North American Network Operators Group

Date Prev | Date Next | Date Index | Thread Index | Author Index | Historical

RE: rack power question

  • From: michael.dillon
  • Date: Tue Mar 25 12:36:08 2008

>  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.  
 
HCFC-123 is likely what would be used, which means that you would want to limit the amount of time that you spend inside the data center because, with the large number of connections in the facility, leaks will be inevitable and inhaling the gas causes liver damage.
 
Essentially, you are saying that we should get rid of chillers and turn the entire data center into a giant chiller. Instead of being a building with rooms and equipment, the data center becomes a machine and humans only venture inside when the machine is shut down for maintenance. 
 
>  Less practical but more fun to contemplate would be data centers pressurized  
>  with a working gas that offers better heat transfer than oxygen/nitrogen and no  
>  oxidation potential.  Airlocks and suits for the techs, but no fire worries ever.   
>  Heck, just close the room and inject liquid nitrogen under the raised floor to be  
>  scavenged overhead and re-compressed, chilled, liquefied and sent round again.  
>  Reserve cooling for power outages is just huge dewars full of liquid nitrogen :)

 >  Not so serious today,
 
Why not? If you take your pressurized liquid nitrogen scenario and turn it inside out, then it might well be workable and there would be no need for suits. For instance, imagine a cylinder containing the liquid nitro cooling (liquid air might be cheaper) with devices attached all around like the petals on a flower. Each device has heat exchangers for cooling the hottest parts (CPUs) and the heat exchangers are attached to the cooling cylinder. With continued increase in density of cores, this could be feasible. In essence it would be a kind of blade server with the cooling and backplane in a central cylinder. Added benefits might come from supercooling the backplane.
 
Consider what is happening beyond the consumer dual and 8-core (PS3) machines.
<http://www.tilera.com/products/boards.php>
<http://www.sicortex.com/architecture_tour>
 
--Michael Dillon