Messages in this thread | | | From | Thomas Renninger <> | Subject | Re: [PATCH] cpupower: mperf monitor: fix output in MAX_FREQ_SYSFS mode | Date | Wed, 27 May 2015 15:24:56 +0200 |
| |
Hi,
and sorry for the late answer, this had not highest prio...
On Wednesday, May 20, 2015 02:26:47 AM Rafael J. Wysocki wrote: > On Monday, May 11, 2015 12:40:22 PM Herton R. Krzesinski wrote: > > On Mon, May 11, 2015 at 11:35:35AM -0300, Herton R. Krzesinski wrote: > > > There is clearly wrong output when mperf monitor runs in MAX_FREQ_SYSFS > > > mode: average frequency shows in kHz unit (despite the intended output > > > to be in MHz), and percentages for C state information are all wrong > > > (including high/negative values shown). > > > > > > The problem is that the max_frequency read on initialization isn't used > > > where it should have been used on mperf_get_count_percent (to estimate > > > the number of ticks in the given time period), and the value we read > > > from sysfs is in kHz, so we must divide it to get the MHz value to use > > > in current calculations. > > > > > > While at it, also I fixed another small issues in the debug output of > > > max_frequency value in mperf_get_count_freq. > > > > > > Signed-off-by: Herton R. Krzesinski <herton@redhat.com> > > > --- > > > > > > tools/power/cpupower/utils/idle_monitor/mperf_monitor.c | 5 +++-- > > > 1 file changed, 3 insertions(+), 2 deletions(-) > > > > Actually please consider v2 patch below, just a minor change in the debug > > output, which isn't a percentage... > > Thomas, any comments?
I tried to find fitting HW without much success. The MAX_FREQ_SYSFS is used only on rare HW and it may never got a proper test.
Patch looks sane. Even I cannot add a Tested-by: you may add:
Acked-by: Thomas Renninger <trenn@suse.de>
and add it.
Thanks,
Thomas
| |