linux/kernel/sched
Vincent Guittot f6cad8df6b sched/fair: Fix imbalance due to CPU affinity
The load_balance() has a dedicated mecanism to detect when an imbalance
is due to CPU affinity and must be handled at parent level. In this case,
the imbalance field of the parent's sched_group is set.

The description of sg_imbalanced() gives a typical example of two groups
of 4 CPUs each and 4 tasks each with a cpumask covering 1 CPU of the first
group and 3 CPUs of the second group. Something like:

	{ 0 1 2 3 } { 4 5 6 7 }
	        *     * * *

But the load_balance fails to fix this UC on my octo cores system
made of 2 clusters of quad cores.

Whereas the load_balance is able to detect that the imbalanced is due to
CPU affinity, it fails to fix it because the imbalance field is cleared
before letting parent level a chance to run. In fact, when the imbalance is
detected, the load_balance reruns without the CPU with pinned tasks. But
there is no other running tasks in the situation described above and
everything looks balanced this time so the imbalance field is immediately
cleared.

The imbalance field should not be cleared if there is no other task to move
when the imbalance is detected.

Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/1561996022-28829-1-git-send-email-vincent.guittot@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2019-07-25 15:51:52 +02:00
..
autogroup.c sched/autogroup: Make autogroup_path() always available 2019-06-24 19:23:40 +02:00
autogroup.h sched/headers: Simplify and clean up header usage in the scheduler 2018-03-04 12:39:29 +01:00
clock.c treewide: Add SPDX license identifier for missed files 2019-05-21 10:50:45 +02:00
completion.c sched/Documentation: Update wake_up() & co. memory-barrier guarantees 2018-07-17 09:30:34 +02:00
core.c sched/core: Fix preempt warning in ttwu 2019-07-13 11:23:27 +02:00
cpuacct.c sched/headers: Simplify and clean up header usage in the scheduler 2018-03-04 12:39:29 +01:00
cpudeadline.c Linux 5.2-rc5 2019-06-17 12:12:27 +02:00
cpudeadline.h sched/headers: Simplify and clean up header usage in the scheduler 2018-03-04 12:39:29 +01:00
cpufreq_schedutil.c sched/uclamp: Add uclamp support to energy_compute() 2019-06-24 19:23:49 +02:00
cpufreq.c sched/cpufreq: Annotate cpufreq_update_util_data pointer with __rcu 2019-04-03 12:34:31 +02:00
cpupri.c Linux 5.2-rc5 2019-06-17 12:12:27 +02:00
cpupri.h sched/headers: Simplify and clean up header usage in the scheduler 2018-03-04 12:39:29 +01:00
cputime.c treewide: Add SPDX license identifier for missed files 2019-05-21 10:50:45 +02:00
deadline.c It's been a relatively busy cycle for docs: 2019-07-09 12:34:26 -07:00
debug.c Linux 5.2-rc6 2019-06-24 19:19:53 +02:00
fair.c sched/fair: Fix imbalance due to CPU affinity 2019-07-25 15:51:52 +02:00
features.h sched/fair: Replace source_load() & target_load() with weighted_cpuload() 2019-06-03 11:49:39 +02:00
idle.c treewide: Add SPDX license identifier for missed files 2019-05-21 10:50:45 +02:00
isolation.c KVM: LAPIC: Inject timer interrupt via posted interrupt 2019-07-20 09:00:40 +02:00
loadavg.c sched: loadavg: make calc_load_n() public 2018-10-26 16:26:32 -07:00
Makefile psi: pressure stall information for CPU, memory, and IO 2018-10-26 16:26:32 -07:00
membarrier.c treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 157 2019-05-30 11:26:37 -07:00
pelt.c sched/debug: Add new tracepoint to track PELT at se level 2019-06-24 19:23:42 +02:00
pelt.h sched/topology: Remove unused 'sd' parameter from arch_scale_cpu_capacity() 2019-06-24 19:23:39 +02:00
psi.c kernel/sched/psi.c: expose pressure metrics on root cgroup 2019-05-14 19:52:48 -07:00
rt.c sched/cpufreq, sched/uclamp: Add clamps for FAIR and RT tasks 2019-06-24 19:23:48 +02:00
sched-pelt.h sched/fair: Fix "runnable_avg_yN_inv" not used warnings 2019-06-17 12:15:58 +02:00
sched.h sched/uclamp: Add uclamp support to energy_compute() 2019-06-24 19:23:49 +02:00
stats.c proc: introduce proc_create_seq{,_data} 2018-05-16 07:23:35 +02:00
stats.h psi: make disabling/enabling easier for vendor kernels 2018-11-30 14:56:14 -08:00
stop_task.c sched: Clean up and harmonize the coding style of the scheduler code base 2018-03-03 15:50:21 +01:00
swait.c kernel/sched/: remove caller signal_pending branch predictions 2019-01-04 13:13:48 -08:00
topology.c sched/topology: Remove unused 'sd' parameter from arch_scale_cpu_capacity() 2019-06-24 19:23:39 +02:00
wait_bit.c treewide: Add SPDX license identifier for missed files 2019-05-21 10:50:45 +02:00
wait.c sched/wait: Deduplicate code with do-while 2019-06-24 19:23:40 +02:00