Douglas Eadline wrote:
>I believe it is possible to develop algorithms that can
>handle this type of environment, but, they would not be
>as efficient as a closed solution where you can accurately
>schedule jobs based on guaranteed resources (non-fault tolerant
>situation)
In a previous life I was a Mac programmer, and I can remember an article in
Develop (the (excellent) Apple programming quarterly) describing just a
project like this. IIRC it was called 'Net work' and it focused on getting
the most out of a NOW. It offered some suggestions in parallelizing tasks
when you weren't guaranteed that a remote calculation would complete within
some amount of time (or at all, for that matter). Maybe part of it could be
pertinent to making large jobs more hardware failure resistant ?
If anybody's interested, drop me a line and I'll see if I can dig up the
original article.
>When I have more time....
Yeah, I know. If only there was a way to trade money for time...
Jan-Derk Bakker.
--
In protocol design, perfection has been reached not when there is nothing
left to add, but when there is nothing left to take away.
-- RFC 1925, "Fundamental Truths of Networking"
-
Linux SMP list: FIRST see FAQ at http://www.irisa.fr/prive/mentre/smp-faq/
To Unsubscribe: send "unsubscribe linux-smp" to [EMAIL PROTECTED]
