Vincent Guittot b4c9c9f156 sched/fair: Prefer prev cpu in asymmetric wakeup path ... During fast wakeup path, scheduler always check whether local or prev cpus are good candidates for the task before looking for other cpus in the domain. With commit b7a331615d ("sched/fair: Add asymmetric CPU capacity wakeup scan") the heterogenous system gains a dedicated path but doesn't try to reuse prev cpu whenever possible. If the previous cpu is idle and belong to the LLC domain, we should check it 1st before looking for another cpu because it stays one of the best candidate and this also stabilizes task placement on the system. This change aligns asymmetric path behavior with symmetric one and reduces cases where the task migrates across all cpus of the sd_asym_cpucapacity domains at wakeup. This change does not impact normal EAS mode but only the overloaded case or when EAS is not used. - On hikey960 with performance governor (EAS disable) ./perf bench sched pipe -T -l 50000 mainline w/ patch # migrations 999364 0 ops/sec 149313(+/-0.28%) 182587(+/- 0.40) +22% - On hikey with performance governor ./perf bench sched pipe -T -l 50000 mainline w/ patch # migrations 0 0 ops/sec 47721(+/-0.76%) 47899(+/- 0.56) +0.4% According to test on hikey, the patch doesn't impact symmetric system compared to current implementation (only tested on arm64) Also read the uclamped value of task's utilization at most twice instead instead each time we compare task's utilization with cpu's capacity. Fixes: b7a331615d ("sched/fair: Add asymmetric CPU capacity wakeup scan") Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Tested-by: Dietmar Eggemann <dietmar.eggemann@arm.com> Reviewed-by: Valentin Schneider <valentin.schneider@arm.com> Link: https://lkml.kernel.org/r/20201029161824.26389-1-vincent.guittot@linaro.org		2020-11-10 18:38:48 +01:00
..
autogroup.c
autogroup.h
clock.c
completion.c
core.c	sched/features: Fix !CONFIG_JUMP_LABEL case	2020-10-14 19:55:46 +02:00
cpuacct.c
cpudeadline.c
cpudeadline.h
cpufreq_schedutil.c	Power management updates for 5.9-rc1	2020-08-03 20:28:08 -07:00
cpufreq.c
cpupri.c
cpupri.h
cputime.c
deadline.c	sched/deadline: Unthrottle PI boosted threads while enqueuing	2020-10-03 16:30:53 +02:00
debug.c	sched/topology: Move sd_flag_debug out of #ifdef CONFIG_SYSCTL	2020-09-09 10:09:03 +02:00
fair.c	sched/fair: Prefer prev cpu in asymmetric wakeup path	2020-11-10 18:38:48 +01:00
features.h	sched/rt: Disable RT_RUNTIME_SHARE by default	2020-09-25 14:23:24 +02:00
idle.c	cpuidle: Move trace_cpu_idle() into generic code	2020-08-26 12:41:54 +02:00
isolation.c
loadavg.c	sched: nohz: stop passing around unused "ticks" parameter.	2020-07-22 10:22:04 +02:00
Makefile
membarrier.c	rseq/membarrier: Add MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ	2020-09-25 14:23:27 +02:00
pelt.c	sched: Add a tracepoint to track rq->nr_running	2020-07-08 11:39:02 +02:00
pelt.h
psi.c
rt.c	sched: Remove struct sched_class::next field	2020-06-25 13:45:44 +02:00
sched-pelt.h
sched.h	sched/features: Fix !CONFIG_JUMP_LABEL case	2020-10-14 19:55:46 +02:00
smp.h
stats.c
stats.h
stop_task.c	sched: Remove struct sched_class::next field	2020-06-25 13:45:44 +02:00
swait.c
topology.c	Scheduler changes for v5.10:	2020-10-12 12:56:01 -07:00
wait_bit.c
wait.c	list: add "list_del_init_careful()" to go with "list_empty_careful()"	2020-08-02 20:39:44 -07:00