Re: [PATCH 0/5] Rework system pressure interface to the scheduler

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 





On 12/14/23 08:32, Lukasz Luba wrote:


On 12/14/23 08:29, Vincent Guittot wrote:
On Thu, 14 Dec 2023 at 09:21, Lukasz Luba <lukasz.luba@xxxxxxx> wrote:

Hi Vincent,

I've been waiting for this feature, thanks!


On 12/12/23 14:27, Vincent Guittot wrote:
Following the consolidation and cleanup of CPU capacity in [1], this serie reworks how the scheduler gets the pressures on CPUs. We need to take into account all pressures applied by cpufreq on the compute capacity of a CPU
for dozens of ms or more and not only cpufreq cooling device or HW
mitigiations. we split the pressure applied on CPU's capacity in 2 parts:
- one from cpufreq and freq_qos
- one from HW high freq mitigiation.

The next step will be to add a dedicated interface for long standing
capping of the CPU capacity (i.e. for seconds or more) like the
scaling_max_freq of cpufreq sysfs. The latter is already taken into
account by this serie but as a temporary pressure which is not always the
best choice when we know that it will happen for seconds or more.

[1] https://lore.kernel.org/lkml/20231211104855.558096-1-vincent.guittot@xxxxxxxxxx/

Vincent Guittot (4):
    cpufreq: Add a cpufreq pressure feedback for the scheduler
    sched: Take cpufreq feedback into account
    thermal/cpufreq: Remove arch_update_thermal_pressure()
    sched: Rename arch_update_thermal_pressure into
      arch_update_hw_pressure

   arch/arm/include/asm/topology.h               |  6 +--
   arch/arm64/include/asm/topology.h             |  6 +--
   drivers/base/arch_topology.c                  | 26 ++++-----
   drivers/cpufreq/cpufreq.c                     | 48 +++++++++++++++++
   drivers/cpufreq/qcom-cpufreq-hw.c             |  4 +-
   drivers/thermal/cpufreq_cooling.c             |  3 --
   include/linux/arch_topology.h                 |  8 +--
   include/linux/cpufreq.h                       | 10 ++++
   include/linux/sched/topology.h                |  8 +--
   .../{thermal_pressure.h => hw_pressure.h}     | 14 ++---
   include/trace/events/sched.h                  |  2 +-
   init/Kconfig                                  | 12 ++---
   kernel/sched/core.c                           |  8 +--
   kernel/sched/fair.c                           | 53 ++++++++++---------
   kernel/sched/pelt.c                           | 18 +++----
   kernel/sched/pelt.h                           | 16 +++---
   kernel/sched/sched.h                          |  4 +-
   17 files changed, 152 insertions(+), 94 deletions(-)
   rename include/trace/events/{thermal_pressure.h => hw_pressure.h} (55%)


I would like to test it, but something worries me. Why there is 0/5 in
this subject and only 4 patches?

I removed a patch from the series but copied/pasted the cover letter
subject without noticing the /5 instead of /4

OK



Could you tell me your base branch that I can apply this, please?

It applies on top of tip/sched/core + [1]
and you can find it here:
https://git.linaro.org/people/vincent.guittot/kernel.git/log/?h=sched/system-pressure

Thanks for the info and handy link.


I've tested your patches with: DTPM/PowerCap + thermal gov + cpufreq
sysfs scaling_max_freq. It works fine all my cases (couldn't cause
any issues). If you like to test DTPM you will need 2 fixed pending
in Rafael's tree.

So, I'm looking for a your v2 to continue reviewing it.




[Index of Archives]     [Linux ARM Kernel]     [Linux ARM]     [Linux Omap]     [Fedora ARM]     [Linux for Sparc]     [IETF Annouce]     [Security]     [Bugtraq]     [Linux MIPS]     [ECOS]     [Asterisk Internet PBX]     [Linux API]

  Powered by Linux