From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
To: sashiko-reviews@lists.linux.dev
Cc: linux-rt-devel@lists.linux.dev, tj@kernel.org,
hannes@cmpxchg.org, mkoutny@suse.com,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH v5 22/29] sched/deadline: Make a rebuild use the CPU recorded with a task's bandwidth
Date: Sun, 8 Nov 2026 21:58:13 -0500 [thread overview]
Message-ID: <cba919a2-c540-44a2-af3a-bbade50501e9@efficios.com> (raw)
In-Reply-To: <sashiko-outbox-203947@kernel.org>
On 2026-11-08 14:25, sashiko-bot@kernel.org wrote:
> wrong root domain in dl_task_rebuild_cpu() on empty mask
Thanks. The path is as you describe, but the partition is where the task
runs. At its wakeup, select_fallback_rq() widens the mask of a task of
the top cpuset to top_cpuset.cpus_allowed, which is cpu_possible_mask in
cgroup v2. It then takes the lowest active CPU, CPU 0, in the new
partition. Had the rebuild asked the cpuset, the top root domain would
count the task. Its wakeup would then move the bandwidth into the
partition without room. The case also needs admission control off: with
it on, a deadline task's mask must hold its root domain.
You are right that the test of the record after the cpuset fallback
cannot succeed. It serves the other path, where the mask has an active
CPU. The next version makes that an else branch.
Thanks,
Mathieu
--
Mathieu Desnoyers
EfficiOS Inc.
https://www.efficios.com
next prev parent reply other threads:[~2026-11-09 2:58 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-11-08 18:53 [PATCH v5 00/29] sched/deadline: bandwidth accounting fixes and selftests Mathieu Desnoyers
2026-11-08 18:53 ` [PATCH v5 01/29] sched: Fix cpuset_mutex double unlock in __sched_setscheduler() Mathieu Desnoyers
2026-11-08 18:53 ` [PATCH v5 02/29] sched: Refuse SCHED_FLAG_KEEP_PARAMS that would change the policy or the class Mathieu Desnoyers
2026-11-08 18:53 ` [PATCH v5 03/29] sched/deadline: Do not admit bandwidth for parameters that are kept Mathieu Desnoyers
2026-11-08 18:53 ` [PATCH v5 04/29] sched: Let a task boosted by a deadline waiter change its policy Mathieu Desnoyers
2026-11-08 18:53 ` [PATCH v5 05/29] sched/deadline: Do not divide by zero active CPUs of a root domain Mathieu Desnoyers
2026-11-08 18:53 ` [PATCH v5 06/29] sched: Take cpuset_mutex for a deadline policy change only with pi Mathieu Desnoyers
2026-11-08 18:53 ` [PATCH v5 07/29] sched/deadline: Do not lose a throttled task switched out and back Mathieu Desnoyers
2026-11-08 18:53 ` [PATCH v5 08/29] sched/deadline: Take a deadline boost from the waiter's rt_mutex node Mathieu Desnoyers
2026-11-08 18:53 ` [PATCH v5 09/29] sched/deadline: Reset the deadline and the runtime with the parameters Mathieu Desnoyers
2026-11-08 18:53 ` [PATCH v5 10/29] sched/deadline: Reset the donor's runtime at a deboost in the class Mathieu Desnoyers
2026-11-08 19:17 ` sashiko-bot
2026-11-09 2:56 ` Mathieu Desnoyers
2026-11-08 18:53 ` [PATCH v5 11/29] sched/deadline: Release the bandwidth of a task that leaves the class asleep Mathieu Desnoyers
2026-11-08 18:53 ` [PATCH v5 12/29] sched/deadline: Reject SCHED_DEADLINE on exited tasks Mathieu Desnoyers
2026-11-08 18:53 ` [PATCH v5 13/29] sched/deadline: Keep departing bandwidth across a root domain rebuild Mathieu Desnoyers
2026-11-08 18:53 ` [PATCH v5 14/29] sched/deadline: Fix this_bw when a task is changed during a remote wakeup Mathieu Desnoyers
2026-11-08 18:53 ` [PATCH v5 15/29] sched/deadline: Rebuild the root domains' accounting from the task list Mathieu Desnoyers
2026-11-08 18:53 ` [PATCH v5 16/29] sched/deadline: Record the root domain holding a task's bandwidth Mathieu Desnoyers
2026-11-08 18:53 ` [PATCH v5 17/29] sched/deadline: Leave a dying task out of a rebuild of the accounting Mathieu Desnoyers
2026-11-08 18:53 ` [PATCH v5 18/29] sched/deadline: Move a task's bandwidth only where room was made Mathieu Desnoyers
2026-11-08 19:30 ` sashiko-bot
2026-11-09 2:57 ` Mathieu Desnoyers
2026-11-08 18:53 ` [PATCH v5 19/29] cgroup/cpuset: Wait for an attach before rebuilding the sched domains Mathieu Desnoyers
2026-11-08 18:53 ` [PATCH v5 20/29] cgroup/cpuset: Give back the bandwidth an attach did not move Mathieu Desnoyers
2026-11-08 18:53 ` [PATCH v5 21/29] cgroup/cpuset: Reserve the bandwidth in the root domain a task moves to Mathieu Desnoyers
2026-11-08 19:32 ` sashiko-bot
2026-11-09 2:57 ` Mathieu Desnoyers
2026-11-08 18:53 ` [PATCH v5 22/29] sched/deadline: Make a rebuild use the CPU recorded with a task's bandwidth Mathieu Desnoyers
2026-11-08 19:25 ` sashiko-bot
2026-11-09 2:58 ` Mathieu Desnoyers [this message]
2026-11-08 18:54 ` [PATCH v5 23/29] sched/deadline: Move a task's bandwidth when it must leave its CPU Mathieu Desnoyers
2026-11-08 19:41 ` sashiko-bot
2026-11-09 2:58 ` Mathieu Desnoyers
2026-11-08 18:54 ` [PATCH v5 24/29] sched/deadline: Cancel the replenishment timer with the parameters Mathieu Desnoyers
2026-11-08 18:54 ` [PATCH v5 25/29] sched/deadline: Count the bandwidth a boosted task is given Mathieu Desnoyers
2026-11-08 18:54 ` [PATCH v5 26/29] sched/debug: Show the deadline bandwidth of each runqueue Mathieu Desnoyers
2026-11-08 18:54 ` [PATCH v5 27/29] selftests/sched: Add a test of SCHED_DEADLINE policy round trips Mathieu Desnoyers
2026-11-08 18:54 ` [PATCH v5 28/29] selftests/sched: Test SCHED_DEADLINE bandwidth across a root domain rebuild Mathieu Desnoyers
2026-11-08 18:54 ` [PATCH v5 29/29] selftests/sched: Add a test of SCHED_DEADLINE bandwidth accounting Mathieu Desnoyers
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=cba919a2-c540-44a2-af3a-bbade50501e9@efficios.com \
--to=mathieu.desnoyers@efficios.com \
--cc=hannes@cmpxchg.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-rt-devel@lists.linux.dev \
--cc=mkoutny@suse.com \
--cc=sashiko-reviews@lists.linux.dev \
--cc=tj@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
all inboxes | Powered by JetHome®