> >> On one CPU, load average of 1.0 means 100% CPU usage, but this apparently
> >> isn't a bad thing. It can be more efficient to be running two jobs at once
> >> than sequentially.
> >
> >wow. if that's the case, then my box is overloaded:
> >
> >[mle@localhost 23:08:11 /hdb2]$ uptime
> > 11:08pm up 20 days, 3:06, 15 users, load average: 15.05, 15.09, 15.09
>
> A high load average is not necessarily a bad thing. The load average
> is the number of runnable tasks. If there are lots of runnable tasks
> then the CPU is timeshared. So each task will take longer to complete,
> but if the CPU is fast enough, the users will be satisfied.
>
> But in your case, it looks like it's been pegged at 15.09 for a long time,
> so something is wrong.
something like that. the number of i/o bound processes being done by the
cpu per clock cycle is how it was first explained to me.
i've a pt2/266.
what're the three numbers used for ? 5, 10, 15 minute averages
respectively ?
--
SLUG - Sydney Linux Users Group Mailing List - http://www.slug.org.au
To unsubscribe send email to [EMAIL PROTECTED] with
unsubscribe in the text
