From 371bf42732694d142b0de026e152266c039b97d3 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Thu, 28 Jun 2018 17:45:05 +0200 Subject: sched/rt: Add rt_rq utilization tracking schedutil governor relies on cfs_rq's util_avg to choose the OPP when CFS tasks are running. When the CPU is overloaded by CFS and RT tasks, CFS tasks are preempted by RT tasks and in this case util_avg reflects the remaining capacity but not what CFS want to use. In such case, schedutil can select a lower OPP whereas the CPU is overloaded. In order to have a more accurate view of the utilization of the CPU, we track the utilization of RT tasks. Only util_avg is correctly tracked but not load_avg and runnable_load_avg which are useless for rt_rq. rt_rq uses rq_clock_task and cfs_rq uses cfs_rq_clock_task but they are the same at the root group level, so the PELT windows of the util_sum are aligned. Signed-off-by: Vincent Guittot Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Morten.Rasmussen@arm.com Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: claudio@evidence.eu.com Cc: daniel.lezcano@linaro.org Cc: dietmar.eggemann@arm.com Cc: joel@joelfernandes.org Cc: juri.lelli@redhat.com Cc: luca.abeni@santannapisa.it Cc: patrick.bellasi@arm.com Cc: quentin.perret@arm.com Cc: rjw@rjwysocki.net Cc: valentin.schneider@arm.com Cc: viresh.kumar@linaro.org Link: http://lkml.kernel.org/r/1530200714-4504-3-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar --- kernel/sched/rt.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'kernel/sched/rt.c') diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 572567078b60..0dc8ad1915e6 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -5,6 +5,8 @@ */ #include "sched.h" +#include "pelt.h" + int sched_rr_timeslice = RR_TIMESLICE; int sysctl_sched_rr_timeslice = (MSEC_PER_SEC / HZ) * RR_TIMESLICE; @@ -1576,6 +1578,14 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) rt_queue_push_tasks(rq); + /* + * If prev task was rt, put_prev_task() has already updated the + * utilization. We only care of the case where we start to schedule a + * rt task + */ + if (rq->curr->sched_class != &rt_sched_class) + update_rt_rq_load_avg(rq_clock_task(rq), rq, 0); + return p; } @@ -1583,6 +1593,8 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p) { update_curr_rt(rq); + update_rt_rq_load_avg(rq_clock_task(rq), rq, 1); + /* * The previous task needs to be made eligible for pushing * if it is still active @@ -2312,6 +2324,7 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued) struct sched_rt_entity *rt_se = &p->rt; update_curr_rt(rq); + update_rt_rq_load_avg(rq_clock_task(rq), rq, 1); watchdog(rq, p); -- cgit From 523e979d31648112bad07f427c183525c0258c75 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Thu, 28 Jun 2018 17:45:12 +0200 Subject: sched/core: Use PELT for scale_rt_capacity() The utilization of the CPU by RT, DL and IRQs are now tracked with PELT so we can use these metrics instead of rt_avg to evaluate the remaining capacity available for CFS class. scale_rt_capacity() behavior has been changed and now returns the remaining capacity available for CFS instead of a scaling factor because RT, DL and IRQ provide now absolute utilization value. The same formula as schedutil is used: IRQ util_avg + (1 - IRQ util_avg / max capacity ) * /Sum rq util_avg but the implementation is different because it doesn't return the same value and doesn't benefit of the same optimization. Signed-off-by: Vincent Guittot Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Morten.Rasmussen@arm.com Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: claudio@evidence.eu.com Cc: daniel.lezcano@linaro.org Cc: dietmar.eggemann@arm.com Cc: joel@joelfernandes.org Cc: juri.lelli@redhat.com Cc: luca.abeni@santannapisa.it Cc: patrick.bellasi@arm.com Cc: quentin.perret@arm.com Cc: rjw@rjwysocki.net Cc: valentin.schneider@arm.com Cc: viresh.kumar@linaro.org Link: http://lkml.kernel.org/r/1530200714-4504-10-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar --- kernel/sched/rt.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'kernel/sched/rt.c') diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 0dc8ad1915e6..2df72abfa24a 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -973,8 +973,6 @@ static void update_curr_rt(struct rq *rq) curr->se.exec_start = now; cgroup_account_cputime(curr, delta_exec); - sched_rt_avg_update(rq, delta_exec); - if (!rt_bandwidth_enabled()) return; -- cgit