From: Vincent Guittot <vincent.guittot@linaro.org>
To: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Ingo Molnar <mingo@redhat.com>,
Peter Zijlstra <peterz@infradead.org>,
Juri Lelli <juri.lelli@redhat.com>,
Steven Rostedt <rostedt@goodmis.org>,
Luca Abeni <luca.abeni@santannapisa.it>,
Daniel Bristot de Oliveira <bristot@redhat.com>,
Wei Wang <wvw@google.com>, Quentin Perret <qperret@google.com>,
Alessio Balsini <balsini@google.com>,
Pavan Kondeti <pkondeti@codeaurora.org>,
Patrick Bellasi <patrick.bellasi@matbug.net>,
Morten Rasmussen <morten.rasmussen@arm.com>,
Valentin Schneider <valentin.schneider@arm.com>,
Qais Yousef <qais.yousef@arm.com>,
linux-kernel <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH 1/4] sched/topology: Store root domain CPU capacity sum
Date: Wed, 8 Apr 2020 14:29:16 +0200 [thread overview]
Message-ID: <CAKfTPtC4_+dTddLdoFMdzUvsXwWyi3bUOXcg9kstC8RzZS_a+A@mail.gmail.com> (raw)
In-Reply-To: <20200408095012.3819-2-dietmar.eggemann@arm.com>
On Wed, 8 Apr 2020 at 11:50, Dietmar Eggemann <dietmar.eggemann@arm.com> wrote:
>
> Add the sum of (original) CPU capacity of all member CPUs to the root
> domain.
>
> This is needed for capacity-aware SCHED_DEADLINE admission control.
>
> Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
> ---
> kernel/sched/sched.h | 11 +++++++++++
> kernel/sched/topology.c | 14 ++++++++++----
> 2 files changed, 21 insertions(+), 4 deletions(-)
>
> diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
> index 1e72d1b3d3ce..91bd0cb0c529 100644
> --- a/kernel/sched/sched.h
> +++ b/kernel/sched/sched.h
> @@ -797,6 +797,7 @@ struct root_domain {
> cpumask_var_t rto_mask;
> struct cpupri cpupri;
>
> + unsigned long sum_cpu_capacity;
> unsigned long max_cpu_capacity;
>
> /*
> @@ -2393,6 +2394,16 @@ static inline unsigned long capacity_orig_of(int cpu)
> {
> return cpu_rq(cpu)->cpu_capacity_orig;
> }
> +
> +static inline unsigned long rd_capacity(int cpu)
> +{
> + return cpu_rq(cpu)->rd->sum_cpu_capacity;
> +}
> +#else
> +static inline unsigned long rd_capacity(int cpu)
> +{
> + return SCHED_CAPACITY_SCALE;
> +}
> #endif
>
> /**
> diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
> index 8344757bba6e..74b0c0fa4b1b 100644
> --- a/kernel/sched/topology.c
> +++ b/kernel/sched/topology.c
> @@ -2052,12 +2052,17 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
> /* Attach the domains */
> rcu_read_lock();
> for_each_cpu(i, cpu_map) {
> + unsigned long cap = arch_scale_cpu_capacity(i);
Why do you replace the use of rq->cpu_capacity_orig by
arch_scale_cpu_capacity(i) ?
There is nothing about this change in the commit message
> +
> rq = cpu_rq(i);
> sd = *per_cpu_ptr(d.sd, i);
>
> /* Use READ_ONCE()/WRITE_ONCE() to avoid load/store tearing: */
> - if (rq->cpu_capacity_orig > READ_ONCE(d.rd->max_cpu_capacity))
> - WRITE_ONCE(d.rd->max_cpu_capacity, rq->cpu_capacity_orig);
> + if (cap > READ_ONCE(d.rd->max_cpu_capacity))
> + WRITE_ONCE(d.rd->max_cpu_capacity, cap);
> +
> + WRITE_ONCE(d.rd->sum_cpu_capacity,
> + READ_ONCE(d.rd->sum_cpu_capacity) + cap);
>
> cpu_attach_domain(sd, d.rd, i);
> }
> @@ -2067,8 +2072,9 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
> static_branch_inc_cpuslocked(&sched_asym_cpucapacity);
>
> if (rq && sched_debug_enabled) {
> - pr_info("root domain span: %*pbl (max cpu_capacity = %lu)\n",
> - cpumask_pr_args(cpu_map), rq->rd->max_cpu_capacity);
> + pr_info("root domain span: %*pbl (capacity = %lu max cpu_capacity = %lu)\n",
> + cpumask_pr_args(cpu_map), rq->rd->sum_cpu_capacity,
> + rq->rd->max_cpu_capacity);
> }
>
> ret = 0;
> --
> 2.17.1
>
next prev parent reply other threads:[~2020-04-08 12:29 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-04-08 9:50 [PATCH 0/4] Capacity awareness for SCHED_DEADLINE Dietmar Eggemann
2020-04-08 9:50 ` [PATCH 1/4] sched/topology: Store root domain CPU capacity sum Dietmar Eggemann
2020-04-08 12:29 ` Vincent Guittot [this message]
2020-04-08 16:30 ` Dietmar Eggemann
2020-04-08 17:03 ` Vincent Guittot
2020-04-09 13:50 ` Dietmar Eggemann
2020-04-09 14:13 ` Vincent Guittot
2020-04-14 9:20 ` Dietmar Eggemann
2020-04-14 12:45 ` Quentin Perret
2020-04-14 15:27 ` Dietmar Eggemann
2020-04-14 15:43 ` Vincent Guittot
2020-04-08 9:50 ` [PATCH 2/4] sched/deadline: Improve admission control for asymmetric CPU capacities Dietmar Eggemann
2020-04-08 10:42 ` Valentin Schneider
2020-04-08 12:26 ` Dietmar Eggemann
2020-04-08 13:30 ` luca abeni
2020-04-08 14:23 ` Qais Yousef
2020-04-08 15:01 ` Valentin Schneider
2020-04-09 17:29 ` Dietmar Eggemann
2020-04-14 11:40 ` Qais Yousef
2020-04-14 14:29 ` Valentin Schneider
2020-04-14 15:41 ` Qais Yousef
2020-04-14 14:28 ` Valentin Schneider
2020-04-17 12:19 ` Juri Lelli
2020-04-17 14:55 ` Dietmar Eggemann
2020-04-17 15:08 ` Juri Lelli
2020-04-17 15:47 ` Juri Lelli
2020-04-08 9:50 ` [PATCH 3/4] sched/deadline: Make DL capacity-aware Dietmar Eggemann
2020-04-10 12:52 ` Juri Lelli
2020-04-15 9:39 ` Dietmar Eggemann
2020-04-15 13:20 ` Juri Lelli
2020-04-15 16:42 ` luca abeni
2020-04-16 13:19 ` Juri Lelli
2020-04-08 9:50 ` [PATCH 4/4] sched/deadline: Implement fallback mechanism for !fit case Dietmar Eggemann
2020-04-09 10:25 ` Qais Yousef
2020-04-09 13:00 ` luca abeni
2020-04-09 14:55 ` Qais Yousef
2020-04-09 18:43 ` Dietmar Eggemann
2020-04-14 11:29 ` Qais Yousef
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=CAKfTPtC4_+dTddLdoFMdzUvsXwWyi3bUOXcg9kstC8RzZS_a+A@mail.gmail.com \
--to=vincent.guittot@linaro.org \
--cc=balsini@google.com \
--cc=bristot@redhat.com \
--cc=dietmar.eggemann@arm.com \
--cc=juri.lelli@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=luca.abeni@santannapisa.it \
--cc=mingo@redhat.com \
--cc=morten.rasmussen@arm.com \
--cc=patrick.bellasi@matbug.net \
--cc=peterz@infradead.org \
--cc=pkondeti@codeaurora.org \
--cc=qais.yousef@arm.com \
--cc=qperret@google.com \
--cc=rostedt@goodmis.org \
--cc=valentin.schneider@arm.com \
--cc=wvw@google.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).