lkml.org 
[lkml]   [2020]   [Feb]   [3]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
SubjectRe: [Patch v9 8/8] arm64: Enable averaging of thermal pressure for arm64 based SoCs
From
Date
On 28.01.20 23:36, Thara Gopinath wrote:
> Enable CONFIG_HAVE_SCHED_THERMAL_PRESSURE in arm64 defconfig.
>
> Signed-off-by: Thara Gopinath <thara.gopinath@linaro.org>
> ---
> arch/arm64/configs/defconfig | 1 +
> 1 file changed, 1 insertion(+)
>
> diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
> index 0565a61..7a8145b 100644
> --- a/arch/arm64/configs/defconfig
> +++ b/arch/arm64/configs/defconfig
> @@ -5,6 +5,7 @@ CONFIG_NO_HZ_IDLE=y
> CONFIG_HIGH_RES_TIMERS=y
> CONFIG_PREEMPT=y
> CONFIG_IRQ_TIME_ACCOUNTING=y
> +CONFIG_HAVE_SCHED_THERMAL_PRESSURE=y

I thought about this a bit more and maybe it's not a good idea to enable
this by default. An erroneous thermal setup could have bad influence on
the CPU capacities and hence on the performance without people
understanding the cause of it.
If they have to actively enable it, chances are higher that they also
try to understand how higher thermal-cpufreq-X cooling states lead to
CPU capacity reduction and possibly inversion (big-LITTLE swap).

So if the thermal pressure feature is guarded by
CONFIG_HAVE_SCHED_THERMAL_PRESSURE the thermal pressure related code in
arch_topology.c (thermal_pressure, arch_set_thermal_pressure,
topology_get_thermal_pressure) should too. Saves some text and data of
arch_topology.o. Moreover Arm32 and Arm64 will be handled equally.

\
 
 \ /
  Last update: 2020-02-03 10:00    [W:0.133 / U:1.400 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site