[Beowulf] Servers Too Hot? Intel Recommends a Luxurious Oil Bath

Lux, Jim (337C) james.p.lux at jpl.nasa.gov
Tue Sep 4 21:47:47 PDT 2012


Transformer oil isn't all that big a deal.. You buy it in 5 gallon pails, 55 gallon drums, tank truck lots.  Runs about $3-4/gallon in large quantities (which is what ALL liquids cost, it seems.. Transportation costs are the dominant component.  Sulfuric acid is pretty much the same price as mineral oil which is pretty much the same price as Jet A, etc.)

The flash point is well over 100C, as noted, so it's not like you're likely to get that hot in use.   It's not like you're running a restaurant kitchen, where they have 10s of liters  of similar stuff heated up to 200C or so.

The problems with oil insulation (aside from messy) is that if you DO get an arc going, it generates hydrogen, which has a peculiarly wide flammability range mixed with air. It also can form a fine mist, which is VERY ignitable. (that's where those nice spectacular transformer explosion videos come from.. Arc fault, gas pressure builds up, oil sprays, ignites, and fireball ensues..  (I used to make my living doing fireballs.. A bit of explosive (PETN) to disperse the flammable liquid, a bit of something that burns well (black powder) to ignite it is the usual recipe for the "car falling over a cliff and exploding")

WW II prompted the development and adoption of Gas Insulated Switchgear in Europe (using SF6).  Nothing like dropping an incendiary bomb on an electrical substation full of thousands of liters of oil to get a good fire going.  In the US, we still use mostly oil insulation: it's cheaper, and our switchgear tends to be in places where fire isn't as big a deal AND we didn't have to replace it all in the late 40s.  Cheap oil and expensive SF6 doesn't hurt either.


But when talking cooling substances.. There's an interesting trade between conductivity and viscosity (He and H2 are clear winners.. High conductivity AND low viscosity) and density SF6 is really dense, so on a temperature rise per unit volume basis, it actually does pretty well.

BTW, high power turbomachinery (power plant generator driven by steam turbines and such) are often insulated with H2, because the low viscosity reduces windage losses.

From: "Peter St. John" <peter.st.john at gmail.com<mailto:peter.st.john at gmail.com>>
Date: Tue, 4 Sep 2012 20:35:20 -0400
To: "Robert G. Brown" <rgb at phy.duke.edu<mailto:rgb at phy.duke.edu>>
Cc: Jim Lux <james.p.lux at jpl.nasa.gov<mailto:james.p.lux at jpl.nasa.gov>>, "beowulf at beowulf.org<mailto:beowulf at beowulf.org>" <beowulf at beowulf.org<mailto:beowulf at beowulf.org>>
Subject: Re: [Beowulf] Servers Too Hot? Intel Recommends a Luxurious Oil Bath

Wiki tells me that the flash point of Transformer Oil (a type of mineral oil) is 140 C; does that sound safe in a server room? I'm a worse chemist than I am a physicist so I can't tell if you're serious about OSHA not liking mineral oil in server rooms (I'm **pretty** sure you're not serious about frying chicken in the cpu box :-)
I just don't feel that power-gamers should be able to get away with anything unavailable to HPC.
Peter

On Tue, Sep 4, 2012 at 9:16 AM, Robert G. Brown <rgb at phy.duke.edu<mailto:rgb at phy.duke.edu>> wrote:
On Mon, 3 Sep 2012, Lux, Jim (337C) wrote:

> I'll bet they have to change it more often than that.  This isnt something
> like a pole transformer.

Absolutely. Think of what you can do with a big vat of hot oil handy in
the workspace.  Buffalo Wings.  French Fries.  Chicken.  Fish.  The
reason nobody does this is because OSHA prohibits it -- it is a huge
health hazard.  Not even Jolt Cola can keep you thin in a sedentary
profession with your own personal deep frier as close as your server
room.  Although you do have to change the oil pretty often, as otherwise
shrimp tails and bits of overcooked tempura crust gunk up the memory and
CPU.  Systems people were dying like pudgy little flies of advanced
cardiovascular disease before the practice of using computers to heat
deep fat was banned.

On a more serious note, one wonders why nobody has tried helium instead.
No, silly, not liquid helium, helium gas.  The reason they fill windows
with argon is that it has around 2/3 the thermal conductivity of air,
and hence is a better insulator.  This, in turn, is because it is more
massive -- conductivity is tightly tied to mass and hence the speed of
the molecules when they have kT sorts of energies.

Helium, OTOH, has six times the thermal conductivity of air, and is
relatively inexpensive.  The biggest downside I can think of is that it
requires a pretty good seal and thick walls to keep the slippery little
atoms from sliding right through to the outside, and of course the fact
that systems techs would always be hitting up the helium tanks so that
they could talk like Donald Duck.  And you'd still have to refrigerate
the outside of the systems units.  But all of these things are still
orders of magnitude easier than with oil, and even things like cooling
fans work fine in Helium.  Maybe there are other problems -- lower heat
capacity to match its higher conductivity -- but it seems like it is
worth an experiment or two...

    rgb

Robert G. Brown                        http://www.phy.duke.edu/~rgb/
Duke University Dept. of Physics, Box 90305
Durham, N.C. 27708-0305
Phone: 1-919-660-2567<tel:1-919-660-2567>  Fax: 919-660-2525<tel:919-660-2525>     email:rgb at phy.duke.edu<mailto:email%3Argb at phy.duke.edu>


_______________________________________________
Beowulf mailing list, Beowulf at beowulf.org<mailto:Beowulf at beowulf.org> sponsored by Penguin Computing
To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/listinfo/beowulf

-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://www.beowulf.org/pipermail/beowulf/attachments/20120905/d1b2039b/attachment-0001.html 


More information about the Beowulf mailing list