sched: Add struct rq::cpu_capacity_orig

This new field 'cpu_capacity_orig' reflects the original capacity of a CPU
before being altered by rt tasks and/or IRQ

The cpu_capacity_orig will be used:

  - to detect when the capacity of a CPU has been noticeably reduced so we can
    trig load balance to look for a CPU with better capacity. As an example, we
    can detect when a CPU handles a significant amount of irq
    (with CONFIG_IRQ_TIME_ACCOUNTING) but this CPU is seen as an idle CPU by
    scheduler whereas CPUs, which are really idle, are available.

  - evaluate the available capacity for CFS tasks

Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Kamalesh Babulal <kamalesh@linux.vnet.ibm.com>
Acked-by: Morten Rasmussen <morten.rasmussen@arm.com>
Cc: Morten.Rasmussen@arm.com
Cc: dietmar.eggemann@arm.com
Cc: efault@gmx.de
Cc: linaro-kernel@lists.linaro.org
Cc: nicolas.pitre@linaro.org
Cc: preeti@linux.vnet.ibm.com
Cc: riel@redhat.com
Link: http://lkml.kernel.org/r/1425052454-25797-7-git-send-email-vincent.guittot@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index feda520..7022e90 100644 (file)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7216,7 +7216,7 @@ void __init sched_init(void)
 #ifdef CONFIG_SMP
                rq->sd = NULL;
                rq->rd = NULL;
-               rq->cpu_capacity = SCHED_CAPACITY_SCALE;
+               rq->cpu_capacity = rq->cpu_capacity_orig = SCHED_CAPACITY_SCALE;
                rq->post_schedule = 0;
                rq->active_balance = 0;
                rq->next_balance = jiffies;

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index dc7c693..10f84c3 100644 (file)
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4363,6 +4363,11 @@ static unsigned long capacity_of(int cpu)
        return cpu_rq(cpu)->cpu_capacity;
 }
 
+static unsigned long capacity_orig_of(int cpu)
+{
+       return cpu_rq(cpu)->cpu_capacity_orig;
+}
+
 static unsigned long cpu_avg_load_per_task(int cpu)
 {
        struct rq *rq = cpu_rq(cpu);
@@ -6040,6 +6045,7 @@ static void update_cpu_capacity(struct sched_domain *sd, int cpu)
 
        capacity >>= SCHED_CAPACITY_SHIFT;
 
+       cpu_rq(cpu)->cpu_capacity_orig = capacity;
        sdg->sgc->capacity_orig = capacity;
 
        capacity *= scale_rt_capacity(cpu);
@@ -6094,7 +6100,7 @@ void update_group_capacity(struct sched_domain *sd, int cpu)
                         * Runtime updates will correct capacity_orig.
                         */
                        if (unlikely(!rq->sd)) {
-                               capacity_orig += capacity_of(cpu);
+                               capacity_orig += capacity_orig_of(cpu);
                                capacity += capacity_of(cpu);
                                continue;
                        }

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 3600002..be56dfd 100644 (file)
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -615,6 +615,7 @@ struct rq {
        struct sched_domain *sd;
 
        unsigned long cpu_capacity;
+       unsigned long cpu_capacity_orig;
 
        unsigned char idle_balance;
        /* For active balancing */