All of lore.kernel.org
 help / color / mirror / Atom feed
* [PATCH v5 0/3] Rework CPU capacity asymmetry detection
@ 2021-05-24 10:16 Beata Michalska
  2021-05-24 10:16 ` [PATCH v5 1/3] sched/core: Introduce SD_ASYM_CPUCAPACITY_FULL sched_domain flag Beata Michalska
                   ` (2 more replies)
  0 siblings, 3 replies; 29+ messages in thread
From: Beata Michalska @ 2021-05-24 10:16 UTC (permalink / raw)
  To: linux-kernel
  Cc: peterz, mingo, juri.lelli, vincent.guittot, valentin.schneider,
	dietmar.eggemann, corbet, rdunlap, linux-doc

As of now, the asym_cpu_capacity_level will try to locate the lowest
topology level where the highest available CPU capacity is being
visible to all CPUs. This works perfectly fine for most of existing
asymmetric designs out there, though for some possible and completely
valid setups, combining different cpu microarchitectures within
clusters, this might not be the best approach, resulting in pointing
at a level, at which some of the domains might not see any asymmetry
at all. This could be problematic for misfit migration and/or energy
aware placement. And as such, for affected platforms it might result
in custom changes to wake-up and CPU selection paths.

As mentioned in the previous version, based on the available sources out there,
one of the potentially affected (by original approach) platforms might be
Exynos 9820/990 with it's 'sliced' LLC(SLC) divided between the two custom (big)
cores and the remaining A75/A55 cores, which seems to be reflected in the
made available dt entries for those platforms.

The following patches rework how the asymmetric detection is being
carried out, allowing pinning the asymmetric topology level to the lowest one,
where full range of CPU capacities is visible to all CPUs within given
sched domain. The asym_cpu_capacity_level will also keep track of those
levels where any scope of asymmetry is being observed, to denote
corresponding sched domains with the SD_ASYM_CPUCAPACITY flag
and to enable misfit migration for those.

In order to distinguish the sched domains with partial vs full range
of CPU capacity asymmetry, new sched domain flag has been introduced:
SD_ASYM_CPUCAPACITY_FULL.

The overall idea of changing the asymmetry detection has been suggested
by Valentin Schneider <valentin.schneider@arm.com>

Verified on (mostly):
    - QEMU (version 4.2.1) with variants of possible asymmetric topologies
	- machine: virt
	- modifying the device-tree 'cpus' node for virt machine:

	qemu-system-aarch64 -kernel $KERNEL_IMG
	    -drive format=qcow2,file=$IMAGE
	    -append 'root=/dev/vda earlycon console=ttyAMA0 sched_debug
	     sched_verbose loglevel=15 kmemleak=on' -m 2G  --nographic
	    -cpu cortex-a57 -machine virt -smp cores=8
	    -machine dumpdtb=$CUSTOM_DTB.dtb

	$KERNEL_PATH/scripts/dtc/dtc -I dtb -O dts $CUSTOM_DTB.dts >
	$CUSTOM_DTB.dtb

	(modify the dts)

	$KERNEL_PATH/scripts/dtc/dtc -I dts -O dtb $CUSTOM_DTB.dts >
	$CUSTOM_DTB.dtb

	qemu-system-aarch64 -kernel $KERNEL_IMG
	    -drive format=qcow2,file=$IMAGE
	    -append 'root=/dev/vda earlycon console=ttyAMA0 sched_debug
	     sched_verbose loglevel=15 kmemleak=on' -m 2G  --nographic
	    -cpu cortex-a57 -machine virt -smp cores=8
	    -machine dtb=$CUSTOM_DTB.dtb

v5:
 - building CPUs list based on their capacity now triggered upon init
   and explicit request from arch specific code to rebuild sched domains
 - detecting asymmetry scope now done directly in sd_init
v4:
 - Based on Peter's idea, reworking asym detection to use per-cpu
   capacity list to serve as base for determining the asym scope
v3:
 - Additional style/doc fixes
v2:
 - Fixed style issues
 - Reworked accessing the cached topology data as suggested by Valentin


Beata Michalska (3):
  sched/core: Introduce SD_ASYM_CPUCAPACITY_FULL sched_domain flag
  sched/topology: Rework CPU capacity asymmetry detection
  sched/doc: Update the CPU capacity asymmetry bits

 Documentation/scheduler/sched-capacity.rst |   6 +-
 Documentation/scheduler/sched-energy.rst   |   2 +-
 include/linux/sched/sd_flags.h             |  10 ++
 kernel/sched/topology.c                    | 194 +++++++++++++--------
 4 files changed, 133 insertions(+), 79 deletions(-)

-- 
2.17.1


^ permalink raw reply	[flat|nested] 29+ messages in thread

end of thread, other threads:[~2021-06-03  9:24 UTC | newest]

Thread overview: 29+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2021-05-24 10:16 [PATCH v5 0/3] Rework CPU capacity asymmetry detection Beata Michalska
2021-05-24 10:16 ` [PATCH v5 1/3] sched/core: Introduce SD_ASYM_CPUCAPACITY_FULL sched_domain flag Beata Michalska
2021-05-24 10:16 ` [PATCH v5 2/3] sched/topology: Rework CPU capacity asymmetry detection Beata Michalska
2021-05-24 18:01   ` Valentin Schneider
2021-05-24 22:55     ` Beata Michalska
2021-05-24 23:19       ` Beata Michalska
2021-05-25  9:53       ` Valentin Schneider
2021-05-25 10:29         ` Beata Michalska
2021-05-26  9:52           ` Dietmar Eggemann
2021-05-26 12:15             ` Beata Michalska
2021-05-26 12:51               ` Beata Michalska
2021-05-26 18:17                 ` Dietmar Eggemann
2021-05-26 21:40                   ` Beata Michalska
2021-05-27 15:08                     ` Dietmar Eggemann
2021-05-27 17:07                       ` Beata Michalska
2021-06-02 17:17                         ` Dietmar Eggemann
2021-06-02 19:48                           ` Beata Michalska
2021-06-03  9:09                             ` Dietmar Eggemann
2021-06-03  9:24                               ` Beata Michalska
2021-05-26 18:17               ` Dietmar Eggemann
2021-05-26 21:43                 ` Beata Michalska
2021-05-27  7:03             ` Peter Zijlstra
2021-05-27 12:22               ` Dietmar Eggemann
2021-05-27 12:32                 ` Beata Michalska
2021-05-25  8:25   ` Dietmar Eggemann
2021-05-25  9:30     ` Beata Michalska
2021-05-25 11:59       ` Dietmar Eggemann
2021-05-25 14:04         ` Beata Michalska
2021-05-24 10:16 ` [PATCH v5 3/3] sched/doc: Update the CPU capacity asymmetry bits Beata Michalska

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.