From 7b8a702d943827130cc00ae36075eff5500f86f1 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Mon, 2 Dec 2024 18:45:58 +0100 Subject: sched/fair: Rename h_nr_running into h_nr_queued With delayed dequeued feature, a sleeping sched_entity remains queued in the rq until its lag has elapsed but can't run. Rename h_nr_running into h_nr_queued to reflect this new behavior. Signed-off-by: Vincent Guittot Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Dietmar Eggemann Link: https://lore.kernel.org/r/20241202174606.4074512-4-vincent.guittot@linaro.org --- kernel/sched/debug.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel/sched/debug.c') diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index a1be00a988bf..08d6c2b7caa3 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -379,7 +379,7 @@ static ssize_t sched_fair_server_write(struct file *filp, const char __user *ubu return -EINVAL; } - if (rq->cfs.h_nr_running) { + if (rq->cfs.h_nr_queued) { update_rq_clock(rq); dl_server_stop(&rq->fair_server); } @@ -392,7 +392,7 @@ static ssize_t sched_fair_server_write(struct file *filp, const char __user *ubu printk_deferred("Fair server disabled in CPU %d, system may crash due to starvation.\n", cpu_of(rq)); - if (rq->cfs.h_nr_running) + if (rq->cfs.h_nr_queued) dl_server_start(&rq->fair_server); } @@ -844,7 +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_running", cfs_rq->h_nr_running); + 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", cfs_rq->idle_nr_running); -- cgit v1.2.3 From c2a295bffeaf9461ecba76dc9e4780c898c94f03 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Mon, 2 Dec 2024 18:45:59 +0100 Subject: 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 Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Dietmar Eggemann Link: https://lore.kernel.org/r/20241202174606.4074512-5-vincent.guittot@linaro.org --- kernel/sched/debug.c | 1 + kernel/sched/fair.c | 20 ++++++++++++++++++-- kernel/sched/sched.h | 1 + 3 files changed, 20 insertions(+), 2 deletions(-) (limited to 'kernel/sched/debug.c') 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 d6a9447e5e23..ed01e72b2b77 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; @@ -5930,7 +5932,7 @@ 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); @@ -5962,6 +5964,7 @@ 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) { @@ -5986,6 +5989,7 @@ 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; @@ -6009,6 +6013,7 @@ 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; } @@ -6036,7 +6041,7 @@ 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)]; @@ -6071,6 +6076,7 @@ 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) { @@ -6089,6 +6095,7 @@ 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; @@ -6107,6 +6114,7 @@ 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; @@ -7021,6 +7029,8 @@ 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; @@ -7045,6 +7055,8 @@ 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; @@ -7135,6 +7147,8 @@ 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; @@ -7174,6 +7188,8 @@ 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; -- cgit v1.2.3 From 9216582b0bfb17889eebcf96fb41cd67a3d71133 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Mon, 2 Dec 2024 18:46:01 +0100 Subject: sched/fair: Removed unsued cfs_rq.h_nr_delayed h_nr_delayed is not used anymore. We now have: - h_nr_runnable which tracks tasks ready to run - h_nr_queued which tracks enqueued tasks either ready to run or delayed dequeue Signed-off-by: Vincent Guittot Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Dietmar Eggemann Link: https://lore.kernel.org/r/20241202174606.4074512-7-vincent.guittot@linaro.org --- kernel/sched/debug.c | 1 - kernel/sched/fair.c | 40 ++++++++++++---------------------------- kernel/sched/sched.h | 1 - 3 files changed, 12 insertions(+), 30 deletions(-) (limited to 'kernel/sched/debug.c') diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index fd711cc4d44c..56be3651605d 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -846,7 +846,6 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) 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", cfs_rq->idle_nr_running); SEQ_printf(m, " .%-30s: %d\n", "idle_h_nr_running", diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 3a8bdfbf4867..5c2f049ca3bf 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5470,7 +5470,6 @@ static void set_delayed(struct 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; } @@ -5483,7 +5482,6 @@ static void clear_delayed(struct 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; } @@ -5932,7 +5930,7 @@ 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, runnable_delta, idle_task_delta, delayed_delta, dequeue = 1; + long queued_delta, runnable_delta, idle_task_delta, dequeue = 1; long rq_h_nr_queued = rq->cfs.h_nr_queued; raw_spin_lock(&cfs_b->lock); @@ -5966,7 +5964,6 @@ static bool throttle_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) { struct cfs_rq *qcfs_rq = cfs_rq_of(se); int flags; @@ -5991,7 +5988,6 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq) 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; if (qcfs_rq->load.weight) { /* Avoid re-evaluating load for this entity: */ @@ -6015,7 +6011,6 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq) 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; } /* At this point se is NULL and we are at root level*/ @@ -6041,7 +6036,7 @@ 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, runnable_delta, idle_task_delta, delayed_delta; + long queued_delta, runnable_delta, idle_task_delta; long rq_h_nr_queued = rq->cfs.h_nr_queued; se = cfs_rq->tg->se[cpu_of(rq)]; @@ -6078,7 +6073,6 @@ 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) { struct cfs_rq *qcfs_rq = cfs_rq_of(se); @@ -6097,7 +6091,6 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) 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; /* end evaluation on encountering a throttled cfs_rq */ if (cfs_rq_throttled(qcfs_rq)) @@ -6116,7 +6109,6 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) 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; /* end evaluation on encountering a throttled cfs_rq */ if (cfs_rq_throttled(qcfs_rq)) @@ -6979,7 +6971,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) struct cfs_rq *cfs_rq; struct sched_entity *se = &p->se; int idle_h_nr_running = task_has_idle_policy(p); - int h_nr_delayed = 0; + int h_nr_runnable = 1; int task_new = !(flags & ENQUEUE_WAKEUP); int rq_h_nr_queued = rq->cfs.h_nr_queued; u64 slice = 0; @@ -7006,8 +6998,8 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) if (p->in_iowait) cpufreq_update_util(rq, SCHED_CPUFREQ_IOWAIT); - if (task_new) - h_nr_delayed = !!se->sched_delayed; + if (task_new && se->sched_delayed) + h_nr_runnable = 0; for_each_sched_entity(se) { if (se->on_rq) { @@ -7029,11 +7021,9 @@ 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_runnable += 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; if (cfs_rq_is_idle(cfs_rq)) idle_h_nr_running = 1; @@ -7055,11 +7045,9 @@ 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_runnable += 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; if (cfs_rq_is_idle(cfs_rq)) idle_h_nr_running = 1; @@ -7122,7 +7110,7 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags) struct task_struct *p = NULL; int idle_h_nr_running = 0; int h_nr_queued = 0; - int h_nr_delayed = 0; + int h_nr_runnable = 0; struct cfs_rq *cfs_rq; u64 slice = 0; @@ -7130,8 +7118,8 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags) p = task_of(se); h_nr_queued = 1; idle_h_nr_running = task_has_idle_policy(p); - if (!task_sleep && !task_delayed) - h_nr_delayed = !!se->sched_delayed; + if (task_sleep || task_delayed || !se->sched_delayed) + h_nr_runnable = 1; } else { cfs_rq = group_cfs_rq(se); slice = cfs_rq_min_slice(cfs_rq); @@ -7147,11 +7135,9 @@ 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_runnable -= h_nr_runnable; 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; if (cfs_rq_is_idle(cfs_rq)) idle_h_nr_running = h_nr_queued; @@ -7188,11 +7174,9 @@ 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_runnable -= h_nr_runnable; 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; if (cfs_rq_is_idle(cfs_rq)) idle_h_nr_running = h_nr_queued; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 4374c660f5c7..d3ce5e99b025 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -650,7 +650,6 @@ struct cfs_rq { 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; s64 avg_vruntime; u64 avg_load; -- cgit v1.2.3 From 31898e7b87dd2833eb5dd6aa60ab2a5880c4c12f Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Mon, 2 Dec 2024 18:46:02 +0100 Subject: sched/fair: Rename cfs_rq.idle_h_nr_running into h_nr_idle Use same naming convention as others starting with h_nr_* and rename idle_h_nr_running into h_nr_idle. The "running" is not correct anymore as it includes delayed dequeue tasks as well. Signed-off-by: Vincent Guittot Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Dietmar Eggemann Link: https://lore.kernel.org/r/20241202174606.4074512-8-vincent.guittot@linaro.org --- kernel/sched/debug.c | 3 +-- kernel/sched/fair.c | 52 ++++++++++++++++++++++++++-------------------------- kernel/sched/sched.h | 2 +- 3 files changed, 28 insertions(+), 29 deletions(-) (limited to 'kernel/sched/debug.c') diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 56be3651605d..e21b66b6ee10 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -848,8 +848,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) SEQ_printf(m, " .%-30s: %d\n", "h_nr_queued", cfs_rq->h_nr_queued); SEQ_printf(m, " .%-30s: %d\n", "idle_nr_running", cfs_rq->idle_nr_running); - SEQ_printf(m, " .%-30s: %d\n", "idle_h_nr_running", - cfs_rq->idle_h_nr_running); + SEQ_printf(m, " .%-30s: %d\n", "h_nr_idle", cfs_rq->h_nr_idle); SEQ_printf(m, " .%-30s: %ld\n", "load", cfs_rq->load.weight); #ifdef CONFIG_SMP SEQ_printf(m, " .%-30s: %lu\n", "load_avg", diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 5c2f049ca3bf..2ef33784cbf5 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5930,7 +5930,7 @@ 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, runnable_delta, idle_task_delta, dequeue = 1; + long queued_delta, runnable_delta, idle_delta, dequeue = 1; long rq_h_nr_queued = rq->cfs.h_nr_queued; raw_spin_lock(&cfs_b->lock); @@ -5963,7 +5963,7 @@ static bool throttle_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; + idle_delta = cfs_rq->h_nr_idle; for_each_sched_entity(se) { struct cfs_rq *qcfs_rq = cfs_rq_of(se); int flags; @@ -5983,11 +5983,11 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq) dequeue_entity(qcfs_rq, se, flags); if (cfs_rq_is_idle(group_cfs_rq(se))) - idle_task_delta = cfs_rq->h_nr_queued; + idle_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_idle -= idle_delta; if (qcfs_rq->load.weight) { /* Avoid re-evaluating load for this entity: */ @@ -6006,11 +6006,11 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq) se_update_runnable(se); if (cfs_rq_is_idle(group_cfs_rq(se))) - idle_task_delta = cfs_rq->h_nr_queued; + idle_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_idle -= idle_delta; } /* At this point se is NULL and we are at root level*/ @@ -6036,7 +6036,7 @@ 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, runnable_delta, idle_task_delta; + long queued_delta, runnable_delta, idle_delta; long rq_h_nr_queued = rq->cfs.h_nr_queued; se = cfs_rq->tg->se[cpu_of(rq)]; @@ -6072,7 +6072,7 @@ 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; + idle_delta = cfs_rq->h_nr_idle; for_each_sched_entity(se) { struct cfs_rq *qcfs_rq = cfs_rq_of(se); @@ -6086,11 +6086,11 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) enqueue_entity(qcfs_rq, se, ENQUEUE_WAKEUP); if (cfs_rq_is_idle(group_cfs_rq(se))) - idle_task_delta = cfs_rq->h_nr_queued; + idle_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_idle += idle_delta; /* end evaluation on encountering a throttled cfs_rq */ if (cfs_rq_throttled(qcfs_rq)) @@ -6104,11 +6104,11 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) se_update_runnable(se); if (cfs_rq_is_idle(group_cfs_rq(se))) - idle_task_delta = cfs_rq->h_nr_queued; + idle_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_idle += idle_delta; /* end evaluation on encountering a throttled cfs_rq */ if (cfs_rq_throttled(qcfs_rq)) @@ -6918,7 +6918,7 @@ static inline void check_update_overutilized_status(struct rq *rq) { } /* Runqueue only has SCHED_IDLE tasks enqueued */ static int sched_idle_rq(struct rq *rq) { - return unlikely(rq->nr_running == rq->cfs.idle_h_nr_running && + return unlikely(rq->nr_running == rq->cfs.h_nr_idle && rq->nr_running); } @@ -6970,7 +6970,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) { struct cfs_rq *cfs_rq; struct sched_entity *se = &p->se; - int idle_h_nr_running = task_has_idle_policy(p); + int h_nr_idle = task_has_idle_policy(p); int h_nr_runnable = 1; int task_new = !(flags & ENQUEUE_WAKEUP); int rq_h_nr_queued = rq->cfs.h_nr_queued; @@ -7023,10 +7023,10 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) cfs_rq->h_nr_runnable += h_nr_runnable; cfs_rq->h_nr_queued++; - cfs_rq->idle_h_nr_running += idle_h_nr_running; + cfs_rq->h_nr_idle += h_nr_idle; if (cfs_rq_is_idle(cfs_rq)) - idle_h_nr_running = 1; + h_nr_idle = 1; /* end evaluation on encountering a throttled cfs_rq */ if (cfs_rq_throttled(cfs_rq)) @@ -7047,10 +7047,10 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) cfs_rq->h_nr_runnable += h_nr_runnable; cfs_rq->h_nr_queued++; - cfs_rq->idle_h_nr_running += idle_h_nr_running; + cfs_rq->h_nr_idle += h_nr_idle; if (cfs_rq_is_idle(cfs_rq)) - idle_h_nr_running = 1; + h_nr_idle = 1; /* end evaluation on encountering a throttled cfs_rq */ if (cfs_rq_throttled(cfs_rq)) @@ -7108,7 +7108,7 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags) bool task_sleep = flags & DEQUEUE_SLEEP; bool task_delayed = flags & DEQUEUE_DELAYED; struct task_struct *p = NULL; - int idle_h_nr_running = 0; + int h_nr_idle = 0; int h_nr_queued = 0; int h_nr_runnable = 0; struct cfs_rq *cfs_rq; @@ -7117,7 +7117,7 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags) if (entity_is_task(se)) { p = task_of(se); h_nr_queued = 1; - idle_h_nr_running = task_has_idle_policy(p); + h_nr_idle = task_has_idle_policy(p); if (task_sleep || task_delayed || !se->sched_delayed) h_nr_runnable = 1; } else { @@ -7137,10 +7137,10 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags) cfs_rq->h_nr_runnable -= h_nr_runnable; cfs_rq->h_nr_queued -= h_nr_queued; - cfs_rq->idle_h_nr_running -= idle_h_nr_running; + cfs_rq->h_nr_idle -= h_nr_idle; if (cfs_rq_is_idle(cfs_rq)) - idle_h_nr_running = h_nr_queued; + h_nr_idle = h_nr_queued; /* end evaluation on encountering a throttled cfs_rq */ if (cfs_rq_throttled(cfs_rq)) @@ -7176,10 +7176,10 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags) cfs_rq->h_nr_runnable -= h_nr_runnable; cfs_rq->h_nr_queued -= h_nr_queued; - cfs_rq->idle_h_nr_running -= idle_h_nr_running; + cfs_rq->h_nr_idle -= h_nr_idle; if (cfs_rq_is_idle(cfs_rq)) - idle_h_nr_running = h_nr_queued; + h_nr_idle = h_nr_queued; /* end evaluation on encountering a throttled cfs_rq */ if (cfs_rq_throttled(cfs_rq)) @@ -13527,7 +13527,7 @@ int sched_group_set_idle(struct task_group *tg, long idle) } idle_task_delta = grp_cfs_rq->h_nr_queued - - grp_cfs_rq->idle_h_nr_running; + grp_cfs_rq->h_nr_idle; if (!cfs_rq_is_idle(grp_cfs_rq)) idle_task_delta *= -1; @@ -13537,7 +13537,7 @@ int sched_group_set_idle(struct task_group *tg, long idle) if (!se->on_rq) break; - cfs_rq->idle_h_nr_running += idle_task_delta; + cfs_rq->h_nr_idle += idle_task_delta; /* Already accounted at parent level and above. */ if (cfs_rq_is_idle(cfs_rq)) diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index d3ce5e99b025..afe5cb93db89 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -649,7 +649,7 @@ struct cfs_rq { 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_idle; /* SCHED_IDLE */ s64 avg_vruntime; u64 avg_load; -- cgit v1.2.3 From 43eef7c3a4a65e258244d63a8992d0a8d70e5974 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Mon, 2 Dec 2024 18:46:03 +0100 Subject: sched/fair: Remove unused cfs_rq.idle_nr_running cfs_rq.idle_nr_running field is not used anywhere so we can remove the useless associated computation. Last user went in commit 5e963f2bd465 ("sched/fair: Commit to EEVDF"). Signed-off-by: Vincent Guittot Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Dietmar Eggemann Link: https://lore.kernel.org/r/20241202174606.4074512-9-vincent.guittot@linaro.org --- kernel/sched/debug.c | 2 -- kernel/sched/fair.c | 14 +------------- kernel/sched/sched.h | 1 - 3 files changed, 1 insertion(+), 16 deletions(-) (limited to 'kernel/sched/debug.c') diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index e21b66b6ee10..e300ee4d7956 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -846,8 +846,6 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) 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", "idle_nr_running", - cfs_rq->idle_nr_running); SEQ_printf(m, " .%-30s: %d\n", "h_nr_idle", cfs_rq->h_nr_idle); SEQ_printf(m, " .%-30s: %ld\n", "load", cfs_rq->load.weight); #ifdef CONFIG_SMP diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 2ef33784cbf5..8afa0a4ed09f 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3674,8 +3674,6 @@ account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se) } #endif cfs_rq->nr_running++; - if (se_is_idle(se)) - cfs_rq->idle_nr_running++; } static void @@ -3689,8 +3687,6 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) } #endif cfs_rq->nr_running--; - if (se_is_idle(se)) - cfs_rq->idle_nr_running--; } /* @@ -13507,7 +13503,7 @@ int sched_group_set_idle(struct task_group *tg, long idle) for_each_possible_cpu(i) { struct rq *rq = cpu_rq(i); struct sched_entity *se = tg->se[i]; - struct cfs_rq *parent_cfs_rq, *grp_cfs_rq = tg->cfs_rq[i]; + struct cfs_rq *grp_cfs_rq = tg->cfs_rq[i]; bool was_idle = cfs_rq_is_idle(grp_cfs_rq); long idle_task_delta; struct rq_flags rf; @@ -13518,14 +13514,6 @@ int sched_group_set_idle(struct task_group *tg, long idle) if (WARN_ON_ONCE(was_idle == cfs_rq_is_idle(grp_cfs_rq))) goto next_cpu; - if (se->on_rq) { - parent_cfs_rq = cfs_rq_of(se); - if (cfs_rq_is_idle(grp_cfs_rq)) - parent_cfs_rq->idle_nr_running++; - else - parent_cfs_rq->idle_nr_running--; - } - idle_task_delta = grp_cfs_rq->h_nr_queued - grp_cfs_rq->h_nr_idle; if (!cfs_rq_is_idle(grp_cfs_rq)) diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index afe5cb93db89..9a9220aad9fc 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -648,7 +648,6 @@ struct cfs_rq { 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 h_nr_idle; /* SCHED_IDLE */ s64 avg_vruntime; -- cgit v1.2.3 From 736c55a02c477ad31c57ae4c69130f437855e051 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Mon, 2 Dec 2024 18:46:04 +0100 Subject: sched/fair: Rename cfs_rq.nr_running into nr_queued Rename cfs_rq.nr_running into cfs_rq.nr_queued which better reflects the reality as the value includes both the ready to run tasks and the delayed dequeue tasks. Signed-off-by: Vincent Guittot Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Dietmar Eggemann Link: https://lore.kernel.org/r/20241202174606.4074512-10-vincent.guittot@linaro.org --- kernel/sched/debug.c | 2 +- kernel/sched/fair.c | 38 +++++++++++++++++++------------------- kernel/sched/sched.h | 4 ++-- 3 files changed, 22 insertions(+), 22 deletions(-) (limited to 'kernel/sched/debug.c') diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index e300ee4d7956..5e8e84a2bcb1 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -843,7 +843,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) SPLIT_NS(right_vruntime)); 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", "nr_queued", cfs_rq->nr_queued); 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_idle", cfs_rq->h_nr_idle); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 8afa0a4ed09f..84c0191a8ffa 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -915,7 +915,7 @@ static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq) * We can safely skip eligibility check if there is only one entity * in this cfs_rq, saving some cycles. */ - if (cfs_rq->nr_running == 1) + if (cfs_rq->nr_queued == 1) return curr && curr->on_rq ? curr : se; if (curr && (!curr->on_rq || !entity_eligible(cfs_rq, curr))) @@ -1247,7 +1247,7 @@ static void update_curr(struct cfs_rq *cfs_rq) account_cfs_rq_runtime(cfs_rq, delta_exec); - if (cfs_rq->nr_running == 1) + if (cfs_rq->nr_queued == 1) return; if (resched || did_preempt_short(cfs_rq, curr)) { @@ -3673,7 +3673,7 @@ account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se) list_add(&se->group_node, &rq->cfs_tasks); } #endif - cfs_rq->nr_running++; + cfs_rq->nr_queued++; } static void @@ -3686,7 +3686,7 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) list_del_init(&se->group_node); } #endif - cfs_rq->nr_running--; + cfs_rq->nr_queued--; } /* @@ -5220,7 +5220,7 @@ static inline void update_misfit_status(struct task_struct *p, struct rq *rq) static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq) { - return !cfs_rq->nr_running; + return !cfs_rq->nr_queued; } #define UPDATE_TG 0x0 @@ -5276,7 +5276,7 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) * * EEVDF: placement strategy #1 / #2 */ - if (sched_feat(PLACE_LAG) && cfs_rq->nr_running && se->vlag) { + if (sched_feat(PLACE_LAG) && cfs_rq->nr_queued && se->vlag) { struct sched_entity *curr = cfs_rq->curr; unsigned long load; @@ -5423,7 +5423,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) __enqueue_entity(cfs_rq, se); se->on_rq = 1; - if (cfs_rq->nr_running == 1) { + if (cfs_rq->nr_queued == 1) { check_enqueue_throttle(cfs_rq); if (!throttled_hierarchy(cfs_rq)) { list_add_leaf_cfs_rq(cfs_rq); @@ -5565,7 +5565,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) if (flags & DEQUEUE_DELAYED) finish_delayed_dequeue_entity(se); - if (cfs_rq->nr_running == 0) + if (cfs_rq->nr_queued == 0) update_idle_cfs_rq_clock_pelt(cfs_rq); return true; @@ -5913,7 +5913,7 @@ static int tg_throttle_down(struct task_group *tg, void *data) list_del_leaf_cfs_rq(cfs_rq); SCHED_WARN_ON(cfs_rq->throttled_clock_self); - if (cfs_rq->nr_running) + if (cfs_rq->nr_queued) cfs_rq->throttled_clock_self = rq_clock(rq); } cfs_rq->throttle_count++; @@ -6022,7 +6022,7 @@ done: */ cfs_rq->throttled = 1; SCHED_WARN_ON(cfs_rq->throttled_clock); - if (cfs_rq->nr_running) + if (cfs_rq->nr_queued) cfs_rq->throttled_clock = rq_clock(rq); return true; } @@ -6122,7 +6122,7 @@ unthrottle_throttle: assert_list_leaf_cfs_rq(rq); /* Determine whether we need to wake up potentially idle CPU: */ - if (rq->curr == rq->idle && rq->cfs.nr_running) + if (rq->curr == rq->idle && rq->cfs.nr_queued) resched_curr(rq); } @@ -6423,7 +6423,7 @@ static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq) if (!cfs_bandwidth_used()) return; - if (!cfs_rq->runtime_enabled || cfs_rq->nr_running) + if (!cfs_rq->runtime_enabled || cfs_rq->nr_queued) return; __return_cfs_rq_runtime(cfs_rq); @@ -6941,14 +6941,14 @@ requeue_delayed_entity(struct sched_entity *se) if (sched_feat(DELAY_ZERO)) { update_entity_lag(cfs_rq, se); if (se->vlag > 0) { - cfs_rq->nr_running--; + cfs_rq->nr_queued--; if (se != cfs_rq->curr) __dequeue_entity(cfs_rq, se); se->vlag = 0; place_entity(cfs_rq, se, 0); if (se != cfs_rq->curr) __enqueue_entity(cfs_rq, se); - cfs_rq->nr_running++; + cfs_rq->nr_queued++; } } @@ -8873,7 +8873,7 @@ static struct task_struct *pick_task_fair(struct rq *rq) again: cfs_rq = &rq->cfs; - if (!cfs_rq->nr_running) + if (!cfs_rq->nr_queued) return NULL; do { @@ -8990,7 +8990,7 @@ static struct task_struct *__pick_next_task_fair(struct rq *rq, struct task_stru static bool fair_server_has_tasks(struct sched_dl_entity *dl_se) { - return !!dl_se->rq->cfs.nr_running; + return !!dl_se->rq->cfs.nr_queued; } static struct task_struct *fair_server_pick_task(struct sched_dl_entity *dl_se) @@ -9780,7 +9780,7 @@ static bool __update_blocked_fair(struct rq *rq, bool *done) if (update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq)) { update_tg_load_avg(cfs_rq); - if (cfs_rq->nr_running == 0) + if (cfs_rq->nr_queued == 0) update_idle_cfs_rq_clock_pelt(cfs_rq); if (cfs_rq == &rq->cfs) @@ -12949,7 +12949,7 @@ static inline void task_tick_core(struct rq *rq, struct task_struct *curr) * MIN_NR_TASKS_DURING_FORCEIDLE - 1 tasks and use that to check * if we need to give up the CPU. */ - if (rq->core->core_forceidle_count && rq->cfs.nr_running == 1 && + if (rq->core->core_forceidle_count && rq->cfs.nr_queued == 1 && __entity_slice_used(&curr->se, MIN_NR_TASKS_DURING_FORCEIDLE)) resched_curr(rq); } @@ -13093,7 +13093,7 @@ prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio) if (!task_on_rq_queued(p)) return; - if (rq->cfs.nr_running == 1) + if (rq->cfs.nr_queued == 1) return; /* diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 9a9220aad9fc..aef716c41edb 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -645,7 +645,7 @@ struct balance_callback { /* CFS-related fields in a runqueue */ struct cfs_rq { struct load_weight load; - unsigned int nr_running; + unsigned int nr_queued; unsigned int h_nr_queued; /* SCHED_{NORMAL,BATCH,IDLE} */ unsigned int h_nr_runnable; /* SCHED_{NORMAL,BATCH,IDLE} */ unsigned int h_nr_idle; /* SCHED_IDLE */ @@ -2565,7 +2565,7 @@ static inline bool sched_rt_runnable(struct rq *rq) static inline bool sched_fair_runnable(struct rq *rq) { - return rq->cfs.nr_running > 0; + return rq->cfs.nr_queued > 0; } extern struct task_struct *pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf); -- cgit v1.2.3 From 8061b9f5e111a3012f8b691e5b75dd81eafbb793 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Thu, 9 Jan 2025 16:24:33 -0800 Subject: sched/debug: Change need_resched warnings to pr_err need_resched warnings, if enabled, are treated as WARNINGs. If kernel.panic_on_warn is enabled, then this causes a kernel panic. It's highly unlikely that a panic is desired for these warnings, only a stack trace is normally required to debug and resolve. Thus, switch need_resched warnings to simply be a printk with an associated stack trace so they are no longer in scope for panic_on_warn. Signed-off-by: David Rientjes Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Madadi Vineeth Reddy Acked-by: Josh Don Link: https://lkml.kernel.org/r/e8d52023-5291-26bd-5299-8bb9eb604929@google.com --- kernel/sched/debug.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'kernel/sched/debug.c') diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 5e8e84a2bcb1..fd7e85220715 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -1292,8 +1292,10 @@ void resched_latency_warn(int cpu, u64 latency) { static DEFINE_RATELIMIT_STATE(latency_check_ratelimit, 60 * 60 * HZ, 1); - WARN(__ratelimit(&latency_check_ratelimit), - "sched: CPU %d need_resched set for > %llu ns (%d ticks) " - "without schedule\n", - cpu, latency, cpu_rq(cpu)->ticks_without_resched); + if (likely(!__ratelimit(&latency_check_ratelimit))) + return; + + pr_err("sched: CPU %d need_resched set for > %llu ns (%d ticks) without schedule\n", + cpu, latency, cpu_rq(cpu)->ticks_without_resched); + dump_stack(); } -- cgit v1.2.3 From 9065ce69754dece78606c8bbb3821449272e56bf Mon Sep 17 00:00:00 2001 From: Christian Loehle Date: Wed, 29 Jan 2025 17:59:44 +0000 Subject: sched/debug: Provide slice length for fair tasks Since commit: 857b158dc5e8 ("sched/eevdf: Use sched_attr::sched_runtime to set request/slice suggestion") ... we have the userspace per-task tunable slice length, which is a key parameter that is otherwise difficult to obtain, so provide it in /proc/$PID/sched. [ mingo: Clarified the changelog. ] Signed-off-by: Christian Loehle Signed-off-by: Ingo Molnar Cc: Peter Zijlstra Link: https://lore.kernel.org/r/453349b1-1637-42f5-a7b2-2385392b5956@arm.com --- kernel/sched/debug.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel/sched/debug.c') diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index a1be00a988bf..5b32d3cc393b 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -1265,6 +1265,8 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns, if (task_has_dl_policy(p)) { P(dl.runtime); P(dl.deadline); + } else if (fair_policy(p->policy)) { + P(se.slice); } #ifdef CONFIG_SCHED_CLASS_EXT __PS("ext.enabled", task_on_scx(p)); -- cgit v1.2.3