From: Peter Zijlstra <a.p.zijlstra@chello.nl>
To: David Rientjes <rientjes@google.com>
Cc: Mike Galbraith <efault@gmx.de>,
LKML <linux-kernel@vger.kernel.org>, Tejun Heo <htejun@gmail.com>,
Li Zefan <lizf@cn.fujitsu.com>, Paul Menage <paul@paulmenage.org>
Subject: Re: patch] cpusets, cgroups: disallow attaching kthreadd
Date: Thu, 20 Oct 2011 12:32:07 +0200 [thread overview]
Message-ID: <1319106727.8653.3.camel@laptop> (raw)
In-Reply-To: <alpine.DEB.2.00.1110191243110.2892@chino.kir.corp.google.com>
On Wed, 2011-10-19 at 12:47 -0700, David Rientjes wrote:
> On Wed, 19 Oct 2011, Peter Zijlstra wrote:
>
> > My thinking is that kthreadd is the mother of all kernel threads and the
> > kernel assumes it can spawn kthreads without constraints, a valid
> > assumption IMO.
> >
>
> Cgroups don't necessarily imply constraints,
And yet they're called: Control Groups..
> though, you could devise a
> cgroup to just do monitoring or statistics tracking for an aggregate of
> tasks and placing kthreadd in such a cgroup would make perfect sense
> because then, since children are forked in the same cgroup, you can
> monitor or gather statistics for all kthreads. This can be your only
> cgroup on the system.
I guess you could, but does it really make sense? Also, you could sort
this by extending the cgroup interface to explicitly distinct between
controllers and !controllers.
> Cpusets, though, does imply cpu constraints, which is why we decline
> PF_THREAD_BOUND threads from moving in the first place, which is the
> source of Mike's issue. It's can_attach() function can explicitly decline
> kthreadd as well since the cpu constraints of both types of threads should
> never be altered by either cpusets or sched_setaffinity().
Yeah, and I'm saying we want to exclude _all_ controllers from placing
constraints on kthreadd, even those that might not immediately break
stuff.
next prev parent reply other threads:[~2011-10-20 10:32 UTC|newest]
Thread overview: 56+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-09-23 6:21 [patch] cpusets: allow PF_THREAD_BOUND kworkers to escape from a cpuset Mike Galbraith
2011-09-23 7:00 ` Li Zefan
2011-09-23 7:19 ` Mike Galbraith
2011-09-23 9:12 ` David Rientjes
2011-09-23 9:42 ` Mike Galbraith
2011-09-23 10:53 ` Mike Galbraith
2011-09-23 13:27 ` David Rientjes
2011-09-23 14:33 ` Mike Galbraith
2011-09-23 18:16 ` Mike Galbraith
2011-09-23 20:20 ` David Rientjes
2011-09-24 3:21 ` Tejun Heo
2011-10-10 5:34 ` Mike Galbraith
2011-10-10 8:03 ` [patch] cpusets, cgroups: disallow attaching kthreadd Mike Galbraith
2011-10-10 16:43 ` Tejun Heo
2011-10-11 2:31 ` Mike Galbraith
2011-10-11 14:08 ` Peter Zijlstra
2011-10-11 16:57 ` Mike Galbraith
2011-10-12 1:22 ` David Rientjes
2011-10-12 1:45 ` Mike Galbraith
2011-10-12 1:20 ` David Rientjes
2011-10-18 8:10 ` patch] " Mike Galbraith
2011-10-18 8:16 ` David Rientjes
2011-10-18 8:42 ` Peter Zijlstra
2011-10-18 8:47 ` Mike Galbraith
2011-10-18 9:06 ` Peter Zijlstra
2011-10-18 9:23 ` Mike Galbraith
2011-10-18 10:11 ` Mike Galbraith
2011-10-18 20:38 ` David Rientjes
2011-10-19 4:00 ` Mike Galbraith
2011-10-19 4:53 ` Paul Menage
2011-10-19 4:56 ` Paul Menage
2011-10-19 5:28 ` Mike Galbraith
2011-10-19 7:50 ` Peter Zijlstra
2011-10-19 19:47 ` David Rientjes
2011-10-20 10:32 ` Peter Zijlstra [this message]
2011-10-20 21:24 ` David Rientjes
2011-10-19 4:57 ` Paul Menage
2011-10-19 5:24 ` [patch-final] " Mike Galbraith
2011-10-19 7:54 ` Peter Zijlstra
2011-10-19 8:00 ` Paul Menage
2011-10-19 8:21 ` Mike Galbraith
2011-10-26 20:27 ` David Rientjes
2011-11-10 20:51 ` David Rientjes
2011-12-06 20:13 ` David Rientjes
2011-12-06 22:47 ` Andrew Morton
2011-12-06 23:53 ` David Rientjes
2011-12-07 0:05 ` Andrew Morton
2011-12-07 3:18 ` [resubmit] " Mike Galbraith
2011-12-07 4:36 ` Mike Galbraith
2011-12-07 22:03 ` David Rientjes
2011-12-14 20:16 ` Andrew Morton
2011-12-15 2:50 ` David Rientjes
2012-01-06 22:06 ` Andrew Morton
2012-01-07 6:34 ` Mike Galbraith
2012-01-07 7:59 ` Andrew Morton
2011-12-07 22:01 ` David Rientjes
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=1319106727.8653.3.camel@laptop \
--to=a.p.zijlstra@chello.nl \
--cc=efault@gmx.de \
--cc=htejun@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=lizf@cn.fujitsu.com \
--cc=paul@paulmenage.org \
--cc=rientjes@google.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
Powered by JetHome