Want to read Slashdot from your mobile device? Point it at m.slashdot.org and keep reading!


Forgot your password?

Using Jet Engines to Cool Servers 109

rpmsci writes "The computer servers that fill huge data centers are producing more heat with every new generation of processors. It's a problem that's sending engineers on a search for cooling fans that are both small enough to fit inside ever-smaller server chassis and powerful enough to dispel increasing amounts of heat. At Hewlett-Packard, they've found one answer in an unexpected place: model jet airplanes."
This discussion has been archived. No new comments can be posted.

Using Jet Engines to Cool Servers

Comments Filter:
    • Yeah, I've long had a similar Thermaltake product [thermaltakeusa.com] and people at LANs often comment on the "jet engine" that I have cooling my CPU.
    • Not really. The fan blade on front looks pretty much like one from a standard computer fan. It has seven shallow blades, just like every other fan in my computer case. The article led me to believe that this was just more than a standard fan blade in a new housing. More likely, it is going to be a completely different shape. The picture in the article even shown a rounded or pointed hub, as compared to the picture that you linked to, which just has a flat spot to hold a sticker.

      • As an HP Tech in their manufacturing division, I can tell you this, the fans do sound like a jet engine. But they also move a lot of air. And their on the back of a special box, with five fans each on top and bottom, so air flow is from the front middle through the back top and bottom. The blades do stay cool. And I don't know if they intend on utilizing this idea on the smaller fans as well, for now, they are only with the blades
    • This of course leads to the obligatory lines, "Thank you for flying with HP Airlines. I'm Miss Goodbint, and I'll be your data server on this flight. Please ignore the vast sucking noises coming from the rack, they're normal. In the event of a loss of cabin pressure, strange little yellow masks will pop out of the equipment so your data center technicians don't asphyxiate."
    • Not the same thing (Score:5, Insightful)

      by linuxkrn ( 635044 ) <gwatson@@@linuxlogin...com> on Friday June 16, 2006 @10:24AM (#15548534)
      That asus is just a standard fan mounted in a case that looks like a jet engine, but it's the same technology.

      On the other hand, the HP one uses small blades that are shorter and that spin faster. As such they create more thrust/airflow and reduce noise that normal blades produce from the tips of their blades.

      RTFA, it's got a good discription, yeah, I know it's /. but sometimes it's worth reading.

      • I need to remember to use smiley faces. That's supposed to be a joke, not a serious comment. (That's +3 Funny for your moderators, not +3 Insightful!) Anyone who's ever seen the StarIce invariably comments, "It's a freaking jet engine!" :)
      • How they work. (Score:5, Informative)

        by twitter ( 104583 ) on Friday June 16, 2006 @01:38PM (#15549998) Homepage Journal
        On the other hand, the HP one uses small blades that are shorter and that spin faster. As such they create more thrust/airflow and reduce noise that normal blades produce from the tips of their blades.

        That's about all the article says.

        The key ingredient to a ducted fan is efficient expansion. Any old array of twisted parts can propell air. I read another article and fabricated such a thing from Dixie cups. After your rotor comes the stator, a very important component missing from ordinary fans, which removes the angular component of the flow velocity. You want to move the air down your axis not around it. Getting the air moving along the axis and expanding it out to larger volumes without wasting your effort is hard to do. Adding any stator will help. Doing it quietly and efficiently is one of those rocket science things.

        Wikipedia, of course, has a quick article, [wikipedia.org]

        and Google turns up an easy design text [pair.com].
      • Not the same thing

        That asus is just a standard fan mounted in a case that looks like a jet engine, but it's the same technology.

        On the other hand, the HP one uses small blades that are shorter and that spin faster. As such they create more thrust/airflow and reduce noise that normal blades produce from the tips of their blades.

        On the other hand neither technology is even remotely related to jet engines in the normal sense of the word and both are really just electric fans. I probably wouldn't have bothered

  • Not a jet. (Score:4, Insightful)

    by LWATCDR ( 28044 ) on Friday June 16, 2006 @10:19AM (#15548492) Homepage Journal
    These are just ducted fans. There are actually tiny gas turbine engines available for model aircraft.
    I have to wonder how much if this is really just hype. Last time I looked at my cooling fan it was already a ducted fan.
    Are they adding extra stages? Maybe more an more efficient airfoil on the fan blades? Longer duct? Higher RPM?
    I find this a huge so what.
    • by arivanov ( 12034 )
      There are actually tiny gas turbine engines available for model aircraft.

      You mean "used to be available". Have you tried to order these after 9/11?

  • by xxxJonBoyxxx ( 565205 ) on Friday June 16, 2006 @10:20AM (#15548501)
    "The end product is HP's Active Cool Fan..."

    Christ, is "active" a hip marketing term again? I thought "ActiveX" put a bullet in that fad...

  • Why bother? (Score:5, Insightful)

    by RingDev ( 879105 ) on Friday June 16, 2006 @10:21AM (#15548513) Homepage Journal
    Air is such a poor heat transfer medium. Why not build a rack with a water cooling system built in? I have an external water cooled solution on my home PC connected via a set of no-break quick release couplings. So any time I need to pull my PC apart I can pop the coolant lines with out losing a drop of coolant or introducing air into the system.

    I can't imaging running a fleet of model airplane engines is going to be quite, cheap, or all that reliable. Especially when compared to an rack integrated water cooling system.

    • I picked up a Zelman Reserator 1 Plus yesterday and cant wait to get it installed. Far better cooling then any air fan out there and no noise. (sure, it set me back a mint, but worth it)
    • I don't have much experience with water cooling solutions, but what happens when that full-rack system springs a leak or develops some other problem? Do you end up losing the whole rack of machines (either temporarily or permanantly)?
      • I don't know much about in a rack system, but I had been running a Big Water [thermaltake.com] system in my gaming rig for about a year, and it developed a slow leak. Mind you, they recommend that you check the fittings every so often for leaks, which is something that I didn't do as religiously as I should have. I had modified it by including 2 VGA coolers, and a leak developed on one of the VGA coolers and a smaller leak on the CPU block.

        The leak from the CPU block was such a small leak that it dripped sludge, as the wa
        • Ya, leaks suck. My Koolance setup has been great for about three years, except with I over tighened the fill plug and it was leaking outside the case. There was no threat to my machine, just had to replace the resovoir. As for your leaky water blocks. SOrry to say, but you must have had some really cheap connectors on it or or peiced together your own hose, fasteners and blocks from different sources. http://www.koolance.com/shop/product_info.php?cPa t h=29_44&products_id=114 [koolance.com] is just one example of
          • Actually everything I was using was included in the kit or, in the case of the VGA blocks, still thermaltake and made for the watercooling system. Same setup, push the hose over the nipple and tighten down a nut to hold the hose in place. I honestly could never really tell where the leak was, but my guess was from the connection of the nipple to the actual block.
            • If it was the connection between the nipple and the block then it was a manufacturing error. You could atleast get the water cooler replaced under warenty and you may be able to hold the manufacturer liable for the rest of the damages.

              • I agree. I would have tried to get it replaced. With the reliability of my setup, I always recommend water cooling to friends.
        • Re:Why bother? (Score:5, Informative)

          by SatanicPuppy ( 611928 ) * <Satanicpuppy.gmail@com> on Friday June 16, 2006 @11:08AM (#15548888) Journal
          Might want to try some Fluid XP [xoxide.com] coolant. It's non-conductive, so no zapped parts. It's non-corrosive, so fewer motor problems. And it's non-toxic, so if your 2-year old glugs a quart of it, all they get is blue teeth.

          I've never heard anything bad about it, and it works fine for me.
          • Hard Lesson (Score:2, Insightful)

            by Gr8Apes ( 679165 )
            That's a hard lesson learned there, spend the $35 for a non-conductive liquid and save hundreds, if not thousands in hardware costs. The same thing applies to UPSes.
            • The thing that really sold me on it was the fact that it was non-toxic. I have too many kids and animals lurking around the house for me to feel comfortable leaving a nice toxic candy-colored liquid lying around the house.
              • I've got that issue as well. Good point. So far I've only done air-cooled, but was considering a liquid cooled system. This definitely helps, esp after all the "my water cooled system leaked!" posts. I was actually considering a low-viscosity non-conductive oil, similar to the concept of the oil-filled/cooled PC [slashdot.org].
        • Somewhat related - has anyone seen a water-cooled external hdd enclosure? I'd like a nice little self-contained unit.
          • Somewhat related - has anyone seen a water-cooled external hdd enclosure? I'd like a nice little self-contained unit.I

            Did you even TRY to look? I spent 10 seconds with google and this is on the first page of results:

            Clicky [performance-pcs.com]

            Here is the google URL so you can look further:

            ClickyX2 [google.com]
        • Similar Story.

          I've had an Asetek (http://www.frozencpu.com/ex-wat-72.html) cooling system installed in my box for almost 2 years now. I love it. Even running the thing at full processor load on both the video card and the processor (a p4 prescot), temperatures won't go more than 10 degrees above ambient. And yes, that's with very minimal fan noise.

          Unfortunately, my system developed a leak too. The leak actually occurred on the chipset block, between the block and the fitting. It was a slow leak, but
      • When I was in college, we had a computer that had a water-cooling leak that sprayed directly at the motherboard and fried it. Unfortunately, since this was ~1975, the computer was the IBM 370 mainframe that provided most of the computing for the campus, and it was down for a few weeks.

        In a smaller, more modern environment, the effect on other computers is going to depend on whether the cases let water leak from one to the next - e.g. in a stack of 1U, are there vents on the top and bottom or only sides -

    • Re:Why bother? (Score:3, Insightful)

      by harrkev ( 623093 )
      This is not my field, but I would imagine that it would be because business are averse to risk. Fans are known and reliable. Watercooling is new and unknown in a 19" rack. What if YOU were the first one to suggest installing it, and it leaked? Bye bye job.

      If an enthusiast's system leaks, he misses the next LAN party. If it happend on the top computer on a rack, that system goes down. The water then trickes down to the next lower computer and destroys it. Maybe the water will go down to the next compu
    • Because it's all ultimately aircooling anyway. Where does your water radiate its heat to? The air. If you can air cool it directly, it cuts out the middle man and the cost of water cooling.
      • Water can store a lot more heat than air can. It's also easier to put a small waterblock on the cpu and have it pump into a huge external take with a huge surface area.

        • The problem is that datacenters don't use home PCs. The reason watercooling works so well in home systems is because the water stores an enormous amount of energy and you can put a giant heatsink on the back of your system with one big slow moving fan to get a very cool running (especially since you only use it for a few hours at a time and then let it cool back down afterwards) system that is very quiet but also takes up enormous amounts of space and will still get hot if you run it continuously at full b
          • All you need to do for it to work on a larger scale is to increase the amount of water in the system (the amount of energy the system can contain) and improve the transfer of that energy from the system. Instead of using an air conditioner to cool hundreds of thousands of cubic feet of air to cool a server room, you can use a chiller to pull the heat out much more efficiently.

            As for failure modes, water cooling isn't all cheap little toys with no engineering. With proper design and quality the critical fail
            • With proper engineering and good materials you can reduce the failure rate, but the failure modes are still the same (water all over the rack). Worse, even if you reduce the failure rate by a factor of 3, that leaves you dead even when you have a datacenter with a measly 1,000 machines in it.

              Other posters have mentioned tapping the building cooling system directly, which is a clever idea that might work someday, but is completely unrealistic in a datacenter you're building today. There is no building sc
              • So, proper engineering it is. First, use a non-conductive cooling fluid. That will immediately reduce the critical nature of a leak. Second, get a plastics manufacturer to make a 1/2U tray with a slant to force any spilt fluid to one specific corner. Next use a GFCI style system on the flow, measure the amount of coolant going into the line, and the amount being returned, if they don't match, use a UPS interface to send a shutdown command to the server, notify the staff, and once the machine is down close t
          • Actually most datacenters already have massive water-cooling systems: only they're building wide and generally used to cool the air. I'm talking about the HVAC system, of course.

            Large buildings generally don't circulate Freon from one floor to another, it would be too expensive. Instead, they have a big refrigeration unit (roof mounted, usually) with big cooling towers and the rest, and use it to chill water, which is pumped throughout the building and used to cool air.

            It wouldn't be very difficult to tap i
            • It doesn't make sense to tap into the water system and run that through your computers because it's going to be conductive. It makes much more sense to run some kind of special coolant through the computers, and use a fluid-fluid heat exchanger to cool that liquid from that running through the HVAC plant.
            • One likely reason for not using HVAC cooled water with out warming it is condensation. Yeah, 40 degree water would really cool the proc down, but it would also cool the air surrounding the pipe and CPU block down too, which would lead to condensation inside the box. I'm not sure how conductive it would be, but it likely wouldn't be good. If instead you use water that is 60-65 degrees, 5 to 10 degrees under room temperature, you'll not have nearly as much of a problem with condensation.

      • Not really... water is a better conductor of heat than air. When you run the water through your heatsink, it takes away more heat, faster than air. Then when you go to radiate the water in its tank, the air takes the heat away (yes, albeit slower, but with the right amount of water/storage tank, the transfer is much better than that of just plain air).
      • But look at the energy used in the situation. A single 1/2 hp pump could push water through the entire rack and to an external radiator. You stick that radiator in the building HVAC exhaust vent (ie: passive, or parasitic) or into a highly efficient cooling system (active, phase change, peltier, etc..) and you have a pretty low power, high efficiency system. And a single water pump is a pretty reliable device. And for saftey, it wouldn't be hard to put a second redundant pump in place. I can head down to ho
        • If you bothered to RTFA, you'd see they're talking about electric ducted fans. Not gas engines. Its an electric motor with a fan in a tube. Nothing earthshattering here, except perhaps that HP is starting to actually develop some ideas now that whats-her-name is gone. Now, if they were talking about one of the gas-turbine jet engines, or a glow-fuel piston engine, you'd have valid points.
          • [sob]I never learned to read![crying]

            Err, my bust. The article mentions "Jets" numerous times, I mistakenly thought the electric part of the title was referring to the duct (in so form of control) and the jet was referring to the power source. I see now that it article was just craply written. Thanks for the clarification.

    • HP built many, many liquid-cooled processors, with tubing leading to remote heat exchangers. They were doing them as early as the late '80's, and quite possibly earlier.The problem is: in the end you're still dumping heat into air, on the end of the heat exchanger. I know there are systems that actually have full-loss water running through them and out into the sewer but that doesn't seem to be very popular, doubtless because there are environmental and ongoing-cost concerns.
      • HP is retackling this one too (news coming to you directly from their Houston campus)

        you should hear about it in the next 6 months or so, but don't hold your breath on my account
      • I'm sure all the big computer manufacturers have used some form of liquid cooling on their non-PC machines at some point in time. This is probably a solution for those businesses that need servers, but don't have the infrastructure or personnel to properly run a set of liquid cooled racks. So HP is using ducted fans to increase the cooling efficiency of their air cooled products. Yippy skippy. I hope their customers like them.
    • Seriously...

      If rack-mount servers all had standardized couplings, you could just buy the server, slap it in the rack, and plug the rack hoses into the server. Even better is that once you've got the heat contained in the water, just plug the rack into the centralized (and external to the server room) heat exchanger (via another standardized coupling) and start saving a bundle on a/c costs. Unfortunately I think you'd still need to worry about a bunch of small pumps everywhere, though. One big one to circula
    • Until fairly recently (well 10 years), high end IBM mainframes used water cooling, so many datacenters may alreay have water heat exchangers. With blades esp. I wonder how much power is used cooling them, and how much could be saved by switching to water based cooling?
    • Ah, like an old Control Data mainframe or similar ilk. It's hilarious when you get a leak, and a fountain of water shoots 20 feet in the air (it was a 2 story data room).

      Well, it was funny for a short while, anyway.
  • by AgentAce ( 246327 ) on Friday June 16, 2006 @10:22AM (#15548516)
    http://www.asciimation.co.nz/beer/ [asciimation.co.nz]

    Yeah, real innovative HP. *yawn*
  • Sheesh, a ducted fan is NOT a jet engine.
    It just means they put a fan inside a tube, rather than have a propeller outside.
    It's a cosmetic thing to keep the appearance of a jet.

    Other than the fan being in a aerodynamic tube, it really isn't any different.
  • I am SO disappointed. I was hoping it would be the real thing.

    That would've been entertaining.

    You might want to reinforce the footings for those racks before you.. *WHINE* *ROAR* *CRASH*


  • Those 400psi water chillers on IBM TCM (Themo-Conduction-Module) mainframes did an awesome job of keeping them cool. I'm sure some research into it could yield smaller cheaper units with better thermal conductivity - perhaps some new fluid that's non electrical conducting and better heat characteristics.
  • 1) Tech installs HP jet fans into all his servers.
    2) Tech restarts all his servers.
    3) Tech shits himself as all servers simultainiously (sic) take flight smash though the wall and put themselves into a flight path heading fot the North Pole.
  • Apple did this years ago, but with real jet engines. Its called the PowerMac G4 [wired.com]. I was so impressed by this advance, that I immortalised it in my sig.
  • Intel already killed netburs.
  • by blueZ3 ( 744446 ) on Friday June 16, 2006 @10:43AM (#15548680) Homepage
    Sheesh, Zonk -- could we at least take, say, three seconds to think before writing the article title. How about "Using jet engine technology..." instead of "Using jet engines..."

    Little clue: Jet exhaust is... well, let's just call it "a little warm for cooling a server" and leave it at that. The article title gave me this picture of a Rolls jet engine (http://www.rolls-royce.com/education/schools/how_ things_work/default.jsp) sucking JP4 and blowing 1000's of cubic feet per second of very hot air into the server room here at work.

    Oh the humanity!
    • Well, technically, they could have the jet engine intake port going into the server room and passive heatsinks open to the outside on everything. Probably not a great idea, but it would be better than the output port.

      PHB: "Why is the system down"
      Tech2: "Well, we forgot to power down the cooling system before Tech1 went in to service the system and it sprayed him all over the outside of the building"
      PHB: "OK, whatever, I guess you got a promotion. Can you get the thing back up ASAP? Oh, and hire another
    • The article title gave me this picture of a Rolls jet engine (http://www.rolls-royce.com/education/schools/how _ things_work/default.jsp) sucking JP4 and blowing 1000's of cubic feet per second of very hot air into the server room here at work.

      Same here, though at least I had the sense to assume it would be blowing in an exhaust direction, using the atmosphere to keep the data center full. :)

      My machine is coloed in a building with thousands of other servers, at some scale it must make sense, especially if y
    • The article title gave me this picture of a Rolls jet engine (http://www.rolls-royce.com/education/schools/how _ things_work/default.jsp) sucking JP4 and blowing 1000's of cubic feet per second of very hot air into the server room here at work.

      Turbo prop jet engines that use atmospheric air to cool the turbine can have exhausts below ambient if designed for the task (the air compresses at the beginning of the engine, radiates heat into the bypass down to something approaching ambient, then both air flows ex
    • How do you think jet airliners provide a/c? They use bleed air from the turbine, that's how. If you take a very high pressure gas and allow it to expand very quickly it cools down a great deal. The same principle could be applied to cooling a data center. Why you would want to, well that's why I read the article. Only to be disappointed by the lack of real jet engines.
  • From TFA:
    "They literally blow you away," he says; "it's like picking up a leaf blower."

    Great. As if I don't get enough of that sound when I'm trying to sleep in on weekends...

  • Use jet engines to cool servers?! Are you mad? Can you imagine how much this will ramp up global warming? Is it really worth it?... Yeah I guess so. Nevermind
  • Drat (Score:3, Interesting)

    by hcdejong ( 561314 ) <hobbes&xmsnet,nl> on Friday June 16, 2006 @10:59AM (#15548814)
    For a moment I thought they were using actual jet engines [kritzberg.com] to cool the server, but noooooo, they had to go for boring ol' electric fans instead.

    [insert rant about misleading summary]
  • They couldn't hear the complaint that "your hardware sucks and blows at the same time" so they had to come up with something so they can just smile and nod.
  • What I don't get is this: Since there is all that heat coming off of processors, etc...how can the energy in that hot air be captured and put to good use? Seems all cooling solutions just "consume" more energy to transfer energy (in the form of heat) from here to there.

    The net effect is we take a bunch of energy (as electricity) and lose a lot of it as heat then take a bunch more of it (again, electricity) to just move the other "lost" energy (heat) around. It just seems wasteful and expensive to me. T
    • Have you ever heard of actually *reading the article*? Wait, no, this is Slashdot...
      • I'm a little taken aback by your response and want desperately to respond with ad hominems and name calling, etc. I'm trying to be better about those things though, so I'll refrain.

        At any rate, yes, I read the article. Perhaps you didn't. There was no mention of anything whatsoever about recovering the energy from the heat transfer. Only mention of more efficient fans, water cooling, peltiers, etc. All things that amount to the same thing: using electricity to generate heat then using even more elect
        • Oh, crap. My apologies. I read your post as talking about waste heat from the "jet engines", not waste heat from the cpus themselves. I can only blame not enough coffee.

          Where I live it's only hot for a few months of the year, so most of the time the waste heat from my own computers is used to keep *me* warm.

          It does seem like it would make sense to be able to funnel the exhaust from the server rooms into the building HVAC systems somehow. Or team up with a greenhouse next door, or something.
          • Oh, crap. My apologies. I read your post as talking about waste heat from the "jet engines", not waste heat from the cpus themselves. I can only blame not enough coffee.
            No worries...I am definitely glad I refrained now.
    • Its all about expense.

      You could put a bunch of thermocouples, or rig up lengths of heatpipe to pipe several servers worth of heat into a single location. Do you realize the cost of this?

      Keep in mind that low-level heat (anything under a few hundred degrees) isn't enough to generate enough useful energy to make this worthwhile. Perhaps if we can find some other way of power generation..however..

      We could use the heat to maybe put some heat back into the HVAC system of a building in the wintertime..might sav
      • We could use the heat to maybe put some heat back into the HVAC system of a building in the wintertime..might save on a little power.

        That's the kind of thing I'm talking about, at least initially. I realize it isn't done now because it's more expensive than just paying for more electricity to, for all intents and purposes, blow the heat away. But piping the hot air into the heating ducts in the winter is a good start. As for water cooled systems, do they have to be closed loop? Why couldn't water co

  • If a jet engine can cool a can of beer [asciimation.co.nz], why not a server?
  • by necro81 ( 917438 ) on Friday June 16, 2006 @12:12PM (#15549378) Journal
    Since these ducted fan's aren't really jet engines, and certainly aren't what I had in mind when I saw the term "jet engine" in the headline (think very large and noisy!), here's a proposal for using a real, full-sized, jet engine for cooling your servers:

    Take one jet engine,
    Add stages to capture the thrust and transform it into more torque,
    Connect output shaft to massive freakin' compressor turbine,
    Use turbine to compress gaseous coolant back to a liquid,
    Attach big large radiator/heat exchanger/water cooling tower

    Viola! you now have many tonnes of refrigeration capacity, good for blowing cold air through your equipment room, or circulating liquid coolant directly to the chips.

    The best part is, you get to have a jet engine tacked on to your server farm.
  • In the article it mentions that this will help reduce the need for improved air conditioning in the server room (or something like that), but I can't help but wonder how they expect to achieve efficient cooling if all you are doing is moving the same air arround. After all, any air cooling simply moves the heat from one place to another, so when the room's ambient temperature increases as a result of more rapid heat tranfer from the hotter and more dense collection of processors and other heat sources then
  • What You Missed
    • Revealing How Marijuana Affects the Brain
    • Lack of Human Eggs Could Hamper US Cloning Efforts
    • Logic from Chaos
    • Administration to Innovators: Database not Dollars
    • Better Mobile Web Browsing
    • A New Method of Getting Drugs into the Brain

    Those editors sure have an interesting profile of their target readers!

  • Anyone everthought to pump said waste heat round a building to either heat water/rooms/divert to the handryers in the loos(or bathrooms. Although I have never had a bath at work whay are they called bathrooms when there is no bath in them!?)?

To write good code is a worthy challenge, and a source of civilized delight. -- stolen and paraphrased from William Safire