[ ... named redacted by request ... ] wrote:
> > Well, here's what the sendmail folks **REAL** opinion of Linux is and
> > the way load average is calculated (senders name removed)
> > [... sendmail person ...]
> >> Ok, here's my blunt answer: Linux sucks. Why does it have a load
> >> average of 10 if there are two processes running? Let's check the
> >> man page:
> >> and the three load averages for the system. The load
> >> averages are the average number of process ready to
> >> run during the last 1, 5 and 15 minutes. This line
> >> is just like the output of uptime(1).
> >> So: Linux load average on these systems is broken.
> If that is _our_ man page, it is broken. (well, old) Otherwise,
> this is just a case of not mindlessly obeying the BSD "standard".
> Linux 2.4.xx includes some blocked processes in the load average
> calculation. This is because the BSD load average calculation
> could give a load of 0.0 when the system is severely overloaded
> by IO. I think only uninterruptable processes got added in.
> Maybe this isn't the best solution... there could have been
> a second load average for IO maybe.
> Feel free to forward this to the sendmail people, to the BSD people
> in case they'd like to "standardize" the new calculation, or to the
> linux-kernel mailing list for discussion -- w/o my name please.
Forwarded at the request of a tier 1 Linux person after redacting their