From: Viresh Kumar <viresh.kumar@linaro.org>
To: Rafael Wysocki <rjw@rjwysocki.net>,
Ben Segall <bsegall@google.com>,
Dietmar Eggemann <dietmar.eggemann@arm.com>,
Ingo Molnar <mingo@redhat.com>,
Juri Lelli <juri.lelli@redhat.com>, Mel Gorman <mgorman@suse.de>,
Peter Zijlstra <peterz@infradead.org>,
Steven Rostedt <rostedt@goodmis.org>,
Vincent Guittot <vincent.guittot@linaro.org>,
Viresh Kumar <viresh.kumar@linaro.org>
Cc: linux-pm@vger.kernel.org, Lukasz Luba <lukasz.luba@arm.com>,
cristian.marussi@arm.com, sudeep.holla@arm.com,
linux-kernel@vger.kernel.org
Subject: [PATCH V2 0/4] cpufreq: Record stats with fast-switching
Date: Wed, 16 Sep 2020 12:15:27 +0530 [thread overview]
Message-ID: <cover.1600238586.git.viresh.kumar@linaro.org> (raw)
Hi,
We disabled recording cpufreq stats when fast switching was introduced
to the cpufreq core as the cpufreq stats required to take a spinlock and
that can't be allowed (for performance reasons) on scheduler's hot path.
Here is an attempt to get rid of the lock and bring back the support.
V1-V2:
- Use READ_ONCE/WRITE_ONCE instead of atomic in the first patch.
--
Viresh
Viresh Kumar (4):
cpufreq: stats: Defer stats update to
cpufreq_stats_record_transition()
cpufreq: stats: Remove locking
cpufreq: stats: Enable stats for fast-switch as well
cpufreq: Move traces and update to policy->cur to cpufreq core
drivers/cpufreq/cpufreq.c | 16 +++++-
drivers/cpufreq/cpufreq_stats.c | 87 ++++++++++++++++++++------------
kernel/sched/cpufreq_schedutil.c | 12 +----
3 files changed, 72 insertions(+), 43 deletions(-)
base-commit: 856deb866d16e29bd65952e0289066f6078af773
--
2.25.0.rc1.19.g042ed3e048af
next reply other threads:[~2020-09-16 6:45 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-09-16 6:45 Viresh Kumar [this message]
2020-09-16 6:45 ` [PATCH V2 1/4] cpufreq: stats: Defer stats update to cpufreq_stats_record_transition() Viresh Kumar
2020-09-23 13:48 ` Rafael J. Wysocki
2020-09-24 9:25 ` Lukasz Luba
2020-09-24 10:24 ` Rafael J. Wysocki
2020-09-24 11:00 ` Lukasz Luba
2020-09-24 11:07 ` Rafael J. Wysocki
2020-09-24 12:39 ` Viresh Kumar
2020-09-24 16:10 ` Lukasz Luba
2020-09-25 6:09 ` Viresh Kumar
2020-09-25 8:10 ` Lukasz Luba
2020-09-24 13:15 ` Viresh Kumar
2020-09-25 10:04 ` Rafael J. Wysocki
2020-09-25 10:58 ` Viresh Kumar
2020-09-25 11:09 ` Rafael J. Wysocki
2020-09-25 11:26 ` Viresh Kumar
2020-09-25 8:21 ` Lukasz Luba
2020-09-25 10:46 ` Viresh Kumar
2020-09-16 6:45 ` [PATCH V2 2/4] cpufreq: stats: Remove locking Viresh Kumar
2020-09-16 6:45 ` [PATCH V2 3/4] cpufreq: stats: Enable stats for fast-switch as well Viresh Kumar
2020-09-23 15:14 ` Rafael J. Wysocki
2020-09-23 15:17 ` Rafael J. Wysocki
2020-09-16 6:45 ` [PATCH V2 4/4] cpufreq: Move traces and update to policy->cur to cpufreq core Viresh Kumar
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=cover.1600238586.git.viresh.kumar@linaro.org \
--to=viresh.kumar@linaro.org \
--cc=bsegall@google.com \
--cc=cristian.marussi@arm.com \
--cc=dietmar.eggemann@arm.com \
--cc=juri.lelli@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pm@vger.kernel.org \
--cc=lukasz.luba@arm.com \
--cc=mgorman@suse.de \
--cc=mingo@redhat.com \
--cc=peterz@infradead.org \
--cc=rjw@rjwysocki.net \
--cc=rostedt@goodmis.org \
--cc=sudeep.holla@arm.com \
--cc=vincent.guittot@linaro.org \
/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).