[SunHELP] actual, not average CPU load?
sebastien.daubigne at atosorigin.com
Tue Mar 7 07:35:32 CST 2006
Valery Yankin a icrit :
> 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.
You can use Solaris standard commad "truss -cfp" to get theses figures.
You can get CPU time in kernel and userland, and for each syscall
precisely, with a little performance drop, e.g :
#truss -cfp 9406
^Csyscall seconds calls errors
write .00 3
yield .00 5
pread .19 1283
------- ------ ----
sys totals: .19 1291 0
usr time: .51
Then you can compute the CPU load for this process ((sys+usr)/elapsed).
You can start it evey 30 seconds and get the figures
Here is a sample scipt that will display the truss output every 30 seconds :
while : ; do
truss -cfp <pid_of_process_to_monitor> &
trap "kill $trusspid ; exit" INT QUIT
Sebastien.daubigne at atosorigin.com - +33(0)188.8.131.52.36
AtosOrigin Infogerance - IMS/ERP/Pessac
More information about the SunHELP