Subject: get_offset_pmtmr - msg#00078

List: linux.oprofile

Date: Prev Next Index Thread: Prev Next Index

Hi, When running oprofile 0.9.1 I notice about 40% of cycles being spent in the
above vmlinux function. This is when running on a core-duo machine. Obviously
this is wrong in that too much time is being spent in the kernel.

My question is: Is the kernel really spending so much time in the kernel or is
it an artifact of something else going on; the clockticks event counting
incorrect or somthing else altogether.

Any help is appreciated

Thanks
pak

-------------------------------------------------------
This SF.Net email is sponsored by xPML, a groundbreaking scripting language
that extends applications into web and mobile media. Attend the live webcast
and join the prime developer group breaking into this new coding territory!
http://sel.as-us.falkag.net/sel?cmd=lnk&kid=110944&bid=241720&dat=121642

Was this page helpful?

Thread at a glance:

Previous Message by Date: click to view message preview

Re: About randomizing (again, ignore the previous mail with same title)

On Tue, Apr 18, 2006 at 08:48:04AM -0700, Stephane Eranian wrote: > I am talking about sampling on events that are not affected by any other > activities in the system, e.g., instructions retired, taken branches and the > likes. Eh? These are most certainly affected as soon as you switch out the target process, enter the kernel, use a library function etc. The ones that might not are XMM events etc. where nothing else on the CPU is going to trigger the event. regards john ------------------------------------------------------- This SF.Net email is sponsored by xPML, a groundbreaking scripting language that extends applications into web and mobile media. Attend the live webcast and join the prime developer group breaking into this new coding territory! http://sel.as-us.falkag.net/sel?cmd=lnk&kid=110944&bid=241720&dat=121642

Next Message by Date: click to view message preview

oprofile results in Kernel panic

Hi, a run of oprofile on one of our production-hosts has resulted in a kernel panic (see attached screenshot). Can anyone help? Our Configuration is: kernel version 2.6.12 oprofile version 0.8.1 oprofile setup: --no-vmlinux --separate=lib Thanks in advance, Olaf -- Olaf Bachmann, PhD Team Leader, Delivery Technology IS.Teledata AG Stollwerckstr. 7 D-51149 Koeln Tel: +49 2203 9009 - 147 Fax: +49 2203 9009 - 105 mailto:Olaf.Bachmann@xxxxxxxxxxxxxxx http://www.is-teledata.com smime.p7s Description: S/MIME Cryptographic Signature

Previous Message by Thread: click to view message preview

getting oprofile out of timer mode

Hello, We are trying to use the Oprofile tool (for a class project), and we have the following problem: if we try to specify events to profile (e.g. --event=DATA_MEM_REFS), the program says it's in the Timer Mode. The Oprofile FAQ tells us to add the "lapic" boot option in this case (we use Pentium III, which should have hardware counters), but doing so does not change anything for us. Oprofile still starts in the Timer Mode. Could there be any other reasons for this? The corresponding line in our grub config file looks like this: kernel /vmlinuz-2.6.11-1.1369_FC4 ro root=LABEL=/ rhgb quiet selinux=0 lapic Thanks, Andrei ------------------------------------------------------- This SF.Net email is sponsored by xPML, a groundbreaking scripting language that extends applications into web and mobile media. Attend the live webcast and join the prime developer group breaking into this new coding territory! http://sel.as-us.falkag.net/sel?cmd=lnk&kid0944&bid$1720&dat1642

Next Message by Thread: click to view message preview

Loading Comments...