rack power question

Joe Abley wrote:

It would sure be nice if along with choosing to order servers with DC or AC power inputs one could choose air or water cooling.

Or perhaps some non-conductive working fluid instead of water. That might not carry quite as much heat as water, but it would surely carry more than air and if chosen correctly would have more benign results when the inevitable leaks and spills occur.

The conductivity of (ion-carrying) water seems like a sensible thing to worry about. The other thing is its boiling point.

I presume that the fact that nobody ever brings that up means it's a non-issue, but it'd be good to understand why.

Seems to me that any large-scale system designed to distribute water for cooling has the potential for hot spots to appear, and that any hot spot that approaches 100C is going to cause some interesting problems.

Wouldn't some light mineral oil be a better option than water?


With IT systems, the equipment being cooled would likely reach thermal
overload and trip offline before the cooling water could flash to steam.
  Of course a properly designed system would have relief valves anyway.

One problem with mineral oil is the specific heat. Water has a specific
heat of 4.19 kJ/kg-degC. Light mineral oil is 1.67 kJ/kg-degC. That
means much higher mass flow rates (bigger pumps, tubing, more
dynamichead loss, etc) for oil than water to transfer the same amount of
heat. Oh, and if you want to see whether mineral oil burns, check out
this video: http://www.youtube.com/watch?v=YZipeaAkuC0 (that transformer
is filled with mineral oil).

Sun has some good concepts going with its green datacenter initiative.
Their approach of using extremely scalable power and cooling
distribution systems that are customizable at the rack level allows for
a wide variety of densities and configurations throughout the room.
Check out the tour at this link: