RE: DS20L

[Iwao Makino <rickey-co mug biglobe ne jp>]

At 16:27 -0400 on 30.05.2002, Peter Petrakis wrote regarding RE: DS20L:
> So you where running hardware that is known to dissipate significant heat in
> a machine room that had inadequate cooling? That's 77 F you're talking about.
> That is uncomfortably warm for a machine room or any room for that matter, You
> should never be past 70F, 65F ideally. At API, Our labs had 'two' full air
> conditioners and even if one failed we wouldn't get the lab hotter than 74F
> tops. It was a cool 63-67F when they where both operational. Cold enough 
> that if

I don't know what environmental conditions in the US, but over here, it's 
almost
impossible to get room about 18C(65F).  Best we can expect is 20C,but most
of places for them machines including telecom centres, it's about 25C.
Inside cabinet is little warmer. So I can agree heat problem...

> Your customers will buy multiple 15K  servers  but wont spend the 6-8K for 
> another AC
> to cool them?
Price wise, your idea works, but AFAIK, usually to add additional AC 
requires a lot
more paperwork than to purchase a cluster.  Plus, extra power consumption
might be another issue.  And big AC is not that cheap here...

>  > I think that in a 20C air-conditioned roomthey will be fine, but at 25C
>  > they get "iffy".
>
> Like they're spec'd for :-).

I've seen 128CPU IA nodes running at 28C or 30C room temp for just fine...
What's exact spec for room temp. on CS20/DS20L?
If it's required to run between 63-67F it'll be hard to find customers at
Universities or telecom use here.  Very few have such a nice condition.

just my $0.02