Re: [PATCH 3/3] PM: Introduce Intel PowerClamp Driver

2012-11-14 Thread Paul E. McKenney
On Tue, Nov 13, 2012 at 06:59:06PM -0800, Arjan van de Ven wrote: > On 11/13/2012 5:34 PM, Paul E. McKenney wrote: > > On Tue, Nov 13, 2012 at 05:14:50PM -0800, Jacob Pan wrote: > >> On Tue, 13 Nov 2012 16:08:54 -0800 > >> Arjan van de Ven wrote: > >> > I think I know, but I feel the need to

Re: [PATCH 3/3] PM: Introduce Intel PowerClamp Driver

2012-11-13 Thread Arjan van de Ven
On 11/13/2012 5:34 PM, Paul E. McKenney wrote: > On Tue, Nov 13, 2012 at 05:14:50PM -0800, Jacob Pan wrote: >> On Tue, 13 Nov 2012 16:08:54 -0800 >> Arjan van de Ven wrote: >> I think I know, but I feel the need to ask anyway. Why not tell RCU about the clamping? >>> >>> I don't mind

Re: [PATCH 3/3] PM: Introduce Intel PowerClamp Driver

2012-11-13 Thread Paul E. McKenney
On Tue, Nov 13, 2012 at 05:14:50PM -0800, Jacob Pan wrote: > On Tue, 13 Nov 2012 16:08:54 -0800 > Arjan van de Ven wrote: > > > > I think I know, but I feel the need to ask anyway. Why not tell > > > RCU about the clamping? > > > > I don't mind telling RCU, but what cannot happen is a bunch o

Re: [PATCH 3/3] PM: Introduce Intel PowerClamp Driver

2012-11-13 Thread Jacob Pan
On Tue, 13 Nov 2012 16:03:00 -0800 "Paul E. McKenney" wrote: > Just to make sure I am really understanding what is happening, let's > suppose we have a HZ=1000 system that has a few tasks that > occasionally run at prio 99. These tasks would run during the clamp > interval, but would (for exampl

Re: [PATCH 3/3] PM: Introduce Intel PowerClamp Driver

2012-11-13 Thread Jacob Pan
On Tue, 13 Nov 2012 16:08:54 -0800 Arjan van de Ven wrote: > > I think I know, but I feel the need to ask anyway. Why not tell > > RCU about the clamping? > > I don't mind telling RCU, but what cannot happen is a bunch of CPU > time suddenly getting used (since that is the opposite of what is

Re: [PATCH 3/3] PM: Introduce Intel PowerClamp Driver

2012-11-13 Thread Arjan van de Ven
> > OK, so the point of clamping all sockets simultaneously is to be able > to power down the electronics surrounding the sockets as well as the > sockets themselves? yup; memory can go to self refresh etc etc >If all you cared about was the individual sockets, > I don't see why you couldn't

Re: [PATCH 3/3] PM: Introduce Intel PowerClamp Driver

2012-11-13 Thread Paul E. McKenney
On Wed, Nov 14, 2012 at 12:02:00AM +0100, Rafael J. Wysocki wrote: > On Tuesday, November 13, 2012 02:45:11 PM Arjan van de Ven wrote: > > On 11/13/2012 2:23 PM, Paul E. McKenney wrote: > > > On Tue, Nov 13, 2012 at 01:39:22PM -0800, Jacob Pan wrote: > > >> On Tue, 13 Nov 2012 13:16:02 -0800 > > >>

Re: [PATCH 3/3] PM: Introduce Intel PowerClamp Driver

2012-11-13 Thread Paul E. McKenney
On Tue, Nov 13, 2012 at 02:45:11PM -0800, Arjan van de Ven wrote: > On 11/13/2012 2:23 PM, Paul E. McKenney wrote: > > On Tue, Nov 13, 2012 at 01:39:22PM -0800, Jacob Pan wrote: > >> On Tue, 13 Nov 2012 13:16:02 -0800 > >> "Paul E. McKenney" wrote: > >> > Please refer to Documentation/thermal

Re: [PATCH 3/3] PM: Introduce Intel PowerClamp Driver

2012-11-13 Thread Rafael J. Wysocki
On Tuesday, November 13, 2012 02:45:11 PM Arjan van de Ven wrote: > On 11/13/2012 2:23 PM, Paul E. McKenney wrote: > > On Tue, Nov 13, 2012 at 01:39:22PM -0800, Jacob Pan wrote: > >> On Tue, 13 Nov 2012 13:16:02 -0800 > >> "Paul E. McKenney" wrote: > >> > Please refer to Documentation/thermal

Re: [PATCH 3/3] PM: Introduce Intel PowerClamp Driver

2012-11-13 Thread Arjan van de Ven
On 11/13/2012 2:23 PM, Paul E. McKenney wrote: > On Tue, Nov 13, 2012 at 01:39:22PM -0800, Jacob Pan wrote: >> On Tue, 13 Nov 2012 13:16:02 -0800 >> "Paul E. McKenney" wrote: >> Please refer to Documentation/thermal/intel_powerclamp.txt for more details. >>> >>> If I read this correctl

Re: [PATCH 3/3] PM: Introduce Intel PowerClamp Driver

2012-11-13 Thread Paul E. McKenney
On Tue, Nov 13, 2012 at 01:39:22PM -0800, Jacob Pan wrote: > On Tue, 13 Nov 2012 13:16:02 -0800 > "Paul E. McKenney" wrote: > > > > Please refer to Documentation/thermal/intel_powerclamp.txt for more > > > details. > > > > If I read this correctly, this forces a group of CPUs into idle for > >

Re: [PATCH 3/3] PM: Introduce Intel PowerClamp Driver

2012-11-13 Thread Arjan van de Ven
On 11/13/2012 1:16 PM, Paul E. McKenney wrote: > On Mon, Nov 12, 2012 at 02:03:51PM -0800, Jacob Pan wrote: >> Intel PowerClamp driver performs synchronized idle injection across >> all online CPUs. The goal is to maintain a given package level C-state >> ratio. >> >> Compared to other throttling m

Re: [PATCH 3/3] PM: Introduce Intel PowerClamp Driver

2012-11-13 Thread Jacob Pan
On Tue, 13 Nov 2012 13:16:02 -0800 "Paul E. McKenney" wrote: > > Please refer to Documentation/thermal/intel_powerclamp.txt for more > > details. > > If I read this correctly, this forces a group of CPUs into idle for > about 600 milliseconds at a time. This would indeed delay grace > periods

Re: [PATCH 3/3] PM: Introduce Intel PowerClamp Driver

2012-11-13 Thread Paul E. McKenney
On Mon, Nov 12, 2012 at 02:03:51PM -0800, Jacob Pan wrote: > Intel PowerClamp driver performs synchronized idle injection across > all online CPUs. The goal is to maintain a given package level C-state > ratio. > > Compared to other throttling methods already exist in the kernel, > such as ACPI PA

Re: [PATCH 3/3] PM: Introduce Intel PowerClamp Driver

2012-11-12 Thread Jacob Pan
On Mon, 12 Nov 2012 22:33:36 -0800 Joe Perches wrote: > > Intel PowerClamp driver performs synchronized idle injection across > > all online CPUs. The goal is to maintain a given package level > > C-state ratio. > > style trivia: they are all good catches. will fix in the next version. -- Th

Re: [PATCH 3/3] PM: Introduce Intel PowerClamp Driver

2012-11-12 Thread Joe Perches
On Mon, 2012-11-12 at 14:03 -0800, Jacob Pan wrote: > Intel PowerClamp driver performs synchronized idle injection across > all online CPUs. The goal is to maintain a given package level C-state > ratio. style trivia: [] > diff --git a/drivers/thermal/intel_powerclamp.c > b/drivers/thermal/inte