[tip: sched/core] sched/fair: Take into account runnable_avg to classify group

From: tip-bot2 for Vincent Guittot
Date: Mon Feb 24 2020 - 10:21:27 EST


The following commit has been merged into the sched/core branch of tip:

Commit-ID: 070f5e860ee2bf588c99ef7b4c202451faa48236
Gitweb: https://git.kernel.org/tip/070f5e860ee2bf588c99ef7b4c202451faa48236
Author: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
AuthorDate: Mon, 24 Feb 2020 09:52:19
Committer: Ingo Molnar <mingo@xxxxxxxxxx>
CommitterDate: Mon, 24 Feb 2020 11:36:37 +01:00

sched/fair: Take into account runnable_avg to classify group

Take into account the new runnable_avg signal to classify a group and to
mitigate the volatility of util_avg in face of intensive migration or
new task with random utilization.

Signed-off-by: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
Signed-off-by: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
Reviewed-by: "Dietmar Eggemann <dietmar.eggemann@xxxxxxx>"
Acked-by: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
Cc: Juri Lelli <juri.lelli@xxxxxxxxxx>
Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
Cc: Valentin Schneider <valentin.schneider@xxxxxxx>
Cc: Phil Auld <pauld@xxxxxxxxxx>
Cc: Hillf Danton <hdanton@xxxxxxxx>
Link: https://lore.kernel.org/r/20200224095223.13361-10-mgorman@xxxxxxxxxxxxxxxxxxx
---
kernel/sched/fair.c | 31 ++++++++++++++++++++++++++++++-
1 file changed, 30 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 49b36d6..87521ac 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5469,6 +5469,24 @@ static unsigned long cpu_runnable(struct rq *rq)
return cfs_rq_runnable_avg(&rq->cfs);
}

+static unsigned long cpu_runnable_without(struct rq *rq, struct task_struct *p)
+{
+ struct cfs_rq *cfs_rq;
+ unsigned int runnable;
+
+ /* Task has no contribution or is new */
+ if (cpu_of(rq) != task_cpu(p) || !READ_ONCE(p->se.avg.last_update_time))
+ return cpu_runnable(rq);
+
+ cfs_rq = &rq->cfs;
+ runnable = READ_ONCE(cfs_rq->avg.runnable_avg);
+
+ /* Discount task's runnable from CPU's runnable */
+ lsub_positive(&runnable, p->se.avg.runnable_avg);
+
+ return runnable;
+}
+
static unsigned long capacity_of(int cpu)
{
return cpu_rq(cpu)->cpu_capacity;
@@ -7752,7 +7770,8 @@ struct sg_lb_stats {
unsigned long avg_load; /*Avg load across the CPUs of the group */
unsigned long group_load; /* Total load over the CPUs of the group */
unsigned long group_capacity;
- unsigned long group_util; /* Total utilization of the group */
+ unsigned long group_util; /* Total utilization over the CPUs of the group */
+ unsigned long group_runnable; /* Total runnable time over the CPUs of the group */
unsigned int sum_nr_running; /* Nr of tasks running in the group */
unsigned int sum_h_nr_running; /* Nr of CFS tasks running in the group */
unsigned int idle_cpus;
@@ -7973,6 +7992,10 @@ group_has_capacity(unsigned int imbalance_pct, struct sg_lb_stats *sgs)
if (sgs->sum_nr_running < sgs->group_weight)
return true;

+ if ((sgs->group_capacity * imbalance_pct) <
+ (sgs->group_runnable * 100))
+ return false;
+
if ((sgs->group_capacity * 100) >
(sgs->group_util * imbalance_pct))
return true;
@@ -7998,6 +8021,10 @@ group_is_overloaded(unsigned int imbalance_pct, struct sg_lb_stats *sgs)
(sgs->group_util * imbalance_pct))
return true;

+ if ((sgs->group_capacity * imbalance_pct) <
+ (sgs->group_runnable * 100))
+ return true;
+
return false;
}

@@ -8092,6 +8119,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,

sgs->group_load += cpu_load(rq);
sgs->group_util += cpu_util(i);
+ sgs->group_runnable += cpu_runnable(rq);
sgs->sum_h_nr_running += rq->cfs.h_nr_running;

nr_running = rq->nr_running;
@@ -8367,6 +8395,7 @@ static inline void update_sg_wakeup_stats(struct sched_domain *sd,

sgs->group_load += cpu_load_without(rq, p);
sgs->group_util += cpu_util_without(i, p);
+ sgs->group_runnable += cpu_runnable_without(rq, p);
local = task_running_on_cpu(i, p);
sgs->sum_h_nr_running += rq->cfs.h_nr_running - local;