From: Juri Lelli <juri.lelli@redhat.com>
To: Waiman Long <longman@redhat.com>, Tejun Heo <tj@kernel.org>,
Johannes Weiner <hannes@cmpxchg.org>,
Michal Koutny <mkoutny@suse.com>, Ingo Molnar <mingo@redhat.com>,
Peter Zijlstra <peterz@infradead.org>,
Vincent Guittot <vincent.guittot@linaro.org>,
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>,
Phil Auld <pauld@redhat.com>
Cc: Qais Yousef <qyousef@layalina.io>,
Sebastian Andrzej Siewior <bigeasy@linutronix.de>,
"Joel Fernandes (Google)" <joel@joelfernandes.org>,
Suleiman Souhlal <suleiman@google.com>,
Aashish Sharma <shraash@google.com>,
Shin Kawamura <kawasin@google.com>,
Vineeth Remanan Pillai <vineeth@bitbyteword.org>,
linux-kernel@vger.kernel.org, cgroups@vger.kernel.org,
Juri Lelli <juri.lelli@redhat.com>
Subject: [PATCH v2 0/2] Fix DEADLINE bandwidth accounting in root domain changes and hotplug
Date: Thu, 14 Nov 2024 14:28:08 +0000 [thread overview]
Message-ID: <20241114142810.794657-1-juri.lelli@redhat.com> (raw)
Hello!
v2 of a patch series [3] that addresses two issues affecting DEADLINE
bandwidth accounting during non-destructive changes to root domains and
hotplug operations. The series is based on top of Waiman's
"cgroup/cpuset: Remove redundant rebuild_sched_domains_locked() calls"
series [1] which is now merged into cgroups/for-6.13 (this series is
based on top of that, commit c4c9cebe2fb9). The discussion that
eventually led to these two series can be found at [2].
Waiman reported that v1 still failed to make his test_cpuset_prs.sh
happy, so I had to change both patches a little. It now seems to pass on
my runs.
Patch 01/02 deals with non-destructive root domain changes. With respect
to v1 we now always restore dl_server contributions, considering root
domain span and active cpus mask (otherwise accounting on the default
root domain would end up to be incorrect).
Patch 02/02 deals with hotplug. With respect to v1 I added special
casing when total_bw = 0 (so no DEADLINE tasks to consider) and when a
root domain is left with no cpus due to hotplug.
In all honesty, I still see intermittent issues that seems to however be
related to the dance we do in sched_cpu_deactivate(), where we first
turn everything related to a cpu/rq off and revert that if
cpuset_cpu_inactive() reveals failing DEADLINE checks. But, since these
seem to be orthogonal to the original discussion we started from, I
wanted to send this out as an hopefully meaningful update/improvement
since yesterday. Will continue looking into this.
Please go forth and test/review.
Series also available at
git@github.com:jlelli/linux.git upstream/dl-server-apply
Best,
Juri
[1] https://lore.kernel.org/lkml/20241110025023.664487-1-longman@redhat.com/
[2] https://lore.kernel.org/lkml/20241029225116.3998487-1-joel@joelfernandes.org/
[3] v1 - https://lore.kernel.org/lkml/20241113125724.450249-1-juri.lelli@redhat.com/
Juri Lelli (2):
sched/deadline: Restore dl_server bandwidth on non-destructive root
domain changes
sched/deadline: Correctly account for allocated bandwidth during
hotplug
kernel/sched/core.c | 2 +-
kernel/sched/deadline.c | 65 +++++++++++++++++++++++++++++++++--------
kernel/sched/sched.h | 2 +-
kernel/sched/topology.c | 8 +++--
4 files changed, 60 insertions(+), 17 deletions(-)
--
2.47.0
next reply other threads:[~2024-11-14 14:28 UTC|newest]
Thread overview: 80+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-11-14 14:28 Juri Lelli [this message]
2024-11-14 14:28 ` [PATCH v2 1/2] sched/deadline: Restore dl_server bandwidth on non-destructive root domain changes Juri Lelli
2024-11-14 15:56 ` Phil Auld
2024-11-14 14:28 ` [PATCH v2 2/2] sched/deadline: Correctly account for allocated bandwidth during hotplug Juri Lelli
2024-11-14 15:58 ` Phil Auld
2024-12-06 10:43 ` Dan Carpenter
2024-12-09 14:20 ` Juri Lelli
2024-11-14 15:48 ` [PATCH v2 0/2] Fix DEADLINE bandwidth accounting in root domain changes and hotplug Waiman Long
2024-11-14 16:14 ` Juri Lelli
2024-11-14 18:16 ` Waiman Long
2024-11-14 18:43 ` Phil Auld
2024-11-15 11:48 ` [PATCH v2 3/2] sched/deadline: Check bandwidth overflow earlier for hotplug Juri Lelli
2025-01-10 11:52 ` Jon Hunter
2025-01-10 15:45 ` Juri Lelli
2025-01-10 18:40 ` Jon Hunter
2025-01-13 9:32 ` Juri Lelli
2025-01-13 13:53 ` Jon Hunter
2025-01-14 13:52 ` Jon Hunter
2025-01-14 14:02 ` Juri Lelli
2025-01-15 16:10 ` Juri Lelli
2025-01-16 13:14 ` Jon Hunter
2025-01-16 15:55 ` Juri Lelli
2025-02-03 11:01 ` Jon Hunter
2025-02-04 17:26 ` Juri Lelli
2025-02-05 6:53 ` Juri Lelli
2025-02-05 10:12 ` Juri Lelli
2025-02-05 16:56 ` Jon Hunter
2025-02-06 9:29 ` Juri Lelli
2025-02-07 10:38 ` Jon Hunter
2025-02-07 13:38 ` Dietmar Eggemann
2025-02-07 14:04 ` Jon Hunter
2025-02-07 15:55 ` Christian Loehle
2025-02-10 17:09 ` Juri Lelli
2025-02-11 8:36 ` Dietmar Eggemann
2025-02-11 9:21 ` Juri Lelli
2025-02-11 10:43 ` Dietmar Eggemann
2025-02-11 10:15 ` Christian Loehle
2025-02-11 10:42 ` Juri Lelli
2025-02-12 18:22 ` Dietmar Eggemann
2025-02-13 6:20 ` Juri Lelli
2025-02-13 12:27 ` Christian Loehle
2025-02-13 13:33 ` Juri Lelli
2025-02-13 13:38 ` Christian Loehle
2025-02-13 14:51 ` Juri Lelli
2025-02-13 14:57 ` Christian Loehle
2025-02-16 16:33 ` Qais Yousef
2025-02-17 14:52 ` Juri Lelli
2025-02-22 23:59 ` Qais Yousef
2025-02-24 9:27 ` Juri Lelli
2025-02-25 0:02 ` Qais Yousef
2025-02-25 9:46 ` Juri Lelli
2025-02-25 10:09 ` Christian Loehle
2025-02-12 23:01 ` Jon Hunter
2025-02-13 6:16 ` Juri Lelli
2025-02-13 9:53 ` Jon Hunter
2025-02-14 10:05 ` Jon Hunter
2025-02-17 16:08 ` Juri Lelli
2025-02-17 16:10 ` Jon Hunter
2025-02-17 16:25 ` Juri Lelli
2025-02-18 9:58 ` Juri Lelli
2025-02-18 10:30 ` Juri Lelli
2025-02-18 14:12 ` Dietmar Eggemann
2025-02-18 14:18 ` Juri Lelli
2025-02-19 9:29 ` Dietmar Eggemann
2025-02-19 10:02 ` Juri Lelli
2025-02-19 11:23 ` Jon Hunter
2025-02-19 13:09 ` Dietmar Eggemann
2025-02-19 18:14 ` Dietmar Eggemann
2025-02-20 10:40 ` Juri Lelli
2025-02-20 15:25 ` Juri Lelli
2025-02-21 11:56 ` Jon Hunter
2025-02-21 14:45 ` Dietmar Eggemann
2025-02-24 13:53 ` Dietmar Eggemann
2025-02-24 14:03 ` Juri Lelli
2025-02-24 23:39 ` Jon Hunter
2025-02-25 9:48 ` Juri Lelli
2025-03-03 14:17 ` Jon Hunter
2025-03-03 16:00 ` Juri Lelli
2025-02-07 14:04 ` Jon Hunter
2025-02-07 15:52 ` Juri Lelli
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=20241114142810.794657-1-juri.lelli@redhat.com \
--to=juri.lelli@redhat.com \
--cc=bigeasy@linutronix.de \
--cc=bsegall@google.com \
--cc=cgroups@vger.kernel.org \
--cc=dietmar.eggemann@arm.com \
--cc=hannes@cmpxchg.org \
--cc=joel@joelfernandes.org \
--cc=kawasin@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=longman@redhat.com \
--cc=mgorman@suse.de \
--cc=mingo@redhat.com \
--cc=mkoutny@suse.com \
--cc=pauld@redhat.com \
--cc=peterz@infradead.org \
--cc=qyousef@layalina.io \
--cc=rostedt@goodmis.org \
--cc=shraash@google.com \
--cc=suleiman@google.com \
--cc=tj@kernel.org \
--cc=vincent.guittot@linaro.org \
--cc=vineeth@bitbyteword.org \
--cc=vschneid@redhat.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