[PATCH 3 2/6] sched: Record the current active power savings level

From: Gautham R Shenoy
Date: Wed Mar 18 2009 - 05:23:17 EST


The current active power savings level of a system is defined as the
maximum of the sched_mc_power_savings and the sched_smt_power_savings.

The decisions during power-aware loadbalancing, depend on this value.

Record this value in a read mostly global variable instead of having to
compute it everytime.

Signed-off-by: Gautham R Shenoy <ego@xxxxxxxxxx>
Cc: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
---

include/linux/sched.h | 1 +
kernel/sched.c | 8 ++++++--
kernel/sched_fair.c | 2 +-
3 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 37fecf7..7dc8aea 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -793,6 +793,7 @@ enum powersavings_balance_level {
};

extern int sched_mc_power_savings, sched_smt_power_savings;
+extern enum powersavings_balance_level active_power_savings_level;

enum sched_domain_level {
SD_LV_NONE = 0,
diff --git a/kernel/sched.c b/kernel/sched.c
index 8e2558c..407ee03 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -3398,7 +3398,7 @@ out_balanced:

if (this == group_leader && group_leader != group_min) {
*imbalance = min_load_per_task;
- if (sched_mc_power_savings >= POWERSAVINGS_BALANCE_WAKEUP) {
+ if (active_power_savings_level >= POWERSAVINGS_BALANCE_WAKEUP) {
cpu_rq(this_cpu)->rd->sched_mc_preferred_wakeup_cpu =
cpumask_first(sched_group_cpus(group_leader));
}
@@ -3683,7 +3683,7 @@ redo:
!test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
return -1;

- if (sched_mc_power_savings < POWERSAVINGS_BALANCE_WAKEUP)
+ if (active_power_savings_level < POWERSAVINGS_BALANCE_WAKEUP)
return -1;

if (sd->nr_balance_failed++ < 2)
@@ -7206,6 +7206,8 @@ static void sched_domain_node_span(int node, struct cpumask *span)
#endif /* CONFIG_NUMA */

int sched_smt_power_savings = 0, sched_mc_power_savings = 0;
+/* Records the currently active power savings level */
+enum powersavings_balance_level __read_mostly active_power_savings_level;

/*
* The cpus mask in sched_group and sched_domain hangs off the end.
@@ -8040,6 +8042,8 @@ static ssize_t sched_power_savings_store(const char *buf, size_t count, int smt)
sched_smt_power_savings = level;
else
sched_mc_power_savings = level;
+ active_power_savings_level = max(sched_smt_power_savings,
+ sched_mc_power_savings);

arch_reinit_sched_domains();

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 0566f2a..a3583c6 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1054,7 +1054,7 @@ static int wake_idle(int cpu, struct task_struct *p)
chosen_wakeup_cpu =
cpu_rq(this_cpu)->rd->sched_mc_preferred_wakeup_cpu;

- if (sched_mc_power_savings >= POWERSAVINGS_BALANCE_WAKEUP &&
+ if (active_power_savings_level >= POWERSAVINGS_BALANCE_WAKEUP &&
idle_cpu(cpu) && idle_cpu(this_cpu) &&
p->mm && !(p->flags & PF_KTHREAD) &&
cpu_isset(chosen_wakeup_cpu, p->cpus_allowed))

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/