From 10a35e6812aa0953f02a956c499d23fe4e68af4a Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Wed, 23 Jan 2019 16:26:54 +0100 Subject: sched/pelt: Skip updating util_est when utilization is higher than CPU's capacity util_est is mainly meant to be a lower-bound for tasks utilization. That's why task_util_est() returns the actual util_avg when it's higher than the estimated utilization. With new invaraince signal and without any special check on samples collection, if a task is limited because of thermal capping for example, we could end up overestimating its utilization and thus perhaps generating an unwanted frequency spike when the capping is relaxed... and (even worst) it will take some more activations for the estimated utilization to converge back to the actual utilization. Since we cannot easily know if there is idle time in a CPU when a task completes an activation with a utilization higher then the CPU capacity, we skip the sampling when utilization is higher than CPU's capacity. Suggested-by: Patrick Bellasi Signed-off-by: Vincent Guittot Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Mike Galbraith Cc: Morten.Rasmussen@arm.com Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: pjt@google.com Cc: pkondeti@codeaurora.org Cc: quentin.perret@arm.com Cc: rjw@rjwysocki.net Cc: srinivas.pandruvada@linux.intel.com Cc: thara.gopinath@linaro.org Link: https://lkml.kernel.org/r/1548257214-13745-4-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar --- kernel/sched/fair.c | 14 +++++++++----- kernel/sched/sched.h | 7 +++++++ 2 files changed, 16 insertions(+), 5 deletions(-) (limited to 'kernel/sched') diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index f41f2eec6186..8c165f0d33b3 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3638,6 +3638,7 @@ util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep) { long last_ewma_diff; struct util_est ue; + int cpu; if (!sched_feat(UTIL_EST)) return; @@ -3671,6 +3672,14 @@ util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep) if (within_margin(last_ewma_diff, (SCHED_CAPACITY_SCALE / 100))) return; + /* + * To avoid overestimation of actual task utilization, skip updates if + * we cannot grant there is idle time in this CPU. + */ + cpu = cpu_of(rq_of(cfs_rq)); + if (task_util(p) > capacity_orig_of(cpu)) + return; + /* * Update Task's estimated utilization * @@ -5542,11 +5551,6 @@ 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); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index fe31bc472f3e..99e2a7772d16 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -2230,6 +2230,13 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {} # define arch_scale_freq_invariant() false #endif +#ifdef CONFIG_SMP +static inline unsigned long capacity_orig_of(int cpu) +{ + return cpu_rq(cpu)->cpu_capacity_orig; +} +#endif + #ifdef CONFIG_CPU_FREQ_GOV_SCHEDUTIL /** * enum schedutil_type - CPU utilization type -- cgit v1.2.3