> Indeed, black would be the most accurate reading because of its 
> radiating properties.
> Other than geeky value, is there a concrete goal?
> I'm mostly interested in inlet temp and outlet temperature, and let the 
> internals handle themselves.

Well, I assemble my own servers, and I want to make sure I didn't do
something stupid airflow-wise that causes one part or another to get hotter
than I'd expect.  

I also want to sanity check software-accessable probes; like I was
saying, SMART occasionally returns possible but extremely unlikely values,
and being able to caliberate my expectations for that sort of thing
would help.


> Aside: Interesting recommendation from James Hamilton (Amazon 
> Infrastructure lead) is to run the inlet around 87F, if your other 
> infrastructure can handle it.

Yup.  But I co-lo;  I've got what, around 15kw of servers, so as far
as I can tell, I'm not really large enough for my own space.  

Once I get a better office, I'll toy with the idea of a rack or two cooled
with outside air and a 'three hours a day for one month out of the year'
a/c, in my area, that's about what I'd need to maintain 87F.  

Of course, I need more infrastructure than just cooling;  I don't plan
on moving anything important into space I fully manage for some time. 

-- 
Luke S. Crawford
http://prgmr.com/xen/         -   Hosting for the technically adept
http://nostarch.com/xen.htm   -   We don't assume you are stupid.  
_______________________________________________
Tech mailing list
[email protected]
https://lists.lopsa.org/cgi-bin/mailman/listinfo/tech
This list provided by the League of Professional System Administrators
 http://lopsa.org/

Reply via email to