On Wed, Dec 05, 2007 at 05:46:14PM -0500, Garrison Hoffman wrote:
> What Sean and Mike didn't address is that I said the system tends to be 
> around 97% idle. Today's averages are:
> 
> 94.37 idle
> 0.23% iowait
> 1.16  load
> 
> So I'm not certain about their theory although I was already thinking 
> the same; anyway what I'm after is not theories but diagnostics I can 
> use to test them.

Actually, yes, we did :)

Loadavg is calculated by the number of processes which aren't running
for some reason.  "Some reason" can be disk load, io load, or "just not
feeling like it".  The latter is especially true for kernel threads for
some hardware, which count towards the loadavg.

If your CPU is idle, you're not seeing performance problems, and you
don't expect the system to be doing something which it can't keep up
with... ignore the loadavg number.  "idling" at 1.something just means
there is a process somewhere which the system thinks is waiting.  The
"something" factor increases depending on hardware and kernel versions,
as well.

-m

-- 
Mike Kershaw/Dragorn <[EMAIL PROTECTED]>
GPG Fingerprint: 3546 89DF 3C9D ED80 3381  A661 D7B2 8822 738B BDB1

Be different: conform.

Attachment: pgpj2v76Kiiiy.pgp
Description: PGP signature

_______________________________________________
Mid-Hudson Valley Linux Users Group                  http://mhvlug.org          
   
http://mhvlug.org/cgi-bin/mailman/listinfo/mhvlug                           
Upcoming Meetings (6pm - 8pm)                         MHVLS Auditorium          
                              
  Dec 5 - Open Source Show and Tell
  Jan 2 - TBD
  Feb 6 - DBUS
  Mar 5 - Setting up a platform-independent home/small office network using 
Linux

Reply via email to