And lo, Dan Bethe saith unto me:
> Nonetheless, in some cases, the benchmarks will rise. That's my
> main reason for linking software optimization to the issue.
> I dont write compilers or drivers, so if my explanation is fulla
> crap, then someone please explain why my benchmarks rise with pgcc :) If
> I'm confusing you, then just go ahead and give it a shot and benchmark it!
>
Just be careful how you benchmark. Bonnie seems to report ~40% CPU
utilization for my 5 Ultrastar 2ES ultra-narrow drives (RAID5, natch)
on two 53c875s under a K6-300; however, top reports ~80% utilization,
split between bonnie and raid5d. I'd like to think that 64M of RAM is
enough, especially since the bonnie sizes one uses are supposed to
greatly exceed the available physical memory. And the bonnie numbers
aren't nearly what I'd hoped. :-(
Keith
--
"The avalanche has already started; |Linux: http://www.linuxhq.com |"Zooty,
it is too late for the pebbles to |KDE: http://www.kde.org | zoot
vote." Kosh, "Believers", Babylon 5 |Keith: [EMAIL PROTECTED] | zoot!"
www.midwinter.com/lurk/lurker.html |http://www.enteract.com/~kwrohrer | --Rebo
