Slashdot Mirror


Oil Soaked Servers Coming Soon

grease_boy writes "A UK company will start selling server racks submerged in oil baths within a year. Very-PC is working on prototypes and says that because oil transfers heat more efficiently, power usage can be cut by fifty percent."

321 comments

  1. Heh by peterprior · · Score: 4, Funny

    Bring a whole new meaning to Oil in a rack...... geddit..

    *grabs coat*

    1. Re:Heh by Anonymous Coward · · Score: 0
    2. Re:Heh by Anonymous Coward · · Score: 0

      Sounds like these new servers would be solid as a rock. (shamelessly stolen from Arrested Development)

    3. Re:Heh by clickclickdrone · · Score: 0, Offtopic

      If I had any +funny mod points this week, you'd have got them. :-)

      --
      I want a list of atrocities done in your name - Recoil
    4. Re:Heh by nacturation · · Score: 3, Funny

      Does this oiled up rack run on 36 double D batteries?

      --
      Want to improve your Karma? Instead of "Post Anonymously", try the "Post Humously" option.
    5. Re:Heh by hobo+sapiens · · Score: 2, Funny

      Ah, the Oily Boid gets the Woim!

      Hot cha cha cha cha

      --
      blah blah blah
    6. Re:Heh by thoughtlover · · Score: 5, Funny

      Awww... I thought you were going to point us to a clip of C3PO being lowered into his oil bath. That's almost like a server soaked in oil, yeah?

      --
      No sig for you! Come back one year!
    7. Re:Heh by Markspark · · Score: 1

      and you never will.. muahahahha.. :P

      --
      i find your lack of faith in science disturbing!
    8. Re:Heh by Archangel+Michael · · Score: 1

      If you're gonna spoof a saying at least have it make sense.

      "The Oily Board gets Warm" (not hot)

      --
      Agent K: A *person* is smart. People are dumb, stupid, panicky animals, and you know it.
    9. Re:Heh by FlatLine84 · · Score: 0

      I can see just a big mess in the future... Racks collapsing under the weight of oil filled computers. Nothing but a big oily pile of gnarled metal, plastic, and electricity. Sounds like a place for OSHA to have a field day.

    10. Re:Heh by pilgrim23 · · Score: 2

      Actually, fluid cooling of circuits has been around quite a while. Oil is a silly choice though. The Cray II had cooling stacks that pumped a liquid coolant through the machine core. Looked kinda futuristic and cool too: http://www.spikynorman.dsl.pipex.com/CrayWWWStuff/ Criscan/Cray2cascade.jpg

      --
      - Minutus cantorum, minutus balorum, minutus carborata descendum pantorum.
    11. Re:Heh by PitaBred · · Score: 1

      Ummm... he was typing in a Bostonian-style accent (some comedian is famous for the Hot-cha-cha-cha-cha meme as well, I can't remember who). Oily is how the word "early" sounds when it's pronounced as such. But hey, go ahead and feel free to misunderstand the joke... just don't drag the rest of us into the ignorance.

    12. Re:Heh by alienmole · · Score: 1

      OSHA and the EPA. We're talking potential Superfund sites in every server room! Yeah baby!

    13. Re:Heh by Kingrames · · Score: 1

      I was thinking it was more along the lines of

      "GRRREASE ME UP, WOMAN!"

      "...okey dokey."

      --
      If you can read this, I forgot to post anonymously.
    14. Re:Heh by hobo+sapiens · · Score: 3, Informative

      thanks for the backup. Some people...sheesh

      It was Curly, actually. In one Three Stooges short, Curly was covered in oil (from an oil well he just discovered, you pervs), and Moe said something like "Whatcha doin, knucklehead?" To which Curly says "You know what they say! The oily boid gets the woim! nyuk nyuk nyuk"

      The Hot cha cha cha was Jimmy Durante, and I just added that in for kicks.

      The funny part is that this post will get modded informative. If there are any other jokes that need in-depth explanations, I'd be happy to serve.

      --
      blah blah blah
    15. Re:Heh by cayenne8 · · Score: 4, Funny
      But, aren't we trying to wean ourselves off dependence on foreign oil??

      Why not start off right, and soak these in biodiesel or ethanol?

      :-)

      --
      Light travels faster than sound. This is why some people appear bright until you hear them speak.........
    16. Re:Heh by JackieBrown · · Score: 1

      As long as I can still smoke in there.

    17. Re:Heh by LordSnooty · · Score: 1

      thanks for the backup. Some people...
      Some people what? Haven't seen the Three Stooges? Frankly I'm amazed when people don't understand every single bizarre obscure reference made on /.
    18. Re:Heh by bobcote · · Score: 1

      The reason the server is down is it's time for 3000 gb oil and filter change.
      Seriously, recycling will be messy.

    19. Re:Heh by iminplaya · · Score: 1

      ...some comedian is famous for the Hot-cha-cha-cha-cha meme as well, I can't remember who...

      The late, great Jimmy Durante, "I've got a million of 'em ---Hot cha cha cha cha!"

      --
      What?
  2. But how do they taste? by Anonymous Coward · · Score: 1, Funny

    I find most fried foods taste the same. Will computers follow this trend?

    1. Re:But how do they taste? by operagost · · Score: 1

      Hopefully. If my server room has a power failure, at least I know it'll smell like french fries!

      --

      Gamingmuseum.com: Give your 3D accelerator a rest.
  3. Interesting by LordPhantom · · Score: 5, Funny

    That sounds like a step forward. At least, until you consider that anyone working on them would get coated in oil... and frankly, server admins coated in oil are really something nobody wants to see.

    1. Re:Interesting by SNR+monkey · · Score: 4, Funny

      There really needs to be a "-1 Disgusting" mod for posts like yours. It made me laugh initially, but then I shuddered when the mental image hit. I'm going to try not to think about that for the rest of the day. Or any other day for that matter.

    2. Re:Interesting by UnknowingFool · · Score: 1

      Thanks a lot! Now I have to burn that image out of my mind! Gahhh!

      --
      Well, there's spam egg sausage and spam, that's not got much spam in it.
    3. Re:Interesting by ajs · · Score: 1

      It's not a step forward. It's a step back in a sense. This has been how large transformers have been build for decades. I'm sure that this application will use the same oil as street transformers, and I've seen a number of hobby applications of this in machine cooling before.

    4. Re:Interesting by jd · · Score: 3, Interesting

      Slashdot ran a story on total-immersion computing using an oil bath, oh, four or five years ago now. He was using mineral oil. This is not to say it's a bad idea - on the contrary, it's rather overdue on the technology front. However, it does take about this amount of time to go from hobbyist to early market, so maybe this story should have been expected some time this year or next.

      --
      It's a small world and it smells funny; I'd buy another if it wasn't for the money; Take back what I paid (SoM)
    5. Re:Interesting by LordPhantom · · Score: 1

      *whoosh*

      They tried using motor oil initially. How cutting edge can they be?

    6. Re:Interesting by LordPhantom · · Score: 1

      Damn preview button. That *woosh* is the sound of both the sarcasm going over your head AND my speedy click on submit.

    7. Re:Interesting by Hoi+Polloi · · Score: 2, Funny

      I don't look forward to taking my PC to Jiffy-Lube for my 500 cpu-hour oil change.

      We also need to break the dependency on foreign PC oil sources. I'm switching to bio-diesel PCs. Ummmm, my PC smells like french fries.

      --
      It is by the juice of the coffee bean that thoughts acquire speed, the teeth acquire stains. The stains become a warning
    8. Re:Interesting by Kadin2048 · · Score: 1

      It's not a step forward. It's a step back in a sense. This has been how large transformers have been build for decades. I'm sure that this application will use the same oil as street transformers, and I've seen a number of hobby applications of this in machine cooling before.

      More than that, back in the day, it wasn't uncommon for supercomputers (I think several of the Cray models specifically) to have their processor cores submerged in liquid coolant. [1]

      It wasn't oil, though. IIRC, it was a hideously expensive, probably ozone-depleting, known-to-the-state-of-California-to-make-your-nuts -shrivel, processed from baby seals, 3M product called "Fluorinert."

      For a few years back in the IBM G5 / Intel P4 days, I was sure we were headed back in that direction. I mean, my computer has a freaking radiator in it, a submersion bath can't be that far away, right? But then the chip manufacturers woke up to the whole power-consumption thing and we got a reprieve.

      I don't know what the boiling point of Fluorinert is, but I've always thought that the best cooling liquid would be some sort of lightly-pressurized gas, such that it was a liquid except for right over the surface of the chips, where it would boil. The state-change would pull away tons of heat, and then you could re-condense it against the top of the container (chill it either just to the atmosphere or with conventional refrigeration systems). Don't think I've ever seen this implemented, though.

      [1] Wikipedia confirms and says it was the Cray II specifically. Photo here; the Fluorinert was cooled via a "waterfall," which is damn cool in itself.

      --
      "Ladies and gentlemen, my killbot features Lotus Notes and a machine gun. It is the finest available."
    9. Re:Interesting by Sneakernets · · Score: 0

      Even more interesting is the quote at the bottom of /.'s page on this story....

      I am covered with pure vegetable oil and I am writing a best seller!

      --
      "No freeman shall ever be debarred the use of arms." -- Thomas Jefferson
    10. Re:Interesting by HolyCrapSCOsux · · Score: 1

      fluorinert is still a good heat transference fluid. (if you don't mind paying upwards of $200 a gallon). I've seen a few hobbyists use a dry ice on the cold side of the heat exchanger. You could always just use a straight liquid nitrogen bath, but the power required to recycle the nitrogen would be prohibitive.

      --
      0xB315AA8D852DCD3F3DCA578FD2E0BF88
    11. Re:Interesting by FlatLine84 · · Score: 0

      Grease monkey will no longer apply to just mechanics.

    12. Re:Interesting by zero_offset · · Score: 1

      Actually Flourinert is very safe stuff.
      Non-toxic, environazi-friendly, the whole nine yards.

      Very expensive though -- about $200 per gallon.

      --

      Slashdot quality declines as the number of hot grits posts decreases. - Provolt's Law, Apr-09-2005

    13. Re:Interesting by zippthorne · · Score: 1

      You mean like tetrafluoroethane found in "canned air" in office supply stores and automobile refrigeration systems?

      --
      Can you be Even More Awesome?!
    14. Re:Interesting by More_Cowbell · · Score: 1
      I work in a data center you insensitive clod!

      Seriously though, I do. And you are right. That's just wrong.

      --
      Experience teaches only the teachable. -AH
    15. Re:Interesting by couchslug · · Score: 1

      If oily servers and oiled admins come to pass, not only will people want to see it, but there will inevitably be a newsgroup.

      Do not visualize any potential content of "alt.binaries.pictures.erotica.sysadmin-sebaceous" and you'll be fine.

      --
      "This post is an artistic work of fiction and falsehood. Only a fool would take anything posted here as fact."
    16. Re:Interesting by Jeremy+Erwin · · Score: 1

      Ethane is C2H6. TetraFluoroethane replaces 4 of those hydrogens with fluorines: C2H2F4. But fluorinert is a perfluorocarbon-- it has no residual hydrogens, and as a result is chemically inert for most practical purposes.

    17. Re:Interesting by wellingj · · Score: 1

      I think the PC that I picked up at the swap meet already smells like french fries.....

    18. Re:Interesting by Verypc · · Score: 1

      The coolant is contained within sealed processing node cartridges, with seporate hard disks, so no you won't have to see this.

  4. Liquid cooled computers, are so last millenium! by 140Mandak262Jamuna · · Score: 2
    --
    sed -e 's/Chuck Norris/Rajnikant/g' joke > fact
    1. Re:Liquid cooled computers, are so last millenium! by Anonymous Coward · · Score: 0

      Ah, those long lost days when real programmers run atmosphere models in FORTRAN on Freon cooled supercomputers...

  5. Hurrah! by Rob+T+Firefly · · Score: 2, Insightful

    This is fantastic! I can't see a single downside to increasing the demand for machine oil in this modern world, nosirree..

    1. Re:Hurrah! by Arkaic · · Score: 1

      I know. Seems like it would do more harm than good in some ways.

      FTA:

      "I don't know why oil is being suggested for computer cooling instead of accepted dielectric fluids," says Garimella, who is not familiar with Very-PCs plans. "The idea itself seems the same as using dielectric fluids and the latter are clean, non-toxic and ozone-friendly."

    2. Re:Hurrah! by Ellis+D.+Tripp · · Score: 1

      Oil IS an accepted dielectric fluid! Highly refined mineral oils are widely used for cooling and insulating electrical equipment (like the transformer that feeds power to your house), and relatively cheap, even given current petroleum prices.

      Specialty fluids like Fluorinert are less messy when you need to work on the submerged parts, but that stuff is EXPENSIVE. How about over $300 per LITER?

      http://www.parallax-tech.com/fluorine.htm

      --
      Remember "News for Nerds, Stuff that Matters"? Help make it a reality again! http://soylentnews.org
    3. Re:Hurrah! by Odiumjunkie · · Score: 4, Interesting

      Exactly, the website and business proposal seem very amateurish. They actually tried using motor oil before realising that by some strange, arcane and entirely unpredictable process it correded PCBs? Am I being too presumptive in assuming that these people know very, very little about electronics?

      Why on earth they didn't at least think to use highly-refined mineral oil like transformer oil is beyond me. I mean, filling a server with motor oil? Are you kidding me?

      Someone saw the Tom's Hardware cooking-oil-cooled-PC experiment that was published a while back, and saw an opportunity to make some money. They didn't realise that Tom's Hardware used oil because it was headline-grabbing, cheap, easy to purchase and --oh yeah-- wasn't being used to cool a server that had to be stable and reliable. That doesn't mean it's the best choice of coolant.

      Hell, you could do it with purified water if you wanted to, but your uptimes might take a hit.

    4. Re:Hurrah! by mwvdlee · · Score: 1

      That statement, together with VeryPC's own statement that they did intial prototyping with normal oil but realized it could corode the systems makes me somewhat... "doubtful" as to their ability to create stable servers.

      --
      Slashdot social media options: AIM, ICQ, Yahoo, Jabber and Mobile Text. Why no MySpace?
    5. Re:Hurrah! by SnowZero · · Score: 1

      Fluorinert, which is what is used for supercomputers, costs something like $3000 a gallon. Perhaps Garimella should consider the implications of that for a company wanting promoting immersion cooling for ordinary servers.

    6. Re:Hurrah! by Mr_Blank · · Score: 2, Informative
      Here is a link the Tom's Hardware article, "Strip Out The Fans, Add 8 Gallons of Cooking Oil"

      Common sense dictates that submerging your high-end PC in cooking oil is not a good idea. But, of course, engineering feats and science breakthroughs were made possible by those who dared to explore the realms of the non-conventional. Members of the Munich-based THG lab are only too happy to confirm this fact. And not only did we find that our AMD Athlon FX-55 and GeForce 6800 Ultra equipped system didn't short out when we filled the sealed shut PC case with cooking oil - but the non-conductive properties of the liquid coupled created a totally cool and quiet high-end PC, devoid of the noise pollution of fans. The PC case - or should we say tank - also offered a new and novel way to display and show off your PC components....
    7. Re:Hurrah! by Broken+scope · · Score: 1

      First time I saw this it was done with cooking oil.

      --
      You mad
    8. Re:Hurrah! by networkBoy · · Score: 1

      And most flourinerts are not nice to the environment.
      despite what the quote in the article says. Dow has replacements for the entire FC line because of environmental concerns.
      the HFE line is almost twice the price though and can leak out of a seal better than helium from a latex baloon!
      -nB

      --
      whois gawk date unzip strip find touch finger mount join nice man top fsck grep eject more yes exit umount sleep dump
    9. Re:Hurrah! by alex4u2nv · · Score: 0

      Yes I would agree that it is very amateurish and a very hasty entrepreneurial decision. You can probably save energy as they claim, I haven't bothered with benchmarks, testings, or reports on this to know that it is unreasonable for server.

      This server undermines the design of a data center for disaster recovery. Letting one of these systems into a server room , or data center is just as good as keeping a container of kerosene next to the racks in case of emergency.

    10. Re:Hurrah! by AP2k · · Score: 1

      Ignorant of electronics, perhaps. Ignorant of chemistry fits the bill more. Moreso, oil companiyes dont generally let out how much of what goes into a can of motor oil, to my knowledge, so I can see why they would be ignorant of corrosive chemicals.

      Motor oil is cheap and transformer oil isnt. Not only that, transformer oil is made for extremely high standoff voltages which would only be present of a rig got struck by lightning. So I can see why it would be seen as unnecessary.

  6. Environmental issues? by owlstead · · Score: 1

    I can see how people would want to do this when hacking their own motherboard, but I would not like to see this become commonplace. For a starter, what to do with the oil after it has been used. I presume that you cannot reuse the oil to bake fries in. And I would really like to know if this would have negative implications considering the life-time of the equipment as well.

    1. Re:Environmental issues? by leuk_he · · Score: 1

      THat oil can be reused real easy. e.g. to convert it to diesel oil to run your car on.

      The only problem i can see is that once you bath your pc components in oil you cannot reuse them elsewhere because the contacts get all dirty. Also i wonder if the components on a Motherboard can handle being oaked in oil. I can imaginge some component will solute in oil after a month or so.

      Note also that Harddrives can not be soaked in oil (they need the air cushing )

    2. Re:Environmental issues? by Anonymous Coward · · Score: 0

      OK, so you glue a tube to the air ducts on the drive...

    3. Re:Environmental issues? by walt-sjc · · Score: 1

      There are many wonderful highly toxic chemicals that can easily clean the oil off...

      But back to the main concern... Obviously when needed you would drain the oil and filter it so it can be reused for cooling again. I would assume that the system would be closed and the same oil could be used for dozens / hundreds of years.

      I would also assume that servers could be more dense - much more dense than traditional blade servers as long as you pump the oil around a little. The spacing between boards could be drastically reduced. The tight spacing reduces the volume of oil needed.

      Obviously you don't put hard drives in the oil. They are also much more prone to fail, and therefore need servicing more frequently. Parts that need more frequent service would not be good candidates for oil submersion.

    4. Re:Environmental issues? by akpoff · · Score: 1

      I presume that you cannot reuse the oil to bake fries in.
      Are you new to the Western world? We refine oil to put in our cars, we burn it in our older cars, we fight wars to get the oil, we put it on our salads, we even slather our bodies in it. But we do not bake our fries in it! Fries we, um, FRY them in oil. In fact, I'm quite sure even dishes like Baked Alaska are at some point fried in oil.
    5. Re:Environmental issues? by saider · · Score: 1

      Dish soap and water can be used to clean electronics as long as they are not powered. Be sure to rinse well with clean water (distilled or reverse osmosis) and dry at an elevated temperature (50C) to be sure that all the water is removed.

      I have cleaned up several coffee soaked instruments in this fashion.

      --


      Remember, You are unique...just like everyone else.
    6. Re:Environmental issues? by PitaBred · · Score: 1

      Several? Sounds like you need to institute a "sippy cups only" policy for coffee near instruments.

    7. Re:Environmental issues? by walt-sjc · · Score: 1

      Yes, but dish soap is not nearly as fun as highly toxic chemicals. :-)

    8. Re:Environmental issues? by owlstead · · Score: 1

      Yeah, those stupid Dutch persons don't know squat about other languages. Shame on them, making such blatant mistakes. C'est ridicule!

    9. Re:Environmental issues? by Anonymous Coward · · Score: 0

      Even worse, they have no sense of humor or ability to recognize someone making an obvious parody of one's own culture.

  7. Starving IT guys rejoice! by LoganTeamX · · Score: 0

    No more long cafeteria lines! Simply bring your lunch to the server room and cook away! Make sure you strain the bits out or they'll clog the tape backup. Nobody wants to restore your lunch, anyways.

    --
    One of the 187.
    1. Re:Starving IT guys rejoice! by rts008 · · Score: 1

      Just beware the /. effect during cooking!
      (or would this change to be the molotov cocktail server?)

      --
      Down With Slashdot BETA!!! I've been around the corner and seen the oliphant; you can only abuse me from your perspecti
  8. Go green... by Capt+James+McCarthy · · Score: 1

    So will Al Gore come out with a corn-oil version?

    --
    There are no loopholes. It's either legal or it's not.
    1. Re:Go green... by Zonekeeper · · Score: 1

      Yes, he will, but it will be for everyone else except him.

    2. Re:Go green... by xfmr_expert · · Score: 2, Informative

      Actually, vegatable oils (natural ester fluids) have been used as an alternative dielectric fluid for several years now. A fair number of distribution-size transformers are filled with it, as it has less environmental consequence in the event of spills. It does have lower oxidation stability than mineral oil, so the system would have to be sealed.

    3. Re:Go green... by bigred85 · · Score: 1

      When he's not defending Earth from the dangers of Manbearpig.

      I'm super serial!

      ...Okay, I'll stop now.

    4. Re:Go green... by MightyYar · · Score: 1

      Well, he made their job pretty easy by using more electricity after he made his environmental movie than before he made his environmental movie. I thought we were supposed to conserve?

      --
      W..w..W - Willy Waterloo washes Warren Wiggins who is washing Waldo Woo.
    5. Re:Go green... by scottv67 · · Score: 1
      Actually, vegatable oils (natural ester fluids) have been used as an alternative dielectric fluid for several years now. A fair number of distribution-size transformers are filled with it,

      I fired-up the way-back machine and dug up this old story that mixed big transformers with deep-frying oil. Old timers (like me) will remember this one.

      http://homes.cerias.purdue.edu/~spaf/Yucks/V4/msg0 0027.html
       
       

      Date: Mon, 26 Sep 1994 11:31:14 -0400
      From: bostic@CS.Berkeley.EDU (Keith Bostic)
      Subject: The mother of all grease fires
      To: /dev/null@python.bostic.com

      Forwarded-by: stripes@uunet.uu.net (Josh Osborne)

      From: Brian Reid
      Date: Fri, 23 Sep 94 17:34:09 PDT

      I work in the very center of the city of Palo Alto, in a nice office
      building. We are surrounded on every side by restaurants, hotels, and so
      forth. But we are a computer company, and so our building ends up needing
      a lot of electricity. We use about a megawatt (1 million watts).

      In order to deliver a million watts of electricity to an office building,
      you need a very large transformer. These transformers are too big to put
      on poles, and besides in quaint downtown areas nobody likes those poles
      any more. So the transformers are put underground. The million-watt
      transformer that powers our office building is located in an underground
      vault in the middle of a walkway that leads to City Hall. The transformer
      is about the size of a small car, and the transformer vault is about the
      size of a one-car garage, except that the way you get in is to climb down
      a ladder from the street level. The top of the transformer vault is well
      ventilated, because a million-watt transformer generates a lot of heat.

      Several fine restaurants are near this walkway, along with a bank, an art
      supply store, and so forth. There's a lot of foot traffic. This being
      California, where it never rains, and this being Palo Alto, where it is
      always springtime, the restaurants have outdoor seating areas that are
      very popular.

      Recently the patrons of one restaurant started to complain that there was
      an unpleasant odor in their otherwise idyllic outdoor seating area. Soon
      the Health Department was called, and they quickly determined that the
      odor was caused by rancid oil that had seeped into the sidewalk. Further
      investigation showed that the source of the rancid oil was overflow from
      a nearby grating. The grating was marked "City of Palo Alto Utilities",
      so the utility department was called.

      The utility crew quickly discovered the problem. The oil wasn't really
      oil, it was molten deep-frying grease, which was molten because it was
      being kept warm by a million-watt transformer. The entire vault was
      completely full of used frying grease, about 2000 gallons of it, which
      was enough to completely cover the transformer. The heat of the
      transformer kept the grease from solidifying.

      Police quickly figured out what had happened. Every night for quite a
      number of years, one of the nearby restaurants had, at closing time,
      emptied its fryer into the transformer vault, thinking that they were
      dumping it into the storm sewer. It's quite illegal to dump grease into
      a storm sewer, of course, but they probably figured they would never get
      caught.

      Transformers do occasionally overheat; this is why they are kept in
      concrete vaults. If this one had overheated, we would have had the mother
      of all grease fires.

      Last night they shut off all of the electrical power, pumped out the hot
      grease, washed out the vault, and replaced the transformer. It's very
      fortunate that nobody was killed.

      Today's "daily special" menu did not include the usual fried fish.

      ---
  9. Cut power in half? by theantipop · · Score: 2, Interesting

    "It is possible to cut power consumption in half," managing director Peter Hopton told New Scientist. "You don't need to drive inefficient fans, or the usual air conditioning."
    Do data centers really use as much power cooling the server farms as running them?
    1. Re:Cut power in half? by Mprx · · Score: 1

      He doesn't specify what power consumption he is talking about, so he probably means the power consumption of the old cooling system. Much less impressive than halving total power consumption.

    2. Re:Cut power in half? by Sobrique · · Score: 3, Informative

      It's probably not far off. Bear in mind that a lot of the 300W of your power supplies in each system is dissipated as heat. I've got a datacenter that's had water cooled racks installed (which as you might imagine, has horrific 'overheads' on installation, cableing and maintenance). At £5k/rack, + overheads, it was still a cheaper solution than standard 19" rack + aircon bill.

    3. Re:Cut power in half? by theantipop · · Score: 1

      Well using an oil bath to coll a semiconductor doesn't magically halve the current needed to switch a transistor so he's got something mixed up here. Or it's a bald-faced lie.

    4. Re:Cut power in half? by theantipop · · Score: 1

      Well, the fuzzy thing about this is that the heat still has to go somewhere. Granted you may not be powering thousands of tiny, whiny fans to remove the heat from the device, but now you've got a heated mass of oil that itself needs to be cooled off.

    5. Re:Cut power in half? by Sobrique · · Score: 1
      http://h71028.www7.hp.com/ERC/downloads/4AA0-5820E NW.pdf

      "How big is the burden in actual dollars? Take 100 server racks full of rack-mount servers. Each rack that requires 12 to 13 kilowatts, uses1.3 megawatts of power for the servers. The power for cooling to remove the heat generated is almost equal to that dissipated by the IT hardware itself. So the air conditioning will need another 1.3 megawatts of power. With the cost of electricity today, 1.3 megawatts at 10 cents a kilowatthour for a 24/7 operation is approximately $1.2 million per year. This is quite significant. And the pressure to reduce it is becoming urgent."
      OK, so it's marketing propaganda, but suggests that energy used by hardware in a datacentre ~= energy used to cool a datacentre. That sounds about right to me, but admit I haven't checked in detail. (Somewhere I have specs on power and cooling at our datacentre I could use for reference, but that'll take me a little longer to find, but as I say, it sounds 'about right'). So, if they completely eliminated the 'cooling power use' then yes, halving our electric bill would be very useful, as 'clean, UPS backed 3-phase' in datacentre quantities gets rather pricey. More likely though, this is a bit of an exaggeration, and they'll halve the 'cooling' bill. Which would only be 25%. However if they can get their cost of hardware under that threshold price of 'electric bill per rack' then they'll get sales in proportion to how much, and how annoying it is to deal with.
    6. Re:Cut power in half? by Spazmania · · Score: 4, Informative

      Do data centers really use as much power cooling the server farms as running them?

      More or less, yes. Efficiency on the A/C units is usually around 2:1 and sometimes approaches 3:1, that is you get twice the cooling as the energy you put in. Since nearly 100% of the power in to servers is expressed as heat, you need the same amount of cooling. Now add inefficiencies in the cooling architecture, power for fans in the servers, inefficiency of semiconductors when running hot, etc. When you add it all up you're approaching 50% of the total power consumption.

      Its a disingenuous marketing claim though. Cooling oil is no more efficient than cooling air and convection won't be the final word at an industrial scale - they'll need pumps which consume as much energy as fans

      On the plus side 10kva in a oil-cooled rack will be a hell of a lot quieter than 10kva in an air-cooled rack with a hundred 3cm fans running at 7krpm.

      --
      Moderating "-1, Disagree" is simple censorship. Have the guts to post your opinion.
    7. Re:Cut power in half? by Anonymous Coward · · Score: 0

      It's entirely plausible, though, to have it go straight to outside, with one big fan and a heat exchanger. If the local temp is too high for that (thnik arizona) then a 1 cell marley heat exchanger would take care of thousdands of computers.

    8. Re:Cut power in half? by DjMd · · Score: 1

      I wouldn't go so far as to call it disingenuous.

      You got it all right regarding A/C inefficiency.
      So right there the efficiency improvement means that C/kva ratio is better. (More cooling for less power)

      But the goal of using oils is their heat transfer properties. Allowing for low speed pumps and radiators. In an ideal system, it would have integration into the building. Servers in their oil, heat exchanged with some central system that leads to roof radiators.

      In Warm climates this would be less effective... but still.

      --
      DJMD - The fourth man - Planetary
    9. Re:Cut power in half? by guruevi · · Score: 0

      It's the other way around with A/C, you have to put 2x-3x the energy into the system to get 1x the cooling energy.

      Meaning: if you would heat the area with a 100% efficient heating system, you use the same amount of energy to add 3 degrees, than to cool it 1 degree.

      A/C aren't very efficient, since they're basically large dry fridges with the door wide open and a heating element (the servers) near it.

      --
      Custom electronics and digital signage for your business: www.evcircuits.com
    10. Re:Cut power in half? by ericferris · · Score: 1

      Do data centers really use as much power cooling the server farms as running them?

      A bit more actually. For every watt of energy burned by a server in a DC, you need another 1 to 2 watts to handle the air, run the AC units, run the pumps (for chilled water systems), etc. A very efficient DC has a Power Utilization Ratio of 2.5 - That is, it consumes a total power of "only" 2.5 W for each watt of computer power inside. In other words, for each watt of computer power, it uses another 1.5 W for ventilation and cooling.Power now costs about 60% as much as server expenditures in a DC.

      There are already several offers on the market for spraying CPU with chilled inert liquids. Oil is just another way to do it.

      --
      Fantasy: http://ferrisfantasy.blogspot.com/
    11. Re:Cut power in half? by b0s0z0ku · · Score: 1
      It's the other way around with A/C, you have to put 2x-3x the energy into the system to get 1x the cooling energy.


      The O.P. has it right, actually. You can move more heat than energy put in - read up on Coefficient of Performance (C.O.P.). A heat pump/AC is basically a heat engine run in reverse mode.


      -b.

    12. Re:Cut power in half? by Sobrique · · Score: 1

      At my previous place of work, there was a large factory bay adjoining the server room. This actually gave us quite a useful thing to do with the 'waste' heat - use it to warm up a huge, wide open space :)

    13. Re:Cut power in half? by DoofusOfDeath · · Score: 1

      Since nearly 100% of the power in to servers is expressed as heat, you need the same amount of cooling.

      That's why I drive a bank of high-intensity LEDs from each server power supply, and shunt the light out of the building with mirrors. It considerably lowers the fraction of power we spend on cooling!

    14. Re:Cut power in half? by walt-sjc · · Score: 1

      Simple. Use a radiator, and put it outside. Most of the heat can be dumped that way, and then you just need a small amount of cooling to get it down when it is really hot outside.

    15. Re:Cut power in half? by Brickwall · · Score: 1
      They could take a lesson from the much-maligned President Bush, and use deep groundwater (I believe he has pipes going down 300 ft at his Crawford, Texas home) to provide a heat sink. Alternately, copy Toronto, where a large pipe is being constructed in Lake Ontario that provides water at approximately 4 degree C to cool office buildings in the downtown core.

      My question is "Why do they have to bathe the components in the liquid?". I seem to recall old stereo components with finned heat sinks sticking out the back. Couldn't some variant of this technology be used, where the actual PCB's don't get near the liquid, but the heat sinks are immersed in it? I realize it might not be as efficient at cooling, but I'd assume it would make the PCB's a lot cheaper to construct, and reduce maintenance costs by making it cheaper to swap out boards, etc.

      --
      What was once true, is no longer so
    16. Re:Cut power in half? by Brickwall · · Score: 2, Funny
      Efficiency on the A/C units is usually around 2:1 and sometimes approaches 3:1, that is you get twice the cooling as the energy you put in.

      In this /., we obey the laws of thermodynamics!

      --
      What was once true, is no longer so
    17. Re:Cut power in half? by guruevi · · Score: 1

      A heat pump (pumping hot air out and pumping cold air in) is not an air-conditioning. That's called a fan (albeit very large) and yes, they can move a lot of energy using minimal energy to do so. That's just displacements of air and doesn't work if the exterior temperature is higher than the required internal temperature.

      Generating the cold air (by extremely cooling the hot air) as a real air conditioning does is not that efficient. You can't possibly remove more energy out of a system than the energy you put into the system (or my physics have been off a long time and I should be working on a perpetuum mobile right now).

      You could use a 'half-open' system, that uses the external air to cool down the systems which is inherently cheaper in energy usage than using a fully-closed system, but the problem is (and I've seen it used in datacenters, don't get me wrong) that on hot summer days, there is a minimal amount of energy to dispense or more heat gets added thus letting the actual cooling work harder or fail and on cold winter days, the circulation freezes and it fails too. Yes, I've seen that system used in an actual large (new) datacenter with those exact problems popping up after a few months.

      --
      Custom electronics and digital signage for your business: www.evcircuits.com
    18. Re:Cut power in half? by Aladrin · · Score: 1

      "Couldn't some variant of this technology be used, where the actual PCB's don't get near the liquid, but the heat sinks are immersed in it?"

      I've got this great idea! Let's put the liquid in TUBES and have pumps to circulate the liquid.

      The answer is simple: That's already being done. This is only news because it sounds crazy and someone did it. It sounds crazy on the surface because 'everyone knows' that liquids and electronics don't mix. You've got to have a bit of knowledge about physics to overcome that stigma. It actually -is- crazy because it'd be a royal nightmare to swap out components, and any geek worth his salt swaps components often.

      --
      "If you make people think they're thinking, they'll love you; But if you really make them think, they'll hate you." - DM
    19. Re:Cut power in half? by b0s0z0ku · · Score: 1
      A heat pump (pumping hot air out and pumping cold air in) is not an air-conditioning.

      A heat pump is a generic term for a system that uses compression and expansion of refrigerant to transfer heat. It can either be run as an A/C to cool a space and dump heat to the outside, or as a heater to heat a space by taking heat from a ground loop.

      What you're talking about is a simple ventilation blower, not a heat pump.

      -b.

    20. Re:Cut power in half? by Random+Destruction · · Score: 1

      You describe a fan, not a heat pump. Plus the OP was right. You can use x amount of energy, to move 2x worth of energy. There isn't energy coming out of nowhere.

      For example, a heat pump uses x amount of energy to run. In operation, it moves 2x worth of heat from A to B. If the heat pump is operating in area B, then area B is now recieving 3x as much heat as it would if the heat pump were replaced with a resistive heater.

      Where did this magic 2x worth of energy come from? Area A, which is now colder.

      For this and more, please consult our good friend wikipedia. http://en.wikipedia.org/wiki/Heat_pump#Efficiency

      --
      :x
    21. Re:Cut power in half? by harrkev · · Score: 2, Informative

      You are right. It IS marketing propaganda. If you have 1.3MW of power used by CPU/motherboard/drives, you still have to remove 1.3MW if heat. Period. Using oil just lets you MOVE the heat easier (and quiter, and in less space), but that heat still has to go SOMEWHERE.

      Of course, depending on the location, it might be easy enough to circulate the oil to cooling coils outside, but that still takes energy.

      Given these guys obvious engineering expertise (not), I wonder if they have ever heard of Polyalphaolefin. Google "PAO cooling" for an idea. It is used for liquid cooling of electronics on military aircraft, and it seems very oil-like (at least when it spills). If it is good enough for the F-22, it is probably good enough for a web server.

      --
      "-1 Troll" is the apparently the same as "-1 I disagree with you."
    22. Re:Cut power in half? by billcopc · · Score: 1

      Liquid cooling doesn't decrease the amount of heat dissipated, it's just a better conductor than air. You still have to cool the liquid. In a closed space like a server room, you're still going to have the same amount of heat energy, it's just getting drawn away from the machines faster but you still need to cool that room somehow.

      Liquid cooling still requires a radiator, and that's where the heat goes. It does move it quicker, so your chips can be pushed harder without overheating, as long as you have a bigass radiator with big fans blowing the heat off. The main source of problems with watercooling rigs is usually inadequate cooling (#2 would be pumps). If that water can't lose the heat as fast at the chip puts out, its temperature will rise exponentially and you end up with burst pipes from the boiling water, and of course a fried computer.

      Now back to the article... I would be weary of this company, simply because it's a little crazy and I'm not sure if a UK company could have the capital and staying power to honor warranties on such tricky setups. Time will tell.

      --
      -Billco, Fnarg.com
    23. Re:Cut power in half? by Critical+Facilities · · Score: 1

      When you add it all up you're approaching 50% of the total power consumption.

      This is an "industry standard" that is a little on the high side. Actually, if the datacenter is designed (and maintained) properly, it's actually quite reasonable to run closer to 33% as far as HVAC electrical loads go. I can tell you that at our datacenter, we've been trending these numbers since opening the building, and we've been hitting the 30-35% range consistently. In fact, this ratio has maintained even as equipment (i.e. servers, silos, etc) has been added to the floor. If the capacity is there and distributed properly, the building infrastructure should be able to handle the heat load.

      Cooling oil is no more efficient than cooling air and convection won't be the final word at an industrial scale - they'll need pumps which consume as much energy as fans


      I'm not sure I'd agree with you there either. The cooling oil may well be more efficient as the heat transfer is likely to be better with the increased surface area. While obviously, the same amount of the components' surface is exposed, you do get better heat transfer with a fluid than with air. This is evidenced by the presence of Water Cooled HVAC systems in Datacenters as opposed to DX (direct expansion). There's nothing wrong with DX, but it just plainly doesn't transfer heat as efficiently as water cooled applications go (DX is also limited as to how far the heat can be "moved" whereas chilled water, you're limited only by pump size and piping).

      they'll need pumps which consume as much energy as fans

      The pumps aren't where the major energy consumption comes from in the HVAC systems, it's the compressors. Particularly with the increased usage of Variable Frequency Drives on pumps and proper modulation via Building Automation, the circulation of the cooling fluid (in this case oil) should be negligable. While using the oil as the heat transfer vehicle doesn't inherently make this miraculously cheaper, it would likely build in more efficiency for heat transfer.
    24. Re:Cut power in half? by rcw-home · · Score: 1

      Efficiency on the A/C units is usually around 2:1 and sometimes approaches 3:1

      A/C unit efficiency is expressed as Coefficient of Performance (or COP), or if you feel like converting BTUs to KWh, SEER. The minimum standard in the US for new A/C units is a SEER of 12 - a COP of 3.5:1 - and they wanted to make it 13 (or 3.8:1). That's the legal minimum - not the state of the art.

      Now add inefficiencies in the cooling architecture, power for fans in the servers, inefficiency of semiconductors when running hot, etc.

      This adds another few percent - certainly not 25%.

    25. Re:Cut power in half? by bloobloo · · Score: 1

      You could use a thermosyphon system to take the hot oil up to air cooled coils on the roof if it is cool / windy enough outside, and you wouldn't need to provide any pumping.

    26. Re:Cut power in half? by Nethemas+the+Great · · Score: 1

      I suspect that if the engineers putting together these server farms bothered to think about the problem for just a bit longer a far simpler solution would present itself. Since that obviously won't happen as they're far more interested in visions of greasy female techs who double as bikini models I'll give it a go... How about simply venting the waste heat off of the power hungry components (PSUs, CPUs, etc.) directly out of the building rather than just blowing it around inside and then relying upon highly inefficient A/C to pump it out of the building.

      --Neth

      --
      Two of my imaginary friends reproduced once ... with negative results.
    27. Re:Cut power in half? by phlinn · · Score: 1

      IIRC, higher temperatures increase resistance a little, and lower resistance means less energy converted to heat in the first place, so the base power draw would also be reduced by reducing the operating temperature. I'm a little out of my depth here though, and I have no idea how significant the reduction would actually be.

      --
      "Pulling together is the aim of despotism and tyranny! Free men pull in all sorts of directions" -- Havelock Vetinari
    28. Re:Cut power in half? by Ellis+D.+Tripp · · Score: 1

      [quote]Couldn't some variant of this technology be used, where the actual PCB's don't get near the liquid, but the heat sinks are immersed in it?[/quote]

      Such things already exist. They're called "cold plates" or "liquid-cooled heat sinks". And no, they aren't as efficient at removing heat as directly immersing the components in the coolant would be. But they make maintenance and input/output connections a lot easier to accomplish.

      Everything in engineering involves tradeoffs. If you want the highest cooling efficiency, ease of maintenance takes a hit.

      --
      Remember "News for Nerds, Stuff that Matters"? Help make it a reality again! http://soylentnews.org
    29. Re:Cut power in half? by fuzz6y · · Score: 1

      If it is good enough for the F-22, it is probably good enough for a web server.

      coming next fall, jet fuel powered servers

      --
      If you're going to be elitist, it would help to be elite.
    30. Re:Cut power in half? by DerekLyons · · Score: 1

      Its a disingenuous marketing claim though. Cooling oil is no more efficient than cooling air

      Actually, cooling oil is much more efficient than cooling air - as air carries much less heat.
       
       

      convection won't be the final word at an industrial scale - they'll need pumps which consume as much energy as fans
      Not with proper design of the racks. You'll want some external piping or internal ducting to direct the flow of rising (heated) oil and falling (cooled) oil, but it's a pretty straightforward process. (Hmm... That may be a clue as to why they are using oil rather than Fluorinert - a greater density change with temperature change?) Those huge transformers you see outdoors in an electrical switching yard? The coolant in them circulates entirely by convection. Heck, there are nuclear reactors that circulate their coolant via convection - you don't get much more 'industrial scale' than that.
    31. Re:Cut power in half? by DjMd · · Score: 1

      A lab I worked at in Cleveland, had so much machine generated heat, that they used almost no actual heating, they just pumped the waste heat into the building. Which ment the in the summer, the cooling had to be insane.

      --
      DJMD - The fourth man - Planetary
    32. Re:Cut power in half? by WhiteDragon · · Score: 1

      Do data centers really use as much power cooling the server farms as running them?
      Yes. If you have a computer using, for instance, 300W of power, that is 300W of heat that must be removed from the data center. However, that heat is still present in the case of oil submersion, merely transferred more efficiently from the computer to the environment.
      --
      Did you mount a military-grade, variable-focus MASER on an unlicensed artificial intelligence?
    33. Re:Cut power in half? by auxsvr · · Score: 1

      All the confusion stems from the fact that Spazmania misappropriately used the term "efficiency" when talking about a heat pump, as efficiency is the amount of energy that was consumed by the pump to operate to the amount of heat that was emitted to the environment. It is always, according to the laws of thermodynamics, less than 1 (entropy always increases); a typical value for a fridge is 0.2. He meant the coefficient of performance (COP), which is defined in a different way.

    34. Re:Cut power in half? by Cramer · · Score: 1

      Except transisters (PN junctions) have a negative thermal coefficient... their resistance drops as they heat up.

    35. Re:Cut power in half? by Spazmania · · Score: 1

      Coefficient of Performance, yes that's the phrase I was looking for. SEER is a funky number but COP is nice and straightfoward.

      I was, of course, not referring to legal standards that shiny new A/C units must meet in the lab. I referred to the performance of existing computer room A/C units installed 5 to 10 years ago with the expected drop in effeciency as the parts aged. Real World Conditions, in other words, where at the moment you typically find COPs between 2:1 and 3:1.

      --
      Moderating "-1, Disagree" is simple censorship. Have the guts to post your opinion.
  10. A sensible idea. by 91degrees · · Score: 2, Interesting

    HWSpirit did a proof of concept here. I wonder if these guys were inspired by that.

    But it's a decent idea. Oil has a high thermal capacity and will circulate through convection keeping the temperature down. Repairs and upgrades aren't going to be all that pleasant but some swarfega will get the grease of your hands after changing the motherboard.

    1. Re:A sensible idea. by only_human · · Score: 1

      Here is a Tom's Hardware Guide article that shows how to do it: http://www.tomshardware.com/2006/01/09/strip_out_t he_fans/index.html By the way, perhaps PCW wrote about this Very-PC oil submerged server on on 4 Apr 2007. "First oil submerged server to go on sale" http://www.pcw.co.uk/personal-computer-world/news/ 2187185/first-oil-submerged-server-sale This article also contains a link to a home enthusiast oil submerged PC.

    2. Re:A sensible idea. by jeremywjones · · Score: 1

      This has been done all over the place. From cooking oil to mineral oil. I did my mineral oil project back in 2005 and it still works today. The mineral oil hasn't been changed at all. It's a great idea and I'm suprised that it has taken this long for people to see it as an option. I agree that upgades are a pain but it is possible. I upgraded memory in my machine and I changed it just like I would in a case that didn't have oil in it. It booted up just fine and read the memory. http://multimediapcs.blogspot.com/2005/07/computer -cooled-with-mineral-oil.html:That is my mineral oil computer. http://oilcooled.blogspot.com/2006/10/oil-cooled-c omputer-links.html: That is some oil cooled links.

  11. zero conductivity ?? by skeldoy · · Score: 0

    I would think oil had some conductivity (?) well anyway
    with the prizes on (non-conducting) cooling liquid from 3M
    I guess oil would be a good alternative.. And on the environmental
    side, you could burn it after you've upgraded.. Delayed combustion ;)

  12. Changing the oil by FredDC · · Score: 1

    So, now you're going to have to take your computer to the garage to change the oil?

    --
    09 f9 11 02 9d 74 e3 5b d8 41 56 c5 63
    1. Re:Changing the oil by aadvancedGIR · · Score: 3, Interesting

      I know it was a joke, but I fear that, by replacing air by oil, the weight of a server rack might be a problem if it is not located in the basement.

      Anyhow, even by reducing the power requirements by using efficient passive cooling to evacuate heat from the chips to the room, you still need to evacuate heat from the room.

    2. Re:Changing the oil by kjart · · Score: 1

      I'm not so much worried about changing the oil as much as changing failed components/servers. I'd think that could be a bit annoying, what with the tank of oil and all.

    3. Re:Changing the oil by Sobrique · · Score: 1

      We've already got re-inforced flooring in our datacentres. Lead acid batteries are pretty heavy :)

    4. Re:Changing the oil by afidel · · Score: 1

      So you do what Google does and DON'T replace/repair the failed hardware.

      --
      There are 4 boxes to use in the defense of liberty: soap, ballot, jury, ammo. Use in that order. Starting now.
    5. Re:Changing the oil by magarity · · Score: 1

      Nevermind changing the oil, what about changing the parts? A modern server has a lot of hot swappable innards; PCI cards, RAM, even CPUs and this elevates the term 'hot swappable' to a new level. Anyone who could afford to install such a convoluted oil pumping rig in their server room has machines that can do such things. I imagine the server tech couldn't be convinced to reach in a server of hot oil to put in a new CPU, even if the oil didn't completely clog up the little socket holes (which I'm sure it would). So really, I don't think anyone is going to be seriously thinking to install this after the initial 'hmm, interesting idea' phase.

    6. Re:Changing the oil by hackstraw · · Score: 1

      I know it was a joke, but I fear that, by replacing air by oil, the weight of a server rack might be a problem if it is not located in the basement.

      Housing large numbers of computers comes at a great expense and a juggling act to balance the variables involved.

      The variables are price, performance, power efficiency, cooling, weight, cabling, floor space, and all of these variables change again when the density of the machines change. And wait a few months, and all of the variables change again.

      Messing around with these things in large numbers is almost as much as an art as it is a science. Sometimes, you just have to say this is good enough, and hope that is a true statement.

    7. Re:Changing the oil by Kavli · · Score: 1
      Why would you need to evacuate heat from the room?
      With heat exchangers water/oil you transport the heat to an evaporator located outside, or recover the energy for heating water, or to heat the building in the cold season.

      -- Kavli

    8. Re:Changing the oil by bill_mcgonigle · · Score: 1

      I know it was a joke, but I fear that, by replacing air by oil, the weight of a server rack might be a problem if it is not located in the basement.

      One way or another, they'll eventually be located in the basement. Hopefully it's done intentionally.

      --
      My God, it's Full of Source!
      OUTSIDE_IP=$(dig +short my.ip @outsideip.net)
  13. my friend's high school project by atamyrat · · Score: 1

    He took box made of glass and filled it with oil. Then he put motherboard inside that oil box, removing all fans from the board. I was not interested much about it at that time, AFAIK project was built for some kind of science fair. I don't remember exactly where power supply was, inside or outside. Does power supply without fan will work inside oil filled box?

  14. Only Kinda new.... by ninji · · Score: 1

    I've seen systems that are submerged in a liquid before for supercomputers. Someone in a post above linked to some cray supercomputers that are like that. I wonder what the future of this technology holds... Scuba diving into a server room to update hardware? ;D

  15. Oil Soaked Servers? by pandrijeczko · · Score: 5, Funny

    Do you want me to make the joke about "fried chips" or do you want to do it?

    --
    Gentoo Linux - another day, another USE flag.
    1. Re:Oil Soaked Servers? by inviolet · · Score: 2, Funny

      Do you want me to make the joke about "fried chips" or do you want to do it?

      Give it to us raw -- and wriggling! You keep nasty chips!

      --
      FATMOUSE + YOU = FATMOUSE
    2. Re:Oil Soaked Servers? by Ardipithecus · · Score: 2, Funny

      With the right chip you could make french fires at the same time

    3. Re:Oil Soaked Servers? by Bat+Country · · Score: 1

      french fires


      Remind me never to eat your cooking.
      --
      The land shall stone them with the bread of his son.
    4. Re:Oil Soaked Servers? by Anonymous Coward · · Score: 0

      I wouldn't touch that, but I've joked for years that the British never made computers because they couldn't figure how to get them to leak oil. Looks like they might do it yet...

  16. The wife is going to love that!! by simm1701 · · Score: 1

    I've overheard her discussing the whole home server obsession with her friends, she is fairly tolerant of my hobby and believes it has one major saving grace.

    Its clean!

    Especially compared to say motorbikes as a hobby, oily bike parts in the sink are not a good way to endear yourself aparantly...

    But now servers come in oil? I can see problems starting here!! ;)

    --
    $_="Slashdotter";$syn="OTT";s;..;;;sub _{print shift||$_};s!ash!Perl !;s=$syn=ack=i;tr+LLEd+BLAH+;_"Just Another ";_
    1. Re:The wife is going to love that!! by LaRoach · · Score: 1

      Oddly enough, I had a similar problem! She didn't understand why there were brake rotors in the oven and wheel hubs in the freezer...

  17. Lunchtime! by hack++slash · · Score: 1

    I hope they do a corn oil version, I do like freshly cooked chips & a battered sausage.

    --
    To do something right, you often have to roll up your sleeves and get busy.
    1. Re:Lunchtime! by Opportunist · · Score: 1

      Well, I guess to get your chips fried, you'd have to leave the oil out.

      --
      We used to have a Bill of Rights. Now, with the rights gone, all we have left is the bill.
  18. Misleading by quote-out-of-context by redelm · · Score: 0, Redundant
    Power consumption for cooling might well be reduced by 50%, but this is perhaps 2-5% of the total. How can overall power be reduced? The CPU consumes the same, wet or dry. PSU ditto.

    1. Re:Misleading by quote-out-of-context by Anonymous Coward · · Score: 0

      cooling consumes 50% of the energy of any real server. Just think about it for a second.

    2. Re:Misleading by quote-out-of-context by BKX · · Score: 1

      Except that the cost for A/C at datacenters (especially during the summer but even in winter, unless you have an outside air recirculator, which I imagine most datacenters do) is generally higher that the cost of running the computers. This is seriously no joke.

      I run a cybercafe with twenty machines. During the winter my electricity bill is cut by over 60% even though I have the same level of computer use. It's only because I don't need A/C. I almost never use a heater during the winter either. I actually have to periodically crack the doors during peak hours when it's above 40 degrees F outside or the temperature in the store will slowly rise to uncomfortable. It will quickly rise to unbearable if the A/C is off during the summer. We have an A/C unit that is (according to the heating/cooling guys who installed it) nearly twice as large as what you would expect for a building that size. It still can't keep up when the store is full and the outside temp is above 75.

      Cooling is 2-3% of operating cost my ass.

    3. Re:Misleading by quote-out-of-context by Ihlosi · · Score: 2, Informative
      We have an A/C unit that is (according to the heating/cooling guys who installed it) nearly twice as large as what you would expect for a building that size.

      Looks like they had no clue then. Building size doesn't produce heat, building contents do. People are 300W each, and you can probably assume computers to be ~200-300W each, too.

    4. Re:Misleading by quote-out-of-context by redelm · · Score: 1
      I did not say cooling as 2-5% of operating cost. I said cooling is 2-5% of computer power. That means the fans or pumps only.

      As you point out, total system cooling can be significant when AC is involved. But this will NOT change with oil-cooling. 98% of the heat will still be generated and have to be removed by the same AC units unless someone mounts external radiators.

    5. Re:Misleading by quote-out-of-context by hab136 · · Score: 1

      People are 300W each, and you can probably assume computers to be ~200-300W each, too.

      So for every human in the Matrix, they could run one computer?
    6. Re:Misleading by quote-out-of-context by Ihlosi · · Score: 1
      So for every human in the Matrix, they could run one computer?

      Only if they manage to circumvent the second law of thermodynamics. All computers I know of run on electricity, not heat.

    7. Re:Misleading by quote-out-of-context by BKX · · Score: 1

      It's a touch bit more complex than that, really. After chatting with the relevant people, I found: In my building's area, the local codes only require (and, in fact, recommend) split-phase power for commercial buildings as small is the one we're in. The A/C people only recommend running a certain level of A/C on split-phase as a (recommended) maximum. Above those A/C requirements, they recommend moving up to 3-phase. This is because motors and compressors are significantly more efficient when wired for 3-phase than for split-phase. However, if the building's already wired, you can go up to about twice their recommendations before A/C units simply aren't available for split-phase at all. They gave us the max that split-phase can handle, double the recommended amount for split-phase (which we have because of the building size). They just confused us a bit with the whole split-phase/3-phase/building-size thing. In the end, I think we're both right, in a sense.

    8. Re:Misleading by quote-out-of-context by BKX · · Score: 1

      The whole point of the oil-cooling is to have external radiators, thereby removing the A/C requirements. Otherwise, you're right, why switch? Or at least, that's what I got out of the concept. If we weren't going to have external radiators, then why not just go with flourinert instead of oil. I thought the whole point of oil was that machine oils don't freeze until very low temperatures so that you can pump them outside in the winter. In the summer, good old-fashioned heat exchangers would be used to keep the temps low.

      Although, now that I read TFA, I see that they don't really talk much about that point. So what if you've got the heat in an easily moved fluid like oil if you don't do something with it other than leave the heat in the room.

    9. Re:Misleading by quote-out-of-context by hab136 · · Score: 1

      So for every human in the Matrix, they could run one computer?

      Only if they manage to circumvent the second law of thermodynamics. All computers I know of run on electricity, not heat.

      My comment was just supposed to be funny, not accurate. Guess I failed on both counts!

      Anyways, you're right, heat to electricity conversion devices aren't anywhere near 100% efficient. They could use steam turbines, but I don't know of a way to boil water using only a bunch of 98F heat sources.. so maybe they have to use Peltier-Seebeck devices.

      So.. maybe a whole busload of humans to power a lightweight computer so you can run a web browser to view my unfunny jokes. No wonder the Matrix machines are so ticked off - no good jokes.
  19. On the other hand... by Anonymous Coward · · Score: 0

    because oil transfers heat more efficiently, power usage can be cut by fifty percent.

    On the other hand, oil usage rises 100%.

  20. Depends on the admin by Opportunist · · Score: 5, Funny

    I, for one, would definitly start lobbying for more female tech workers here!

    --
    We used to have a Bill of Rights. Now, with the rights gone, all we have left is the bill.
    1. Re:Depends on the admin by normuser · · Score: 2, Interesting

      imagine a beowulf cluster of these.

      --
      09 F9 11 02 9D 74 E3 5B D8 41 56 C5 63 56 88 C0
      XXX#######
    2. Re:Depends on the admin by suggsjc · · Score: 5, Funny

      Hold on, that actually might be funny. A beowulf cluster of oil covered female tech workers?

      --
      When I have a kid, I want to put him in one of those strollers for twins and then run around the mall looking frantic.
    3. Re:Depends on the admin by gstoddart · · Score: 2, Funny

      Hold on, that actually might be funny. A beowulf cluster of oil covered female tech workers?

      Ummmm .... schwing
      --
      Lost at C:>. Found at C.
    4. Re:Depends on the admin by Anonymous Coward · · Score: 0

      I want them in hot grits.

    5. Re:Depends on the admin by iggymanz · · Score: 1

      yes, and wrestling naked

    6. Re:Depends on the admin by Opportunist · · Score: 1

      Hmm... dunno, I mean, having them lug around those crates, bending over and picking them up, getting all greased up and having to take their shirts off so they won't get greasy, then crouching behind them to plug them in...

      'scuse me, gotta go to the bathroom.

      --
      We used to have a Bill of Rights. Now, with the rights gone, all we have left is the bill.
  21. Follow up by jamesl · · Score: 1

    I'm sure the Slashdot editors will check back with the company (Very-PC) next year to see if they brought any oil-cooled servers to market. And report back with the results.

    Liquid cooling has been around for a long time and has advantages over air cooling. Energy efficiency is not one of them.

  22. Problems: Connectors, HDD,degradation by Flying+pig · · Score: 5, Interesting
    They will have to run the HDDs outside the oil because they do, in fact, need ventilation. Though perhaps you can get totally sealed HDDs from somewhere by now.

    However, the main problem I see is connectors. Existing connectors have been developed to work in air, except for a few exotic types. Watertight connectors are designed to work with wet environment outside and dry electronics inside, not vice versa, but in any case existing technology would require standard connectors to be used entirely submerged in dielectric. Modern connectors have much smaller contact surfaces than they did even ten years ago, and the distance liquid would have to move by capillary action before breaking the contact is quite small. It's hard to see how you could do accelerated life testing for such a system, which means it could be many years before we know whether they are reliable or not.

    I recall when doing research involving electronics in Fluorinert we had to make soldered connections in liquid. Contacts that were frequently made and broken could be pressure contacts, but that is quite different from the situation in a server. And if we had known of a cheap substitute for Fluorinert we would have used it. The majority of oils degrade quite interestingly - you wouldn't expect bacteria to live in them but they can and do if the conditions are right.

    These guys may have a workable solution to all the problems, but I can't help thinking that technology will make the concept obsolete. How does the performance of an old Fluorinert-cooled Cray stack up against a modern server in flops and GBit/s of IO per watt? (Hint: Don't bet on the Cray.)

    --
    Pining for the fjords
    1. Re:Problems: Connectors, HDD,degradation by Anonymous Coward · · Score: 0

      I guess they have solved these problems, hence the release next year. Just because you failed ti doesn't mean everyone will.

    2. Re:Problems: Connectors, HDD,degradation by LWATCDR · · Score: 2, Interesting

      I wonder if these servers would have to be "disposable" Trying to swap out parts is going to be a major problem. Think of the time to drain the server and get it clean enough to swap out a part. Forget about adding RAM. Probably not an issue for places that use many 1Us for a web front end but for a lot of places it seems like a big pain. I hate to bring it up but what about the fire hazard. Most oils I have see will burn if you get it hot enough.
      For everyone that was posting about hard drives I doubt that would be an issue. I would guess that any place that used this would use NAS.

      Why not just use water cooling? Have quick connect connectors on the back of the case and then attach them to a manifold on each rack. Get the cold water right from the chiller and you would be all set. To be extra safe you could use Fluorinert with a liquid to liquid heat exchanger or to save money mineral oil in the cooling loop with a liquid to liquid heat exchanger.
      All of these seem like better ideas then dunking a server in oil.

      --
      See my blog http://ilovecookes.blogspot.com/ for light hearted technical information.
    3. Re:Problems: Connectors, HDD,degradation by YGingras · · Score: 4, Informative

      The design with the Cray 2 was a bit excessive. They just had the heat reach fluorinert's boiling point and there was a vapor collector and a condensor tower. As you'll recall, the temperature of a liquid will not never exceed the boiling point until it all turned to vapor. That's why car are water cooled. If you have insufficient heat transfer from the radiator, the vapor pressure blows the cap and you have a really visual feedback that it's time to stop. You won't damage anything if you stop before you evaporate all your coolant. Fluorinert boiled at 56 C, a convenient temperature that makes it safe to work around the computer. Oil boils at 175 C. If you have a few boiling racks you will not want humans in your server room and you'll probably burn down your air cooled servers. Oil cooled system will not used the clever technique used by Cray: no pump or other circulatory system was needed and working temperature was ultra stable. Fluorinert and oil cooling are completely different things and I don't think you can compare them.

    4. Re:Problems: Connectors, HDD,degradation by nine-times · · Score: 1

      What part of the hard drive requires ventilation? I mean, I know that hard drives need airflow for cooling, but is there really a part of hard drives that requires new air to be circulated to it? I though the actual hard drive was always sealed and air-tight anyway, and only the circuit board was exposed.

    5. Re:Problems: Connectors, HDD,degradation by xs650 · · Score: 1

      "Fluorinert and oil cooling are completely different things and I don't think you can compare them."

      You just did.

      And it was interesting. Thanks

    6. Re:Problems: Connectors, HDD,degradation by compro01 · · Score: 1

      on all the hard drives i've seen, there is a small hole in the casing with a very fine filter on it.

      air is what keeps the read/write head floating above the platter. the spinning of the platter creates a small cusion of air that the head rests on.

      one major problem i would think with a submerged hard drive would be friction, as the oil would be much denser than air.

      --
      upon the advice of my lawyer, i have no sig at this time
    7. Re:Problems: Connectors, HDD,degradation by Anonymous Coward · · Score: 0

      Actually the likelihood they have solved these problems is low. This whole thing is a fucking scam run be people who apparently have no fucking idea what they are doing.

    8. Re:Problems: Connectors, HDD,degradation by YGingras · · Score: 1

      The hole is there for the pressure to be released when hot air expands. You are right, a HD needs air to float the heads. But, if the working temperature is stable, you don't need the tiny hole and the HD can be sealed with air or some inert gas inside.

    9. Re:Problems: Connectors, HDD,degradation by flaming-opus · · Score: 2, Insightful

      To answer your question - the last Submersion cooled cray was the mid-90's era T90, which submersed 32 processor boards and the memory, in a pool of flourinert. It did not, howerver, submerse the rest of the system, in particular the I/O, which would use standard pin connectors. One of the more exotic pieces of technology in the T90 was the robotic claw connectors that clamped down on the edges of compute boards at 400 contacts per inch. The unit costs of these connectors were very high, in part because they had to operate in the dialectric environment.

      I will point out that after the T90, Cray moved away from immersion cooling, because it made the machine too difficult to service. The T3E used cold-plates, a somewhat more sophisticated version of the waterblocks you see today in some entusiast machines today. The X1, the current Cray vector system uses phase-change spray caps that actually spray dialectric onto the surface of the chip, which vaporizes the liquid. Even this has proved not cost-effective, even at the price-point of a cray. Cray's announced future products are all air-cooled. If immersion cooling isn't prudent on a cray, I can't possibly see how it's a good idea for a rack full of standard servers.

      On the performance front: The T90 offered 60Gflops of performance, which is comparable to a modern 8-core xeon, though with 24GB/s of memory bandwidth per processor, which is STILL, twelve years later, considerably better than Core Duo Xeons, which offer just more than 5GB/s of bandwidth per core. The T90 supported at least 4 gigaring I/O channels at 1GB/s of bandwidth, each. Again, you still need to go to a pretty high-end commodity server to beat the I/O performance of the 12 year old cray. However, your point about per-watt performance is absolutely correct. The T90 consumed hundreds of thousands of watts and required 440volt 3-phase power.

    10. Re:Problems: Connectors, HDD,degradation by Muhammar · · Score: 1

      No bacteria will live in silicon oil, and the heat-related degradation and the wick-seepage effect is less severe with silicone oil too - although a good-grade silicone oil is fairly expensive (about the same as a good-grade scotch). Then there is glycol/diglycol (the antifreeze), very cheap and with huge heat capacity. Then there is diphenyl ether. And squalane hydrocarbon mix.

      --
      I doubt that we will ever figure out - and I suspect that even if we did figure out we couldn't do much about it
  23. COOLING power usage? by Gothmolly · · Score: 0

    Obviously CPU power usage will be unaffected, smitty is probably talking about the cooling requirements.

    --
    I want to delete my account but Slashdot doesn't allow it.
  24. The only problem by xfmr_expert · · Score: 2, Interesting

    The only problem is that oil is a good solvent. Of course, computer equipment is obsolete in 3-5yrs, so maybe it's not an issue. However, the article mentions they tried motor oil first, so I wonder how much they actually thought this through. Motor oil, among other things, is much more viscous than traditional dielectric fluids. The fluids used in transformers are more like water in terms of viscosity. Lower viscosity provides better heat transfer. Also, since high dielectric strength is not an issue, I've got to think that there are some less-corrosive alternatives that will do the job without destroying the components. Half-baked at best, I think.

    1. Re:The only problem by Gordonjcp · · Score: 1

      The fluids used in transformers are more like water in terms of viscosity

      I would have thought that a lighter oil like diesel or LHM (suspension oil) would have been better. Maybe even ATF, although that is a bit thicker.

    2. Re:The only problem by b0s0z0ku · · Score: 1
      I would have thought that a lighter oil like diesel or LHM (suspension oil) would have been better. Maybe even ATF, although that is a bit thicker.

      Or pure mineral oil. Impurities/additives generally cause oil to become more conductive, and car oils are not meant to be good insulators.

      The really good insulating oils - containing PCBs - were phased out due to their environmental toxicity in the 50s.

      -b.

    3. Re:The only problem by xfmr_expert · · Score: 1

      There are many qualities that are required for dielectric fluid in transformers. The most important two are ability to remove heat (viscosity) and dielectric strength. The other big factor is cost. A large power transformer might have over 20,000 gals. of oil. Transformer oil must have a dielectric strength of roughly 30-35kV/mm. It also has to have reasonable viscosity at temperatures as low as perhaps -10C (or lower, depending on location). Oils derived from paraffinic crudes tend to get waxy at low temperatures. The other big factor is oxidation stability. At higher temperatures, particularly in the presence of oxygen, the oil breaks down and forms sludge. These "sludges" are mostly polar contaminants, reducing the dielectric strength of the oil and coating the solid insulation with a film of sludge that could result in a creep failure over the surface of the insulation. As for PCBs, they were generally used as a less-flammable alternative to straight mineral oil. Mineral oil will burn for days. It also produces large quantities of acetylene, methane, ethylene and ethane when you pass an arc through it, resulting in a risk of explosion if the tank ruptures. PCBs were a class of less flammable insulating fluid used for indoor applications and some distribution transformers to reduce fire hazard. Other oil filled equipment may have been contaminated if the same processing equipment was used for PCB and non-PCB fluids. All transformers today are tested for PCB content down to the ppb. PCBs were officially phased out in 1978 or 79, I think. Whenever TSCA was passed. That ban made a lot of people rich...

  25. Old technology. by snarkasaurus · · Score: 1

    I'm pretty sure Thomas Edison invented this technology for cooling transformers. Its been around for like a hundred years.

    I'm no electrical engineer, but don't some oils have a better dielectric coefficient than air?

    1. Re:Old technology. by allscan · · Score: 1

      You're not a historian either. Electric transformers were invented by Michael Faraday, of course it took Westinghouse's company to get a decent working version for AC.

    2. Re:Old technology. by b0s0z0ku · · Score: 1
      I'm pretty sure Thomas Edison invented this technology for cooling transformers. Its been around for like a hundred years.

      I also read that some IBM mainframe core memory units were oil-cooled.

      -b.

    3. Re:Old technology. by Anonymous Coward · · Score: 0

      Who is Michael Faraday?

      I thought Ben Franklin invented transformers. He sure as hell invented electricity!

    4. Re:Old technology. by snarkasaurus · · Score: 1

      Not the transformer, oil cooling. Still, I didn't know Faraday invented the transformer. Figures though, he invented most of the basics of electricity.

  26. Finally a computer that can by Anonymous Coward · · Score: 1, Funny

    leak oil. I knew British ingenuity would eventually overcome the basic problem.

    1. Re:Finally a computer that can by sjwaste · · Score: 1

      If British ingenuity is involved, the oil leak will be a minor concern compared to the electrical fires in the chassis.

  27. Fire risk, anyone ? by Ihlosi · · Score: 1

    You better put these things into the reduced-oxygen-atmosphere rooms that were mentioned a couple of weeks ago.

    1. Re:Fire risk, anyone ? by Sobrique · · Score: 1

      Oil is really not all that flammable. It takes rather a lot of effort to get e.g. diesel to _actually_ burn. Heavier oils are even less likely to do so. OK, so once they do, then that's bad (tm) but by that point, you don't really have a computer room to worry about any more.

  28. GOOD IDEA! by cephus440 · · Score: 1

    You won't have to worry about dust!

  29. Pathetic! by Anonymous Coward · · Score: 0

    How the fuck can this be news when all the major mainframe vendors have done stuff like this since the 60s! For all the kid geeks here; you should know your history...

    G.

  30. BOFH has already done this by Anonymous Coward · · Score: 2, Interesting
  31. Sounds Tasty... by Tickenest · · Score: 1

    Mmm...deep fried server...

    --
    This is the NFL, which stands for "Not For Long" if you keep making those bulls*** calls.
  32. oil by normuser · · Score: 4, Funny

    Oily racks you say? You know this just might catch on.

    --
    09 F9 11 02 9D 74 E3 5B D8 41 56 C5 63 56 88 C0
    XXX#######
  33. Bad consequences by UnknowingFool · · Score: 1

    This sounds good until the first oil cooled computer gets slashdotted. Then the fire department has to be called. At least the computer admins will be drenched in foam forcing them to shower more out of schedule. :)

    --
    Well, there's spam egg sausage and spam, that's not got much spam in it.
  34. Just what overweight geeks need by DanielMarkham · · Score: 3, Funny

    It's not enough that we have jobs where we sit down all of the time, now we have a computer that's also a deep-fryer.

    Or, if they use motor oil, will Penzoil and other oil companies start running TV ads? "I couldn't play DOOM 6 until I switch to 10W-40 ultra. Now I kick butt"

    Maybe the computers can start coming with chrome valve covers.

    1. Re:Just what overweight geeks need by Anonymous Coward · · Score: 0

      Maybe the computers can start coming with chrome valve covers. Haven't checked the modding scene lately?
  35. Yes, but will they use Virgin Olive Oil? by Riptide1884 · · Score: 0

    I have seen pictures of a mini ATX system board suspended in veggy oil and run that way for a couple of years, but the connectors on the back of the board were kept out of the oil so he could mobe things around when he needed. I guess the used veggy oil could be burned in diesel engines, but...

    --
    mod me troll...for get me...not coming back
  36. job interview, 2009: by circletimessquare · · Score: 4, Funny

    "Hello, I'm reviewing your application and I don't see any IT exposure in it at all, no education, no experience... what makes you think that you're suited for a job at a server farm?"

    "Well, I was a fry cook at McDonalds for 2 years"

    "You're hired"

    --
    intellectual property law is philosophically incoherent. it is your moral duty to ignore it or sabotage it
  37. Cooking Oil PC by neersign · · Score: 1

    has been done before. I don't know if I'd ever want to deal with one.

    1. Re:Cooking Oil PC by Anonymous Coward · · Score: 0

      Let's not forget The Screensavers, either. They did a submerged-PC with hydrofluoroether way back in 2002.

      It seems to me like using HFE is a much better idea than using machine oil... it's not a solvent, it's as biologically safe as water, and it's not dangerous or difficult to dispose of. Of course, it's probably more expensive, but with a sealed case you probably wouldn't ever have to change it, either. And because it evaporates like water, and it's got a low viscosity like water, parts inside would almost certainly be easier to work with.

  38. OK, Everybody..... by pedalman · · Score: 1
    Mazola party in the server closet!!!!!

    I'll bring the rubber sheet.

    --
    Friends don't let friends line-dance.
  39. And when something goes wrong... by Anonymous Coward · · Score: 0

    And when something goes wrong and you need to change out a part? With an air cooled server I can swap a card out without having to wait 4 hours for the air to cool to a temperature which won't instantly scar me for life....

    1. Re:And when something goes wrong... by Sobrique · · Score: 1

      I'm afraid at the point at which your oil is too hot to be handled, your computer is no longer a computer, and more like a blob of melty stuff.

  40. and one more (minor problem) by vtcodger · · Score: 1
    One other problem that folks have had in the past with running computer components in oil is that the stuff tends to creep through cabling and leak out the distal end of the cable. Messy. That means that networking, keyboards, monitors, hard drives, etc will very likely have to be coupled to the motherboards by some wireless technology. Not a problem in a home, but is there going to be an interference and bandwidth issue with hundreds or thousands of wireless devices in a server farm?

    Probably leakproof cabling can be devised, but I doubt it will be cheap.

    BTW, I don't know much about connectors, and what I do know is surely a decade out of date. But my impression is that "gas tight" connection technologies replaced simple metal to metal contact technologies in most connectors in the late 1980s due to the high price of gold. Gold is pretty much the ideal metal to metal material as it is soft and doesn't oxidize. But it got expensive and was largely phased out. I have no idea if oil can work its way into a typical "gas tight" connection. My guess would be that it can't/won't, but that's just a guess

    --
    You can't see ANYTHING from a car, You've got to get out of the goddamned contraption and walk...Edward Abbey
    1. Re:and one more (minor problem) by oyenstikker · · Score: 2, Insightful

      Simple. Have the outgoing cables come out of the top and connect to a patch bay, so the little oil that capillary action's itself through the cable will gravity itself right back down the outside.

      --
      The masses are the crack whores of religion.
    2. Re:and one more (minor problem) by Ellis+D.+Tripp · · Score: 1

      Or bring all the I/O lines out of the oil tank through hermetically-sealed connectors. Admittedly, most of the connector types commonly used on computer gear aren't available in hermetic variants. But the good old D-subminiature series is, along with a wide range of circular types.

      Hermetic connectors use glass/metal seals around the individual pins, and either an O-ring and screws or solder flange for attachment to the chassis. Common on military/aircraft/industrial gear exposed to extreme environmental conditions.

      --
      Remember "News for Nerds, Stuff that Matters"? Help make it a reality again! http://soylentnews.org
  41. Cooking Oil? by rodney+dill · · Score: 1

    I always thought there were some server administrators better suited to a vocation that required them to say, "You want fries with that?"

    --

    Use your head, can't you, use your head,
    You're on earth, there's no cure for that
    - S. Beckett
  42. In other news... by Anonymous Coward · · Score: 0

    Google puts in a bid to buy McDonalds...

  43. Thank the Maker! by megacia · · Score: 0

    these oil baths will feel so good.

  44. All that is old is new again...? by vmxeo · · Score: 3, Interesting

    Didn't IBM use oil-cooling on one of their mini/mainframe computer systems back in the day? I seem to recall hearing stories of low oil indicators on the machines. Unfortunately my Google searches on the subject are coming up dry...

    1. Re:All that is old is new again...? by Detritus · · Score: 1

      They used chilled water to cool many of their big mainframes before they switched to CMOS.

      --
      Mea navis aericumbens anguillis abundat
    2. Re:All that is old is new again...? by vmxeo · · Score: 1

      Found it. IBM used oil to keep the magentic core memory of certain model computers at a specific temperature. The oil wasn't used for cooling, it was used for heating. The memory needed to be keep at a stable 106 F(41 C) for it to operate. And yes, according to one source, the machines had dipsticks.

      (Note to moderators, re: my parent post... Funny? Funny? *sigh* I just don't get slashdot moderation anymore...)

    3. Re:All that is old is new again...? by Anonymous Coward · · Score: 0

      IBM had at least one model that used oil cooled core memory. The core was model 7302, and the computer was called the 'stretch', but I can't remember the model number of the actual CPU. It did not have a dipstick, but there was an oil pressure and temperature gauge on the control panel.
      The 7302 core storage unit was about the size of 6 19" racks tied together in a 2x3 array, and weighed about as much as a compact car. I believe that it contained 50 gallons or so of PCB laced 'inhibited insulating oil'. Something like 96Kbytes of magnetic core memory were inside.

    4. Re:All that is old is new again...? by Anonymous Coward · · Score: 0

      My roomate used to have to change the oil for his IBM 7094.

  45. Previously Patented Work? by ITMagic · · Score: 2, Funny

    The opportunities are endless....
    ... but the idea has been eloquently covered before with the Beowoulf Vax Cluster. http://www.theregister.co.uk/2002/05/11/bofh_and_t he_vax_cluster/

    1. Re:Previously Patented Work? by mrmeval · · Score: 1

      I was thinking more along the lines of chloroflorocarbons but perfluoroethane might work.

      --
      I'd go on a Vegan diet but the delivery time from Vega is too long. --brownkitty
  46. 19 inches and all greased up. by Anonymous Coward · · Score: 0

    I better edit my spam filter, some of those messages might actually relate to a technical subject.

  47. Don't underestimate cooling by MadMidnightBomber · · Score: 1

    Can't find the source, but it goes something like "Wannabes worry about clock-speed. Real computer companies worry about cooling."

    We used to have about 90% load on a 100KVA transformer. The run-time on the UPS was only about 20 minutes, but that wouldn't matter because within 30 minutes the servers would all have burnt out anyway. (Fortunately, that site has since upgraded to diesel generator which also supplies the aircon.)

    --
    "It doesn't cost enough, and it makes too much sense."
    1. Re:Don't underestimate cooling by Sobrique · · Score: 1
      I had a lovely 'server room temperature graph' on for the day when all 4 of our redundant air-conditioning controllers all decided to reset. (Power glitch, they weren't on the 'clean' supply, that got fixed).

      Took about 45 minutes for the server room to climb from 19 degrees operating temperature, to 55 degrees. Our more sensible bits of hardware turned themselves off, and over the next ... ooh 8 months, we had a much higher 'failure rate' on our hardware :/ (disks mostly)

    2. Re:Don't underestimate cooling by teh_chrizzle · · Score: 1

      Took about 45 minutes for the server room to climb from 19 degrees operating temperature, to 55 degrees.

      failed AC. worst. catastraphe. ever.

      i inherited the IT operations for a small tissue bank and the server room (8 servers total, definitely less than 20 CPU's) was cooled by a single AC wall unit like you would see in the window of a house. the AC was on a UPS, but the thermostat went out on the AC over the christmas holiday. the AC continued to run full blast until it froze solid and the vent stopped blowing. the result was a server room over 100 degrees fahrenheit when i walked in, and an AC unit that was a block of ice with no ventillation. i got a few panicked pages from the servers before they shat themselves and turned off. thankfully there was no long term damage (that i was present for).

      --
      sarcasm:
      -noun
      1. harsh or bitter derision or irony.
  48. Entire rack? by LoudMusic · · Score: 1

    Why does it have to be the entire rack? Wouldn't it be easier to just use oil in a liquid radiator system and deliver the fluid to the hot spots? Sure would make it simpler to get to the computers when something fails.

    --
    No sig for you. YOU GET NO SIG!
  49. Oil bath by coren2000 · · Score: 1

    Thank the maker! This oil bath is going to feel so good. I've got such a bad case of dust contamination, I can barely move!

  50. I'm a server admin, and I bet you'd like to see ME by Anonymous Coward · · Score: 2, Informative

    ...covered in oil. Some server admins are cute 25 year old women who work out every day!

    The captcha word for me this time is "fondling". How strangely appropriate.

  51. Can someone please explain to me... by Zeek40 · · Score: 1

    How this will reduce power usage? The same amount of heat is going to be generated by the computer equipment, it's going to get transferred out by the oil much better than traditional air cooling, but then the oil will still be transferring the heat to the server room. It's not like the oil is making energy disappear, it's just holding on to more of it and moving it away from the computer faster. The heat will still eventually be moved to the air in the server room, which will still need to be cooled to avoid overheating.

    1. Re:Can someone please explain to me... by Sobrique · · Score: 1

      Net amount of heat output remains the same, however 'wastage' from air conditioning and airflow inefficiency would be greatly reduced. If your external climate permits, then you could probably just use an external passive radiator for your oil circulation, although you'll probably look to specifically refrigerate the system.

    2. Re:Can someone please explain to me... by Single+GNU+Theory · · Score: 1

      You don't keep the hot oil in the server room: you pipe it to a heat exchanger somewhere, probably outside to a radiator. You'll still need a fan to draw air through the radiator, but it's one big fan that makes more airflow than noise and not a thousand tiny fans making more noise than airflow.

      If want to save more on the electricity bill, use the heated oil to pre-heat the line that goes into the water heater and (in the winter at least) the air going into the HVAC system for the building's occupied spaces.

      --
      Little Debian: America's #1 Snack Distro!
  52. Pass the brain bleach! by Svartalf · · Score: 1

    AAAAAAAAAAAAARRRGH!

    You just HAD to paint that picture, didn't you?

    --
    I am not merely a "consumer" or a "taxpayer". I am a Citizen of the State of Texas
  53. Yeah, yeah... April Fool to you too... by pandrijeczko · · Score: 2, Funny
    Let me guess...

    The oil soaked server runs "Mazola" Firefox with the "Grease" Monkey plugin on "Sunflower" Solaris.

    --
    Gentoo Linux - another day, another USE flag.
  54. Re:I'm a server admin, and I bet you'd like to se by Sobrique · · Score: 1

    But the other 99.99995% aren't. Those aren't good odds.

  55. hot swapping issues? by quick_dry_3 · · Score: 1

    no, not wondering if a hot swap involves one of those deep fryer baskets.

    But with comments about doing hardware swaps and waiting for oil drainage, can't these problems be solved with keeping some components in boxes/trays, and cirulating the oil in and out of each compartment via something similar to the dry break connectors used in some motorsport hoses.

    That way you just yank it out and the only bit of oil to worry about is the amount immediately around the swapped part - which you could leave to drain, rather than having the admin looking like he's just been oil wrestling.

    Or is this just a carrot to get IT depts to step up efforts to lure more women into IT?

  56. In a word, no. by Anonymous Coward · · Score: 0

    You have the right idea, but it doesn't work quite that way.

    To run a chiller plant / cooling tower capable of dumping heat at a rate of 10 kW does not itself require a power input of 10 kW.

    1. Re:In a word, no. by compro01 · · Score: 1

      IIRC, it would require about 3kW (i think modern ACs have about 3:1 power:cooling ratio), which isn't 10kW, but is still quite considerable.

      --
      upon the advice of my lawyer, i have no sig at this time
  57. Sunshine by gblackwo · · Score: 1

    They had nice shiny mainframe racks submerged in fancy coolant in the new sunshine movie. Just make sure IT doesn't make it too easy for a villain to walk by and raise the racks out- which ironically then frys them.

  58. Irn Bru with that by Dogtanian · · Score: 1

    It's not enough that we have jobs where we sit down all of the time, now we have a computer that's also a deep-fryer. If they sell one of these computers in Scotland, I guarantee you some ned will try to eat the deep-fried motherboard; it's not like there's anything we *won't* deep fry here...
    --
    "Slashdot - News and Chat Sites Deviant". (Click "homepage" link above for details).
  59. Other ideas.. by Anonymous Coward · · Score: 0

    Can we make the moon a giant server farm?

    Or just put them in orbit?

    Ok, how about Antarctica?

  60. Dielectric Fluids "better"? I think not. by Svartalf · · Score: 4, Interesting

    Fluorinert's ozone depleting.
    Novec's a greenhouse gas problem.

    Every other fluid in this class has the same set of issues, unfortunately.

    They may be "clean" and non-toxic, but they're decidedly NOT environment friendly compared to oils-
    and they're a hell of a lot more expensive than oils and not as effective at cooling things.

    The reason why the fluids are used in the supercomputer industry is more the mess caused by the oils
    on everything- and they're actively cooling the systems. Oils are actually superior to the fluids
    in heat-transfer terms- it's why you have oil filled transformers for power distribution instead of
    dielectric fluid filled ones. The specific heat of Novec is actually less than air's- the only advantages
    these fluids have is that you can effectively move a LOT more of it quickly over a surfaces being cooled
    without noise and you can refrigerate the stuff to below ambient to temperatures close to the freezing
    point of water without condensation risks.

    Oils tend to have issues with active cooling. Unless you're implementing vapor-phase, stirling cycle,
    or aggressive peltier active cooling below ambient, you are actually better off with oils than the fluids
    as they won't work as well at cooling- you'll be better off with air cooling.

    This has been discovered by the overclock crowd and they have done a handful of oil-immersed PC's.
    The main reason why you don't see a lot more of those oil immersed PC's is oil wicking
    by the wires. Each point where a connector would be or a peripheral like a CD/DVD or hard disk is
    hooked in has wires coming out of the system that will wick the oil or dielectric fluid out all over
    the place. In order to deal with this specific problem, you'd have to resort to specialized sealed
    header and other connectors for each edge case for SATA/PATA, VGA/DVI, etc. Those don't come cheap,
    so the overclocker crowd tends to just resort to fishtank and similar plays for lan parties or
    PAX/QuakeCon, etc.

    So, in the end, it is a mixed bag. The oils are messier, but are actually more environmentally friendly
    than the dielectric fluids- and they have a higher heat capacity and thermal conductivity in many cases.

    --
    I am not merely a "consumer" or a "taxpayer". I am a Citizen of the State of Texas
  61. SEER = BTU / W.h by redelm · · Score: 2, Informative
    While I generally agree with the parent, AC is more efficient than 2:1 or 3:1 . An older SEER 10 AC unit is then 2.94 W [heat] removed per 1 W [electric]. The newer SEER 13 units are 3.8 W/W .

  62. Greeeeeeat... by Atilla · · Score: 1

    Just what we need - something else British that leaks oil. Like the MG's weren't enough. ;-)

    --
    --- sig moved for great justice.
  63. Not just for mechanics any more by Eudial · · Score: 1

    All black in your face with oil, it's not just for mechanics anymore!

    Coming soon to a computer geek near you.

    --
    GAAH! MY PRINTER IS ON FIRE!!! PUT IT OUT! PUT IT OUT!
  64. ... with water by Craig+Ringer · · Score: 1

    slosh

    fizz!

    Aah... not only have we saved ALL of our VAX power bill, but we've eliminated all noise in the process.

    Now to persuade the Boss to dive in to look for the drain plug...

  65. And since we're posting on /. by Svartalf · · Score: 2, Funny

    You'd not be any more likely to get laid in that situation than the normal one.
    (I will admit, though, that the scenery would probably be more appealing then... >:-) )

    --
    I am not merely a "consumer" or a "taxpayer". I am a Citizen of the State of Texas
    1. Re:And since we're posting on /. by suggsjc · · Score: 1

      (I will admit, though, that the scenery would probably be more appealing then... >:-) )
      Have you actually seen most of the women in the tech industry???

      There is probably a reason that most of the IT types lock themselves in their basements.


      P.S. If you are an IT hottie, then I give you my most sincere apologies.
      --
      When I have a kid, I want to put him in one of those strollers for twins and then run around the mall looking frantic.
    2. Re:And since we're posting on /. by Fordiman · · Score: 0

      I don't know about the industry as a whole, but the female IT workers here almost always seem to be adorable little asian girls.

      --
      110100 1101000 1101000 1100110 0 1101111 1101000 1100011 1
    3. Re:And since we're posting on /. by Anonymous Coward · · Score: 0

      And the problem with that is....?

    4. Re:And since we're posting on /. by drinkypoo · · Score: 3, Funny

      I don't know about the industry as a whole, but the female IT workers here almost always seem to be adorable little asian girls.

      I think all of slashdot wants to know... are you hiring?

      --
      "You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
    5. Re:And since we're posting on /. by MrCreosote · · Score: 1
      --
      MrCreosote Meow!Thump!Meow!Thump!Meow!Thump! "You're right! There isn't enough room to swing a cat in here!"
    6. Re:And since we're posting on /. by Eivind · · Score: 1
      Nonsense. Females in IT are on the average as attractive as females in pretty much any other industry, barring the few where there is a strong selection for looks. (music, showbiz, acting, modeling etc)

      If you care about brains too, they're more attractive than average. And I ain't talking just knowing nerd-stuff, contrary to cliche, knowledgeable people tend to know lots of interesting stuff across the board, not just on a single narrow topic. Goes for the males too.

      The other clichees fail to match reality too. It-workers are no more likely to be single than say lawyers, doctors or car-mecanics. Among the ~20 programmers/sysadmins at my workplace, 80% or so are in a stable relationship or marriage. This is completely in line with the salesforce, managment, designers and others.

    7. Re:And since we're posting on /. by Opportunist · · Score: 1

      I've always been wondering why there aren't any porn movies for geeks. I mean, wouldn't it be a lot more ... entertaining, or at least something new, if you saw an admin laying some cable instead of seeing the ever ol' plumber lay a pipe? With a few hot servers in the background, flashing in sync with the 'rhythm', and on the server room floor they start to...

      I mean, let's be honest here, the market for geek porn should be quite large. Considering the chance of the average geek to score. But then again, he'd prolly .torrent it rather than buying it, so... :(

      --
      We used to have a Bill of Rights. Now, with the rights gone, all we have left is the bill.
  66. obligitory by barefoothannibal · · Score: 3, Informative
  67. Why cooking oil? by Winterblink · · Score: 1

    Can someone explain why cooking oil was preferred over mineral oil? I remember an older attempt at oil-submerged PCs where mineral oil was used because the cleanup was easier than other oils. Is it that cooking oil is a cheaper alternative or something? Just curious.

    --
    "I'm a leaf on the wind. Watch how I soar."
    -Hoban Washburn
  68. An extreme case will explode by cheros · · Score: 1
    See YouTube:


    First you get the heat, then you get the breaking of the box seal so the oil vapourises - and at that point it can ignite. Enjoy :-)

    --
    Insert .sig here. Send no money now. Owner may sue, contents will settle. Batteries not included.
  69. Fluorinert by Anonymous Coward · · Score: 0

    Fluorinert not impressed. http://en.wikipedia.org/wiki/Fluorinert

  70. marketing strategy by pedramnavid · · Score: 0

    let's call it the i-rack

  71. But can they run headless? by Anonymous Coward · · Score: 0

    Yeah, I know, that's cold.

    Getoverit! :-)

  72. I wonder if it will be a mess by Secrity · · Score: 1

    When I was in the Air Force I worked on radio transmitters that were cooled with silicone oil -- what a mess. Silicone oil as a coolant is NASTY, it leaks and doesn't clean up very easily with detergent. The solvents that we used to clean up silicone oil have been banned (first trichloroethane and then Freon 11).

  73. Dr. Ffreeze did this almost a decade ago... by thenols · · Score: 2, Interesting

    I remember a guy called Dr. Ffreeze who submerged a motherboard in oil to push the limits of overclocking even further. So this isn't a new idea. His website describing his project is http://drffreeze.net/. The site doesn't look like it's been updated in a while, but it still contains info about what he did.

    1. Re:Dr. Ffreeze did this almost a decade ago... by Anonymous Coward · · Score: 0

      Yes I did. =)

      Sorry, no overclocking updates. Family is where it is at for me now.
      Dr. Ffreeze

      www.drffreeze.net

  74. Welcome to MacServers by subl33t · · Score: 1

    Would you like fries with your chips?

  75. any other old-timers think of the model33 TT? by TheGratefulNet · · Score: 1

    that was a teletype machine. completely mechanical.

    the usual fix or PM for it is to dunk the whole machine in oil to clean it.

    I'm serious.

    but no, you didn't RUN it in oil. you just 'fixed' it with oil.

    model 33 ref

    --

    --
    "It is now safe to switch off your computer."
  76. Threepio's thought's by SailingDeity · · Score: 1

    Ooh, this oil bath is going to feel sooo good!

  77. high voltage power transformers use Oil by Joe+The+Dragon · · Score: 1

    The ones at substations use Oil and some times they go up in flames.
    just Google substation fire

  78. One deep fried please? by Lukasz+(Qr) · · Score: 1

    This gives another meaning to "my computer just fried".

    On the other hand they should open a French(aise) Fries with MC Donalds, just add potatoes.

  79. What!? No they don't. by Anonymous Coward · · Score: 0

    "They will have to run the HDDs outside the oil because they do, in fact, need ventilation."

    What?? No they don't.

    When the harddrive is submerged in oil, the oil cools the hdd with the natural thermal convection or with the help of a pump to circulate the oil.

    Just like any other electrical component.

    "However, the main problem I see is connectors. Existing connectors have been developed to work in air, except for a few exotic types. Watertight connectors are designed to work with wet environment outside and dry electronics inside, not vice versa, but in any case existing technology would require standard connectors to be used entirely submerged in dielectric. Modern connectors have much smaller contact surfaces than they did even ten years ago, and the distance liquid would have to move by capillary action before breaking the contact is quite small."

    Que?
    Flourinert is a dielectric, so is the oil they're using (it's not as good as flourinert I'm sure). If the connectors are connected before submerging, and probably even after, the connection will still be enough to work.
    Flourinert isn't really a very deep penetrating substance, so getting between two connecting surfaces (insulate) is quite small. And veggy oils are even worse ;)

    1. Re:What!? No they don't. by Anonymous Coward · · Score: 0

      Some (older, probably) hard drives aren't sealed, they exchange air through a tiny hole+air filter. Presumably to equalize air pressure.

  80. Oil Change by wwillia99 · · Score: 1

    So do you have to take these servers in for oil changes every 3000 miles.

  81. The smell of slashdotted server... by Ruvim · · Score: 1

    The smell of slashdotted server will never be the same!

  82. What happened to alcohol? by Grinin · · Score: 1

    I thought companies were making giant improvements with some sort of alcohol/water mixture and running that over the processors themselves. This coiled oil soaking around the entire server seems a bit ridiculous. As previously stated, what happens when someone has to work on them? You need to pull them out and wipe them clean, and get going. This also must open the door to at least some potential for disaster if one of the cases isn't properly sealed and the whole thing floods with oil... no?

  83. Oil soaked? by iminplaya · · Score: 1

    What did they do? Dump the machines into Prince William Sound?

    --
    What?
  84. British company, computers, oil! by whoever57 · · Score: 2, Funny

    It just had to be a British company! (If you don't understand, search this page for the word "British".)

    --
    The real "Libtards" are the Libertarians!
    1. Re:British company, computers, oil! by alienmole · · Score: 1

      Since you left it on the table, I'll do the hono[u]rs:

      At last, the British have found a way to make computers leak oil!

    2. Re:British company, computers, oil! by Gilmoure · · Score: 1

      I thought the joke (I first heard on brit bikes site) was;

      Q: Why don't the British make computers?

      A: They haven't figured out how to make them leak oil.

      That out of the way, I wonder how long it'll be before they require Whitworth sockets to work on these things?

      --
      I drank what? -- Socrates
    3. Re:British company, computers, oil! by alienmole · · Score: 1

      That was the original joke, the point is that it's now outdated. The British are now free to make computers because they've figured out how to make them leak oil. Watch out, Dell, the redcoats are coming for you!

    4. Re:British company, computers, oil! by modecx · · Score: 1

      At last, the British have found a way to make computers leak oil!

      However, as a new feature, British computer makers will design data centers to be suspended over blacktop, so that traffic passing by underneath will continuously re-pave the road surface.

      --
      Constitutional rights may be respected, repealed, or modified; but they must never be ignored.
  85. Re:I'm a server admin, and I bet you'd like to see by FunkyELF · · Score: 2, Insightful

    Sure...I bet most people hiding behind Slashdot anonymity are cute 25 year old women.

    I of course believe anything on the internet and bring it up later in conversation...

    Somebody : All computer geeks are ugly males.
    Me : Not true, there are some hot 25 year old server admins all over the place. I saw one post anonymously without posting a picture the other day.

    Seriously, either post a picture of a hot girl wearing a real nerdy admin t-shirt doing some admin stuff or shut the hell up. I'll spare the whole "living in the parent's basement" rant here....

  86. What's the weight of a rack? by CrimsonScythe · · Score: 1

    I guess it's got to be extremely heavy if they actually plan on filling the whole rack with oil. Either you'd have to build the floors very, very sturdy or stick with a single-story data center.

    --
    The view was horrible and the smell was even worse; Julie severely regretted becoming a proctologist.
  87. MEK by Kadin2048 · · Score: 1

    The only problem i can see is that once you bath your pc components in oil you cannot reuse them elsewhere because the contacts get all dirty.

    Well, yeah, but that's what methyl ethyl ketone is for!

    Slightly offtopic: I had always assumed that MEK was increasingly hard to get because they had discovered it caused cancer or something, but Wikipedia indicates that it's actually a drug precursor? Bizarre. Anyway, you used to be able to get the stuff in most hardware stores, and it's just about the best degreaser that you'll ever use. You can put a greasy part in MEK, swish it around a little, and pull it out ... just dry it off, and it's clean. Really great for taking cutting oil off of parts after machining.

    Not sure when exactly it happened, but all of a sudden it became really hard to just go out and buy anymore. Seems to me it was about 10 years ago. But if Wikipedia is to be believed, it still gets used as a solvent in a lot of paints and stuff.

    --
    "Ladies and gentlemen, my killbot features Lotus Notes and a machine gun. It is the finest available."
    1. Re:MEK by leuk_he · · Score: 1

      and mek does not make a big hole in your components? Make a solution out of them?

    2. Re:MEK by Kadin2048 · · Score: 1

      Details, details ... ;)

      --
      "Ladies and gentlemen, my killbot features Lotus Notes and a machine gun. It is the finest available."
  88. Ah, the irony by CompMD · · Score: 1

    the fortune up right now is "I am covered with pure vegetable oil and I am writing a best seller!"

  89. multi tasking by wwillia99 · · Score: 1

    The waste heat form oil cooled servers will be used to cook sweet delicious French fries and funnel cakes. Yes friends the server room now has a drive up window. Thanks for choosing Server King.

  90. Chilled water probably easier by Kadin2048 · · Score: 1

    That's one way of doing it. However, I suspect that the cheapest way is probably to just keep the oil constrained to the racks, and use chilled water throughout the building. There's a lot of existing experience and infrastructure related to chilled water.

    Depending on the temperature you need to get it down to, it might be acceptable to just use passive cooling (cooling/evaporative towers, radiators) and not actual refrigerative (state-change, with compressors and the rest) systems. Certainly if you built your datacenter in a northern climate, you'd probably be fine most of the year by just pumping the water/coolant through some radiators on the roof and back down.

    And you could do the same thermosiphoning stuff with water as you can with oil, but with a lot less oil. Sure, you have an extra heat-exchange step, but you don't have to worry about using oil-proof fittings throughout the building -- regular plumbing would suffice.

    --
    "Ladies and gentlemen, my killbot features Lotus Notes and a machine gun. It is the finest available."
  91. Hot swapping by Anonymous Coward · · Score: 0

    Now hot-swapping components will involve breathing gear.

  92. Still going to need air conditioning by Locklin · · Score: 1

    The servers will still be producing most of the heat, this would *hypothetically* just increase the rate of heat transfer to the outside of the machine.

    Without removing the heat from the room, you're still going to end up with environmental heat buildup.

    --
    "Knowledge is the only instrument of production that is not subject to diminishing returns" -Journal of Political Econom
    1. Re:Still going to need air conditioning by Anonymous Coward · · Score: 0

      Pump it through a radiator outside, and/or your central heating system in colder weather.

    2. Re:Still going to need air conditioning by Spazmania · · Score: 1

      I'm not sure you appreciate just how much heat you're talking about. Its not unheard of in modern data centers to pack 10kva of equipment into a 3 foot by 2 foot cabinet. That's about the same amount of heat that keeps your 1000 square foot house toasty warm when there's snow on the ground. And that data center has hundreds of 2 foot by 3 foot cabinets each putting off the same amount of heat.

      --
      Moderating "-1, Disagree" is simple censorship. Have the guts to post your opinion.
  93. Re:I'm a server admin, and I bet you'd like to see by Carlos+Laviola · · Score: 1

    apparently some of them are also desperate attention whores

  94. No, you obviously did not learn by WindBourne · · Score: 1

    It was not just conversation. It was the fact that you could do offsets. Apparently, he spends a fair amount of money on doing trees and other offsets so that he is carbon neutral. IOW, he is not adding CO2 to the planet while you ARE.

    --
    I prefer the "u" in honour as it seems to be missing these days.
    1. Re:No, you obviously did not learn by PitaBred · · Score: 1

      So... if I recycle, I can afford to throw more shit into the neighborhood stream? You realize that argument is bullshit, right? Just because he pays more doesn't mean he is doing a better job. He's still using more energy per square foot of space than most American homes, with absolutely no reason to do so other than "I've got the money!"

    2. Re:No, you obviously did not learn by MightyYar · · Score: 2

      Yell at me if you like, but I live in a small apartment, use compact florescent bulbs where practical, and don't have a car. And yet I still use more resources than a starving peasant, so I guess we all "could do better". You can buy into this "offsets" garbage if you like, but it is just as much B.S. as the conservatives disregarding everything the man has to say just because he happens to be a hypocrite. He may not be adding CO2, but he is certainly using up resources at a prodigious rate. He plays up this offsets crap because he's financially vested in it.

      All of that said, I didn't criticize his energy use, but his INCREASE year-over-year. Even if it was because of the weather or some other reason, the man should have moved out of his mansion and shut it down for 3 months or so just to avoid giving opponents such an easy way to make him look like a hypocrite.

      If it will make you lay off of me, I'll stop cleaning my bathtub and let the mold grow - that should offset some carbon :)

      --
      W..w..W - Willy Waterloo washes Warren Wiggins who is washing Waldo Woo.
    3. Re:No, you obviously did not learn by triffid_98 · · Score: 1
      Yes it's indeed astonishing that operating a ~10,000 square foot mansion in the middle of Georgia uses quite a bit of electricity. Someone should write him a memo or something (on recycled paper of course). Equally ironic is his championing of hybrid-electrics, which are far more damaging to the environment than other alternatives, chief among those would be not buying a goddamn new car every 4 years.

      So... if I recycle, I can afford to throw more shit into the neighborhood stream? You realize that argument is bullshit, right? Just because he pays more doesn't mean he is doing a better job. He's still using more energy per square foot of space than most American homes, with absolutely no reason to do so other than "I've got the money!"
    4. Re:No, you obviously did not learn by mink · · Score: 1

      My prius is almost 5 years old now and shows no sign of me needing to buy a brand new one.
      The pdf in your link part of that debunked study that showed the H2 was supposedly a better cost vehicle? Read the last /. article where people who actually live near that mine explain the info in that BS study (paid for reaserch) is about 20 years out of date at least and it's numbers for a lot of things are wrong.

      --
      Well I've wrestled with reality for thirty five years doctor, and I'm happy to say I finally won out over it.
    5. Re:No, you obviously did not learn by triffid_98 · · Score: 1

      Regardless of whether you agree with the article, the basic point is sound enough. There is more to emissions than what comes out of the tailpipe, the processes involved in building cars involves a fair amount of pollution and hybrids are worse than most. How does that = environmentally conscious?

    6. Re:No, you obviously did not learn by mink · · Score: 1

      My reason for buying a Prius was geek/tech and not "SAVE TEH PLANETES!!!1". I needed a car, and liked the technology I saw. If you do not believe me check out previous posts in my history.

      I never claimed it was environmentally conscious to make any vehicle (or are you saying the H2/H3 is an environmentally sound product).

      The one thing most anti-hybrid people harp on is the batteries, but Toyota recycles them (I believe they shoot for all recyclable materials in the build) as well as makes sure to get them back due to the bounty.

      The whole Hummer good, Prius bad thing is nothing but paid for advert research crap.

      Like the whole issue of the mining town referenced. Old information that is night and day different from what is the truth since the start of the existence of the Prius (in fact the town and plant were turned around many years before Toyota was their customer). Facts and figures being bad math work or total fiction. All that part of the "study" was in there for was to make an emotional appeal to people.

      This is the same study that shows that the Prius costs $300K to drive and needs the batteries replaced every 2 years. From that study, and my Prius just now (last night) hitting 100K miles I should be out massive amounts of cash. I'm not.

      I'm all for hearing how I have destroyed the earth and caused the end of the world in 2012, but get some facts and figures that are not written by a paid marketing group for "blowjobs" and actually accurate please.

      For example "Most of the gas is consumed as the car goes from 0 to 30" that's true for any vehicle depending on how you choose to drive.

      Do you have any proof other them a made up BS article that the Hybrids are all worse on the environment in production then a Hummer H2/H3? Did you study the manufacturing process in both cases? If one company works to mitigate pollution issues during production, but another creates less pollution pipes it into the environment, the first company is doing something to prevent contaminating the environment. Now that was a made up hypothetical example and I make no claims that is what happens, but there is a lot more to pollution and environmental impact then blindly taking a paid marketers words in support of the product they are paid to push. This applies to Toyota as well as GM and every other manufacturer of any product (even farms).

      I expect people on /. to be able to filter out BS a lot better then you have. Don't post total BS and then be surprised when people call you on it.

      --
      Well I've wrestled with reality for thirty five years doctor, and I'm happy to say I finally won out over it.
  95. This has been by JustNiz · · Score: 1

    done by the more radical fringe of the PC overclocking world for a couple of years now.
    Just google for it, there's plenty of references.

    One thing I don't understand though... why doesn't the oil get between any of the push-fit connectors like power connectors and PCI slots etc and cause bad connections? I thought oil was both an insulator and very prone to spreading through osmosis, like spraying WD40 on a jammed nut or something, it works its way in to the thread.

  96. Wrongo! by Anonymous Coward · · Score: 0

    Check your MSDS. Both products have an ozone depeletion potential of zero - there's no chlorine in them. Fluorinert's 100-year global warming potential is very high - over 5000. Novec, on the other hand (assuming you mean HFE-7100), has a 100-year GWP of 320, which is about the same level as nitrous oxide. It's not the best, but then again it's also in the company's best interest to make sure none of it gets into the atmosphere - it's expensive as hell, so letting it evaporate is like watching money blow away. With this taken into account, I'd probably say that Novec 7100 is the "greener" choice.

  97. Re:Dielectric Fluids "better"? I think not. by operagost · · Score: 2, Informative

    Fluorinert does not deplete ozone! See 3m's website or Wikipedia.

    --

    Gamingmuseum.com: Give your 3D accelerator a rest.
  98. Re:Dielectric Fluids "better"? I think not. by Anonymous Coward · · Score: 0

    This guy doesn't know WTF he's talking about, refined oils CAN be used as a dielectic, there a MANY organic oil based dielectric fluids.

  99. Not new -- just a new application by Vitriol+Angst · · Score: 1

    I'd heard of this oil being used in SuperComputers many years ago.
    They have to use a special "non conductive" oil -- I believe it doesn't damage electronics and plastics.
    So other than a few fans and viscosity issues -- it should be pretty easy to implement. Should be better than "water" cooling, because you can have oil over most everything.

    It's just they are taking a supercomputer trick and moving it to a server/blade farm. I don't know about the cost of this oil -- but I would suspect they would quickly save the money in electriciy costs -- and air conditioning bills, because you could pump the oil outside the building and do your heat exchange there.

    I was suprised they didn't use this instead of the water cooling when it first emerged -- because there is less of an issue if you spring a leak (should also be easier to keep oil from leaking than water).

    --
    >>"ad space available -- low rates!!!"
    1. Re:Not new -- just a new application by Creepy+Crawler · · Score: 1

      It's just transformer oil.

      Nothing fancy, really. You just have to make sure that board contaminants dont ionize. Ions = electrical circuits. Thats bad.

      --
  100. Bad science by PPH · · Score: 2, Interesting
    From TFA

    "It is possible to cut power consumption in half," managing director Peter Hopton told New Scientist. "You don't need to drive inefficient fans, or the usual air conditioning."


    Half the power is consumed by cooling? Not likely. Given the current air conditioning technology, the coefficient of performance (Joules of heat moved by 1 Joule of air conditioning energy) is about 2.5 to 1. Assuming their system requires zero energy (It doesn't. They propose using a refrigeration unit to create convection currents) the best savings they could hope for is 28%. In reality, the heat needing to be moved will not go down. The energy savings will be produced by moving the same quantity of heat with a smaller volume of working fluid (oil instead of air). Some savings will also be realized by not having to condition the entire data center building to suit the equipment requirements.

    --
    Have gnu, will travel.
    1. Re:Bad science by chmod+a+x+mojo · · Score: 1

      You forget that by using a liquid based coolant ( the oil ) versus a gas based coolant ( Air OR water cooled with heat dissapated to the air) they could Easily use geothermal cooling E.G. pump the oil slowly though the rack vats and into a geothermal sink ( all it is is a pipe dropped 50+ feet into the ground) and letting the excess heat dissapate into the soil. Also the refrigeration of say 100 gallons of oil will be much cheaper than the equivilant of air because of the density. It is much easier to remove heat from a smaller surface than a really large one ( and they would be roughly the same temperatures) you can cool 100 gallons of oil from say 150F to 140F MUCH quicker than the equivilant of air.

      --
      To err is human; effective mayhem requires the root password!
    2. Re:Bad science by PPH · · Score: 1

      You forget that by using a liquid based coolant ( the oil ) versus a gas based coolant ( Air OR water cooled with heat dissapated to the air) they could Easily use geothermal cooling E.G. pump the oil slowly though the rack vats and into a geothermal sink ( all it is is a pipe dropped 50+ feet into the ground) and letting the excess heat dissapate into the soil.


      Better to use water for a geothermal heat exchanger. Less damage to the water table in the event of a leak. This also assumes that access to a suitable geothermal heat sink in the vicinity of the server farm exists. Soil doesn't always conduct heat very well and significant temperature rise around the heat exchanger will decrease its efficiency.


      Also the refrigeration of say 100 gallons of oil will be much cheaper than the equivilant of air because of the density.


      Not so much density as specific heat. Water is the best by far. Other refrigerants excel only when their boiling point happens to fall within the operating temperature of the system and heat of vaporization comes into play.


      It is much easier to remove heat from a smaller surface than a really large one ( and they would be roughly the same temperatures) you can cool 100 gallons of oil from say 150F to 140F MUCH quicker than the equivilant of air.


      Again, its a matter of specific heat. A delta T of 10F transfers much more heat with water than with oil (density differences taken into consideration). Air is worse than either oil or water. But the main consideration is the pumping losses of the larger quantity of air needed to move X amount of heat than water or oil. The surface size is a secondary issue. It is determined mainly by the specific heats of working fluids (gasses) on either side, how fast you have to move each through the exchanger and the losses incurred by moving them around.

      --
      Have gnu, will travel.
  101. Could we cool it with biodiesel? by haaz · · Score: 1

    Yes, that was my first thought on reading the headline. We're so fixed on eliminating the use of oil that sometimes it's all we can think about...

    But, biodiesel would be A) home grown, B) non-toxic, C) nice-smelling, and D) reusable in to make DIESELPOWAH.

    --
    -- haaz.
  102. oil filled? by Sandbags · · Score: 1

    OK, so first of all, how do you get systems, cables, etc in and out once it's soaked. Also, what kind of floor reinforcing are we talking about after we fill a rack with a hundred or more gallons of oil. And what if I have to move it!?!?

    Why don't we just put in centralized water cooling attachments in the rack risers so we can add and remove cooling blocks? sounds like a better idea to me. It would not be hard at all to do. In fact, I'm about to do some patent research and file one on this idea if I can :)

    --
    There is no contest in life for which the unprepared have the advantage.
  103. British? Should be Scottish by ackthpt · · Score: 1

    It just had to be a British company! (If you don't understand, search this page for the word "British".)

    I hear tell the scots will attempt to fry anything!

    Imagine a beowulf cluster at the bottom of a McDonald's French Frier.

    --

    A feeling of having made the same mistake before: Deja Foobar
  104. French Fries by cenonce · · Score: 1

    Would you like fries with that?

  105. Re:Heh - Fluorinert by fahrbot-bot · · Score: 2, Informative
    The Cray II had cooling stacks that pumped a liquid coolant through the machine core.

    The fluid was Fluorinert and it was pretty expensive when I admin'ed the Cray II at NASA Langley back in 1988.

    --
    It must have been something you assimilated. . . .
  106. Questions generated by the article by beaverfever · · Score: 1

    This article seems to be incomplete. The comments noted in the closing of the article are presented and left hanging, despite being very important to the topic.

    'I don't know why oil is being suggested for computer cooling instead of accepted dielectric fluids," says Garimella, who is not familiar with Very-PCs plans. "The idea itself seems the same as using dielectric fluids and the latter are clean, non-toxic and ozone-friendly.

    Tom Halfhill, an expert with electronics industry publication Microprocessor Report, says the solution is far from ideal. "There are a number of exotic ways to cool electronics, all the way up to vats of liquid helium," he told New Scientist "However, a better solution is to avoid generating all that heat in the first place. Heat is wasted power. Heat is inefficiency. Reducing the power consumption of processors and other components is more desirable than exotic cooling."'

  107. Re:British? Should be Scottish by Oktober+Sunset · · Score: 1

    The Scottish are British.

  108. This is a terrable Idea by John+Sokol · · Score: 1

    I spend three years working on a server solution that used various oil's, solvents and water in tubes to cool servers, we also had a silient computer http://www.silentcomputing.com/ http://www.silentcomputing.com/i.html
    There is also some Super high thermal conductive Materials we called Bridges in there. All stock Motherboards and cards.
    If you get any ideas from the Photo's please remember to credit me.

    In 2001 to 2004 No investors would touch anything with fluids in the server room. Also the Corperate IT guys were also rejecting it outright.

    Ducted Air was getting more promise.

    At this time there is no reason to Wet all of the electronic with Oil, talk about a messy unmanagable solution. I friend of my actually built one, but you still have problems with the hard drives and you still need to circultate the oil just as with fans. Also beyond a certain point, you would still need to have heat exchangers (radiators) to cool the oil with outside air, and possible a compressor based chiller too.

    At Nisvara, we had developed and prototyped systems with Fluid cooling, phase change fluid cooling, ducted air and chilled water as well as a total silent desk top system that didn't require any moving fans cooling components and just based on thermal conduction using High termal conductivity materials.

    We had figured out how to build a fluid cool server room that wouldn't need any air conditioning even in 130F outside air tempteratures.
    Again using all off the shelf computer components and could be 100% sure of no fluid leakage into the system. So everything stayed cool, quiet and easy to service, even easier then the conventional designs used now.
    Almost had a contract with NASA Ames ARC center to build a 1000 server clusted that use the technology.

    Anyhow the company is mostly dead at this time, I'd be happy to collaborate with anybody interested in still persuing this technology.

    --
    I am always doing that which I can not do, in order that I may learn how to do it. - Pablo Picasso
  109. Re:Dielectric Fluids "better"? I think not. by Anonymous Coward · · Score: 0

    True. However, it's expensive as fsck, and that alone is probably a good enough reason not to use it.

  110. Demo of PC Cooled With Cooking Oil by miller60 · · Score: 1
    There's actually a detailed presentation on Tom's Hardware Guide of a high-end PC sitting in a reservoir filled with cooking oil.

    An excerpt from a demo by the Munich-based THG lab: "Not only did we find that our AMD Athlon FX-55 and GeForce 6800 Ultra equipped system didn't short out when we filled the sealed shut PC case with cooking oil - but the non-conductive properties of the liquid coupled created a totally cool and quiet high-end PC, devoid of the noise pollution of fans. The PC case - or should we say tank - also offered a new and novel way to display and show off your PC components."

  111. do you know the calypshuile? by tuxliner · · Score: 1

    ...an oil-cooled PC in a fishtank : the calypshuile page

  112. Re:Heh - Fluorinert by pilgrim23 · · Score: 1

    Yeah it was; I saw mine at Sandia Base Albuquerque....
    The joke back then ( about the round Cray design and the fact that they kept getting smaller) was "we designed a Cray 5, but someone dunked it in their coffee ;)

    The Architecture for those beasts was WAY ahead of its time. One thing I always found interesting; the Macintosh was designed on a Cray (YMP I think) that about a year ago was sold on eBay, now, I can run a Cray YMP emulator on my Mac. The Circle of Life as it were...

    --
    - Minutus cantorum, minutus balorum, minutus carborata descendum pantorum.
  113. Coming soon...? by Anonymous Coward · · Score: 0

    Oil-submerged systems have been used since the eighties. What's next? "Breaking news: company announces dedicated graphics processor with 3D acceleration"...?

  114. A lot? by Rui+del-Negro · · Score: 1

    > Bear in mind that a lot of the 300W
    > of your power supplies in each system
    > is dissipated as heat.


    A lot? Well, unless you count the noise and air movement (which are eventually also turned into heat, though not in the actual box), it's pretty much all of it, no? It's not like it's being stored in some sort of chemical compound or potential energy "reservoir".

  115. Re:Heh - Fluorinert by OwnedByTwoCats · · Score: 1

    Apple used a Cray to help design models of the Macintosh.

    Cray used Macintosh computers to help design the (next) Cray.

  116. Re:Heh - Fluorinert by fahrbot-bot · · Score: 1
    The Architecture for those beasts was WAY ahead of its time.

    Well... We did manage to crash our Cray II by taking a flash photograph.

    Apparently, the system had a fluid sensor to shutdown the box if the Fluorinert level dropped. The sensor worked by tracking the light level -- fluid dropped, more light received -- you see where I'm going with this. They repositioned the sensor so it wasn't pointing at the plexiglass facing the observation window.

    Ahh, those were the days.

    --
    It must have been something you assimilated. . . .
  117. It's about time Schwin made servers. by NRAdude · · Score: 0

    If each Schwin was outfit with an upgraded Wireless Access Point/embedded computer supported by a mechanical-Generator on the bicycle transmission complemented by a Uninteruptable Power Supply Unit to a small Solar Array for redundancy, then we can load-balance the politic to relay the route and distribution of Data just when the CIA screens all the web with the intentional drop of Internet1 by their DRM-contained Internet2.

    --
    without prejudice
  118. Re:EPA-proof oil is only $10 gallon by Anonymous Coward · · Score: 0

    This was discussed on the overclockers.com (look into oilcolled PSU - neat)

    I looked into exactly this problem for using oil to assemble silent systems here in California.

    Take a look into Envirotemp FR3 transformer fluid from Cooper Power
    Systems.

    It is organics based and is free of most of restrictions on use.

    It is sold in 4 gallon drums for about $9 per gallon - exactly the size you need for an average fish-tank fitting an ATX-sized mobo.

    Try Cooper's west coast service facility, Western Utilities Transformer Service for pricing.

  119. Substations by highwaytohell · · Score: 1

    This "new technology" is not so much new. Oil has been used for decades to cool high voltage substations. It is only now able to be applied to new technology such as racks etc.

    The interesting thing is not that oil is being used to dissipate heat, but how they managed to get the racks made in such a way that they will still function whilst surrounded by oil.

  120. but...but.... by Anonymous Coward · · Score: 0

    that's me RETIREMENT grrrrease!

  121. Re:EPA-proof oil is only $10 gallon by alienmole · · Score: 1

    Wow. This has to be the most factually interesting response to a joke I've ever seen. Thanks!

  122. And expensive by unassimilatible · · Score: 1
    Have you priced Florinert?

    Nothing new. Both HardOCP and Bit-Tech did experiments on submersion oil cooling years ago.

    --
    Slashdot "libertarians": Small government for me, big government for those I disagree with. -1, I disagree with you