Corey, That's a good point, I will fix that for next release. Thanks.
On Sat, May 3, 2008 at 7:38 PM, Corey J Ashford <[EMAIL PROTECTED]> wrote: > > Ah, ok, thanks. The files in the Documentation subdir are still showing > the old location, which helped to confuse me. > > Regards. > > - Corey > > Corey Ashford > Software Engineer > IBM Linux Technology Center, Linux Toolchain > Beaverton, OR > 503-578-3507 > [EMAIL PROTECTED] > > > "stephane eranian" <[EMAIL PROTECTED]> wrote on 05/02/2008 11:22:25 PM: > > > > Corey, > > > > Since 2.6.24, perfmon statistics are not under /sys anymore. They are > > implemented via debugfs. > > You need to mount a debugfs filesystem: mount -tdebugfs none /debugfs. > > You'll have a perfmon > > subdir in there. > > > > > > On Sat, May 3, 2008 at 2:00 AM, Corey J Ashford <[EMAIL PROTECTED]> > wrote: > > > > > > > > > Hi Stephane, > > > > > > I'm attempting to look at the ovfl_intr_replay_count entry, > whichshould be > > > > > in /sys/devices/cpu/cpuXX/perfmon/ovfl_replay_count right? > > > Well, I don't see a 'perfmon' subdirectory of any > > > /sys/devices/system/cpu/cpuXX directory, and this is after successfully > > > running a number of PAPI (on perfmon2) tests. > > > Do these entries need to be enabled somehow? What am I missing? > > > > > > Thanks, > > > > > > - Corey > > > > > > Corey Ashford > > > Software Engineer > > > IBM Linux Technology Center, Linux Toolchain > > > Beaverton, OR > > > 503-578-3507 > > > [EMAIL PROTECTED] > > > > > > > > > [EMAIL PROTECTED] wrote on 04/25/2008 > 12:55:36 > > > PM: > > > > > > > Hello everyone, > > > [snip] > > > > > > > Thus, I believe they are subject the problem. It can easily be > detected > > > if you > > > > look at the statistics maintained by perfmon via debugfs. Perfmon > > > maintains > > > > the number of times you had to replay in the ovfl_intr_replay_count > > > entry. > > > > If you see a value different than zero then it means you needed > replay > > > > capability. To trigger this condition you can pin multiple self- > > > > sampling threads > > > > onto the same core and have monitoring run at kernel+user+force a > lot of > > > > context switches. > > > [snip] > ------------------------------------------------------------------------- This SF.net email is sponsored by the 2008 JavaOne(SM) Conference Don't miss this year's exciting event. There's still time to save $100. Use priority code J8TL2D2. http://ad.doubleclick.net/clk;198757673;13503038;p?http://java.sun.com/javaone _______________________________________________ perfmon2-devel mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/perfmon2-devel
