On 1/24/2018 7:26 AM, Peter Zijlstra wrote:
On Mon, Jan 08, 2018 at 07:15:13AM -0800, kan.li...@intel.com wrote:
The formula to calculate the event->count is as below:
event->count = period left from last time +
(reload_times - 1) * reload_val +
On 1/24/2018 7:26 AM, Peter Zijlstra wrote:
On Mon, Jan 08, 2018 at 07:15:13AM -0800, kan.li...@intel.com wrote:
The formula to calculate the event->count is as below:
event->count = period left from last time +
(reload_times - 1) * reload_val +
On Mon, Jan 08, 2018 at 07:15:13AM -0800, kan.li...@intel.com wrote:
> The formula to calculate the event->count is as below:
> event->count = period left from last time +
> (reload_times - 1) * reload_val +
> latency of PMI handler
>
> prev_count is the last
On Mon, Jan 08, 2018 at 07:15:13AM -0800, kan.li...@intel.com wrote:
> The formula to calculate the event->count is as below:
> event->count = period left from last time +
> (reload_times - 1) * reload_val +
> latency of PMI handler
>
> prev_count is the last
On Wed, Jan 10, 2018 at 09:31:01AM -0500, Liang, Kan wrote:
>
>
> On 1/10/2018 5:22 AM, Jiri Olsa wrote:
> > On Mon, Jan 08, 2018 at 07:15:13AM -0800, kan.li...@intel.com wrote:
> >
> > SNIP
> >
> > > There is nothing need to do in x86_perf_event_set_period(). Because it
> > > is fixed period.
On Wed, Jan 10, 2018 at 09:31:01AM -0500, Liang, Kan wrote:
>
>
> On 1/10/2018 5:22 AM, Jiri Olsa wrote:
> > On Mon, Jan 08, 2018 at 07:15:13AM -0800, kan.li...@intel.com wrote:
> >
> > SNIP
> >
> > > There is nothing need to do in x86_perf_event_set_period(). Because it
> > > is fixed period.
On 1/10/2018 5:22 AM, Jiri Olsa wrote:
On Mon, Jan 08, 2018 at 07:15:13AM -0800, kan.li...@intel.com wrote:
SNIP
There is nothing need to do in x86_perf_event_set_period(). Because it
is fixed period. The period_left is already adjusted.
Signed-off-by: Kan Liang
On 1/10/2018 5:22 AM, Jiri Olsa wrote:
On Mon, Jan 08, 2018 at 07:15:13AM -0800, kan.li...@intel.com wrote:
SNIP
There is nothing need to do in x86_perf_event_set_period(). Because it
is fixed period. The period_left is already adjusted.
Signed-off-by: Kan Liang
---
On Mon, Jan 08, 2018 at 07:15:13AM -0800, kan.li...@intel.com wrote:
SNIP
> There is nothing need to do in x86_perf_event_set_period(). Because it
> is fixed period. The period_left is already adjusted.
>
> Signed-off-by: Kan Liang
> ---
> arch/x86/events/intel/ds.c
On Mon, Jan 08, 2018 at 07:15:13AM -0800, kan.li...@intel.com wrote:
SNIP
> There is nothing need to do in x86_perf_event_set_period(). Because it
> is fixed period. The period_left is already adjusted.
>
> Signed-off-by: Kan Liang
> ---
> arch/x86/events/intel/ds.c | 69
>
From: Kan Liang
There is bug when mmap read event->count with large PEBS enabled.
Here is an example.
#./read_count
0x71f0
0x122c0
0x11c54
0x10001257d
0x2bdc5
There is auto-reload mechanism enabled for PEBS events in fixed period
mode. But
From: Kan Liang
There is bug when mmap read event->count with large PEBS enabled.
Here is an example.
#./read_count
0x71f0
0x122c0
0x11c54
0x10001257d
0x2bdc5
There is auto-reload mechanism enabled for PEBS events in fixed period
mode. But the calculation of
12 matches
Mail list logo