Re: Cluster computing drawbacks


In article <42E6593D.1040107@xxxxxxxxxx>,
Anne & Lynn Wheeler <lynn@xxxxxxxxxx> writes:
|> Ketil Malde wrote:
|> > ¹ People who were raised on punched cards may at this point feel free
|> > to vent their annoyance over the spoiled youth of today, who expect
|> > interactivity.
|>
|> my frequent observation is that the batch system developed from a
|> paradigm that the person wasn't likely to be present ...
|>
|> ... most of the world still turns on environments
|> where it isn't expected that the responsible human is present and
|> directly in control.

Yes, and it is at least as much for the convenience of the users
as anything else. I have been very blunt to several idiots who
have told me that interactive-only debuggers are worth bothering
with in the HPC arena. Do you REALLY want to sit around waiting
for a failure that occurs in one job in ten, anywhere between 6
and 24 hours into its run?


Regards,
Nick Maclaren.
.