How many ways are there to get CPU idle-time percentages
  (my examples not all from the same system, in case anyone cares)

top -n1 | grep ^Cpu
> Cpu(s):  3.0%us,  0.5%sy, 96.2%ni,  0.3%id,  0.0%wa,  0.0%hi,  0.0%si, 0.0%st

iostat|grep -A1 avg-cpu
> avg-cpu:  %user   %nice %system %iowait  %steal   %idle
>            3.12   96.33    0.32    0.01    0.00    0.22

vmstat 1 3
> procs -----------memory---------- ---swap-- -----io---- --system-- 
> -----cpu------
>  r  b   swpd   free   buff  cache   si   so    bi    bo   in   cs us sy id wa 
> st
>  0  0 397328 180788  21712 308620    4    6    36    34  116   59  9  5 85  1 
>  0
>  0  0 397328 180780  21720 308612    0    0     0    48 1017  178  8  1 91  0 
>  0
>  0  0 397328 180780  21720 308620    0    0     0     0 1076  602  8  0 92  0 
>  0

(if the sysstat service is running..)
sar -P | egrep 'CPU|Average'
> 09:50:02 AM     CPU     %user     %nice   %system   %iowait    %steal     
> %idle
> Average:        all      8.58      0.01      0.64      0.75      0.00     
> 90.02


I'm sure it can be done via ps, but I've sort-of given up on
understanding what options control what for ps. :-(


Then there are the GUI programs:

System Monitor (gnome-system-monitor)
  subtract: 100% system-usage, I guess
gkrellm
  subtract ..

Who's got more?

- - -

One burning question I have, is how do (each of) these programs
determine CPU usage -- I see the proc filesystem has things like
/proc/stat, /proc/vmstat, and of course each process has its own set of
data.

It does seem that different programs have different ways of defining
their usage categories.

Is there someplace that nicely explains this kind of stuff? Does anyone
want to ramble about it here?  Or do have to break down and read the
docs in /usr/share/doc/kernel-doc-XXXX.Documentation/filesystems/proc.txt?

Regards,
..jim


-- 
[email protected]
http://www.kernel-panic.org/cgi-bin/mailman/listinfo/kplug-list

Reply via email to