From: Tim Chen <tim.c.chen@linux.intel.com>
To: K Prateek Nayak <kprateek.nayak@amd.com>,
Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
Dave Hansen <dave.hansen@linux.intel.com>,
Peter Zijlstra <peterz@infradead.org>,
Juri Lelli <juri.lelli@redhat.com>,
Vincent Guittot <vincent.guittot@linaro.org>,
x86@kernel.org, linux-kernel@vger.kernel.org
Cc: "H. Peter Anvin" <hpa@zytor.com>,
Dietmar Eggemann <dietmar.eggemann@arm.com>,
Steven Rostedt <rostedt@goodmis.org>,
Ben Segall <bsegall@google.com>, Mel Gorman <mgorman@suse.de>,
Valentin Schneider <vschneid@redhat.com>,
"Rafael J. Wysocki" <rafael.j.wysocki@intel.com>,
Ricardo Neri <ricardo.neri-calderon@linux.intel.com>,
Mario Limonciello <mario.limonciello@amd.com>,
Meng Li <li.meng@amd.com>, Huang Rui <ray.huang@amd.com>,
"Gautham R. Shenoy" <gautham.shenoy@amd.com>
Subject: Re: [PATCH 3/8] x86/itmt: Move the "sched_itmt_enabled" sysctl to debugfs
Date: Fri, 13 Dec 2024 09:19:11 -0800 [thread overview]
Message-ID: <c805040fa2300a186cb8b0e9650543c529bd82ab.camel@linux.intel.com> (raw)
In-Reply-To: <926692eb-8982-475f-b3ef-4409251623f4@amd.com>
On Fri, 2024-12-13 at 09:31 +0530, K Prateek Nayak wrote:
> Hello Tim,
>
> Thank you for reviewing the series.
>
> On 12/13/2024 12:45 AM, Tim Chen wrote:
> > On Wed, 2024-12-11 at 18:55 +0000, K Prateek Nayak wrote:
> > > "sched_itmt_enabled" was only introduced as a debug toggle for any funky
> > > ITMT behavior. Move the sysctl controlled from
> > > "/proc/sys/kernel/sched_itmt_enabled" to debugfs at
> > > "/sys/kernel/debug/x86/sched_itmt_enabled" with a notable change that a
> > > cat on the file will return "Y" or "N" instead of "1" or "0" to
> > > indicate that feature is enabled or disabled respectively.
> > >
> >
> > Valid values of setting "sched_itmt_enabled" likewise change from "1" or "0"
> > to "Y" or "N".
>
> Turns out you can still use "1" and "0". Running:
>
> echo Y > /sys/kernel/debug/sched/verbose
> echo "sched_itmt_enabled: $(cat /sys/kernel/debug/x86/sched_itmt_enabled)";
> for i in 0 1 N Y;
> do
> echo "Writing $i to /sys/kernel/debug/x86/sched_itmt_enabled";
> echo $i > /sys/kernel/debug/x86/sched_itmt_enabled;
> echo "sched_itmt_enabled: $(cat /sys/kernel/debug/x86/sched_itmt_enabled)";
> echo "sched domain flags:";
> cat /sys/kernel/debug/sched/domains/cpu0/domain*/flags;
> echo;
> done
>
> Yields the following output on my system:
>
> sched_itmt_enabled: Y
>
> Writing 0 to /sys/kernel/debug/x86/sched_itmt_enabled
> sched_itmt_enabled: N
> sched domain flags:
> SD_BALANCE_NEWIDLE SD_BALANCE_EXEC SD_BALANCE_FORK SD_WAKE_AFFINE SD_SHARE_CPUCAPACITY SD_SHARE_LLC SD_PREFER_SIBLING
> SD_BALANCE_NEWIDLE SD_BALANCE_EXEC SD_BALANCE_FORK SD_WAKE_AFFINE SD_SHARE_LLC SD_PREFER_SIBLING
> SD_BALANCE_NEWIDLE SD_BALANCE_EXEC SD_BALANCE_FORK SD_WAKE_AFFINE SD_PREFER_SIBLING
>
> Writing 1 to /sys/kernel/debug/x86/sched_itmt_enabled
> sched_itmt_enabled: Y
> sched domain flags:
> SD_BALANCE_NEWIDLE SD_BALANCE_EXEC SD_BALANCE_FORK SD_WAKE_AFFINE SD_SHARE_CPUCAPACITY SD_SHARE_LLC SD_PREFER_SIBLING
> SD_BALANCE_NEWIDLE SD_BALANCE_EXEC SD_BALANCE_FORK SD_WAKE_AFFINE SD_SHARE_LLC SD_ASYM_PACKING SD_PREFER_SIBLING
> SD_BALANCE_NEWIDLE SD_BALANCE_EXEC SD_BALANCE_FORK SD_WAKE_AFFINE SD_ASYM_PACKING SD_PREFER_SIBLING
>
> Writing N to /sys/kernel/debug/x86/sched_itmt_enabled
> sched_itmt_enabled: N
> sched domain flags:
> SD_BALANCE_NEWIDLE SD_BALANCE_EXEC SD_BALANCE_FORK SD_WAKE_AFFINE SD_SHARE_CPUCAPACITY SD_SHARE_LLC SD_PREFER_SIBLING
> SD_BALANCE_NEWIDLE SD_BALANCE_EXEC SD_BALANCE_FORK SD_WAKE_AFFINE SD_SHARE_LLC SD_PREFER_SIBLING
> SD_BALANCE_NEWIDLE SD_BALANCE_EXEC SD_BALANCE_FORK SD_WAKE_AFFINE SD_PREFER_SIBLING
>
> Writing Y to /sys/kernel/debug/x86/sched_itmt_enabled
> sched_itmt_enabled: Y
> sched domain flags:
> SD_BALANCE_NEWIDLE SD_BALANCE_EXEC SD_BALANCE_FORK SD_WAKE_AFFINE SD_SHARE_CPUCAPACITY SD_SHARE_LLC SD_PREFER_SIBLING
> SD_BALANCE_NEWIDLE SD_BALANCE_EXEC SD_BALANCE_FORK SD_WAKE_AFFINE SD_SHARE_LLC SD_ASYM_PACKING SD_PREFER_SIBLING
> SD_BALANCE_NEWIDLE SD_BALANCE_EXEC SD_BALANCE_FORK SD_WAKE_AFFINE SD_ASYM_PACKING SD_PREFER_SIBLING
>
> Would you like me to extend that note as:
>
> ... with a notable change that a
> cat on the file will return "Y" or "N" instead of "1" or "0" to
> indicate that feature is enabled or disabled respectively. User can
> either write "0" or "1" to toggle the feature off when enabled, or
> "1" or "Y" to toggle the feature on when disabled.
>
> for the record?
>
>
Sure. Thanks.
Tim
next prev parent reply other threads:[~2024-12-13 17:19 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-12-11 18:55 [PATCH 0/8] x86, sched: Dynamic ITMT core ranking support and some yak shaving K Prateek Nayak
2024-12-11 18:55 ` [PATCH 1/8] x86/itmt: Convert "sysctl_sched_itmt_enabled" to boolean K Prateek Nayak
2024-12-12 18:09 ` Tim Chen
2024-12-11 18:55 ` [PATCH 2/8] x86/itmt: Use guard() for itmt_update_mutex K Prateek Nayak
2024-12-12 18:22 ` Tim Chen
2024-12-11 18:55 ` [PATCH 3/8] x86/itmt: Move the "sched_itmt_enabled" sysctl to debugfs K Prateek Nayak
2024-12-12 19:15 ` Tim Chen
2024-12-13 4:01 ` K Prateek Nayak
2024-12-13 17:19 ` Tim Chen [this message]
2024-12-13 9:16 ` Peter Zijlstra
2024-12-11 18:55 ` [PATCH 4/8] x86/topology: Remove x86_smt_flags and use cpu_smt_flags directly K Prateek Nayak
2024-12-12 21:05 ` Tim Chen
2024-12-11 18:55 ` [PATCH 5/8] x86/topology: Use x86_sched_itmt_flags for PKG domain unconditionally K Prateek Nayak
2024-12-13 21:07 ` Tim Chen
2024-12-11 18:55 ` [PATCH 6/8] sched/fair: Do not compute NUMA Balancing stats unnecessarily during lb K Prateek Nayak
2024-12-12 11:05 ` Vincent Guittot
2024-12-12 11:43 ` K Prateek Nayak
2024-12-12 13:28 ` Vincent Guittot
2024-12-13 14:55 ` Shrikanth Hegde
2024-12-11 18:55 ` [PATCH 7/8] sched/fair: Do not compute overloaded status " K Prateek Nayak
2024-12-12 9:56 ` Vincent Guittot
2024-12-12 11:01 ` K Prateek Nayak
2024-12-12 11:18 ` Vincent Guittot
2024-12-12 11:30 ` K Prateek Nayak
2024-12-13 14:57 ` Shrikanth Hegde
2024-12-13 19:51 ` K Prateek Nayak
2024-12-11 18:55 ` [RFC PATCH 8/8] sched/fair: Uncache asym_prefer_cpu and find it during update_sd_lb_stats() K Prateek Nayak
2024-12-13 15:02 ` Shrikanth Hegde
2024-12-13 20:00 ` K Prateek Nayak
2024-12-13 0:33 ` [PATCH 0/8] x86, sched: Dynamic ITMT core ranking support and some yak shaving Tim Chen
2024-12-13 4:12 ` K Prateek Nayak
2024-12-13 21:11 ` Tim Chen
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=c805040fa2300a186cb8b0e9650543c529bd82ab.camel@linux.intel.com \
--to=tim.c.chen@linux.intel.com \
--cc=bp@alien8.de \
--cc=bsegall@google.com \
--cc=dave.hansen@linux.intel.com \
--cc=dietmar.eggemann@arm.com \
--cc=gautham.shenoy@amd.com \
--cc=hpa@zytor.com \
--cc=juri.lelli@redhat.com \
--cc=kprateek.nayak@amd.com \
--cc=li.meng@amd.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mario.limonciello@amd.com \
--cc=mgorman@suse.de \
--cc=mingo@redhat.com \
--cc=peterz@infradead.org \
--cc=rafael.j.wysocki@intel.com \
--cc=ray.huang@amd.com \
--cc=ricardo.neri-calderon@linux.intel.com \
--cc=rostedt@goodmis.org \
--cc=tglx@linutronix.de \
--cc=vincent.guittot@linaro.org \
--cc=vschneid@redhat.com \
--cc=x86@kernel.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