When task is migrated from CPU_A to CPU_B, scheduler will decrease
the task's load/util from the task's cfs_rq and also add them into
migrated cfs_rq. But if kernel enables CONFIG_FAIR_GROUP_SCHED then this
cfs_rq is not the same one with cpu's cfs_rq. As a result, after task is
migrated to CPU_B, then CPU_A still have task's stale value for
load/util; on the other hand CPU_B also cannot reflect new load/util
which introduced by the task.
So this patch is to operate the task's load/util to cpu's cfs_rq, so
finally cpu's cfs_rq can really reflect task's migration.
Signed-off-by: Leo Yan <leo.yan(a)linaro.org>
---
kernel/sched/fair.c | 27 +++++++++++++++++++++++++++
1 file changed, 27 insertions(+)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0fe30e6..10ca1a9 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2825,12 +2825,24 @@ static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq);
static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
{
struct sched_avg *sa = &cfs_rq->avg;
+ struct sched_avg *cpu_sa = NULL;
int decayed, removed = 0;
+ int cpu = cpu_of(rq_of(cfs_rq));
+
+ if (&cpu_rq(cpu)->cfs != cfs_rq)
+ cpu_sa = &cpu_rq(cpu)->cfs.avg;
if (atomic_long_read(&cfs_rq->removed_load_avg)) {
s64 r = atomic_long_xchg(&cfs_rq->removed_load_avg, 0);
sa->load_avg = max_t(long, sa->load_avg - r, 0);
sa->load_sum = max_t(s64, sa->load_sum - r * LOAD_AVG_MAX, 0);
+
+ if (cpu_sa) {
+ cpu_sa->load_avg = max_t(long, cpu_sa->load_avg - r, 0);
+ cpu_sa->load_sum = max_t(s64,
+ cpu_sa->load_sum - r * LOAD_AVG_MAX, 0);
+ }
+
removed = 1;
}
@@ -2838,6 +2850,12 @@ static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
long r = atomic_long_xchg(&cfs_rq->removed_util_avg, 0);
sa->util_avg = max_t(long, sa->util_avg - r, 0);
sa->util_sum = max_t(s32, sa->util_sum - r * LOAD_AVG_MAX, 0);
+
+ if (cpu_sa) {
+ cpu_sa->util_avg = max_t(long, cpu_sa->util_avg - r, 0);
+ cpu_sa->util_sum = max_t(s64,
+ cpu_sa->util_sum - r * LOAD_AVG_MAX, 0);
+ }
}
decayed = __update_load_avg(now, cpu_of(rq_of(cfs_rq)), sa,
@@ -2896,6 +2914,8 @@ static inline void update_load_avg(struct sched_entity *se, int update_tg)
static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
+ int cpu = cpu_of(rq_of(cfs_rq));
+
if (!sched_feat(ATTACH_AGE_LOAD))
goto skip_aging;
@@ -2919,6 +2939,13 @@ skip_aging:
cfs_rq->avg.load_sum += se->avg.load_sum;
cfs_rq->avg.util_avg += se->avg.util_avg;
cfs_rq->avg.util_sum += se->avg.util_sum;
+
+ if (&cpu_rq(cpu)->cfs != cfs_rq) {
+ cpu_rq(cpu)->cfs.avg.load_avg += se->avg.load_avg;
+ cpu_rq(cpu)->cfs.avg.load_sum += se->avg.load_sum;
+ cpu_rq(cpu)->cfs.avg.util_avg += se->avg.util_avg;
+ cpu_rq(cpu)->cfs.avg.util_sum += se->avg.util_sum;
+ }
}
static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
--
1.9.1
When log CPU's load and utilization, should directly use CPU's cfs_rq
for tracking. If use the task's cfs_rq, it may introduce error value
by using task_group's cfs_rq but not real CPU's cfs_rq.
Signed-off-by: Leo Yan <leo.yan(a)linaro.org>
---
kernel/sched/fair.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 6ac9ea3..26f3f2d 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2825,7 +2825,7 @@ static inline void update_load_avg(struct sched_entity *se, int update_tg)
if (entity_is_task(se))
trace_sched_load_avg_task(task_of(se), &se->avg);
- trace_sched_load_avg_cpu(cpu, cfs_rq);
+ trace_sched_load_avg_cpu(cpu, &cpu_rq(cpu)->cfs);
}
static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
--
1.9.1
