Re: [RFC][PATCH 1/9] sched: Introduce power scheduler

2013-07-10 Thread Vincent Guittot
On 10 July 2013 13:11, Morten Rasmussen wrote: > On Wed, Jul 10, 2013 at 03:10:15AM +0100, Arjan van de Ven wrote: >> On 7/9/2013 8:55 AM, Morten Rasmussen wrote: >> > + mod_delayed_work_on(schedule_cpu(), system_wq, , >> > + msecs_to_jiffies(INTERVAL)); >> >> so

Re: [RFC][PATCH 1/9] sched: Introduce power scheduler

2013-07-10 Thread Morten Rasmussen
On Wed, Jul 10, 2013 at 03:10:15AM +0100, Arjan van de Ven wrote: > On 7/9/2013 8:55 AM, Morten Rasmussen wrote: > > + mod_delayed_work_on(schedule_cpu(), system_wq, , > > + msecs_to_jiffies(INTERVAL)); > > so thinking about this more, this really really should not be

Re: [RFC][PATCH 1/9] sched: Introduce power scheduler

2013-07-10 Thread Morten Rasmussen
On Wed, Jul 10, 2013 at 03:10:15AM +0100, Arjan van de Ven wrote: On 7/9/2013 8:55 AM, Morten Rasmussen wrote: + mod_delayed_work_on(schedule_cpu(), system_wq, dwork, + msecs_to_jiffies(INTERVAL)); so thinking about this more, this really really should not be a

Re: [RFC][PATCH 1/9] sched: Introduce power scheduler

2013-07-10 Thread Vincent Guittot
On 10 July 2013 13:11, Morten Rasmussen morten.rasmus...@arm.com wrote: On Wed, Jul 10, 2013 at 03:10:15AM +0100, Arjan van de Ven wrote: On 7/9/2013 8:55 AM, Morten Rasmussen wrote: + mod_delayed_work_on(schedule_cpu(), system_wq, dwork, +

Re: [RFC][PATCH 1/9] sched: Introduce power scheduler

2013-07-09 Thread Arjan van de Ven
On 7/9/2013 8:55 AM, Morten Rasmussen wrote: + mod_delayed_work_on(schedule_cpu(), system_wq, , + msecs_to_jiffies(INTERVAL)); so thinking about this more, this really really should not be a work queue. a work queue will cause a large number of context

Re: [RFC][PATCH 1/9] sched: Introduce power scheduler

2013-07-09 Thread Arjan van de Ven
On 7/9/2013 8:55 AM, Morten Rasmussen wrote: +void power_schedule_wq(struct work_struct *work) +{ + __power_schedule(); + mod_delayed_work_on(schedule_cpu(), system_wq, , + msecs_to_jiffies(INTERVAL)); +} please tell me this is at least a deferable

[RFC][PATCH 1/9] sched: Introduce power scheduler

2013-07-09 Thread Morten Rasmussen
Proof of concept capacity managing power scheduler. Supports simple packing without any consideration of power topology. The power scheduler is meant to use a platform specific power driver to obtain information about power topology and select idle states and frequency/P-states. For now, the

Re: [RFC][PATCH 1/9] sched: Introduce power scheduler

2013-07-09 Thread Arjan van de Ven
On 7/9/2013 8:55 AM, Morten Rasmussen wrote: + mod_delayed_work_on(schedule_cpu(), system_wq, dwork, + msecs_to_jiffies(INTERVAL)); so thinking about this more, this really really should not be a work queue. a work queue will cause a large number of context

[RFC][PATCH 1/9] sched: Introduce power scheduler

2013-07-09 Thread Morten Rasmussen
Proof of concept capacity managing power scheduler. Supports simple packing without any consideration of power topology. The power scheduler is meant to use a platform specific power driver to obtain information about power topology and select idle states and frequency/P-states. For now, the

Re: [RFC][PATCH 1/9] sched: Introduce power scheduler

2013-07-09 Thread Arjan van de Ven
On 7/9/2013 8:55 AM, Morten Rasmussen wrote: +void power_schedule_wq(struct work_struct *work) +{ + __power_schedule(); + mod_delayed_work_on(schedule_cpu(), system_wq, dwork, + msecs_to_jiffies(INTERVAL)); +} please tell me this is at least a