Re: [RFC PATCH V2 01/19] sched/power: Remove cpu idle state selection and cpu frequency tuning

[Nicolas Pitre]

On Mon, 11 Aug 2014, Preeti U Murthy wrote:

> As a first step towards improving the power awareness of the scheduler,
> this patch enables a "dumb" state where all power management is turned off.
> Whatever additionally we put into the kernel for cpu power management must
> do better than this in terms of performance as well as powersavings.
> This will enable us to benchmark and optimize the power aware scheduler
> from scratch.If we are to benchmark it against the performance of the
> existing design, we will get sufficiently distracted by the performance
> numbers and get steered away from a sane design.

I understand your goal here, but people *will* compare performance 
between the old and the new design anyway.  So I think it would be a 
better approach to simply let the existing code be and create a new 
scheduler-based governor that can be swapped with the existing ones at 
run time.  Eventually we'll want average users to test and compare this, 
and asking them to recompile a second kernel and reboot between them 
might get unwieldy to many people.

And by allowing both to coexist at run time, we're making sure both the 
old and the new code are built helping not breaking the old code.  And 
that will also cut down on the number of #ifdefs in many places.

In other words, CONFIG_SCHED_POWER is needed to select the scheduler 
based governor but it shouldn't force the existing code disabled.


> Signed-off-by: Preeti U Murthy <preeti@xxxxxxxxxxxxxxxxxx>
> ---
> 
>  arch/powerpc/Kconfig                   |    1 +
>  arch/powerpc/platforms/powernv/Kconfig |   12 ++++++------
>  drivers/cpufreq/Kconfig                |    2 ++
>  drivers/cpuidle/Kconfig                |    2 ++
>  kernel/Kconfig.sched                   |   11 +++++++++++
>  5 files changed, 22 insertions(+), 6 deletions(-)
>  create mode 100644 kernel/Kconfig.sched
> 
> diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
> index 80b94b0..b7fe36a 100644
> --- a/arch/powerpc/Kconfig
> +++ b/arch/powerpc/Kconfig
> @@ -301,6 +301,7 @@ config HIGHMEM
>  
>  source kernel/Kconfig.hz
>  source kernel/Kconfig.preempt
> +source kernel/Kconfig.sched
>  source "fs/Kconfig.binfmt"
>  
>  config HUGETLB_PAGE_SIZE_VARIABLE
> diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig
> index 45a8ed0..b0ef8b1 100644
> --- a/arch/powerpc/platforms/powernv/Kconfig
> +++ b/arch/powerpc/platforms/powernv/Kconfig
> @@ -11,12 +11,12 @@ config PPC_POWERNV
>  	select PPC_UDBG_16550
>  	select PPC_SCOM
>  	select ARCH_RANDOM
> -	select CPU_FREQ
> -	select CPU_FREQ_GOV_PERFORMANCE
> -	select CPU_FREQ_GOV_POWERSAVE
> -	select CPU_FREQ_GOV_USERSPACE
> -	select CPU_FREQ_GOV_ONDEMAND
> -	select CPU_FREQ_GOV_CONSERVATIVE
> +	select CPU_FREQ if !SCHED_POWER
> +	select CPU_FREQ_GOV_PERFORMANCE if CPU_FREQ
> +	select CPU_FREQ_GOV_POWERSAVE if CPU_FREQ
> +	select CPU_FREQ_GOV_USERSPACE if CPU_FREQ
> +	select CPU_FREQ_GOV_ONDEMAND if CPU_FREQ
> +	select CPU_FREQ_GOV_CONSERVATIVE if CPU_FREQ
>  	select PPC_DOORBELL
>  	default y
>  
> diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig
> index ffe350f..8976fd6 100644
> --- a/drivers/cpufreq/Kconfig
> +++ b/drivers/cpufreq/Kconfig
> @@ -2,6 +2,7 @@ menu "CPU Frequency scaling"
>  
>  config CPU_FREQ
>  	bool "CPU Frequency scaling"
> +	depends on !SCHED_POWER
>  	help
>  	  CPU Frequency scaling allows you to change the clock speed of 
>  	  CPUs on the fly. This is a nice method to save power, because 
> @@ -12,6 +13,7 @@ config CPU_FREQ
>  	  (see below) after boot, or use a userspace tool.
>  
>  	  For details, take a look at <file:Documentation/cpu-freq>.
> +	  This feature will turn off if power aware scheduling is enabled.
>  
>  	  If in doubt, say N.
>  
> diff --git a/drivers/cpuidle/Kconfig b/drivers/cpuidle/Kconfig
> index 32748c3..2c4ac79 100644
> --- a/drivers/cpuidle/Kconfig
> +++ b/drivers/cpuidle/Kconfig
> @@ -3,6 +3,7 @@ menu "CPU Idle"
>  config CPU_IDLE
>  	bool "CPU idle PM support"
>  	default y if ACPI || PPC_PSERIES
> +	depends on !SCHED_POWER
>  	select CPU_IDLE_GOV_LADDER if (!NO_HZ && !NO_HZ_IDLE)
>  	select CPU_IDLE_GOV_MENU if (NO_HZ || NO_HZ_IDLE)
>  	help
> @@ -11,6 +12,7 @@ config CPU_IDLE
>  	  governors that can be swapped during runtime.
>  
>  	  If you're using an ACPI-enabled platform, you should say Y here.
> +	  This feature will turn off if power aware scheduling is enabled.
>  
>  if CPU_IDLE
>  
> diff --git a/kernel/Kconfig.sched b/kernel/Kconfig.sched
> new file mode 100644
> index 0000000..374454c
> --- /dev/null
> +++ b/kernel/Kconfig.sched
> @@ -0,0 +1,11 @@
> +menu "Power Aware Scheduling"
> +
> +config SCHED_POWER
> +        bool "Power Aware Scheduler"
> +        default n
> +        help
> +           Select this to enable the new power aware scheduler.
> +endmenu
> +
> +
> +
> 
> 
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/