An interesting question.
The power cycling reliability thing is probably not a big deal - the
temperatures change a lot between light load and heavy load already, and if a
"server class" PC can't take a power cycle per day, when the grungiest consumer
unit can do it, I'd be surprised. It's not like you're cycling between -40C and
70C every hour like in an automotive application.
Managing the chillers, though - That might be a bigger problem.
And as Jörg points out, there's a fair amount of sophistication needed in
setting your turn on and turn off thresholds.
On the "spool RAM to disk" idea - That's sort of like checkpointing, and it can
take surprisingly long, so there's another tradeoff there.
On 7/16/21, 12:35 PM, "Beowulf on behalf of Douglas Eadline"
<beowulf-boun...@beowulf.org on behalf of deadl...@eadline.org> wrote:
Hi everyone:
Reducing power use has become an important topic. One
of the questions I always wondered about is
why more cluster do not turn off unused nodes. Slurm
has hooks to turn nodes off when not in use and
turn them on when resources are needed.
My understanding is that power cycling creates
temperature cycling, that then leads to premature node
failure. Makes sense and has anyone ever studied/tested
this ?
The only other reason I can think of is that the delay
in server boot time makes job starts slow or power
surge issues.
I'm curious about other ideas or experiences.
Thanks
--
Doug
--
Doug
_______________________________________________
Beowulf mailing list, Beowulf@beowulf.org sponsored by Penguin Computing
To change your subscription (digest mode or unsubscribe) visit
https://urldefense.us/v3/__https://beowulf.org/cgi-bin/mailman/listinfo/beowulf__;!!PvBDto6Hs4WbVuu7!ef5Z3NxzUcVChBwMKSYQ9u5d4nI_weKdbvUWM6BY8x2UyBeye1j64LNSRzJZUkml3wOJ0TM$
_______________________________________________
Beowulf mailing list, Beowulf@beowulf.org sponsored by Penguin Computing
To change your subscription (digest mode or unsubscribe) visit
https://beowulf.org/cgi-bin/mailman/listinfo/beowulf
