From: Nathan Lynch <ntl@pobox.com>
To: Dinakar Guniguntala <dino@in.ibm.com>
Cc: Paul Jackson <pj@sgi.com>,
Simon.Derr@bull.net, lse-tech@lists.sourceforge.net,
Andrew Morton <akpm@osdl.org>,
Nick Piggin <nickpiggin@yahoo.com.au>,
V Srivatsa <vatsa@in.ibm.com>,
lkml <linux-kernel@vger.kernel.org>
Subject: Re: [Lse-tech] Re: [PATCH] cpusets+hotplug+preepmt broken
Date: Fri, 13 May 2005 16:27:45 -0500 [thread overview]
Message-ID: <20050513212745.GJ3614@otto> (raw)
In-Reply-To: <20050513123216.GB3968@in.ibm.com>
On Fri, May 13, 2005 at 06:02:17PM +0530, Dinakar Guniguntala wrote:
> On Wed, May 11, 2005 at 02:51:56PM -0500, Nathan Lynch wrote:
>
> > This trace is what should be fixed -- we're trying to schedule while
> > the machine is "stopped" (all cpus except for one spinning with
> > interrupts off). I'm not too familiar with the cpusets code but I
> > would like to stay away from nesting these semaphores if at all
> > possible.
>
> Vatsa pointed out another scenario where cpusets+hotplug is currently
> broken. attach_task in cpuset.c is called without holding the hotplug
> lock and it is possible to call set_cpus_allowed for a task with no
> online cpus.
> Given this I think the patch I sent first is the most appropriate
> patch.
Your original patch is deadlocky since cpuset_cpus_allowed() does
task_lock() while write_lock_irq(&tasklist_lock) is already held by
migrate_live_tasks().
Nathan
prev parent reply other threads:[~2005-05-13 21:34 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2005-05-11 19:16 [PATCH] cpusets+hotplug+preepmt broken Dinakar Guniguntala
2005-05-11 19:25 ` [Lse-tech] " Paul Jackson
2005-05-11 19:55 ` Paul Jackson
2005-05-11 20:26 ` Nathan Lynch
2005-05-11 20:45 ` Paul Jackson
2005-05-11 19:51 ` Nathan Lynch
2005-05-11 20:42 ` Paul Jackson
2005-05-11 20:58 ` Paul Jackson
2005-05-14 2:23 ` Paul Jackson
2005-05-14 12:14 ` Nathan Lynch
2005-05-14 17:04 ` Paul Jackson
2005-05-14 17:44 ` Paul Jackson
2005-05-18 4:14 ` Paul Jackson
2005-05-18 9:29 ` [Lse-tech] " Dinakar Guniguntala
2005-05-18 14:48 ` Nathan Lynch
2005-05-18 21:16 ` Paul Jackson
2005-05-14 16:28 ` Srivatsa Vaddagiri
2005-05-12 15:10 ` Dinakar Guniguntala
2005-05-13 12:15 ` [Lse-tech] " Dinakar Guniguntala
2005-05-13 0:34 ` Nathan Lynch
2005-05-13 12:32 ` [Lse-tech] " Dinakar Guniguntala
2005-05-13 17:25 ` Srivatsa Vaddagiri
2005-05-13 19:59 ` Paul Jackson
2005-05-13 20:20 ` Dipankar Sarma
2005-05-13 20:46 ` Nathan Lynch
2005-05-13 21:05 ` Paul Jackson
2005-05-13 21:06 ` Dipankar Sarma
2005-05-13 20:52 ` Paul Jackson
2005-05-13 21:02 ` Dipankar Sarma
2005-05-14 2:58 ` Paul Jackson
2005-05-14 16:09 ` Srivatsa Vaddagiri
2005-05-14 17:50 ` Paul Jackson
2005-05-14 17:57 ` Paul Jackson
2005-05-14 16:30 ` Nathan Lynch
2005-05-14 17:23 ` Srivatsa Vaddagiri
2005-05-14 23:17 ` Nathan Lynch
2005-05-13 19:59 ` Paul Jackson
2005-05-13 21:27 ` Nathan Lynch [this message]
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=20050513212745.GJ3614@otto \
--to=ntl@pobox.com \
--cc=Simon.Derr@bull.net \
--cc=akpm@osdl.org \
--cc=dino@in.ibm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=lse-tech@lists.sourceforge.net \
--cc=nickpiggin@yahoo.com.au \
--cc=pj@sgi.com \
--cc=vatsa@in.ibm.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