Re: [PATCH 4/5] cpufreq: schedutil: map raw required frequency to CPU-supported frequency

2016-05-19 Thread Rafael J. Wysocki
On Thu, May 19, 2016 at 9:35 PM, Steve Muckle wrote: > On Thu, May 19, 2016 at 01:37:40AM +0200, Rafael J. Wysocki wrote: >> On Mon, May 9, 2016 at 11:20 PM, Steve Muckle >> wrote: >> > The mechanisms for remote CPU updates and slow-path frequency >> > transitions are relatively expensive - the

Re: [PATCH 4/5] cpufreq: schedutil: map raw required frequency to CPU-supported frequency

2016-05-19 Thread Steve Muckle
On Thu, May 19, 2016 at 01:37:40AM +0200, Rafael J. Wysocki wrote: > On Mon, May 9, 2016 at 11:20 PM, Steve Muckle wrote: > > The mechanisms for remote CPU updates and slow-path frequency > > transitions are relatively expensive - the former is an IPI while the > > latter requires waking up a thre

Re: [PATCH 4/5] cpufreq: schedutil: map raw required frequency to CPU-supported frequency

2016-05-18 Thread Rafael J. Wysocki
On Mon, May 9, 2016 at 11:20 PM, Steve Muckle wrote: > The mechanisms for remote CPU updates and slow-path frequency > transitions are relatively expensive - the former is an IPI while the > latter requires waking up a thread to do work. These activities should > be avoided if they are not necessa

[PATCH 4/5] cpufreq: schedutil: map raw required frequency to CPU-supported frequency

2016-05-09 Thread Steve Muckle
The mechanisms for remote CPU updates and slow-path frequency transitions are relatively expensive - the former is an IPI while the latter requires waking up a thread to do work. These activities should be avoided if they are not necessary. To that end, calculate the actual target-supported frequen