aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/sched/cpufreq_schedutil.c
diff options
context:
space:
mode:
authorPeter Zijlstra <peterz@infradead.org>2018-07-05 14:36:17 +0200
committerIngo Molnar <mingo@kernel.org>2018-07-16 00:16:29 +0200
commit45f5519ec55e75af3565dd737586d3b041834f71 (patch)
tree01b85dfc9c2122cc96039b8fdd87deb43cb6a622 /kernel/sched/cpufreq_schedutil.c
parentsched/sysctl: Remove unused sched_time_avg_ms sysctl (diff)
downloadlinux-dev-45f5519ec55e75af3565dd737586d3b041834f71.tar.xz
linux-dev-45f5519ec55e75af3565dd737586d3b041834f71.zip
sched/cpufreq: Clarify sugov_get_util()
Add a few comments to (hopefully) clarifying some of the magic in sugov_get_util(). Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Viresh Kumar <viresh.kumar@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Morten.Rasmussen@arm.com Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vincent Guittot <vincent.guittot@linaro.org> 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 Link: http://lkml.kernel.org/r/20180705123617.GM2458@hirez.programming.kicks-ass.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to '')
-rw-r--r--kernel/sched/cpufreq_schedutil.c75
1 files changed, 54 insertions, 21 deletions
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index c9622b3f183d..97dcd4472a0e 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -177,6 +177,26 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy,
return cpufreq_driver_resolve_freq(policy, freq);
}
+/*
+ * This function computes an effective utilization for the given CPU, to be
+ * used for frequency selection given the linear relation: f = u * f_max.
+ *
+ * The scheduler tracks the following metrics:
+ *
+ * cpu_util_{cfs,rt,dl,irq}()
+ * cpu_bw_dl()
+ *
+ * Where the cfs,rt and dl util numbers are tracked with the same metric and
+ * synchronized windows and are thus directly comparable.
+ *
+ * The cfs,rt,dl utilization are the running times measured with rq->clock_task
+ * which excludes things like IRQ and steal-time. These latter are then accrued
+ * in the irq utilization.
+ *
+ * The DL bandwidth number otoh is not a measured metric but a value computed
+ * based on the task model parameters and gives the minimal utilization
+ * required to meet deadlines.
+ */
static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu)
{
struct rq *rq = cpu_rq(sg_cpu->cpu);
@@ -188,47 +208,60 @@ static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu)
if (rt_rq_is_runnable(&rq->rt))
return max;
+ /*
+ * Early check to see if IRQ/steal time saturates the CPU, can be
+ * because of inaccuracies in how we track these -- see
+ * update_irq_load_avg().
+ */
irq = cpu_util_irq(rq);
-
if (unlikely(irq >= max))
return max;
- /* Sum rq utilization */
+ /*
+ * Because the time spend on RT/DL tasks is visible as 'lost' time to
+ * CFS tasks and we use the same metric to track the effective
+ * utilization (PELT windows are synchronized) we can directly add them
+ * to obtain the CPU's actual utilization.
+ */
util = cpu_util_cfs(rq);
util += cpu_util_rt(rq);
/*
- * Interrupt time is not seen by RQS utilization so we can compare
- * them with the CPU capacity
+ * We do not make cpu_util_dl() a permanent part of this sum because we
+ * want to use cpu_bw_dl() later on, but we need to check if the
+ * CFS+RT+DL sum is saturated (ie. no idle time) such that we select
+ * f_max when there is no idle time.
+ *
+ * NOTE: numerical errors or stop class might cause us to not quite hit
+ * saturation when we should -- something for later.
*/
if ((util + cpu_util_dl(rq)) >= max)
return max;
/*
- * As there is still idle time on the CPU, we need to compute the
- * utilization level of the CPU.
+ * There is still idle time; further improve the number by using the
+ * irq metric. Because IRQ/steal time is hidden from the task clock we
+ * need to scale the task numbers:
*
+ * 1 - irq
+ * U' = irq + ------- * U
+ * max
+ */
+ util *= (max - irq);
+ util /= max;
+ util += irq;
+
+ /*
* Bandwidth required by DEADLINE must always be granted while, for
* FAIR and RT, we use blocked utilization of IDLE CPUs as a mechanism
* to gracefully reduce the frequency when no tasks show up for longer
* periods of time.
*
- * Ideally we would like to set util_dl as min/guaranteed freq and
- * util_cfs + util_dl as requested freq. However, cpufreq is not yet
- * ready for such an interface. So, we only do the latter for now.
+ * Ideally we would like to set bw_dl as min/guaranteed freq and util +
+ * bw_dl as requested freq. However, cpufreq is not yet ready for such
+ * an interface. So, we only do the latter for now.
*/
-
- /* Weight RQS utilization to normal context window */
- util *= (max - irq);
- util /= max;
-
- /* Add interrupt utilization */
- util += irq;
-
- /* Add DL bandwidth requirement */
- util += sg_cpu->bw_dl;
-
- return min(max, util);
+ return min(max, util + sg_cpu->bw_dl);
}
/**