[Beowulf] Re: UPS & power supply instability

[Robert G. Brown]

David Mathog writes:

> RGB mentioned that "the HVAC is a nasty load".  That got me
> thinking - when you increase the number of nodes running the
> HVAC servicing that rack(s) is going to sense the increased
> heat and compensate, presumably by running its motors more. 
> So you could have an indirect problem such as: 
> 
>  increased load -> 
>  increased HVAC activity ->
>  UPS instability
> 
> Where the load correlates with the instability
> but is not the direct cause.
> 
> Does the HVAC cooling the test rack run off the same UPS
> as the rack itself??? 

Boy, sure hope not.  That IS the kind of thing that might well cause
problems.  I'd think that you'd want the HVAC unit(s) each on their own
circuit and sharing nothing that can brown out node power or couple its
harmonics, surges, inductive phase shifts onto the battery.  The mixture
of switching power supplies and motors might well have some unexpected
side effects on the ability of the UPS to shape the outgoing sine wave.
IIRC, a UPS just creates a shaped wave by using something like the
inverse of the process that one uses to make AC->DC -- rapid switching,
smoothed with capacitors and all that.  Capacitors, underlying rapid
switching on the supply line, and a highly inductive load mixed with a
harmonically distorted load?  Oh my.

   rgb
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 189 bytes
Desc: not available
Url : http://www.scyld.com/pipermail/beowulf/attachments/20051001/aece860d/attachment.bin