| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20241202174606.4074512-5-vincent.guittot@linaro.org>
Date: Mon, 2 Dec 2024 18:45:59 +0100
From: Vincent Guittot <vincent.guittot@...aro.org>
To: mingo@...hat.com,
peterz@...radead.org,
juri.lelli@...hat.com,
dietmar.eggemann@....com,
rostedt@...dmis.org,
bsegall@...gle.com,
mgorman@...e.de,
vschneid@...hat.com,
linux-kernel@...r.kernel.org
Cc: kprateek.nayak@....com,
pauld@...hat.com,
efault@....de,
luis.machado@....com,
tj@...nel.org,
void@...ifault.com,
Vincent Guittot <vincent.guittot@...aro.org>
Subject: [PATCH 04/11 v3] sched/fair: Add new cfs_rq.h_nr_runnable
With delayed dequeued feature, a sleeping sched_entity remains queued in
the rq until its lag has elapsed. As a result, it stays also visible
in the statistics that are used to balance the system and in particular
the field cfs.h_nr_queued when the sched_entity is associated to a task.
Create a new h_nr_runnable that tracks only queued and runnable tasks.
Signed-off-by: Vincent Guittot <vincent.guittot@...aro.org>
---
kernel/sched/debug.c | 1 +
kernel/sched/fair.c | 20 ++++++++++++++++++--
kernel/sched/sched.h | 1 +
3 files changed, 20 insertions(+), 2 deletions(-)
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 08d6c2b7caa3..fd711cc4d44c 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -844,6 +844,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
spread = right_vruntime - left_vruntime;
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "spread", SPLIT_NS(spread));
SEQ_printf(m, " .%-30s: %d\n", "nr_running", cfs_rq->nr_running);
+ SEQ_printf(m, " .%-30s: %d\n", "h_nr_runnable", cfs_rq->h_nr_runnable);
SEQ_printf(m, " .%-30s: %d\n", "h_nr_queued", cfs_rq->h_nr_queued);
SEQ_printf(m, " .%-30s: %d\n", "h_nr_delayed", cfs_rq->h_nr_delayed);
SEQ_printf(m, " .%-30s: %d\n", "idle_nr_running",
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0f6dc4d9b15f..46cf1c72598c 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5469,6 +5469,7 @@ static void set_delayed(struct sched_entity *se)
for_each_sched_entity(se) {
struct cfs_rq *cfs_rq = cfs_rq_of(se);
+ cfs_rq->h_nr_runnable--;
cfs_rq->h_nr_delayed++;
if (cfs_rq_throttled(cfs_rq))
break;
@@ -5481,6 +5482,7 @@ static void clear_delayed(struct sched_entity *se)
for_each_sched_entity(se) {
struct cfs_rq *cfs_rq = cfs_rq_of(se);
+ cfs_rq->h_nr_runnable++;
cfs_rq->h_nr_delayed--;
if (cfs_rq_throttled(cfs_rq))
break;
@@ -5933,7 +5935,7 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq)
struct rq *rq = rq_of(cfs_rq);
struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
struct sched_entity *se;
- long queued_delta, idle_task_delta, delayed_delta, dequeue = 1;
+ long queued_delta, runnable_delta, idle_task_delta, delayed_delta, dequeue = 1;
long rq_h_nr_queued = rq->cfs.h_nr_queued;
raw_spin_lock(&cfs_b->lock);
@@ -5965,6 +5967,7 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq)
rcu_read_unlock();
queued_delta = cfs_rq->h_nr_queued;
+ runnable_delta = cfs_rq->h_nr_runnable;
idle_task_delta = cfs_rq->idle_h_nr_running;
delayed_delta = cfs_rq->h_nr_delayed;
for_each_sched_entity(se) {
@@ -5989,6 +5992,7 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq)
idle_task_delta = cfs_rq->h_nr_queued;
qcfs_rq->h_nr_queued -= queued_delta;
+ qcfs_rq->h_nr_runnable -= runnable_delta;
qcfs_rq->idle_h_nr_running -= idle_task_delta;
qcfs_rq->h_nr_delayed -= delayed_delta;
@@ -6012,6 +6016,7 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq)
idle_task_delta = cfs_rq->h_nr_queued;
qcfs_rq->h_nr_queued -= queued_delta;
+ qcfs_rq->h_nr_runnable -= runnable_delta;
qcfs_rq->idle_h_nr_running -= idle_task_delta;
qcfs_rq->h_nr_delayed -= delayed_delta;
}
@@ -6039,7 +6044,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
struct rq *rq = rq_of(cfs_rq);
struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
struct sched_entity *se;
- long queued_delta, idle_task_delta, delayed_delta;
+ long queued_delta, runnable_delta, idle_task_delta, delayed_delta;
long rq_h_nr_queued = rq->cfs.h_nr_queued;
se = cfs_rq->tg->se[cpu_of(rq)];
@@ -6074,6 +6079,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
}
queued_delta = cfs_rq->h_nr_queued;
+ runnable_delta = cfs_rq->h_nr_runnable;
idle_task_delta = cfs_rq->idle_h_nr_running;
delayed_delta = cfs_rq->h_nr_delayed;
for_each_sched_entity(se) {
@@ -6092,6 +6098,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
idle_task_delta = cfs_rq->h_nr_queued;
qcfs_rq->h_nr_queued += queued_delta;
+ qcfs_rq->h_nr_runnable += runnable_delta;
qcfs_rq->idle_h_nr_running += idle_task_delta;
qcfs_rq->h_nr_delayed += delayed_delta;
@@ -6110,6 +6117,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
idle_task_delta = cfs_rq->h_nr_queued;
qcfs_rq->h_nr_queued += queued_delta;
+ qcfs_rq->h_nr_runnable += runnable_delta;
qcfs_rq->idle_h_nr_running += idle_task_delta;
qcfs_rq->h_nr_delayed += delayed_delta;
@@ -7024,6 +7032,8 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
enqueue_entity(cfs_rq, se, flags);
slice = cfs_rq_min_slice(cfs_rq);
+ if (!h_nr_delayed)
+ cfs_rq->h_nr_runnable++;
cfs_rq->h_nr_queued++;
cfs_rq->idle_h_nr_running += idle_h_nr_running;
cfs_rq->h_nr_delayed += h_nr_delayed;
@@ -7048,6 +7058,8 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
se->slice = slice;
slice = cfs_rq_min_slice(cfs_rq);
+ if (!h_nr_delayed)
+ cfs_rq->h_nr_runnable++;
cfs_rq->h_nr_queued++;
cfs_rq->idle_h_nr_running += idle_h_nr_running;
cfs_rq->h_nr_delayed += h_nr_delayed;
@@ -7138,6 +7150,8 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
break;
}
+ if (!h_nr_delayed)
+ cfs_rq->h_nr_runnable -= h_nr_queued;
cfs_rq->h_nr_queued -= h_nr_queued;
cfs_rq->idle_h_nr_running -= idle_h_nr_running;
cfs_rq->h_nr_delayed -= h_nr_delayed;
@@ -7177,6 +7191,8 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
se->slice = slice;
slice = cfs_rq_min_slice(cfs_rq);
+ if (!h_nr_delayed)
+ cfs_rq->h_nr_runnable -= h_nr_queued;
cfs_rq->h_nr_queued -= h_nr_queued;
cfs_rq->idle_h_nr_running -= idle_h_nr_running;
cfs_rq->h_nr_delayed -= h_nr_delayed;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index b011081aff97..869d5d3521f2 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -647,6 +647,7 @@ struct cfs_rq {
struct load_weight load;
unsigned int nr_running;
unsigned int h_nr_queued; /* SCHED_{NORMAL,BATCH,IDLE} */
+ unsigned int h_nr_runnable; /* SCHED_{NORMAL,BATCH,IDLE} */
unsigned int idle_nr_running; /* SCHED_IDLE */
unsigned int idle_h_nr_running; /* SCHED_IDLE */
unsigned int h_nr_delayed;
--
2.43.0
Powered by blists - more mailing lists