[Discuss] Server Room Power

[matt at mattshields.org (Matt Shields)]

On Thu, Oct 13, 2011 at 8:46 PM, Edward Ned Harvey <blu at nedharvey.com>wrote:

> > From: discuss-bounces+blu=nedharvey.com at blu.org [mailto:discuss-
> > bounces+blu=nedharvey.com at blu.org] On Behalf Of Matt Shields
> >
> > A long time ago I got fed up with trying to calculate amperage, so I
> > invested in a clamp on ammeter.  Then I test my servers when I get them
> and
> > record the high and average usage.
>
> This is an excellent practice.  I have been using kill-a-watt, but the
> clamp
> is more convenient.  Besides knowing the A, you also want to know the VA
> and
> W so you can spec your UPS appropriately.
>
> One thing to be keenly aware of is that power draw of a server is variable.
> To reach max power, you need to find ways of stressing the high power
> components - Usually the CPU and GPU (if any.)  But a "while 1 { ; }" loop
> will not stress much of the cpu, so it doesn't do a good job of reaching
> max
> power.  The best stuff will be things like the AES instruction set, and
> generating random numbers and doing parallel compression.  Get the max
> power
> of the system and fluff it a bit.
>
>
I also have a killawatt but the problem comes when I have to work on someone
else's live equipment.  The clampon ammeter means I don't have to shut the
server's off. I can also clamp on to the rack's main power feed if I don't
have a APC PDU.  Well worth the money I spent.

Matthew Shields
Owner
BeanTown Host - Web Hosting, Domain Names, Dedicated Servers, Colocation,
Managed Services
www.beantownhost.com
www.sysadminvalley.com
www.jeeprally.com
Like us on Facebook <http://www.facebook.com/beantownhost>
Follow us on Twitter <https://twitter.com/#!/beantownhost>