Liang Chen 51d4aae73f sched/fair: optimize scheduler for performance ... 1. init util_avg of new task to half the util of big core. 2. treat task wait time as busy time. 3. do not put task to the cpu whose max util can not fit the task. 4. boost cpufreq when a task is wakeup. if prefer powersave, we can disable this optimization by command: echo 0 > /proc/sys/kernel/sched_performance_bias Change-Id: I937d1cc2295645a1d044e0735ef575b6507bb752 Signed-off-by: Liang Chen <cl@rock-chips.com>		2020-07-16 14:50:45 +08:00
..
autogroup.h
clock.h
coredump.h
cpufreq.h	This is the 4.19.92 stable release	2019-12-31 17:11:54 +01:00
cputime.h
deadline.h
debug.h
hotplug.h
idle.h
init.h
isolation.h
jobctl.h
loadavg.h
mm.h	sched/membarrier: Call sync_core only before usermode for same mm	2019-10-11 18:21:21 +02:00
nohz.h
numa_balancing.h	sched/fair: Don't free p->numa_faults with concurrent readers	2019-08-04 09:30:56 +02:00
prio.h
rt.h
signal.h	ptrace: take into account saved_sigmask in PTRACE{GET,SET}SIGMASK	2019-05-04 09:20:22 +02:00
smt.h
stat.h
sysctl.h	sched/fair: optimize scheduler for performance	2020-07-16 14:50:45 +08:00
task.h	fork: fix some -Wmissing-prototypes warnings	2019-12-05 09:21:04 +01:00
task_stack.h
topology.h	UPSTREAM: sched/uclamp: Add CPU's clamp buckets refcounting	2020-02-01 14:39:37 +00:00
user.h
wake_q.h
xacct.h