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

Robert G. Brown rgb at phy.duke.edu
Wed Sep 5 09:57:27 PDT 2012


On Wed, 5 Sep 2012, Lux, Jim (337C) wrote:

> 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")

Gawd, some people have all the luck!  What a career!  Why in the world
would you quit doing that to go to work in a boring, plodgy organization
like NASA?  Oh, wait, they do like to blow things up, don't they...;-)

> 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.

Yeah, like that.  It is a MIX of considering conductivity, heat
capacity, viscosity and related turbulence/reynolds number.

Prototyping justified, instant adoption not so much until after the
prototype and perhaps a bit of -- dare I say it -- engineering and CBA?

    rgb

> 
> From: "Peter St. John" <peter.st.john at gmail.com>
> Date: Tue, 4 Sep 2012 20:35:20 -0400
> To: "Robert G. Brown" <rgb at phy.duke.edu>
> Cc: Jim Lux <james.p.lux at jpl.nasa.gov>, "beowulf at beowulf.org"
> <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> 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  Fax: 919-660-2525     email:rgb at phy.duke.edu
> 
> 
> _______________________________________________
> Beowulf mailing list, Beowulf at beowulf.org sponsored by Penguin
> Computing
> To change your subscription (digest mode or unsubscribe) visit
> http://www.beowulf.org/mailman/listinfo/beowulf
> 
> 
> 
>

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  Fax: 919-660-2525     email:rgb at phy.duke.edu



More information about the Beowulf mailing list