From: Steven Rostedt <rostedt@goodmis.org>
To: Ran Hongyun <ranhongyun1@huawei.com>
Cc: <namcao@linutronix.de>, <axboe@kernel.dk>,
<bigeasy@linutronix.de>, <brauner@kernel.org>,
<clrkwllms@kernel.org>, <frederic@kernel.org>, <jack@suse.cz>,
<jdamato@fastly.com>, <john.ogness@linutronix.de>,
<kprateek.nayak@amd.com>, <linux-fsdevel@vger.kernel.org>,
<linux-kernel@vger.kernel.org>, <linux-rt-devel@lists.linux.dev>,
<linux-rt-users@vger.kernel.org>, <mkarsten@uwaterloo.ca>,
<stable@vger.kernel.org>, <torvalds@linux-foundation.org>,
<viro@zeniv.linux.org.uk>, <vschneid@redhat.com>,
<xry111@xry111.site>, <chengzhihao1@huawei.com>,
<yangerkun@huawei.com>, <yi.zhang@huawei.com>,
<wozizhi@huawei.com>
Subject: Re: [QUESTION] Are these issues PREEMPT_RT-specific?
Date: Fri, 4 Sep 2026 09:47:33 -0400 [thread overview]
Message-ID: <20260904094733.538d2af6@gandalf.local.home> (raw)
In-Reply-To: <20260904081149.3000727-1-ranhongyun1@huawei.com>
On Fri, 4 Sep 2026 16:11:41 +0800
Ran Hongyun <ranhongyun1@huawei.com> wrote:
> 1.Priority inversion – On PREEMPT_RT, rwlock_t readers lack priority
> inheritance (PI), so a low-priority reader holding the lock can be
> preempted by a medium-priority task, blocking a high-priority writer
> indefinitely.
Priority inheritance to boost readers from a writer is an exponentially
difficult problem to solve. PI is already hard enough, but multiple readers
is exponentially more difficult (we tried).
The solution is to make sure you do not have any RT critical tasks taking
rw writer locks. This is something that the Runtime Verifier (RV) can help
make sure you never hit this situation.
-- Steve
next prev parent reply other threads:[~2026-09-04 13:47 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-07-15 12:46 [PATCH v4 0/1] eventpoll: Fix priority inversion problem Nam Cao
2025-07-15 12:46 ` [PATCH v4 1/1] eventpoll: Replace rwlock with spinlock Nam Cao
2025-07-15 12:58 ` Nam Cao
2025-07-15 16:42 ` Linus Torvalds
2025-07-16 7:41 ` Nam Cao
2025-07-16 8:34 ` K Prateek Nayak
2025-08-26 8:43 ` Nam Cao
2025-09-03 8:40 ` Sebastian Andrzej Siewior
2025-09-05 13:52 ` Christian Brauner
2026-09-04 8:10 ` [QUESTION] Are these issues PREEMq:PT_RT-specific? Ran Hongyun
2026-09-04 8:11 ` [QUESTION] Are these issues PREEMPT_RT-specific? Ran Hongyun
2026-09-04 8:52 ` Florian Bezdeka
2026-09-09 3:05 ` Ran Hongyun
2026-09-09 12:49 ` Steven Rostedt
2026-09-04 9:00 ` K Prateek Nayak
2026-09-04 13:47 ` Steven Rostedt [this message]
2025-09-05 13:52 ` [PATCH v4 0/1] eventpoll: Fix priority inversion problem Christian Brauner
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=20260904094733.538d2af6@gandalf.local.home \
--to=rostedt@goodmis.org \
--cc=axboe@kernel.dk \
--cc=bigeasy@linutronix.de \
--cc=brauner@kernel.org \
--cc=chengzhihao1@huawei.com \
--cc=clrkwllms@kernel.org \
--cc=frederic@kernel.org \
--cc=jack@suse.cz \
--cc=jdamato@fastly.com \
--cc=john.ogness@linutronix.de \
--cc=kprateek.nayak@amd.com \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-rt-devel@lists.linux.dev \
--cc=linux-rt-users@vger.kernel.org \
--cc=mkarsten@uwaterloo.ca \
--cc=namcao@linutronix.de \
--cc=ranhongyun1@huawei.com \
--cc=stable@vger.kernel.org \
--cc=torvalds@linux-foundation.org \
--cc=viro@zeniv.linux.org.uk \
--cc=vschneid@redhat.com \
--cc=wozizhi@huawei.com \
--cc=xry111@xry111.site \
--cc=yangerkun@huawei.com \
--cc=yi.zhang@huawei.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