Forgot your password?
typodupeerror
IT

The 100 Degree Data Center 472

Posted by CmdrTaco
from the so-take-off-all-your-clothes dept.
miller60 writes "Are you ready for the 100-degree data center? Rackable Systems has introduced a new enclosure that it says can run high-density racks safely in environments as hot as 104 degrees (40 degrees C), offering customers the option of saving energy in their data center. Most data centers operate in a range between 68 and 74 degrees. Raising the thermostat can lower the power bill, allowing data centers to use less power for cooling. But higher temperatures can be less forgiving in the event of a cooling failure, and not likely to be welcomed by employees working in the data center."
This discussion has been archived. No new comments can be posted.

The 100 Degree Data Center

Comments Filter:
  • by Anonymous Coward on Thursday March 19, 2009 @10:19AM (#27255339)

    Its better

    • by sakdoctor (1087155) on Thursday March 19, 2009 @10:22AM (#27255369) Homepage

      Agreed. Stupid sumary.

      I had this image of shimmering heat, rising steam, and burning barrels inside a post apocalyptic data center.

      It wasn't until line 2 that my image was ruined.

      • by Mr2cents (323101) on Thursday March 19, 2009 @10:53AM (#27255887)

        When is this Fahrenheit unit going to die? Last time I checked, only a couple of developing countries were using it (Birma, USA).

        • by FooAtWFU (699187) on Thursday March 19, 2009 @11:14AM (#27256247) Homepage
          I like Farenheit. It maps very well to the range of habitable temperatures that a human is likely to experience. I realize Freezing Water isn't in the best place, sure, and will willingly concede it would be better if it were tweaked down to something rounder (30 or so, perhaps) but aside from that: 100 is (about) as hot as it gets normally, 0 is about as cold as it gets normally, and anything outside that range is sure to be obnoxious and waxing uninhabitable.

          I don't care about how hot it needs to be to boil water, or how many gram-degrees-Celcius are in your calorie, or anything like that. And furthermore, if you're going to be Mr. Science, why not just break out the Kelvin and be done with it?

          • by Fross (83754) on Thursday March 19, 2009 @11:21AM (#27256341) Homepage

            I completely fail to see how a range of 40-80 (after all, you did say "habitable temperatures" for humans), is better than a range of 5-30.

            Farenheight has no basis in anything practical at *any* range. At least Celsius is based around water, which is useful for a number of reasons.

            • by Trepidity (597) <.gro.hsikcah. .ta. .todhsals-muiriled.> on Thursday March 19, 2009 @11:37AM (#27256583)

              A single degree Celsius is qualitatively a bit too big, to the point where most European climate-control systems with digital displays have to resort to using half-degrees as the base control unit.

              • Re: (Score:3, Insightful)

                by frieko (855745)
                so?
                • by Spazmania (174582) on Thursday March 19, 2009 @12:38PM (#27257567) Homepage

                  So, us fahrenheit-feet thinking people find it inconvenient to think in terms of decimal points. Measuring 7.9 cm is no easier than measuring 3 1/8th inches. I care about the difference between 72 and 73 degrees Fahrenheit. It's more of a pain to deal with the difference between 22.0 and 22.5 degrees Celsius.

                  • by frieko (855745) on Thursday March 19, 2009 @12:51PM (#27257755)
                    I'm an American, and I disagree completely.

                    On my metric wrench set, the 8 is one next to the 7. On my American wrench set, the 5/32 is next to the.. I have no idea, I would have to go look. It's even worse if I have to add 3/32" to 5 7/8".

                    If you really need fractions, then 7.9 cm is 7 9/10 cm and 22.5 C is 22 1/2 C.
                    • by Andy Dodd (701) <atd7@nOspaM.cornell.edu> on Thursday March 19, 2009 @01:09PM (#27258055) Homepage

                      That's because for wrench/socket sets, the situation is just the opposite. Metric's unit (mm) is "just right" and doesn't need fractions or decimals, imperial's unit (inch) is way too big and nearly everything is less than one unit.

                      It goes the other way for Celsius vs Fahrenheit. Celsius units are "too big" and require dealing with fractional units, while most Fahrenheit-based systems can use single-full-unit increments.

                    • Re: (Score:3, Insightful)

                      by Grishnakh (216268)

                      Exactly right. Mod this guy up.

                      When you're working on your car, you don't have situations where you need an 8.5mm socket wrench. All the fasteners on a metric car are in integer mm numbers: 6, 8, 10, 12, 14, 17, 19 are the most popular. If you try 14 and it's a little too big, then you know that 12mm is the correct size. It's easier than inches because the inch is simply too large, and every bolt size is a fraction of an inch.

                      Celcius is too large. To a typical human, there's a noticeable difference bet

                    • Re: (Score:3, Interesting)

                      by rahvin112 (446269)

                      The US will never fully implement the metric system. And I mean NEVER (see my caveat below). It's an impediment to foreign companies supplying or working in our craft sector. Ever wonder why you don't see any European or Chinese sawn lumber or Chinese or European steel beams for purchase? Because they don't have factories that generate Imperial sizes. All the foreign factories are geared to the metric system. The only areas where I've seen a shift to metric was the car industry where foreign imports caused

            • Re: (Score:3, Interesting)

              by johndierks (784521)

              Farenheight has no basis in anything practical at *any* range. At least Celsius is based around water, which is useful for a number of reasons.

              That's not quite true, 0*F to 100*F is pretty much the range humans can survive in without any kind of crazy technology. Makes sense to me.

            • Re: (Score:3, Insightful)

              I completely fail to see how a range of 40-80 (after all, you did say "habitable temperatures" for humans), is better than a range of 5-30.

              Simple. Fahrenheit is useful using two digits. A unit of Celsius is too coarse, and to be practical you have to resort to decimal figures.

              I'm mostly with people who like metric, but there's no doubt that F is superior to C for human use.

        • Re: (Score:3, Insightful)

          by poot_rootbeer (188613)

          When is this Fahrenheit unit going to die?

          Not until people develop the intuition to evaluate temperature relative to a volume of water, rather than to their own bodies.

          Which is a more logical numeric range for representing a perceived continuum from "cold" to "hot": 0 to 100 , or -18 to 38?

    • Re: (Score:2, Funny)

      by Anonymous Coward

      You care about the metric system, but can't even be bothered to spell correctly.

    • by Shakrai (717556) on Thursday March 19, 2009 @10:31AM (#27255497) Journal

      Actually, this is an American site, so use something that most Americans can intuitively relate to. I have no problem working with most metric measurements (indeed, I did so for a number of years working in machining) but temperature just doesn't compute for me unless I do the calculations in my head.

      Fahrenheit just makes more sense to most of us. 30s = cold, 40s = chilly, 50s = cool, 60s = decent/might need a windbreaker, 70s = nice, 80s = warm, 90s = hot, etc, etc. Celsius is no where near that intuitive and was as arbitrarily defined as Fahrenheit was.

      • by kcbanner (929309) *
        But we get to say its below zero outside, which usually means its time to put on a sweater instead of a tshirt.
        • by Shakrai (717556)

          Yeah but below zero in Celsius loses it's special meaning when you live in an cold climate. Below zero Fahrenheit on the other hand.... that's freeze your nose hairs weather ;)

          WTF in my original comment was "trolling", BTW? Pointing out that /. is an American site or having the nerve to come out against one aspect of the metric system?

          • by Quothz (683368)

            WTF in my original comment was "trolling", BTW? Pointing out that /. is an American site or having the nerve to come out against one aspect of the metric system?

            Sir, or madam, I salute you. I haven't seen a troll that artfully done in years. These days, trolling seems to be about spouting bile and filth, rather than dropping a comment precisely calculated to raise folks' hackles. If you didn't intend it as a troll, for heaven's sake, don't admit it. If I had points, I'd mod you troll as a compliment.

      • by psergiu (67614) on Thursday March 19, 2009 @10:39AM (#27255629)
        Fahrenheit is stupid.
        Celsius on the other hand is much easier to remember:
        0 - Water freezes
        10 - Cool
        20 - Nice
        30 - Hot
        40 - Scorching hot
        50 - Burn sensation
        100 - Water boils

        And slashdot.org is not an american-only site as it's domain name ends in .org and not in .us
        • Re: (Score:2, Interesting)

          by Shakrai (717556)

          Fahrenheit is stupid.

          Wow, how insightful and deep. You have to think real hard to come up with such compelling commentary?

          Celsius on the other hand is much easier to remember:
          0 - Water freezes
          10 - Cool
          20 - Nice
          30 - Hot
          40 - Scorching hot
          50 - Burn sensation
          100 - Water boils

          Surely you mean water freezes and boils at one standard atmosphere, right? Which brings me back to my point about it being just as arbitrarily defined as Fahrenheit was. Fahrenheit also offers more precision without using decimals.

          And slashdot.org is not an american-only site as it's domain name ends in .org and not in .us

          Domain names don't mean jack. Slashdot is American owned with a largely American readership. Yet someone still managed to whine about the fucking summary using American meas

        • by markov_chain (202465) on Thursday March 19, 2009 @11:11AM (#27256205) Homepage

          Neither Celsius nor Fahrenheit are intuitive to me.

          373.15 - Water boils at 1 atmosphere
          310 - Very hot
          300 - Hot
          290 - Nice
          280 - Chilly
          273.15 - Water freezes at 1 atmosphere
          0 - absolute zero! how easy is that.

          Kelvin ftw chumps!

          • by Mr. Underbridge (666784) on Thursday March 19, 2009 @11:17AM (#27256289)

            373.15 - Water boils at 1 atmosphere 310 - Very hot 300 - Hot 290 - Nice 280 - Chilly 273.15 - Water freezes at 1 atmosphere 0 - absolute zero! how easy is that.

            'xactly. These trolls try to go anti-US with their fancy metric system then they fuck it up with Centigrade. Try plugging centigrade temperatures into the ideal gas law and lemme know how it goes. ;)

            • Re: (Score:3, Interesting)

              by jc42 (318812)

              Try plugging centigrade temperatures into the ideal gas law and lemme know how it goes. ;)

              Actually, the fun part is that there's a long history of people doing exactly that. The patent offices in the US and other countries have an ongoing problem of people attempting to patent perpetual-motion machines. In most cases, a "proof" that a particular gadget will work is produced by taking the standard equations and using Celsius/Centigrade numbers when temperature in "degrees" is needed. This seems to be some

      • by Chrisq (894406) on Thursday March 19, 2009 @10:41AM (#27255667)

        Fahrenheit just makes more sense to most of us. 30s = cold, 40s = chilly, 50s = cool, 60s = decent/might need a windbreaker, 70s = nice, 80s = warm, 90s = hot, etc, etc. Celsius is no where near that intuitive and was as arbitrarily defined as Fahrenheit was.

        Its not intuitive, its just what you're used to

      • Re: (Score:2, Redundant)

        Fahrenheit just makes more sense to most of us. 30s = cold, 40s = chilly, 50s = cool, 60s = decent/might need a windbreaker, 70s = nice, 80s = warm, 90s = hot, etc, etc. Celsius is no where near that intuitive and was as arbitrarily defined as Fahrenheit was.

        Arbitrarily defined? 0C = Freezing point of water at 1 atmosphere (within 0.01C); 100C = Boiling point of water at 1 atmosphere (within 0.02C). Celsius makes more sense to everyone else who uses it - why would "30s [F] = cold" be more sensible than "0-10C = cold"?

        0C = Freezing
        10C = Chilly/cold
        20C = Warm (around room temperature)
        30C = Hot
        40C = Very hot
        100C = You're being cooked by cannibals

        This is no less sensible than fahrenheit, the only difference being celsius has a logical and practical 0-point which ma

      • Re: (Score:2, Funny)

        by Anonymous Coward

        this is an American site

        And merka is a christian nation dagnubbit. Ya'll should be usin de proper bible units of cubits and hogs heads.

      • as arbitrarily defined

        For regular humans, maybe. For the scientific community, not so much.
        • by Shakrai (717556)

          For the scientific community, not so much.

          I need something useful for the scientific community when deciding [weather.gov] what to wear today?

          For regular humans, maybe.

          I think you just proved my point.

      • Re: (Score:3, Insightful)

        by Blkdeath (530393)

        Fahrenheit just makes more sense to most of us. 30s = cold, 40s = chilly, 50s = cool, 60s = decent/might need a windbreaker, 70s = nice, 80s = warm, 90s = hot, etc, etc. Celsius is no where near that intuitive and was as arbitrarily defined as Fahrenheit was.

        Celsius, however, does not rely solely on memorization to "make sense". It's based on certain scientific principals that remain as yet unwavering. 0C is the freezing point of water, 100C is the boiling point of water. It's quite simple to deduce the relative levels of comfort in between; when you know that it's 0C outside the precipitation that's falling isn't going to be rain but instead the frozen variety. When it's 40C outside you know it's pretty damn warm, and when it pushes the 50s and 60s you start t

      • by dwater (72834)

        I posit that you've (plural) just made those definitions up and that they are only intuitive because you've defined them that way.

        Furthermore, I think you'd easily come up with similar definitions using Celsius once you get used to it. For example, I have a pretty good idea how I'd feel in whatever Celsius number you care to pick...perhaps just split it into 5s...and you'd feel like it's just as intuitive.

        0 freezing
        05 very cold
        510 cold
        1015 chilly
        1520 slightly chilly
        2025 comfortable
        2530 warm
        bla bla

    • by Chrisq (894406)
      Absolutelty. I thought it would be like a sauna, when in fact it is just a warm room. I have been in computer rooms at 40 C (after cooling failure) and everything still ran OK until the cooling was fixed.
    • by tritonman (998572)
      How about completely immersing the entire data center in oil? You may need some sort of SCUBA gear to to server maintenance though.
    • There is absolutely no advantage to Celsius over Fahrenheit. It is what you grow up with. If you argued Kelvin was better, I would agree as it has enough sense to start the scale at "zero". Is 20 Celsius twice as hot as 10 Celsius? No. Twenty Kelvin, though, is twice as hot as ten.

      Other metric scales are many times more useful than imperial. Temperature is not one of them.

  • I'd be happy with a 75-degree data center.

    • Re: (Score:3, Interesting)

      by 0racle (667029)
      We upped the temperature in our small data center to 75~80. Those systems in there run just fine at around (and a little higher then) room temperature. I didn't really see any need to keep it running like a refrigerator for no reason. The AC runs less, there must have been some money saved, but it is more comfortable in there the few times I have to do something there.
  • it will run at 100 degrees Fahrenheit and not crash, but for how long?
    • by Skater (41976)
      If it's not going to crash, I'd say quite a long time.
    • I don't know, it seems both the UK and Australia's government data centers seem to be running very well at Fahrenheit 451! Makes Censorship of the internet soo much more efficient..

  • Drives (Score:5, Interesting)

    by maz2331 (1104901) on Thursday March 19, 2009 @10:22AM (#27255373)

    I'd be mostly concerned about the lifespan of hard drives at these temperatures. The electronics can be easily made to tolerate heat, but drives are a weak link. The bearings and lubricants are especially vulnerable.

    • by wiz31337 (154231) *

      Solid state drives, for the win.

    • Re:Drives (Score:5, Interesting)

      by Alphager (957739) <florian@haas.gmail@com> on Thursday March 19, 2009 @10:42AM (#27255691) Homepage Journal
      I think the google hard-drive whitepaper (~2004? 2005?) said that hard-drives running in an environment around 38C were less prone to failures than cool hard-drives.
      • Re: (Score:3, Interesting)

        by MilesAttacca (1016569)

        Here's the whitepaper [74.125.47.132] (HTML-converted).

        I'm not able to open the PDF right now to see the pretty graphs, but it says "The figure shows that failures do not increase when the average temperature increases. In fact, there is a clear trend showing that lower temperatures are associated with higher failure rates. Only at very high temperatures is there a slight reversal of this trend." However, it also notes that "What stands out are the 3 and 4-year old drives, where the trend for higher failures with higher t

    • by afidel (530433)
      Put the SAN in a more controlled environment, you spend a little more on cabling but that's probably peanuts compared to the energy savings.
    • Re: (Score:3, Informative)

      It's really not so bad. Most drives are rated to about 55deg C (131F), 104F is only 40C.

      The key is to design the server with sufficient airflow to try and keep the temperature of the components close to the room's temperature.

      Looking at the Datasheet [rackable.com], it looks like they are running the servers on DC power. That way, each server doesn't have it's own power supply, they just hook up to a separate power unit elsewhere in the rack.

      The servers don't seem to have fans either. The fans are in the cabinet door.

      Th

  • Throw some sand on the floor (it is conductive after all and the racks are enclosed anyways right?), Relax dress attire to allow for sandals and shorts (not too much relaxing, as IT personel and skimpy clothing rarely mix), and you will attract more IT personnel due to the tropic weather in your location!
  • by Em Emalb (452530) <ememalb@@@gmail...com> on Thursday March 19, 2009 @10:25AM (#27255411) Homepage Journal

    I realize it's the trendy thing these days to target the data center as an area of concern monetarily, but this is a little ridiculous.

    All it will take is one poor geek spending a 12 hour day in the data center for this to be deemed a horrible idea. (Like that never happens)

    Seriously, this is retarded. If you do your cooling and power CORRECTLY, you won't have a ridiculous bill and your data center will be at a more reasonable temperature.

    I hate really hot weather...you can always put on more clothes, but you reach a limit on what you can take off.

    • you might as well pipe water pass the walls next to the racks and install heat collectors, you'd be able to have free hot water for the bathrooms.

    • by Shakrai (717556)

      but you reach a limit on what you can take off.

      Obviously you've never worked in the insurance or legal businesses ;)

    • by clickety6 (141178)

      but you reach a limit on what you can take off.

      With your average geek, that limit is reached sooner than with most people!

  • by geekmux (1040042) on Thursday March 19, 2009 @10:28AM (#27255459)

    "...But higher temperatures can be less forgiving in the event of a cooling failure, and not likely to be welcomed by employees working in the data center."

    Not welcome? That all depends, on if I can relocate my Data Center to a topless beach in Miami. Sure beats the current scenery, and the dress code would likely change.

    Of course, the fact that you probably don't want to see your average IT person running around topless wearing a thong is another matter entirely...

  • by turgid (580780) on Thursday March 19, 2009 @10:30AM (#27255475) Journal

    Buildings provide hot water for washing hands etc. Cold water comes in from outside and is heated using electricity or gas to make hot water which costs money and energy.

    Pipe the cold water (which is usually somewhere between 0 and 20 degrees C) through heat exchangers in the hot data centre before heating it up to working temperature with gas or electricity.

    That way, you reduce the data centre's temperature to more like 20-25C, and you heat the water up by 10C (say) saving on gas or electricity bills since there is less of a temperature difference to get it up to the required temperature.

    I eagerly await my Nobel Prize for Common Sense.

    • by Shakrai (717556)

      Pipe the cold water (which is usually somewhere between 0 and 20 degrees C) through heat exchangers in the hot data centre before heating it up to working temperature with gas or electricity.

      And once your cold water reaches the same temperature as the data center, what then? Most office buildings don't use a lot of hot water (it's mostly hand washing as you pointed out) and I'd be surprised if they go through enough to absorb the BTUs from a typical data center for any meaningful amount of time.

      • by wpiman (739077)
        If we had hot water pipes on the street they could sell it back.

        Can't a Sterling engine be used to turn the hot water into power to feed back to the data center?

      • by turgid (580780)

        And once your cold water reaches the same temperature as the data center, what then?

        You heat it up more to become hot water.

        The water you want to be cold, you don't pipe through the data centre.

        Water has a very high specific heat capacity [wikipedia.org] compared to air. You don't need a lot of it to absorb a lot of heat energy. That equates to a cooler data centre.

      • Why, you convert the heat energy back into electricity, of course, and use it to power the servers!
    • And since heat exchangers never leak, there's no problem putting them in the data center with all the electrical devices...

      • by turgid (580780)

        And since heat exchangers never leak, there's no problem putting them in the data center with all the electrical devices...

        Apparently not. We've managed with air conditioners for 40+ years, with drip trays and drains. My old Nucular(TM) power station used to have them in the Temperature Monitoring Room to keep the PDP-11s cool.

  • by jollyreaper (513215) on Thursday March 19, 2009 @10:32AM (#27255509)

    The proper question is "Are our coworkers ready to deal with how we'll smell like after spending time in that server room?" It'll smell like a monkey house, but probably with less feces. Unless we're working with that superstar bastard programmer a few articles back who poo'd in the lobby.

  • by JFlex (763276) on Thursday March 19, 2009 @10:36AM (#27255585)
    welcome our new sweaty sysadmins.
  • 80 degrees (Score:3, Interesting)

    by tthomas48 (180798) on Thursday March 19, 2009 @10:43AM (#27255713) Homepage

    We have an 80 degree data center. It's not particularly pleasant to be in (as you get buffeted by hotter winds coming off of power supplies), but we haven't seen any more failures than normal.

  • Don't conductors generally get more resistive when they heat up?

    Is there a cost to data centers when their computers' circuits become more resistive?

  • But this would mean that we'd need a new law, banning any manager from trying to enforce any sort of dress code above and beyond "please wear clothing" for the IT department. If I'm going to be working in a warm data center, there's no way in hell that I'm dressing in 'business casual.' Management can kiss my ass. :)

  • I wouldn't mind a DC between 75 and 80 degree F. I'm tired of shivering when I walk into the DC. Of course I'm not constantly racking larger servers. Those guys might like it sub 70.
  • I have never understood why data centers located in colder climates need cooling systems. Surely the only thing they need is access to as much outside temperature as possible and humidity filters? The other solution is to design data centers to use things like Windcatchers [wikipedia.org] to use natural physical processes.

    • Re: (Score:3, Informative)

      by Darth Muffin (781947)
      That might work for 6 months of the year, but we get these things called summers... We can hit 100 degrees or more here in Washington State. Even Alaska gets warm in the summer (Fairbanks record high of 99F).
  • ...not likely to be welcomed by employees working in the data center.

    Especially big fat sweaty BOFHs ;-)

  • Really bad idea (Score:4, Insightful)

    by John Sokol (109591) on Thursday March 19, 2009 @11:08AM (#27256147) Homepage Journal

    Yes there saving money on cooling cost, or at least they seem to believe that and I am sure when they fail to take everything into account this is true.

    The reality it the server room still has to pull that heat out. Increased Delta T is just lost energy.

    Here is really why it's a terrible idea.

    1.) Component failures. Of all parts from bearing in the drives, and fans to the silicon itself has a much higher failure rate.

    2.) The components use more power at higher temperatures! This is from increased leakage currents in the silicon.

    Below is a graph from Research My Startup company did!
    http://www.silentcomputing.com/tech/market2.gif [silentcomputing.com]

    They really need to used ducted air or any other technology to reduce the Delta T! By this I mean bring the cooling as close to the components as possible.
    Right now server rooms need to run internally at 10C to 15C to keep the CPU chips below 60C.
    If they just brought the cooling directly to the cpu's and let that cool spread from there they could use out door passive radiators! 0 air conditioning cost and the most power savings.

    This is what my start was doing till someone tried to steal the who damb thing and sunk the company.

    • 2.) The components use more power at higher temperatures! This is from increased leakage currents in the silicon.
      Below is a graph from Research My Startup company did! http://www.silentcomputing.com/tech/market2.gif [silentcomputing.com]

      May I point out the obvious: not only the higher power consumption comes from increased leakage currents in the silicon, but it also comes from the fact that power supplies are less efficient at higher temperatures, so they need to pull more current from the wall socket to maintain the same ou

  • by sacremon (244448) on Thursday March 19, 2009 @12:25PM (#27257345)

    ...but the servers aren't the only thing in a data center. If the switches and routers can't take the higher heat, then you aren't going to get much use out of those servers.

Genius is ten percent inspiration and fifty percent capital gains.

Working...