[RC5] client versions - AIX

Timothy Marsh Timothy.Marsh at usm.edu
Wed Oct 2 12:30:32 EDT 2002


When using the checkpoint file this shouldn't be a problem at all.  When
using checkpoint files the machine can always pick up from the last
checkpoint when it crashes.  It seems like you think that having smaller
work units makes you less likely to lose work.  This is not true.  If I work
on a block that is 100 times the size of yours and use checkpoint files then
I am likely to only lose a 1/10th or 1/100th the work you would if you were
crunching the smaller block with no checkpoint files.  Just consider that
the checkpoint file saves your work much more often than you would complete
the smallest work units offered even in RC5-64.  When using checkpoint files
you should never lose a very significant portion of work, no matter how slow
your computer is.  Maybe a dnet staff member can elaborate on this, but I
believe the checkpoint files save work on a time basis (ie every 5 minutes)
as opposed to a work basis.

> The problem with taking a week is that, if your system crashes in that
week, you lose the whole block.
> My P90 took huge amounts of time to do OGR-25 blocks, and would crash
before they were done semi-
> consistently.
>
> I recognize there are features which can mitigate this somewhat, but point
it out as another problem
> with work units that take too much time.
>
> Take care,
> Blain
>
> --
> ( ) ASCII ribbon campaign
>  X  against HTML e-mail
> / \

--
To unsubscribe, send 'unsubscribe rc5' to majordomo at lists.distributed.net
rc5-digest subscribers replace rc5 with rc5-digest



More information about the rc5 mailing list