@@ -4271,11 +4271,13 @@ static void find_max_util(const struct cpumask *mask, int cpu, int util,
* + 1-curr_util(sg) * idle_power(sg)
* energy_after = new_util(sg) * busy_power(sg)
* + 1-new_util(sg) * idle_power(sg)
+ * + new_util(sg) * task_wakeups
+ * * wakeup_energy(sg)
* energy_diff += energy_before - energy_after
* }
*
*/
-static int energy_diff_util(int cpu, int util)
+static int energy_diff_util(int cpu, int util, int wakeups)
{
struct sched_domain *sd;
int i;
@@ -4368,7 +4370,8 @@ static int energy_diff_util(int cpu, int util)
* The utilization change has no impact at this level (or any
* parent level).
*/
- if (aff_util_bef == aff_util_aft && curr_cap_idx == new_cap_idx)
+ if (aff_util_bef == aff_util_aft && curr_cap_idx == new_cap_idx
+ && unused_util_aft < 100)
goto unlock;
/* Energy before */
@@ -4380,6 +4383,13 @@ static int energy_diff_util(int cpu, int util)
energy_diff += (aff_util_aft*new_state->power)/new_state->cap;
energy_diff += (unused_util_aft * sge->idle_power)
/new_state->cap;
+ /*
+ * Estimate how many of the wakeups that happens while cpu is
+ * idle assuming they are uniformly distributed. Ignoring
+ * wakeups caused by other tasks.
+ */
+ energy_diff += (wakeups * sge->wakeup_energy >> 10)
+ * unused_util_aft/new_state->cap;
}
/*
@@ -4410,6 +4420,8 @@ static int energy_diff_util(int cpu, int util)
energy_diff += (aff_util_aft*new_state->power)/new_state->cap;
energy_diff += (unused_util_aft * sse->idle_power)
/new_state->cap;
+ energy_diff += (wakeups * sse->wakeup_energy >> 10)
+ * unused_util_aft/new_state->cap;
}
unlock:
@@ -4420,7 +4432,8 @@ unlock:
static int energy_diff_task(int cpu, struct task_struct *p)
{
- return energy_diff_util(cpu, p->se.avg.load_avg_contrib);
+ return energy_diff_util(cpu, p->se.avg.load_avg_contrib,
+ p->se.avg.wakeup_avg_sum);
}
#else
The energy cost of waking a cpu and sending it back to sleep can be quite significant for short running frequently waking tasks if placed on an idle cpu in a deep sleep state. By factoring task wakeups in such tasks can be placed on cpus where the wakeup energy cost is lower. For example, partly utilized cpus in a shallower idle state, or cpus in a cluster/die that is already awake. Current cpu utilization of the target cpu is factored in guess how many task wakeups that translate into cpu wakeups (idle exits). It is a very naive approach, but it is virtually impossible to get an accurate estimate. wake_energy(task) = unused_util(cpu) * wakeups(task) * wakeup_energy(cpu) There is no per cpu wakeup tracking, so we can't estimate the energy savings when removing tasks from a cpu. It is also nearly impossible to figure out which task is the cause of cpu wakeups if multiple tasks are scheduled on the same cpu. Support for multiple idle-states per sched_group (e.g. WFI and core shutdown on ARM) is not implemented yet. wakeup_energy in struct sched_energy needs to be a table instead and cpuidle needs to tells what the most likely state is. Signed-off-by: Morten Rasmussen <morten.rasmussen@arm.com> --- kernel/sched/fair.c | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-)