that hot copper doesn't corrode - that or use a lot of brass instead which is a reasonable conductor.

    4. Re:Ratio of specific heat capacities by Aceticon · · Score: 4, Informative

      My personal experience with using passive (no fans) water-cooling with my desktop PC at home (the setup is similar to this: http://www.silent.se/bilder/reserator1_c_p-410.jpg) is that that it's exceptionally effective.

      In my setup a cylinder full of water surrounded by fins to dissipate the heat and with a pump to make water flow as the only active element have replaced a big nasty CPU heatsink with a large fan (on a heavily overclocked CPU)* and a set of fans on a single high-end graphics card of the previous generation. At an ambient temperature in the room where this is in of about 20-25C The whole thing idles at 28C and stays at around 60C with everything going on at max - considering that with everything going on at full throttle the system is using almost 400W, it's impressive how efficient it all is.

      In practice, "home" water-cooling mostly just uses the water as a heat carrier to quickly move the heat around from the inside of the computer case (and it's constrained airflow) to a place where it is easier to dissipate that heat into the ambient air either with a more efficient radiator and fans (for the active systems) or with an outsized heatsink (like the one I use which has roughly 10 times the surface of the ones it replaces).

      In an "industrial" deployment, said heat being carried in the water cold potentially be used/dissipated in many more ways. For example large pipes could transport the hot water coming out of a data-center to the sea or a river and let it be dissipated there (keeping a closed circuit and returning the cool water back for reuse). The actual running costs in terms of active elements for such a system are limited to the cost of running a number of large efficient water pumps that make the water flow around the circuite as opposed to most data-centers out there at the moment that use (less efficient) small fans to move the air out of the blade boxes into the room and then active refrigeration to cool down the air in the room.

      * Since the point of my argument is not to show off my "virtual dick", I've moved the relevant stats down here for those that are curious on the details: CPU - Core 2 Quad 2.4 GHz which is overclocked to 3.2GHz, GPU - GTS280

    5. Re:Ratio of specific heat capacities by advocate_one · · Score: 1

      strictly speaking, a "Passive" cooling system has no moving parts... therefore your system was not passive as you had a pump.

      --
      Donald 'Duck' Dunn: We had a band powerful enough to turn goat piss into gasoline.
    6. Re:Ratio of specific heat capacities by Antique+Geekmeister · · Score: 1

      Yes, but you have to *pump* that air. Pumping all that air through your rack door, your server covers, past all the components in the server, and out that rat's nest of cabling at the back is awkward, expensive, and unreliable, especially with (as someone else pointed out) dust collecting and clotting your filters or collecting on your heat sinks. It's not as bad in a good server room because the air is filtered, but it still collects, especially in less sophisticated server environments such as many offices have. And snaking the airflow past the cabling is still pesky, although switching to thinner SATA and SAS cabling instead of IDE and SCSI have helped quite a lot. Getting that waterflow directly to the heat sink of the CPU, or at least to a big heat sink that the server will pull its air past, can make for a lot of both design and energy efficiency.

      These cooling issues are also why I take the doors and cute little server covers off all my equipment racks. There is nothing stupider in your data center than blocking the airflow with a door that you don't use, never lock, and which breaks protruding cable left by interns who haven't learned to wire neatly yet.

    7. Re:Ratio of specific heat capacities by Targon · · Score: 1

      You didn't mention that if the water is hot, it would be possible to recapture some of the energy in the form of an electric generator. The amount may not be terribly high initially, but if you are pumping water to help with cooling, the system could also supply some energy to help offset the water pump costs.

    8. Re:Ratio of specific heat capacities by Anonymous Coward · · Score: 0

      Ok. I am not saying your math is wrong. But if water is that much better at cooling. Why is the earth (75% water) suffering from Global Warming. We should be in '4000' ice ages... LOL

    9. Re:Ratio of specific heat capacities by russotto · · Score: 1

      I don't think they're talking about a phase-change cooling system; if they wanted to do that, there's liquids which boil closer to chip temperature than water.

    10. Re:Ratio of specific heat capacities by m50d · · Score: 1
      Water is actually probably the most efficient coolant around, however, the latent heat of evaporation means it works best when it is boiled off the surface to be cooled.

      Which is why mineral oil is often a better choice for computers - lower SHC, sure, but it's quite easy to get the boiling point at 50-70 degrees where you want it. I believe the original Crays had a very elegant system that worked this way.

      --
      I am trolling
    11. Re:Ratio of specific heat capacities by Anonymous Coward · · Score: 0

      Passive cooling means no fans, it makes no mention of pumps. It would be pretty stupid to have a water loop with stagnant water. I doubt anyone would call such a system remotely "cooling".

    12. Re:Ratio of specific heat capacities by NCamero · · Score: 1

      Pumping air is also much worse than pushing water around. Air is a compressible fluid, while water is practically incompressible. Extra energy is wasted at the pressure source (AC), and at the exit, as the air changes volume.

      A similar effect from the "canned air" that turns cold when uncompressed. Unless you are pushing that air over your skin while sweating in hot weather, the energy is pure extra waste. You cannot make a can of "compressed water", because it is not compressible.

    13. Re:Ratio of specific heat capacities by advocate_one · · Score: 1

      hey dimdill... passive means there is no external energy input to move the cooling medium... the liquid will circulate by convection...warm liquid rises and is replaced by cold liquid drawn in.

      and just FYI... I have professional experience in liquid cooling systems for very large server rooms... I was a commissioning engineer on a very large project in a west country town in the UK...

      --
      Donald 'Duck' Dunn: We had a band powerful enough to turn goat piss into gasoline.
    14. Re:Ratio of specific heat capacities by jbengt · · Score: 1

      At the pressures generated by fans in a typical data center A/C unit (around 2" water column or so, i.e. less than 0.1 psi) engineers can model air as incompressible for the purposes of designing the fans, ducting, etc. with more than sufficient accuracy.

    15. Re:Ratio of specific heat capacities by turbidostato · · Score: 1

      "Passive cooling means no fans"

      No, sir. Passive cooling means, as its name itself implies, no active means for cooling. That means no induced-moving parts, be them either fans, or pumps or anything else (passive-moving parts, like a turbine on a vehicle at a speed would be OK).

      "It would be pretty stupid to have a water loop with stagnant water"

      But it would be pretty clever using, i.e. the temperature gradient itself to move the water by means of convection on a closed circuit from the hot to the cold spot, wouldn't it? And exactly *that* is what it takes for a passive cooling system to stay passive.

      "I doubt anyone would call such a system remotely "cooling"."

      Anyone... but anyone with a barnish of engineer-101.

    16. Re:Ratio of specific heat capacities by turbidostato · · Score: 1

      " I am not saying your math is wrong. But if water is that much better at cooling. Why is the earth (75% water) suffering from Global Warming."

      I know you were joking, but anyway.

      Earth mass is about 5.9742×10^24Kg, where all the oceans' watter mass is about 1.4×10^21Kg, or about 0.023% of the Earth's total mass, so the Earth as a whole is basically a very dry rock.

      On the other hand, global warming is, of course, a surface effect: water is that much better at cooling because it's that much better at exchange (and collect) heat that air, which you can have it both ways. That's what you can get both ice ages and greenhouse ages.

    17. Re:Ratio of specific heat capacities by Anonymous Coward · · Score: 0

      The IBM system is definitely single phase - no boiling. Yes, boiling the water would allow much higher heat transfer, but unless you reduce the pressure to way below one atmosphere, the temperature at which it boils will be too high to be of much good. Not sure where you get the 360C junction temperature - most parts that I work with have maximum junction temps of 125C at most. Mil-Spec parts can go higher, but certainly not 360C. Some of the wideband gap semiconductors can operate at higher temperatures, but finding packaging that can handle thosse high of temps is difficult.

      Regarding direct contact of water with the silicon - no way you can do it on an active surface. There has been a lot of work looking at putting microchannels in the back of integrated circuits and water could potentially be used. But it seems to me that it would be a definite challenge in real world integration. Even if you are using DI water, which is a dielectric, it won't stay deionized for long in the system as it picks up stuff.

      So water cooling is always indirect and in electronics cooling virtually always single phase (one exception would be heat pipes in which the pressure is low enough that the water can boil at room temperature). Direct cooling, such as what Cray did in the SV2, uses Fluorinert (typically FC-72, although 3M is going away from those fluorinerts due to new restrictions; I think that the replacements are HFE's?). Dielectric fluids such as FC-72 pretty much suck thermally in every way except that they are dielectric and their boiling point can be tailored (heat capacity and thermal conductivity of water are by far better).

  16. Air is not necessarily simpler by Kupfernigk · · Score: 5, Interesting
    Actually, you are wrong. Designing an air cooled system is hard. You have to deal with problems of filtration (there will be dust - but where do you want it to build up?), ensuring that the flow goes where you want, turbulence, finding room for the ducting, designing the system so that components do not mask other components, and needing to handle high volumes of air. With properly designed water cooling, you have a few quite simple heat removal blocks and a simple plumbing system which can route pretty much anywhere.

    This is why nowadays virtually all internal combustion engines of any power output use liquid cooling despite the apparent reliability benefits of air cooling. To take the transition period, WW2, as an example, you only have to look at the complexity of American rotary aircooled designs versus, say, the liquid cooled Merlin engine, to see the point. It would be astonishing if the same transition did not eventually occur for large computers.

    --
    From scarped cliff or quarried stone she cries "A thousand types are gone, I care for nothing, no not one."
    1. Re:Air is not necessarily simpler by mangu · · Score: 3, Informative

      you only have to look at the complexity of American rotary aircooled designs versus, say, the liquid cooled Merlin engine,

      I think you mean radial engines, because rotary engines may look similar when not running but are an entirely different thing.

      Air cooled engines are still used in small planes, their weight to power ratio is better than in water cooled engines. In larger aircraft both water and air cooled engines were replaced by turbines.

      Also, air cooled engines are still widely used in motorcycles. I think the main motive for not using them in cars anymore is due mostly to the difficulty in cooling in an enclosed region, have you seen how cramped is a modern car under the hood?

      The main advantage of water cooling is that it's easier to carry the heat away to some place where it can be either reused for some other purpose or dumped to the environment. With air cooling you have to bring a substantial amount of cool air to where the heat is being generated.

      However I still think computers are mostly in the range where it's easier to bring the air in. The amount of heat dissipated per volume of equipment is not so great that the additional complexity of water cooling would be justified.

    2. Re:Air is not necessarily simpler by Targon · · Score: 1

      I would expect it to happen eventually to normal home computers, the key is in how reliable the systems are, plus getting the public to be aware of adding new coolant to the system. Many people HATE how loud computers can be, so liquid would help solve that in the long term.

      Before you can point out the problems with end-users and water cooling, keep in mind that as any technology gains in popularity, there will be increasing amounts of innovation that would improve on the designs.

    3. Re:Air is not necessarily simpler by lazyforker · · Score: 1

      Also, air cooled engines are still widely used in motorcycles. I think the main motive for not using them in cars anymore is due mostly to the difficulty in cooling in an enclosed region, have you seen how cramped is a modern car under the hood?

      Water-cooled engines are quieter. In addition to the sound-baffling that water provides, many air-cooled engines need additional fans. Think of the original VW Beetle or the older Porsche 911's. Their engines sound a lot different from most cars.

    4. Re:Air is not necessarily simpler by iamhigh · · Score: 1

      Wait, are we talking about water-cooled servers (as in the water flows right over the cpu) or water-cooled rooms? Because if it is the former, then you are probably still going to have to deal with an air cooling system. Perhaps it won't be as complex or as important in the overall sense, but you probably still have to have the room cooled in some fashion, which brings up most of the issues you claim it will remove. If it is the latter, then I am unaware of the feasibility of water cooled rooms with such heat producing monsters as a room full of racks.

      --
      No comprende? Let me type that a little slower for you...
    5. Re:Air is not necessarily simpler by Zontar_Thing_From_Ve · · Score: 2, Interesting

      Actually, you are wrong. Designing an air cooled system is hard. You have to deal with problems of filtration (there will be dust - but where do you want it to build up?), ensuring that the flow goes where you want, turbulence, finding room for the ducting, designing the system so that components do not mask other components, and needing to handle high volumes of air. With properly designed water cooling, you have a few quite simple heat removal blocks and a simple plumbing system which can route pretty much anywhere.

      The reality is that there are pros and cons to water cooling vs. air cooling and people have to weigh both and decide what works for them. While your post is essentially correct, it's also a bit heavy on the theoretical. I remember working at a place that had water cooled IBM mainframes. This was a US government facility and it was in a building I almost never had to go to. I remember downtimes there because "the water chiller is down" or there was a leak and a hellacious mess of water was under the floor. So please do not continue to suggest that water cooling is 100% great and has no flaws. People went to air cooling for a reason - to stop having to deal with the messes that could happen when there were leaks or downtimes when the water chilling device broke down.

    6. Re:Air is not necessarily simpler by jhw539 · · Score: 1

      I find it interesting that you bring up engines. With some clients now proposing things like 120 kW single racks, we honestly are approaching a computer rack putting off the same waste heat as a small automobile. And dealing with the waste heat needs to be treated the same way. The days of throwing CRAC units against the wall blowing into a raised floor are numbered unless power density starts trending dramatically down - you just can't control these types of loads that way.

    7. Re:Air is not necessarily simpler by BetterSense · · Score: 1

      Air cooled engines are no longer widely used in motorcycles. High-performance dirt bikes went water cooled about a decade ago and most road bikes that look air-cooled actually have finned water jackets and radiators. There are air-cooled motorcycles, but I would say that modern motorcycles are mostly water-cooled.

    8. Re:Air is not necessarily simpler by icebrain · · Score: 1

      This is why nowadays virtually all internal combustion engines of any power output use liquid cooling despite the apparent reliability benefits of air cooling. To take the transition period, WW2, as an example, you only have to look at the complexity of American rotary aircooled designs versus, say, the liquid cooled Merlin engine, to see the point.

      (disclaimer: I'm an aerospace engineer who flies homebuilt airplanes)

      I see what you're getting at, but comparing server cooling to aircraft engines is a little more complicated than that. The issue isn't really power output.

      The biggest benefit of the liquid-cooled engines of the era was that they were more easily packaged. Instead of having to have a big, round, gaping cowling with a radial engine, you could package everything into a nice, tightly-cowled, low-drag V-12 shape with a clean radiator duct somewhere else. You got a nice clean airframe from that, but you had to put in the radiator and all of the piping and regulation equipment associated with it. Sleek, fast, high-altitude fighters like the P-51 needed this drag reduction.

      Aircooling an aircraft engine, on the other hand, doesn't require ducting, radiators, or filters--you can quite literally have it just hanging out in the breeze. You do have to worry about the drag imposed by this arrangement, which is mostly done through careful attention to cowling shape and the cooling intlet/exhaust design. It's mechanically simpler.

      However, the most noticable difference is apparent in damage tolerance. A liquid-cooled engine is entirely dependent on its radiator and cooling fluid to keep working. A single little hole anywhere in your coolant loop meant that it was only a matter of time until your engine overheated and seized up. On the other hand, there are countless documented cases of radial-engined airplanes returning to their base or carrier with entire cylinders shot away, but the engines were still making power.

      I'd actually argue that the air-cooled engine won out for most piston-engined aircraft applications. Look at the late-war/post-war bombers and transports like the B-36, C/KC-97, Constellation, Skyraider, Tracker/Tracer, Neptune etc. All of them use radial engines. I believe the most powerful aviation piston engines were all radials. All of them were air-cooled. Air cooling is the overwhelming choice for light airplanes, with only a few special cases being liquid cooled. (the state of light airplane engines themselves is a matter for a nice long rant that I will spare you from).

      Of course, large piston engines virtually disappeared once turbines were available. More power and better reliability won the day.

      --
      The meek may inherit the earth, but the strong shall take the stars.
    9. Re:Air is not necessarily simpler by eldorel · · Score: 1

      People went to air cooling for a reason - to stop having to deal with the messes that could happen when there were leaks or downtimes when the water chilling device broke down

      Except that having only one air conditioner or only one chiller is called a single point of failure. If you don't have redundancy, then you will have bigger issues than a little bit of downtime.

      Also, If your system doesn't have flow/pressure sensors with automatic shutoffs, then you did something seriously wrong.
      Each server should have a small cutoff valve, each rack a larger one, and each main loop should have 2 routes and a nice, big cutoff. Also, each system should be configured to automatically cut off if the temp goes above a certain point, and the rack itself should have a local pump block with pressure monitoring on each blades coolant feed.

      Worst case should be lowered capacity if you lose a chiller (or 2), or you lose one loop worth of coolant to the floor drain.

      Also, if you do have a huge leak start, (for example: catastrophic failure of a main pump) there should be both automatic and manual shutoffs, and a tech on site monitoring the datacenter. JUST LIKE AIR COOLING!

    10. Re:Air is not necessarily simpler by Anonymous Coward · · Score: 0

      Interesting post, thank you.

    11. Re:Air is not necessarily simpler by fafaforza · · Score: 1

      I don't know how once can quantify "widely used" but off the top of my head, as far as street bikes go, only the less powerful Ducatis are air cooled. There are also the old-tech Thunderbolt powered Buells, but those get so hot, they could melt your leather boots. If you take an honest look, water cooling is more common. I suppose the only advantage of an air cooled bike is the lower maintenance, and the Ducatis especially are trying to lower their cost of ownership. But that wouldn't be an issue in a dc, what with service contracts, etc.

    12. Re:Air is not necessarily simpler by mangu · · Score: 1

      off the top of my head, as far as street bikes go, only the less powerful Ducatis are air cooled

      Ducati? I think you are way too elitist, a Ducati isn't what most people ride.

      Anyhow, internal combustion engines and computers have vastly different cooling needs. My car has a 1.6 liter 113 HP (83 kW) engine. Considering that the IC engine has an efficiency around 20%, there are hundreds of kilowatts of heat that must be dissipated from a volume of 1.6 liter. In a data center, it takes a roomful of equipment to dissipate 100 kW.

    13. Re:Air is not necessarily simpler by Anonymous Coward · · Score: 0

      I'm guessing you've never built a liquid cooled computer yet. the kits are readily available now, and at reasonable prices. Often the kits suggest using a type of radiator fluid rather than water. I just built one that was toolless (okay, i needed a pair of scissors to cut the tubing) - it was a thermaltake kit. Took very little time to put together ...i ran it for quite a while to bleed it and make sure it was fine before placing parts other than the cooling together in the case.

      I later even installed a flowmeter/thermometer into the tubing/system, and STILL needed nothing but a pair a scissors. Took me maybe 5-10 minutes. No mess at all lost less than a cup of fluid ...into my sink. And that was BECAUSE i took scissors to the tubing to get it to fit where i wanted it. I thought i'd loose more fluid doing it but the quick release tube valves made that a no brainer. The screw on valve-bits on the flowmeter made it easier than the original kit valves where to put together.

      Liquid cooling is still being used by the great majority of motorcycles. Harley Davison has now made the switch as well, after their v-max bike, siting that they can squeeze another 50% proformance out of the bike because they could deal with the heating of its components in a lot more of a controlled way. Pretty much holds true with electronis as well. Hell, if you think the liquid is scary then you haven't discovered Peltier kits, have you?

      Plus this tech is NOTHING new. Look at the High voltage equipment in your area... notice something? most high voltage transformers are oil cooled.

      Believe it or not plumbing is not dangerous. Not even around electronics.

      Most PVC boards are sprayed with acrylic sealing anyway... you know, to protect and isolate the working materials from the real world. Hells, I've seen people spray paint NIC cards to make them glow in the dark, using only tape on the contacts to keep them clean. Guess what - it works.

      The same tech has been in laptops for a long while now. They refer to it as water pipe coolers. It's not as much of a stretch as you might think.

    14. Re:Air is not necessarily simpler by fafaforza · · Score: 1

      I don't understand your point about Ducati. Elitist? Hmm? They have a few air cooled monsters, no?

      Nor do I understand your link to that Honda. I suppose its ridden by countries where most still can't afford a car. But not in the states. You don't see many 125cc bikes. Why wouldn't you just get a scooter at that point?

      And that link probably proved my point in that the main reason to use air cooling is for the lower maintenance and cost. In my dc, we haven't had many issues with the glycol that's used to cool our ACs. I'd imagine a grounds-up system from IBM wouldn't need much maintenance either.

  17. Random related fact by Another,+completely · · Score: 3, Interesting

    The Lindt & Sprungli chocolate factory in Zurich, Switzerland uses waste heat from the factory to heat a public swimming pool across the road.

    1. Re:Random related fact by Anonymous Coward · · Score: 0

      Oops, accidentally clicked "offtopic" when I meant "interesting". So posting to undo the moderation... Ignore me :-)

  18. multi-story approach by edittard · · Score: 1

    Sounds like a tall tale to me.

    --
    At the bottom of the /. main page it says 'Yesterday's News'. Well they got that right.
  19. Water cooling should not be a sop to consumption by niks42 · · Score: 2, Insightful
    Whatever the technologies that are available, we shouldn't as a society use them to be wasteful. If we could still efficiently cool a power-hungry, inefficient processor complex using a liquid rather than air, it doesn't make it a good idea. It would be better to design a data center that didn't require such amounts of energy in the first place.

    This reminds me of recycling schemes that make people think it is OK to overpackage goods in the first place.

  20. Meeting Resistance by selven · · Score: 1

    Try replacing the copper pipes with gold ones, that should make the current flow more easily.

  21. Central Watercooling. by SharpFang · · Score: 1

    I expect integrated power-and-watercooling sockets all over the house. The forced flow, the air conditioning unit integrated with water cooling facility, pump and reservoir, also using the heated water as heat source for heat pump.

    --
    45 5F E1 04 22 CA 29 C4 93 3F 95 05 2B 79 2A B2
    1. Re:Central Watercooling. by zrq · · Score: 1

      integrated power-and-watercooling sockets

      That is just plain scary.

  22. IBM stories by Anonymous Coward · · Score: 0

    I worked for IBM in the 80's for a little while. One site I visited sold the waste heat from their seven (water-cooled) mainframes to a nearby housing estate. There was also a story the sales guys likes to tell about Amdahl (a major rival) and their air-cooled mainframes.

    So the Amdahl engineers had installed the new machine in its shiny new machine room, threaded all the cables under the false floor, hooked up the disk drives etc. and started commissioning it. All went well for a few hours then CRASH.

    Turned out the disk drive cables had come loose from the underside of the CPU. OK, plug them back in, tighten all the screws, put the flooring back down, start again. Few hours later the same thing, with added stripped screws on the plug (think of a VGA plug magnified about 3 times in each direction).

    Transpired that the nw false floor was a bit too shiny and the cooling air exhaust from the CPU (a box maybe 6 feet long, 2 wide and 5 high, weighing a ton or two) was slowly sliding it across the room by jet propulsion.

    A couple of summers later I worked for a civil service site. They had two IBM mainframes and two Crays, but vented all the heat (and that from the nuclear reactors) into the surrounding air. Meanwhile the site was heated by an ancient coal boiler several miles away and leaky steam pipes!

    Steve

    1. Re:IBM stories by turbidostato · · Score: 1
      "I worked for IBM in the 80's for a little while [...] There was also a story the sales guys likes to tell about Amdahl"

      So you really, really know what FUD exactly means, don't you?

  23. Looking forward, not back by Targon · · Score: 1

    For those who are in a position to design their own building with this sort of thing in mind, then yes, there may be ways to just design the building to get a better cooling environment. That is not always possible or practical though. Using a liquid cooling solution may very well be the future, but the real key is to make sure the cooling systems require as little attention as possible, and the amount of maintenance for cooling is fairly low.

    Think about it, if you run your systems off-site, the last thing you want would be to have to fly someone to the site just to maintain the cooling system if it is unusual. It really depends on the design, and how long the liquid cooling system within a computer can go without maintenance. Most air cooled systems can go for upwards of five years without a fan going bad.

  24. Meeting Resistance? by Anonymous Coward · · Score: 0

    sounds like the Tubes are blocked - bring out the descalers!

  25. IBM will do anything to justify their design... by Osvaldo+Doederlein · · Score: 1

    ...that insists pushing bigger clock speeds. I fully expect IBM to promote liquid Nitrogen cooling in another couple years.

  26. They omit an important detail. by jonnat · · Score: 1

    The thermal energy that can be utilized from harnessing waste heat from the server farm is proportional to the the temperature of the heated fluid.

    It is true that water is a better medium for storing and transferring heat, but if the goal is to be able to run the servers cooler, then that lower temperature is the maximum temperature they will be able to heat the water to.

    Plus, it also boils down to fixed costs. Is it much more expensive to install large heat exchangers that would transfer the heat from cooling air to water (allowing it to reach higher temperatures) than to install the water cooling system in each server?

  27. Re:Water cooling should not be a sop to consumptio by PJ1216 · · Score: 1

    Until the desire for efficient power use outweighs the desire (or even need) for faster, more powerful data centers, there will always be a need for cooling systems. When it gets to a point where people want efficiency (or need efficiency), then you'll see data centers that don't require as much power.

    You can't realistically develop towards maximizing efficiency AND power. At a certain point, you have to sacrifice a little bit of one for the other. To maximize both would require too much time in development and you'll fall behind in the competition. Being one generation (or more) will kill most, though the efficiency niche market will still hold you up, just not all that well.

  28. Do you want 10MW of free energy? by jhw539 · · Score: 1

    Then learn how to capture the waste heat from a datacenter. In the cooling field, there is a wide range of ways to provide very efficient cooling - all the way down to putting 'em in a tent and just letting the wind blow through (a PUE of 1 - more realistically, a PUE of 1.3-1.1 is easily doable if your mechanical is up to par.) BUT, we are just fighting to throw away all that energy. Does Dean Kamen have a sterling engine for us yet that be hooked up to a generator to recover some of that usable heat? I can give him 10MW at a 40 - 60F temperature delta 8760 hours a year if he can just give me the engine...

  29. Geothermal Cooling by Doc+Ruby · · Score: 1

    Geothermal heat pumps use the ground as a heat sink, usually letting electric powered circulation pumps and compressors move 4-5x as much heat energy as electric power consumed when water (or a fluid like antifreeze) is the circulating medium. Generally they sink heat in the ground, which has only so much capacity (room heating/cooling apps get the heat back in the colder weather). But they could transfer the heat to sewage water that flows out of buildings, taking heat with it. Such a system could be 4-5x as efficient as air fans cooling computers.

    I think that the computer industry would be a great mass market for this technology. Which would probably see dramatic improvement, as computer engineers are some of the most effective in innovating for efficiency. Someday we might see water circuits at power outlets for all kinds of appliances, not just computers in data centers.

    --

    --
    make install -not war

  30. I like the idea. by Anonymous Coward · · Score: 0

    IBM not only put in a cup holder, now their PCs make hot water for your coffee too!

  31. 35kW/rack piped cooling: Liebert (and Sun) by Anonymous Coward · · Score: 0

    Liebert has their XD system where you have pipes distributed around the data centre just like power, and you tap into it. You can either buy a system that uses water or refrigerant.

    Sun sells rack doors that attach to this system, and can cool up to 35 kW per rack:

    http://www.sun.com/servers/cooling/

    You don't have to make any changes to the server design.

  32. Air cooling provider claims air is the way to go? by uarch · · Score: 1

    So a company that provides air cooling solutions to data-center design believes air cooling is the way to go? Who would have thought!

    Data center cooling requirements vary wildly. In some cases water cooling may be the correct answer. In others air cooling may be the correct answer. You will almost certainly continue to see both solutions for quite a while.

  33. Yes, meant radial by Kupfernigk · · Score: 1

    You are correct, but both radial and rotary engines are complex beasts. I think too that if you look into aircraft engines you will find that the way they made many air cooled engines light and powerful was basically by wasting fuel - the heat removed from the cylinder head by fuel evaporation was significant, and the specific output was terrible. Liquid cooled engines can use high super- and turbocharge while still being quite thermally efficient. And, as someone has noted above, modern motorcycle engines are normally liquid cooled - even when they have fake fins on the cylinders to look pretty!

    --
    From scarped cliff or quarried stone she cries "A thousand types are gone, I care for nothing, no not one."
  34. Hard to fault IBM on this ... by gordguide · · Score: 1

    The idea of using water cooling and then re-using the stored heat energy by redirecting it to an area that is heat-deficient is sound, green, and all that, at least in principle. The objections, if there are any, would come from the implementation. Since that is unique to each circumstance, the right answer is "it depends", but most certainly not "that's crazy talk" or "everyone should be doing this".

    If we're talking about efficiency, then I'm not sure where to start ... getting more work out of a processor via superior cooling also means getting more power into the CPU and other stuff around it. It is the waste power we need to dissipate via cooling (whether passive air, active (fan assisted) air, via water, unobtanium, whatever), after all. This stuff requires careful scrutiny and is not the province of lowly Slashdot contributors, although any company contemplating such questions is certainly free to hire one.

    Water is 20 times more efficient at removing heat than air; I know this from my "other" job, which occasionally involves saving lives, where hypothermia is a real risk. Aided with forced air cooling (the wind) you have a very effective method of removing a tremendous amount of heat from a device (the human body) that generates it's own on a constant basis, as long as it's still working (alive), that is. Very much similar to a CPU doing work, and also showing how the inherent 20x can be improved upon, so I won't argue any claims about how efficient this particular method of IBM's is; I reserve my right to fall back to "it sounds like it might work".

    Re-using the waste heat is a good idea and some buildings already employ hot-water heating/cooling systems that could easily incorporate a new source of heated water energy. Others ... who knows?

  35. Alternative solution by GameboyRMH · · Score: 1

    The heat could power a Stirling engine which charges a battery that then powers the coffee maker...

    But that's

    Electrical-->Thermal-->Kinetic-->Electrical-->Thermal

    The best solution would probably be to run the hot water through a Stirling engine and sell the power back to the grid. That way no expensive batteries are needed, and you can still imagine the electrons from the Stirling engine going into the coffee maker :P

    --
    "When information is power, privacy is freedom" - Jah-Wren Ryel
  36. bad moderation :( by drinkypoo · · Score: 1

    Whoever modded this as flamebait obviously didn't get the joke. Everything you need to understand is is contained in the following link: Dr. Cow Nut Cheese - A Tasty Splurge.

    I've been subjected to raw food. Some of the desserts are actually quite amazing, I would buy them on purpose, but basically everything else is a pathetic imitation. I belong to the camp that believes that if you have to pretend a nut or a bean or is meat, that's a sign that you need to eat some meat. If you're happy eating nuts and beans and grains, right on. I do like a nice salad... especially with bacon.

    --
    "You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
  37. IBM 9000 used this by ctrl-alt-canc · · Score: 1

    I remember that years ago, visiting a data center in London, the system engineer showed me a water-cooled CPU used on IBM9000 mainframes. It was amazingly engineered, with water in- and outlets running through the thermal dissipator. I think that Cray used a more aggressive approach dipping the whole computer into a cooled bath of Fomblin(TM). It is nice to see this technology kicking back...

  38. Water cooling prevails in vendor Chill-Off by 1sockchuck · · Score: 1

    IBM's water-cooling rear-door heat exchanger (known as "Cool Blue") was judged the most energy-efficient entry in a "chill-off" between cooling vendors last year. The contest was sponsored by the Silicon Valley Leaders Group and conducted in the data center on Sun's Santa Clara HQ campus. The same unit is also sold by Vette Corp., which offered a video demo at Data Center World.

  39. Water Cooler Servers by XiaoK · · Score: 1

    I first read the title as "Water Cooler Server" I think IBM should do this instead. Build a nice server that doubles as a water cooler. If it also has a toaster drive and a microwave on top it could replace the appliances in my company's kitchenette.

  40. 40 Years On by mathman47 · · Score: 1

    Shades of the 360s/370s in a building?

    --
    "There are good ships, and there are wood ships, the ships that sail the sea. But the best ships are friendships, and ma