* [PATCH] sched: cpufreq: ignore SMT when determining max cpu capacity
@ 2016-08-19 20:43 Steve Muckle
2016-08-24 8:31 ` Morten Rasmussen
0 siblings, 1 reply; 2+ messages in thread
From: Steve Muckle @ 2016-08-19 20:43 UTC (permalink / raw)
To: Peter Zijlstra, Ingo Molnar, Rafael J . Wysocki
Cc: linux-kernel, linux-pm, Vincent Guittot, Morten Rasmussen,
Dietmar Eggemann, Juri Lelli, Patrick Bellasi, Steve Muckle
PELT does not consider SMT when scaling its utilization values via
arch_scale_cpu_capacity(). The value in rq->cpu_capacity_orig does
take SMT into consideration though and therefore may be smaller than
the utilization reported by PELT.
On an Intel i7-3630QM for example rq->cpu_capacity_orig is 589 but
util_avg scales up to 1024. This means that a 50% utilized CPU will show
up in schedutil as ~86% busy.
Fix this by using the same CPU scaling value in schedutil as that which
is used by PELT.
Signed-off-by: Steve Muckle <smuckle@linaro.org>
---
kernel/sched/cpufreq_schedutil.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 60d985f4dc47..cb8a77b1ef1b 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -147,7 +147,9 @@ static unsigned int get_next_freq(struct sugov_cpu *sg_cpu, unsigned long util,
static void sugov_get_util(unsigned long *util, unsigned long *max)
{
struct rq *rq = this_rq();
- unsigned long cfs_max = rq->cpu_capacity_orig;
+ unsigned long cfs_max;
+
+ cfs_max = arch_scale_cpu_capacity(NULL, smp_processor_id());
*util = min(rq->cfs.avg.util_avg, cfs_max);
*max = cfs_max;
--
2.7.3
^ permalink raw reply related [flat|nested] 2+ messages in thread
* Re: [PATCH] sched: cpufreq: ignore SMT when determining max cpu capacity
2016-08-19 20:43 [PATCH] sched: cpufreq: ignore SMT when determining max cpu capacity Steve Muckle
@ 2016-08-24 8:31 ` Morten Rasmussen
0 siblings, 0 replies; 2+ messages in thread
From: Morten Rasmussen @ 2016-08-24 8:31 UTC (permalink / raw)
To: Steve Muckle
Cc: Peter Zijlstra, Ingo Molnar, Rafael J . Wysocki, linux-kernel,
linux-pm, Vincent Guittot, Dietmar Eggemann, Juri Lelli,
Patrick Bellasi, Steve Muckle
On Fri, Aug 19, 2016 at 01:43:47PM -0700, Steve Muckle wrote:
> PELT does not consider SMT when scaling its utilization values via
> arch_scale_cpu_capacity(). The value in rq->cpu_capacity_orig does
> take SMT into consideration though and therefore may be smaller than
> the utilization reported by PELT.
>
> On an Intel i7-3630QM for example rq->cpu_capacity_orig is 589 but
> util_avg scales up to 1024. This means that a 50% utilized CPU will show
> up in schedutil as ~86% busy.
>
> Fix this by using the same CPU scaling value in schedutil as that which
> is used by PELT.
>
> Signed-off-by: Steve Muckle <smuckle@linaro.org>
> ---
> kernel/sched/cpufreq_schedutil.c | 4 +++-
> 1 file changed, 3 insertions(+), 1 deletion(-)
>
> diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
> index 60d985f4dc47..cb8a77b1ef1b 100644
> --- a/kernel/sched/cpufreq_schedutil.c
> +++ b/kernel/sched/cpufreq_schedutil.c
> @@ -147,7 +147,9 @@ static unsigned int get_next_freq(struct sugov_cpu *sg_cpu, unsigned long util,
> static void sugov_get_util(unsigned long *util, unsigned long *max)
> {
> struct rq *rq = this_rq();
> - unsigned long cfs_max = rq->cpu_capacity_orig;
> + unsigned long cfs_max;
> +
> + cfs_max = arch_scale_cpu_capacity(NULL, smp_processor_id());
Until we have figured out how to define utilization (and capacity)
better for SMT I think this is a better solution.
Morten
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2016-08-24 8:42 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2016-08-19 20:43 [PATCH] sched: cpufreq: ignore SMT when determining max cpu capacity Steve Muckle
2016-08-24 8:31 ` Morten Rasmussen
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.