linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Tejun Heo <tj@kernel.org>
To: Andrea Arcangeli <aarcange@redhat.com>, Oleg Nesterov <oleg@redhat.com>
Cc: "Srivatsa S. Bhat" <srivatsa.bhat@linux.vnet.ibm.com>,
	"Rafael J. Wysocki" <rjw@suse.com>,
	linux-pm@vger.kernel.org, linux-kernel@vger.kernel.org,
	Jiri Slaby <jirislaby@gmail.com>,
	linux-mm@kvack.org, Andrew Morton <akpm@linux-foundation.org>
Subject: Re: [PATCH] thp: reduce khugepaged freezing latency
Date: Wed, 9 Nov 2011 09:06:57 -0800	[thread overview]
Message-ID: <20111109170657.GE1260@google.com> (raw)
In-Reply-To: <20111109165925.GC1260@google.com>

Hello,

On Wed, Nov 09, 2011 at 08:59:25AM -0800, Tejun Heo wrote:
> Freezer depends on the usual "set_current_state(INTERRUPTIBLE); check
> freezing; schedule(); check freezing" construct and sends
> INTERRUPTIBLE wake up after setting freezing state.  The
> synchronization hasn't been completely clear but recently been cleaned
> up, so as long as freezing condition is tested after INTERRUPTIBLE is
> set before going to sleep, the event won't go missing.
> 
> Maybe we need a helper here, which would be named horribly -
> schedule_timeout_interruptible_freezable().  (cc'ing Oleg) Oleg, maybe
> we need schedule_timeout(@sleep_type) too?

Ah, crap, still waking up.  Sorry about that.  So, yes, there's a race
condition above.  You need to set TASK_INTERRUPTIBLE before testing
freezing and use schedule_timeout() instead of
schedule_timeout_interruptible().  Was getting confused with
prepare_to_wait().  That said, why not use prepare_to_wait() instead?

Thanks.

-- 
tejun

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  parent reply	other threads:[~2011-11-09 17:07 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-11-08  8:33 khugepaged doesn't want to freeze Jiri Slaby
2011-11-08 15:29 ` Andrea Arcangeli
2011-11-08 15:29   ` [PATCH] thp: reduce khugepaged freezing latency Andrea Arcangeli
2011-11-08 20:01     ` Srivatsa S. Bhat
2011-11-09  0:01       ` Andrea Arcangeli
2011-11-09  9:03         ` Srivatsa S. Bhat
2011-11-09 12:45       ` Srivatsa S. Bhat
2011-11-09 15:53         ` Tejun Heo
2011-11-09 16:20           ` Srivatsa S. Bhat
2011-11-09 16:52           ` Andrea Arcangeli
2011-11-09 16:59             ` Tejun Heo
2011-11-09 17:02               ` Tejun Heo
2011-11-09 17:29                 ` Andrea Arcangeli
2011-11-09 18:09                   ` Tejun Heo
2011-11-09 18:19                     ` Andrea Arcangeli
2011-11-09 18:34                       ` Tejun Heo
2011-11-09 19:40                         ` Andrea Arcangeli
2011-11-11 12:20                           ` Jiri Slaby
2011-11-09 17:06               ` Tejun Heo [this message]
2011-11-09 17:33                 ` Andrea Arcangeli

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=20111109170657.GE1260@google.com \
    --to=tj@kernel.org \
    --cc=aarcange@redhat.com \
    --cc=akpm@linux-foundation.org \
    --cc=jirislaby@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-pm@vger.kernel.org \
    --cc=oleg@redhat.com \
    --cc=rjw@suse.com \
    --cc=srivatsa.bhat@linux.vnet.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;
as well as URLs for NNTP newsgroup(s).