On 24 February 2015 at 12:29, Morten Rasmussen wrote:
> On Tue, Feb 24, 2015 at 10:38:29AM +, Vincent Guittot wrote:
>> On 23 February 2015 at 16:45, Morten Rasmussen
>> wrote:
>> > On Fri, Feb 20, 2015 at 02:54:09PM +, Vincent Guittot wrote:
>> >> On 20 February 2015 at 15:35, Morten
On Tue, Feb 24, 2015 at 10:38:29AM +, Vincent Guittot wrote:
> On 23 February 2015 at 16:45, Morten Rasmussen
> wrote:
> > On Fri, Feb 20, 2015 at 02:54:09PM +, Vincent Guittot wrote:
> >> On 20 February 2015 at 15:35, Morten Rasmussen
> >> wrote:
> >> > On Fri, Feb 20, 2015 at
On 23 February 2015 at 16:45, Morten Rasmussen wrote:
> On Fri, Feb 20, 2015 at 02:54:09PM +, Vincent Guittot wrote:
>> On 20 February 2015 at 15:35, Morten Rasmussen
>> wrote:
>> > On Fri, Feb 20, 2015 at 02:13:21PM +, Vincent Guittot wrote:
>> >> On 20 February 2015 at 12:52, Morten
On 23 February 2015 at 16:45, Morten Rasmussen morten.rasmus...@arm.com wrote:
On Fri, Feb 20, 2015 at 02:54:09PM +, Vincent Guittot wrote:
On 20 February 2015 at 15:35, Morten Rasmussen morten.rasmus...@arm.com
wrote:
On Fri, Feb 20, 2015 at 02:13:21PM +, Vincent Guittot wrote:
On
On Tue, Feb 24, 2015 at 10:38:29AM +, Vincent Guittot wrote:
On 23 February 2015 at 16:45, Morten Rasmussen morten.rasmus...@arm.com
wrote:
On Fri, Feb 20, 2015 at 02:54:09PM +, Vincent Guittot wrote:
On 20 February 2015 at 15:35, Morten Rasmussen morten.rasmus...@arm.com
wrote:
On 24 February 2015 at 12:29, Morten Rasmussen morten.rasmus...@arm.com wrote:
On Tue, Feb 24, 2015 at 10:38:29AM +, Vincent Guittot wrote:
On 23 February 2015 at 16:45, Morten Rasmussen morten.rasmus...@arm.com
wrote:
On Fri, Feb 20, 2015 at 02:54:09PM +, Vincent Guittot wrote:
On
On Fri, Feb 20, 2015 at 02:54:09PM +, Vincent Guittot wrote:
> On 20 February 2015 at 15:35, Morten Rasmussen
> wrote:
> > On Fri, Feb 20, 2015 at 02:13:21PM +, Vincent Guittot wrote:
> >> On 20 February 2015 at 12:52, Morten Rasmussen
> >> wrote:
> >> > On Fri, Feb 20, 2015 at
On Fri, Feb 20, 2015 at 02:54:09PM +, Vincent Guittot wrote:
On 20 February 2015 at 15:35, Morten Rasmussen morten.rasmus...@arm.com
wrote:
On Fri, Feb 20, 2015 at 02:13:21PM +, Vincent Guittot wrote:
On 20 February 2015 at 12:52, Morten Rasmussen morten.rasmus...@arm.com
wrote:
On 20 February 2015 at 15:35, Morten Rasmussen wrote:
> On Fri, Feb 20, 2015 at 02:13:21PM +, Vincent Guittot wrote:
>> On 20 February 2015 at 12:52, Morten Rasmussen
>> wrote:
>> > On Fri, Feb 20, 2015 at 11:34:47AM +, Peter Zijlstra wrote:
>> >> On Thu, Feb 19, 2015 at 12:49:40PM
On Fri, Feb 20, 2015 at 02:13:21PM +, Vincent Guittot wrote:
> On 20 February 2015 at 12:52, Morten Rasmussen
> wrote:
> > On Fri, Feb 20, 2015 at 11:34:47AM +, Peter Zijlstra wrote:
> >> On Thu, Feb 19, 2015 at 12:49:40PM +, Morten Rasmussen wrote:
> >>
> >> > Also, it still not
On 20 February 2015 at 12:52, Morten Rasmussen wrote:
> On Fri, Feb 20, 2015 at 11:34:47AM +, Peter Zijlstra wrote:
>> On Thu, Feb 19, 2015 at 12:49:40PM +, Morten Rasmussen wrote:
>>
>> > Also, it still not clear why patch 10 uses relative capacity reduction
>> > instead of absolute
On Fri, Feb 20, 2015 at 11:34:47AM +, Peter Zijlstra wrote:
> On Thu, Feb 19, 2015 at 12:49:40PM +, Morten Rasmussen wrote:
>
> > Also, it still not clear why patch 10 uses relative capacity reduction
> > instead of absolute capacity available to CFS tasks.
>
> As present in your
On Thu, Feb 19, 2015 at 12:49:40PM +, Morten Rasmussen wrote:
> Also, it still not clear why patch 10 uses relative capacity reduction
> instead of absolute capacity available to CFS tasks.
As present in your asymmetric big and small systems? Yes it would be
unfortunate to migrate a task to
On Thu, Feb 19, 2015 at 12:49:40PM +, Morten Rasmussen wrote:
Also, it still not clear why patch 10 uses relative capacity reduction
instead of absolute capacity available to CFS tasks.
As present in your asymmetric big and small systems? Yes it would be
unfortunate to migrate a task to an
On Fri, Feb 20, 2015 at 11:34:47AM +, Peter Zijlstra wrote:
On Thu, Feb 19, 2015 at 12:49:40PM +, Morten Rasmussen wrote:
Also, it still not clear why patch 10 uses relative capacity reduction
instead of absolute capacity available to CFS tasks.
As present in your asymmetric big
On 20 February 2015 at 12:52, Morten Rasmussen morten.rasmus...@arm.com wrote:
On Fri, Feb 20, 2015 at 11:34:47AM +, Peter Zijlstra wrote:
On Thu, Feb 19, 2015 at 12:49:40PM +, Morten Rasmussen wrote:
Also, it still not clear why patch 10 uses relative capacity reduction
instead of
On Fri, Feb 20, 2015 at 02:13:21PM +, Vincent Guittot wrote:
On 20 February 2015 at 12:52, Morten Rasmussen morten.rasmus...@arm.com
wrote:
On Fri, Feb 20, 2015 at 11:34:47AM +, Peter Zijlstra wrote:
On Thu, Feb 19, 2015 at 12:49:40PM +, Morten Rasmussen wrote:
Also, it
On 20 February 2015 at 15:35, Morten Rasmussen morten.rasmus...@arm.com wrote:
On Fri, Feb 20, 2015 at 02:13:21PM +, Vincent Guittot wrote:
On 20 February 2015 at 12:52, Morten Rasmussen morten.rasmus...@arm.com
wrote:
On Fri, Feb 20, 2015 at 11:34:47AM +, Peter Zijlstra wrote:
On
On Thu, Jan 15, 2015 at 10:09:20AM +, Vincent Guittot wrote:
> This patchset consolidates several changes in the capacity and the usage
> tracking of the CPU. It provides a frequency invariant metric of the usage of
> CPUs and generally improves the accuracy of load/usage tracking in the
>
On Thu, Jan 15, 2015 at 10:09:20AM +, Vincent Guittot wrote:
This patchset consolidates several changes in the capacity and the usage
tracking of the CPU. It provides a frequency invariant metric of the usage of
CPUs and generally improves the accuracy of load/usage tracking in the
This patchset consolidates several changes in the capacity and the usage
tracking of the CPU. It provides a frequency invariant metric of the usage of
CPUs and generally improves the accuracy of load/usage tracking in the
scheduler. The frequency invariant metric is the foundation required for the
This patchset consolidates several changes in the capacity and the usage
tracking of the CPU. It provides a frequency invariant metric of the usage of
CPUs and generally improves the accuracy of load/usage tracking in the
scheduler. The frequency invariant metric is the foundation required for the
22 matches
Mail list logo