On Thu, Jan 12, 2017 at 3:47 AM, Mark Rutland wrote:
> On Tue, Jan 10, 2017 at 12:20:00PM -0800, David Carrillo-Cisneros wrote:
>> On Tue, Jan 10, 2017 at 6:14 AM, Mark Rutland wrote:
>> > On Tue, Jan 10, 2017 at 02:24:58AM -0800, David Carrillo-Cisneros wrote:
>> > For example, on a big.LITTLE s
On Tue, Jan 10, 2017 at 12:20:00PM -0800, David Carrillo-Cisneros wrote:
> On Tue, Jan 10, 2017 at 6:14 AM, Mark Rutland wrote:
> > On Tue, Jan 10, 2017 at 02:24:58AM -0800, David Carrillo-Cisneros wrote:
> > For example, on a big.LITTLE system, big and little CPU PMUs share the
> > same context,
On Tue, Jan 10, 2017 at 6:14 AM, Mark Rutland wrote:
> On Tue, Jan 10, 2017 at 02:24:58AM -0800, David Carrillo-Cisneros wrote:
>> Add a rb-tree that indexes inactive events by {CPU/cgroup,flexible,stamp}.
>>
>> The original idea by Peter Z. was to sort task events in an rb-tree using
>> {pmu,cpu,
On Tue, Jan 10, 2017 at 02:24:58AM -0800, David Carrillo-Cisneros wrote:
> Add a rb-tree that indexes inactive events by {CPU/cgroup,flexible,stamp}.
>
> The original idea by Peter Z. was to sort task events in an rb-tree using
> {pmu,cpu,timestamp} as key.
>
> Having the PMU as part of the key g
Add a rb-tree that indexes inactive events by {CPU/cgroup,flexible,stamp}.
The original idea by Peter Z. was to sort task events in an rb-tree using
{pmu,cpu,timestamp} as key.
Having the PMU as part of the key gets complicated for contexts that
share pmus (i.e. software context) because all even
5 matches
Mail list logo