[SunHELP] actual, not average CPU load?

Brigance, Leslie V, WCS lbrigance at att.com
Tue Mar 7 07:15:34 CST 2006

U might get close to what you want by using just the sar cpu command at
5 sec intervals with a count of 20 or 30.
CPU is the default.  Keep in mind that the 1st couple of lines are
pretty much meaningless.
By this I  mean just (on the command line as root, of course)

#  sar 5 20

Which will give you 20 reports at 5 second intervals. You get much more
rapid rises and falls in CPU usage.
If you decrease your interval much below 5, the sar command itself
starts to really distort your data.

-----Original Message-----
From: sunhelp-bounces at sunhelp.org [mailto:sunhelp-bounces at sunhelp.org]
On Behalf Of Valery Yankin
Sent: Tuesday, March 07, 2006 1:22 AM
To: The SunHELP List
Subject: Re: [SunHELP] actual, not average CPU load?

   James Fogg wrote:

Speaking from my experience, you are asking for a miracle.
There are good performance tools available, but anything
which gave you the kind of accuracy and timing you are asking
for would carry so much overhead that the tool itself would
distort your information to the point of uselessness.
Hopefully others have better options/opinions for you.

I'd agree with this, and add the following -

Average CPU is a fine measure unless you are working with a real-time
system. Since Solaris/SPARC is stable up to 100% CPU load, if a
momentary resource hog consumes the system it doesn't matter. The
average system response time is going to be reflected by average CPU
load. Human users aren't very sensitive to brief load spikes. If you
*are* dealing with something that is very response-sensitive then Unix
is probably not the OS you should be working with.

Thanks, James. Your point is clear. I would like to explain why the need
for such
h precise measurements. My aim is to monitor a process that receives
data every
 15 minutes and processes it for some short time. I need then to draw a
graph t
hat would show how long the process is busy processing the data. On my
graphs based on the results from `ps` I have something that resembles a
ram. So, people are asking me "Hey, why is that process so reluctant to
free the
e CPU after the processing is over? Because on the CPU load graph we see
a peak
 rise, then the line goes flat for some time (processing occurs) and
then it sl
owly goes down instead of dropping. Why?" So I guess I need to make it
clear fo
r the colleagues that this is the way `ps` measures the CPU load time.

The problem is, I am using sort of a factory-tailored Solaris
installation with
 a fixed set of tools, and it is forbidden to install anything else. So,
no pkg
_add for me.

SunHELP maillist  -  SunHELP at sunhelp.org

More information about the SunHELP mailing list