Re: [PATCH 2/6] drivers base/arch_topology: frequency-invariant load-tracking support

On 08/06/17 08:55, Dietmar Eggemann wrote: > Implements an arch-specific frequency-scaling function > topology_get_freq_scale() which provides the following frequency > scaling factor: > > current_freq(cpu) << SCHED_CAPACITY_SHIFT / max_supported_freq(cpu) [...] Frequency and cpu-invariant

Re: [PATCH 2/6] drivers base/arch_topology: frequency-invariant load-tracking support

On 08/06/17 08:55, Dietmar Eggemann wrote: > Implements an arch-specific frequency-scaling function > topology_get_freq_scale() which provides the following frequency > scaling factor: > > current_freq(cpu) << SCHED_CAPACITY_SHIFT / max_supported_freq(cpu) [...] Frequency and cpu-invariant

Re: [PATCH 2/6] drivers base/arch_topology: frequency-invariant load-tracking support

On Thu, Jun 22, 2017 at 09:36:43AM +0530, Viresh Kumar wrote: > On 21-06-17, 17:57, Morten Rasmussen wrote: > > It is true that this patch relies on the notifiers, but I don't see how > > that prevents us from adding a non-notifier based solution for > > fast-switch enabled platforms later? > >

Re: [PATCH 2/6] drivers base/arch_topology: frequency-invariant load-tracking support

On Thu, Jun 22, 2017 at 09:36:43AM +0530, Viresh Kumar wrote: > On 21-06-17, 17:57, Morten Rasmussen wrote: > > It is true that this patch relies on the notifiers, but I don't see how > > that prevents us from adding a non-notifier based solution for > > fast-switch enabled platforms later? > >

Re: [PATCH 2/6] drivers base/arch_topology: frequency-invariant load-tracking support

On 21-06-17, 17:57, Morten Rasmussen wrote: > It is true that this patch relies on the notifiers, but I don't see how > that prevents us from adding a non-notifier based solution for > fast-switch enabled platforms later? No it doesn't, but I thought it would be better to have a single solution

Re: [PATCH 2/6] drivers base/arch_topology: frequency-invariant load-tracking support

On 21-06-17, 17:57, Morten Rasmussen wrote: > It is true that this patch relies on the notifiers, but I don't see how > that prevents us from adding a non-notifier based solution for > fast-switch enabled platforms later? No it doesn't, but I thought it would be better to have a single solution

Re: [PATCH 2/6] drivers base/arch_topology: frequency-invariant load-tracking support

On 21-06-17, 17:38, Dietmar Eggemann wrote: > On 20/06/17 07:17, Viresh Kumar wrote: > > Any specific reason on why are we doing this from PRECHANGE and > > not POSTCHANGE ? i.e. we are doing this before the frequency is > > really updated. > > Not really. In case I get a CPUFREQ_POSTCHANGE all

Re: [PATCH 2/6] drivers base/arch_topology: frequency-invariant load-tracking support

On 21-06-17, 17:38, Dietmar Eggemann wrote: > On 20/06/17 07:17, Viresh Kumar wrote: > > Any specific reason on why are we doing this from PRECHANGE and > > not POSTCHANGE ? i.e. we are doing this before the frequency is > > really updated. > > Not really. In case I get a CPUFREQ_POSTCHANGE all

Re: [PATCH 2/6] drivers base/arch_topology: frequency-invariant load-tracking support

On 21/06/17 01:31, Saravana Kannan wrote: > On 06/19/2017 11:17 PM, Viresh Kumar wrote: >> On Thu, Jun 8, 2017 at 1:25 PM, Dietmar Eggemann >> wrote: >> >>> diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c >> >>> static int __init

Re: [PATCH 2/6] drivers base/arch_topology: frequency-invariant load-tracking support

On 21/06/17 01:31, Saravana Kannan wrote: > On 06/19/2017 11:17 PM, Viresh Kumar wrote: >> On Thu, Jun 8, 2017 at 1:25 PM, Dietmar Eggemann >> wrote: >> >>> diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c >> >>> static int __init register_cpufreq_notifier(void) >>> {

Re: [PATCH 2/6] drivers base/arch_topology: frequency-invariant load-tracking support

On Wed, Jun 21, 2017 at 11:07:35AM +0530, Viresh Kumar wrote: > On 20-06-17, 17:31, Saravana Kannan wrote: > > On 06/19/2017 11:17 PM, Viresh Kumar wrote: > > >On Thu, Jun 8, 2017 at 1:25 PM, Dietmar Eggemann > > > wrote: > > > > > >>diff --git

Re: [PATCH 2/6] drivers base/arch_topology: frequency-invariant load-tracking support

On Wed, Jun 21, 2017 at 11:07:35AM +0530, Viresh Kumar wrote: > On 20-06-17, 17:31, Saravana Kannan wrote: > > On 06/19/2017 11:17 PM, Viresh Kumar wrote: > > >On Thu, Jun 8, 2017 at 1:25 PM, Dietmar Eggemann > > > wrote: > > > > > >>diff --git a/drivers/base/arch_topology.c

Re: [PATCH 2/6] drivers base/arch_topology: frequency-invariant load-tracking support

On 14/06/17 14:08, Vincent Guittot wrote: > On 14 June 2017 at 09:55, Dietmar Eggemann wrote: >> >> On 06/12/2017 04:27 PM, Vincent Guittot wrote: >>> On 8 June 2017 at 09:55, Dietmar Eggemann wrote: [...] >> >> Yes, we should free

Re: [PATCH 2/6] drivers base/arch_topology: frequency-invariant load-tracking support

On 14/06/17 14:08, Vincent Guittot wrote: > On 14 June 2017 at 09:55, Dietmar Eggemann wrote: >> >> On 06/12/2017 04:27 PM, Vincent Guittot wrote: >>> On 8 June 2017 at 09:55, Dietmar Eggemann wrote: [...] >> >> Yes, we should free cpus_to_visit if the policy notifier registration >> fails.

Re: [PATCH 2/6] drivers base/arch_topology: frequency-invariant load-tracking support

On 20/06/17 07:17, Viresh Kumar wrote: > On Thu, Jun 8, 2017 at 1:25 PM, Dietmar Eggemann > wrote: > >> diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c > >> static int >> init_cpu_capacity_callback(struct notifier_block *nb, >> @@ -185,6

Re: [PATCH 2/6] drivers base/arch_topology: frequency-invariant load-tracking support

On 20/06/17 07:17, Viresh Kumar wrote: > On Thu, Jun 8, 2017 at 1:25 PM, Dietmar Eggemann > wrote: > >> diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c > >> static int >> init_cpu_capacity_callback(struct notifier_block *nb, >> @@ -185,6 +192,7 @@

Re: [PATCH 2/6] drivers base/arch_topology: frequency-invariant load-tracking support

On 20-06-17, 17:31, Saravana Kannan wrote: > On 06/19/2017 11:17 PM, Viresh Kumar wrote: > >On Thu, Jun 8, 2017 at 1:25 PM, Dietmar Eggemann > > wrote: > > > >>diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c > > > >> static int __init

Re: [PATCH 2/6] drivers base/arch_topology: frequency-invariant load-tracking support

On 20-06-17, 17:31, Saravana Kannan wrote: > On 06/19/2017 11:17 PM, Viresh Kumar wrote: > >On Thu, Jun 8, 2017 at 1:25 PM, Dietmar Eggemann > > wrote: > > > >>diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c > > > >> static int __init register_cpufreq_notifier(void) > >>

Re: [PATCH 2/6] drivers base/arch_topology: frequency-invariant load-tracking support

On 06/19/2017 11:17 PM, Viresh Kumar wrote: On Thu, Jun 8, 2017 at 1:25 PM, Dietmar Eggemann wrote: diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c static int __init register_cpufreq_notifier(void) { + int ret; + /*

Re: [PATCH 2/6] drivers base/arch_topology: frequency-invariant load-tracking support

On 06/19/2017 11:17 PM, Viresh Kumar wrote: On Thu, Jun 8, 2017 at 1:25 PM, Dietmar Eggemann wrote: diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c static int __init register_cpufreq_notifier(void) { + int ret; + /* * on ACPI-based

Re: [PATCH 2/6] drivers base/arch_topology: frequency-invariant load-tracking support

On Thu, Jun 8, 2017 at 1:25 PM, Dietmar Eggemann wrote: > diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c > static int > init_cpu_capacity_callback(struct notifier_block *nb, > @@ -185,6 +192,7 @@ init_cpu_capacity_callback(struct

Re: [PATCH 2/6] drivers base/arch_topology: frequency-invariant load-tracking support

On Thu, Jun 8, 2017 at 1:25 PM, Dietmar Eggemann wrote: > diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c > static int > init_cpu_capacity_callback(struct notifier_block *nb, > @@ -185,6 +192,7 @@ init_cpu_capacity_callback(struct notifier_block *nb, >

Re: [PATCH 2/6] drivers base/arch_topology: frequency-invariant load-tracking support

Hi, On 14/06/17 15:08, Vincent Guittot wrote: > On 14 June 2017 at 09:55, Dietmar Eggemann wrote: > > > > On 06/12/2017 04:27 PM, Vincent Guittot wrote: > > > On 8 June 2017 at 09:55, Dietmar Eggemann > > > wrote: > > > > Hi Vincent, > > > >

Re: [PATCH 2/6] drivers base/arch_topology: frequency-invariant load-tracking support

Hi, On 14/06/17 15:08, Vincent Guittot wrote: > On 14 June 2017 at 09:55, Dietmar Eggemann wrote: > > > > On 06/12/2017 04:27 PM, Vincent Guittot wrote: > > > On 8 June 2017 at 09:55, Dietmar Eggemann > > > wrote: > > > > Hi Vincent, > > > > Thanks for the review! > > > > [...] > > > > >> @@

Re: [PATCH 2/6] drivers base/arch_topology: frequency-invariant load-tracking support

On 14 June 2017 at 09:55, Dietmar Eggemann wrote: > > On 06/12/2017 04:27 PM, Vincent Guittot wrote: > > On 8 June 2017 at 09:55, Dietmar Eggemann wrote: > > Hi Vincent, > > Thanks for the review! > > [...] > > >> @@ -225,8 +265,14 @@ static

Re: [PATCH 2/6] drivers base/arch_topology: frequency-invariant load-tracking support

On 14 June 2017 at 09:55, Dietmar Eggemann wrote: > > On 06/12/2017 04:27 PM, Vincent Guittot wrote: > > On 8 June 2017 at 09:55, Dietmar Eggemann wrote: > > Hi Vincent, > > Thanks for the review! > > [...] > > >> @@ -225,8 +265,14 @@ static int __init register_cpufreq_notifier(void) > >> > >>

Re: [PATCH 2/6] drivers base/arch_topology: frequency-invariant load-tracking support

On 06/12/2017 04:27 PM, Vincent Guittot wrote: > On 8 June 2017 at 09:55, Dietmar Eggemann wrote: Hi Vincent, Thanks for the review! [...] >> @@ -225,8 +265,14 @@ static int __init register_cpufreq_notifier(void) >> >> cpumask_copy(cpus_to_visit,

Re: [PATCH 2/6] drivers base/arch_topology: frequency-invariant load-tracking support

On 06/12/2017 04:27 PM, Vincent Guittot wrote: > On 8 June 2017 at 09:55, Dietmar Eggemann wrote: Hi Vincent, Thanks for the review! [...] >> @@ -225,8 +265,14 @@ static int __init register_cpufreq_notifier(void) >> >> cpumask_copy(cpus_to_visit, cpu_possible_mask); >> >> -

Re: [PATCH 2/6] drivers base/arch_topology: frequency-invariant load-tracking support

On 8 June 2017 at 09:55, Dietmar Eggemann wrote: > Implements an arch-specific frequency-scaling function > topology_get_freq_scale() which provides the following frequency > scaling factor: > > current_freq(cpu) << SCHED_CAPACITY_SHIFT / max_supported_freq(cpu) > >

Re: [PATCH 2/6] drivers base/arch_topology: frequency-invariant load-tracking support

On 8 June 2017 at 09:55, Dietmar Eggemann wrote: > Implements an arch-specific frequency-scaling function > topology_get_freq_scale() which provides the following frequency > scaling factor: > > current_freq(cpu) << SCHED_CAPACITY_SHIFT / max_supported_freq(cpu) > > The debug output in

[PATCH 2/6] drivers base/arch_topology: frequency-invariant load-tracking support

Implements an arch-specific frequency-scaling function topology_get_freq_scale() which provides the following frequency scaling factor: current_freq(cpu) << SCHED_CAPACITY_SHIFT / max_supported_freq(cpu) The debug output in init_cpu_capacity_callback() has been changed to be able to

[PATCH 2/6] drivers base/arch_topology: frequency-invariant load-tracking support

Implements an arch-specific frequency-scaling function topology_get_freq_scale() which provides the following frequency scaling factor: current_freq(cpu) << SCHED_CAPACITY_SHIFT / max_supported_freq(cpu) The debug output in init_cpu_capacity_callback() has been changed to be able to