From: Peter Zijlstra <peterz@infradead.org>
To: Oleg Nesterov <oleg@redhat.com>
Cc: Chris Mason <chris.mason@oracle.com>,
Frank Rowand <frank.rowand@am.sony.com>,
Ingo Molnar <mingo@elte.hu>, Thomas Gleixner <tglx@linutronix.de>,
Mike Galbraith <efault@gmx.de>, Paul Turner <pjt@google.com>,
Jens Axboe <axboe@kernel.dk>,
linux-kernel@vger.kernel.org
Subject: Re: [RFC][PATCH 5/5] sched: Reduce ttwu rq->lock contention
Date: Fri, 17 Dec 2010 19:41:04 +0100 [thread overview]
Message-ID: <1292611264.2266.344.camel@twins> (raw)
In-Reply-To: <1292610297.2266.334.camel@twins>
On Fri, 2010-12-17 at 19:24 +0100, Peter Zijlstra wrote:
> > Even simpler. This can race with, say, __migrate_task() which does
> > deactivate_task + activate_task and temporary clears on_rq. Although
> > this is simple to fix, I think.
>
> Yes, another hole..
__migrate_task() is a tad special in that it should only migrate
runnable tasks, but of course we can have it preempted with ->state !=
TASK_RUNNING, which makes life interesting, but we can fix that by
including a PREEMPT_ACTIVE test in ttwu.
Other such callers are more straight fwd though:
rt_mutex_setprio()
set_user_nice()
sched_move_task()
__sched_setscheduler()
normalize_task()
none of those are fast-path operations, so it is quite doable to also
take the ->pi_lock there and fully serialize them.
next prev parent reply other threads:[~2010-12-17 18:41 UTC|newest]
Thread overview: 44+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-12-16 14:56 [RFC][PATCH 0/5] Reduce runqueue lock contention -v2 Peter Zijlstra
2010-12-16 14:56 ` [RFC][PATCH 1/5] sched: Always provide p->oncpu Peter Zijlstra
2010-12-18 1:03 ` Frank Rowand
2010-12-16 14:56 ` [RFC][PATCH 2/5] mutex: Use p->oncpu for the adaptive spin Peter Zijlstra
2010-12-16 17:34 ` Oleg Nesterov
2010-12-16 19:29 ` Peter Zijlstra
2010-12-17 19:17 ` Oleg Nesterov
2010-12-16 14:56 ` [RFC][PATCH 3/5] sched: Change the ttwu success details Peter Zijlstra
2010-12-16 15:23 ` Frederic Weisbecker
2010-12-16 15:27 ` Peter Zijlstra
2010-12-16 15:30 ` Peter Zijlstra
2010-12-16 15:45 ` Frederic Weisbecker
2010-12-16 15:35 ` Frederic Weisbecker
2010-12-18 1:05 ` Frank Rowand
2010-12-16 14:56 ` [RFC][PATCH 4/5] sched: Clean up ttwu stats Peter Zijlstra
2010-12-18 1:09 ` Frank Rowand
2010-12-16 14:56 ` [RFC][PATCH 5/5] sched: Reduce ttwu rq->lock contention Peter Zijlstra
2010-12-16 15:31 ` Frederic Weisbecker
2010-12-16 17:58 ` Oleg Nesterov
2010-12-16 18:42 ` Oleg Nesterov
2010-12-16 18:58 ` Peter Zijlstra
2010-12-16 19:03 ` Peter Zijlstra
2010-12-16 19:47 ` Peter Zijlstra
2010-12-16 20:32 ` Peter Zijlstra
2010-12-17 3:06 ` Yan, Zheng
2010-12-17 13:23 ` Peter Zijlstra
2010-12-17 16:54 ` Oleg Nesterov
2010-12-17 17:43 ` Peter Zijlstra
2010-12-17 18:15 ` Peter Zijlstra
2010-12-17 19:28 ` Oleg Nesterov
2010-12-17 21:02 ` Peter Zijlstra
2010-12-18 14:49 ` Yong Zhang
2010-12-18 20:08 ` Oleg Nesterov
2010-12-19 11:20 ` Yong Zhang
2010-12-17 18:21 ` Oleg Nesterov
2010-12-17 17:50 ` Oleg Nesterov
2010-12-17 18:24 ` Peter Zijlstra
2010-12-17 18:41 ` Peter Zijlstra [this message]
2010-12-16 19:12 ` [RFC][PATCH 0/5] Reduce runqueue lock contention -v2 Frank Rowand
2010-12-16 19:36 ` Frank Rowand
2010-12-16 19:39 ` Frank Rowand
2010-12-16 19:42 ` Peter Zijlstra
2010-12-16 20:45 ` Frank Rowand
2010-12-16 19:36 ` Frank Rowand
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=1292611264.2266.344.camel@twins \
--to=peterz@infradead.org \
--cc=axboe@kernel.dk \
--cc=chris.mason@oracle.com \
--cc=efault@gmx.de \
--cc=frank.rowand@am.sony.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=oleg@redhat.com \
--cc=pjt@google.com \
--cc=tglx@linutronix.de \
/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