From: already5chosen@yahoo.com   
      
   On Thu, 25 Sep 2025 23:16:00 +0200   
   Terje Mathisen  wrote:   
      
   > George Neuner wrote:   
   > > On Wed, 24 Sep 2025 21:08:10 +0300, Michael S   
   > >  wrote:   
   > >   
   > >> On Mon, 22 Sep 2025 19:36:05 GMT   
   > >> MitchAlsup  wrote:   
   > >>   
   > >>> Big servers have rather equal power in the peripherals {DISKs,   
   > >>> SSDs, and NICs} and DRAM {plus power supplies and cooling} than   
   > >>> in the cores.   
   > >>   
   > >>   
   > >> Still, CPU power often matters.   
   > >   
   > > Yes ... and no.   
   > >   
   > > 80+% of the power used by datacenters is devoted to cooling the   
   > > computers - not to running them. At the same time, most of the heat   
   > > generated by typical systems is due to the RAM - not the CPU(s).   
   > >   
   > I am quite sure that number is simply bogus: The power factors we   
   > were quoted when building the largest new datacenter in Norway 10+   
   > years ago, was more like 6-10% of total power for cooling afair.   
   >   
   > .. a quick google...   
   >   
   > https://engineering.fb.com/2011/04/14/core-infra/designing-a-v   
   ry-efficient-data-center/   
   >   
   > This one claims a 1.07 Power Usage Effectiveness.   
   >   
   > Terje   
   >   
      
   I think, 1.07 is for 480VAC outside data center building to 48VDC at   
   server power plug.   
   It does not include losses withing server   
   - 48V to mostly 12V by server's PSU   
   - 12V to the whole zoo of low voltages by on-board DC2DC.   
      
   --- SoupGate-Win32 v1.05   
    * Origin: you cannot sedate... all the things you hate (1:229/2)