Re: "Hypothetical" Datacenter Overheating

[Glenn McGurrin via NANOG <nanog () nanog org>]

Free air cooling loops maybe? (Not direct free air cooling with air 
exchange, the version with something much like an air handler outside 
with a coil and an fan running cold outside air over the coil with the 
water/glycol that would normally be the loop off of the chiller) the 
primary use of them is cost savings by using less energy to cool when 
it's fairly cold out, but it can also prevent low temperature issues on 
compressors by not running them when it's cold.  I'd expect it would not 
require the same sort of facade changes as it could be on the roof and 
depending only need water/glycol lines into the space, depending on 
cooling tower vs air cooled and chiller location it could also 
potentially use the same piping (which I think is the traditional use).

I'm also fairly curious to see the root cause analysis, also hoping 
someone is at least looking at some mechanism to allow transferring 
chiller capacity between floors if they had multiple floors and only had 
the failure on one floor.  This sort of mass failure seems to point 
towards either design issues (like equipment selection/configuration vs 
temperature range for the location), systemic maintenance issues, or 
some sort of single failure point that could take all the chillers out, 
none of which I'd be happy to see in a data center.

Anyone have any idea what the total cost of this incident is likely to 
reach (dead equipment, etc.)

On 1/16/2024 4:08 PM, Sean Donelan wrote:
> 350 Cermak Chicago is a "historic" building which means you can't change 
> the visible outside.  Someone had long discussions about the benefits of 
> outside air economizers, but can't change the windows.  Need to hide 
> HVAC plant (as much as possible).
>
> I would design all colos to look like 375 Pearl St (formerly Verizon, 
> formerly AT&T) New York.  Vents and concrete.
>
> Almost all the windows visible on the outside of 350 Cermak Chicago are 
> "fake." They are enclosed on the inside (with fake indoor decor) because 
> of 1912 glass panes aren't very weatherproof. But they preserve the look 
> and feel of the neighborhood :-)
>
>
> 350 Cermak rebuilt as a colo is over 20-years old. It will be 
> interesting to read the final root cause analysis.
>
> Of course, as always, networks and data centers should not depend on a 
> single POP.  Diversify the redudancy, because something will always fail.
>
> There are multiple POP/IXP in major cities.  And multiple cities with 
> POPs and IXPs.