mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Ingo Molnar <mingo@elte.hu>
To: Mel Gorman <mel@csn.ul.ie>
Cc: Linus Torvalds <torvalds@linux-foundation.org>,
	Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
	akpm@linux-foundation.org
Subject: Re: Linux 2.6.23-rc9 and a heads-up for the 2.6.24 series..
Date: Tue, 2 Oct 2007 14:15:56 +0200	[thread overview]
Message-ID: <20071002121556.GA22864@elte.hu> (raw)
In-Reply-To: <1191326858.28962.8.camel@localhost>


* Mel Gorman <mel@csn.ul.ie> wrote:

> Dirt. Booting with "profile=sleep,2" is broken in 2.6.23-rc9 and 
> 2.6.23-rc8 but working in 2.6.22. I was checking it out as part of a 
> discussion in another thread and noticed it broken in -mm as well 
> (2.6.23-rc8-mm2). Bisect is in progress but suggestions as to the 
> prime candidates are welcome or preferably, pointing out that I'm an 
> idiot because I missed twiddling some config change.

Mel, does the patch below fix this bug for you? (Note: you will need to 
enable CONFIG_SCHEDSTATS=y too.)

if yes, then Linus please pull this single fix from:

  git://git.kernel.org/pub/scm/linux/kernel/git/mingo/linux-2.6-sched.git

  | Ingo Molnar (1):
  |      sched: fix profile=sleep
  |
  |  sched_fair.c |   10 ++++++++++
  |  1 file changed, 10 insertions(+)

risk is low: the new code only runs with CONFIG_SCHEDSTATS=y 
(default:off) and profile=sleep (default:off), so it ought to be fairly 
safe to add at this point. (and we had very similar code in v2.6.22 
anyway)

	Ingo

------------------------->
Subject: sched: fix profile=sleep
From: Ingo Molnar <mingo@elte.hu>

fix sleep profiling - we lost this chunk in the CFS merge.

Found-by: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/sched_fair.c |   10 ++++++++++
 1 file changed, 10 insertions(+)

Index: linux/kernel/sched_fair.c
===================================================================
--- linux.orig/kernel/sched_fair.c
+++ linux/kernel/sched_fair.c
@@ -639,6 +639,16 @@ static void enqueue_sleeper(struct cfs_r
 
 		se->block_start = 0;
 		se->sum_sleep_runtime += delta;
+
+		/*
+		 * Blocking time is in units of nanosecs, so shift by 20 to
+		 * get a milliseconds-range estimation of the amount of
+		 * time that the task spent sleeping:
+		 */
+		if (unlikely(prof_on == SLEEP_PROFILING)) {
+			profile_hits(SLEEP_PROFILING, (void *)get_wchan(tsk),
+				     delta >> 20);
+		}
 	}
 #endif
 }

  reply	other threads:[~2007-10-02 12:16 UTC|newest]

Thread overview: 85+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <alpine.LFD.0.999.0710012029400.3579@woody.linux-foundation.org >
2007-10-02  3:41 ` Linus Torvalds
2007-10-02  9:17   ` Thomas Gleixner
2007-10-02  9:21     ` Andi Kleen
2007-10-02 10:37       ` Jeff Garzik
2007-10-02 10:48         ` Andi Kleen
2007-10-02 11:05           ` Thomas Gleixner
2007-10-02 14:07             ` Ingo Molnar
2007-10-02 14:23               ` Andi Kleen
2007-10-02 14:31                 ` Ingo Molnar
2007-10-02 14:54                   ` Andi Kleen
2007-10-02 14:58                   ` Sam Ravnborg
2007-10-02 15:24                     ` Andi Kleen
2007-10-02 15:27                     ` Ingo Molnar
2007-10-02 15:30                     ` Thomas Gleixner
2007-10-02 15:40                       ` Sam Ravnborg
2007-10-02 12:04       ` Jiri Kosina
2007-10-02 20:12     ` Rafael J. Wysocki
2007-10-02 20:11       ` Andrew Morton
2007-10-02 20:31         ` Rafael J. Wysocki
2007-10-02 20:32         ` Roland Dreier
2007-10-03  3:53     ` Eric St-Laurent
2007-10-02 12:07   ` Mel Gorman
2007-10-02 12:15     ` Ingo Molnar [this message]
2007-10-02 17:21       ` Mel Gorman
2007-10-02 22:09         ` Bill Davidsen
2007-10-03  0:37           ` Mel Gorman
2007-10-03  8:21             ` Ingo Molnar
2007-10-03 12:51               ` Mel Gorman
2007-10-22 15:56                 ` Ingo Molnar
2007-10-03  8:19         ` Ingo Molnar
2007-10-02 14:44   ` John Stoffel
2007-10-02 15:03     ` Ingo Molnar
2007-10-02 15:45     ` John Stoffel
2007-10-02 22:13     ` Bill Davidsen
2007-10-02 22:44   ` Willy Tarreau
2007-10-02 22:51   ` Alistair John Strachan
2007-10-02 23:00     ` Glauber de Oliveira Costa
2007-10-05  5:41       ` Ingo Molnar
2007-10-05  5:38     ` Ingo Molnar
2007-10-05  6:11       ` Sam Ravnborg
2007-10-05  8:32         ` Thomas Gleixner
2007-10-07 23:44           ` Alistair John Strachan
2007-10-02 23:07   ` Diego Calleja
2007-10-02 23:32     ` Linus Torvalds
2007-10-03 15:28       ` Diego Calleja
2007-10-03  8:46   ` [bug] crash when reading /proc/mounts (was: Re: Linux 2.6.23-rc9 and a heads-up for the 2.6.24 series..) Ingo Molnar
2007-10-03  8:50     ` Ingo Molnar
2007-10-03  9:12       ` Ingo Molnar
2007-10-03  9:23         ` Ingo Molnar
2007-10-03 13:34     ` Al Viro
2007-10-03 14:08       ` Ingo Molnar
2007-10-03 14:26         ` Al Viro
2007-10-03 15:12           ` Arjan van de Ven
2007-10-03 15:11     ` Linus Torvalds
2007-10-03 15:40       ` Ingo Molnar
2007-10-03 16:07         ` Linus Torvalds
2007-10-03 15:47       ` Linus Torvalds
2007-10-03 15:49         ` Ingo Molnar
2007-10-03 16:07           ` Ingo Molnar
2007-10-03 15:51       ` Alan Cox
2007-10-03 16:09         ` Linus Torvalds
2007-10-03 16:25           ` Jan Engelhardt
2007-10-03 17:07             ` Linus Torvalds
2007-10-04 14:12       ` Adrian Bunk
2007-10-04 15:08         ` Alexey Dobriyan
2007-10-03 14:21   ` Linux 2.6.23-rc9 and a heads-up for the 2.6.24 series Timo Jantunen
2007-10-03 19:07   ` Jeff Garzik
2007-10-03 19:25     ` Linus Torvalds
2007-10-04 11:55   ` [patch] net, 9p: build fix with !CONFIG_SYSCTL Ingo Molnar
2007-10-04 17:05   ` [BUG] Linux 2.6.23-rc9 and MAX_ARG_PAGES Mathieu Chouquet-Stringer
2007-10-04 17:17     ` Peter Zijlstra
2007-10-04 20:47       ` Mathieu Chouquet-Stringer
2007-10-04 21:58       ` Mathieu Chouquet-Stringer
2007-10-04 17:27     ` Linus Torvalds
2007-10-04 20:44       ` Mathieu Chouquet-Stringer
2007-10-04 21:21         ` Linus Torvalds
2007-10-04 22:27           ` Paul Mackerras
2007-10-05  0:12             ` Linus Torvalds
2007-10-05  3:22               ` Mathieu Chouquet-Stringer
2007-10-05  7:43                 ` Peter Zijlstra
2007-10-04 21:50     ` Chuck Ebbert
2007-10-04 21:54       ` Mathieu Chouquet-Stringer
2007-10-06  8:29     ` Hans-Peter Jansen
2007-10-06 11:29       ` Hans-Peter Jansen
2007-10-06 17:36     ` Bill Davidsen

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=20071002121556.GA22864@elte.hu \
    --to=mingo@elte.hu \
    --cc=akpm@linux-foundation.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mel@csn.ul.ie \
    --cc=torvalds@linux-foundation.org \
    /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