From: jhf@rivenstone.net (Joseph Fannin)
To: Paul Mackerras <paulus@samba.org>
Cc: Andrew Morton <akpm@osdl.org>, Joseph Fannin <jhf@rivenstone.net>,
linux-kernel@vger.kernel.org, linuxppc-dev@lists.linuxppc.org
Subject: Re: 2.6.7-mm7
Date: Sat, 17 Jul 2004 15:19:03 -0400 [thread overview]
Message-ID: <20040717191903.GA1801@zion.rivenstone.net> (raw)
In-Reply-To: <16633.20767.128875.570852@cargo.ozlabs.ibm.com>
[-- Attachment #1: Type: text/plain, Size: 1968 bytes --]
On Sun, Jul 18, 2004 at 02:17:35AM +1000, Paul Mackerras wrote:
> Andrew Morton writes:
>
> > hm, OK. It could be that the debug patch is a bit too aggressive, or that
> > ppc got lucky and happens to always be in state TASK_RUNNING when these
> > calls to schedule() occur.
> >
> > Maybe this task incorrectly has _TIF_NEED_RESCHED set?
>
> Is CONFIG_PREEMPT enabled?
These traces are with preempt enabled, but I tried turning it off
and the messages are still there (there seem to be a lot less of them,
though.)
I would be glad to produce a dmesg with preempt off if it makes
things clearer (tonight, or tommorrow, or I'd just do it now.)
> > Anyway, ppc guys: please take a look at the results from
> > ftp://ftp.kernel.org/pub/linux/kernel/people/akpm/patches/2.6/2.6.7/2.6.7-mm7/broken-out/detect-too-early-schedule-attempts.patch
> > and check that the kernel really should be calling schedule() at this time
> > and place, let us know?
> >
> > Thanks.
> >
> > > The first one looks like:
> > >
> > > Calibrating delay loop... 1064.96 BogoMIPS
> > > Mount-cache hash table entries: 512 (order: 0, 4096 bytes)
> > > Badness in schedule at kernel/sched.c:2153
> > > Call trace:
> > > [c00099e4] dump_stack+0x18/0x28
> > > [c0006bac] check_bug_trap+0x84/0xac
> > > [c0006d38] ProgramCheckException+0x164/0x1a4
> > > [c0006240] ret_from_except_full+0x0/0x4c
> > > [c02021bc] schedule+0x24/0x684
> > > [c0005e80] syscall_exit_work+0x108/0x10c
> > > [c02e0ad0] proc_root_init+0x14c/0x158
> > > [00000000] 0x0
> > > [c02ce5a0] start_kernel+0x158/0x184
> > > [000035fc] 0x35fc
>
> This looks like CONFIG_PREEMPT is enabled and _TIF_NEED_RESCHED is set
> at the end of handling a system call. AFAICS i386 will also call
> schedule in these circumstances. Does this mean we shouldn't do
> system calls until the scheduler is running?
>
> Paul.
>
--
Joseph Fannin
jhf@rivenstone.net
[-- Attachment #2: Digital signature --]
[-- Type: application/pgp-signature, Size: 189 bytes --]
next prev parent reply other threads:[~2004-07-17 19:19 UTC|newest]
Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top
2004-07-09 6:50 2.6.7-mm7 Andrew Morton
2004-07-09 8:15 ` 2.6.7-mm7 Stefano Rivoir
2004-07-09 9:41 ` 2.6.7-mm7 Andrew Morton
2004-07-09 10:27 ` 2.6.7-mm7 Stefano Rivoir
2004-07-09 10:32 ` 2.6.7-mm7 Stefano Rivoir
2004-07-09 11:45 ` 2.6.7-mm7 Jesse Stockall
2004-07-09 18:54 ` 2.6.7-mm7 Andrew Morton
2004-07-09 19:52 ` 2.6.7-mm7 Jesse Stockall
2004-07-09 20:00 ` 2.6.7-mm7 Andrew Morton
2004-07-09 22:21 ` 2.6.7-mm7 Greg KH
2004-07-09 19:56 ` 2.6.7-mm7 Alan Stern
2004-07-09 10:32 ` 2.6.7-mm7 Jurgen Kramer
2004-07-09 10:39 ` 2.6.7-mm7 Andrew Morton
2004-07-09 11:16 ` 2.6.7-mm7 Jurgen Kramer
2004-07-09 14:40 ` 2.6.7-mm7 Felipe Alfaro Solana
2004-07-09 16:40 ` 2.6.7-mm7 Jurgen Kramer
2004-07-09 11:44 ` 2.6.7-mm7 Michael Geithe
2004-07-09 22:15 ` 2.6.7-mm7 Greg KH
2004-07-10 0:07 ` 2.6.7-mm7 Michael Geithe
2004-07-09 20:38 ` 2.6.7-mm7 Joseph Fannin
2004-07-09 21:11 ` 2.6.7-mm7 Andrew Morton
2004-07-14 22:01 ` 2.6.7-mm7 Tom Rini
2004-07-17 16:17 ` 2.6.7-mm7 Paul Mackerras
2004-07-17 19:19 ` Joseph Fannin [this message]
2004-07-09 21:04 ` 2.6.7-mm7 William Lee Irwin III
2004-07-09 22:11 ` 2.6.7-mm7 William Lee Irwin III
2004-07-09 22:14 ` 2.6.7-mm7 Andrew Morton
2004-07-09 22:24 ` 2.6.7-mm7 James Bottomley
2004-07-09 23:40 ` 2.6.7-mm7 Andrew Morton
2004-07-10 2:47 ` 2.6.7-mm7 James Bottomley
2004-07-10 4:34 ` 2.6.7-mm7 Joshua Kwan
2004-07-10 4:40 ` 2.6.7-mm7 Joshua Kwan
2004-07-10 18:29 ` 2.6.7-mm7 Diego Calleja García
2004-07-10 20:04 ` 2.6.7-mm7 Marcin Gibuła
2004-07-10 20:10 ` 2.6.7-mm7 Marcin Gibuła
2004-07-10 20:27 ` 2.6.7-mm7 Andrew Morton
2004-07-10 20:32 ` 2.6.7-mm7 Marcin Gibuła
2004-07-11 4:19 ` 2.6.7-mm7 Dax Kelson
2004-07-11 4:40 ` 2.6.7-mm7 Andrew Morton
-- strict thread matches above, loose matches on Subject: below --
2004-07-10 6:21 2.6.7-mm7 Zoltan Boszormenyi
[not found] <A6974D8E5F98D511BB910002A50A6647615FFB70@hdsmsx403.hd.intel.com>
2004-07-11 2:23 ` 2.6.7-mm7 Len Brown
2004-07-11 10:23 ` 2.6.7-mm7 Thomas Svedberg
2004-07-11 15:49 ` 2.6.7-mm7 Zoltan Boszormenyi
[not found] <A6974D8E5F98D511BB910002A50A6647615FFA5D@hdsmsx403.hd.intel.com>
2004-07-11 2:34 ` 2.6.7-mm7 Len Brown
2004-07-11 18:32 ` 2.6.7-mm7 Michael Geithe
[not found] <A6974D8E5F98D511BB910002A50A6647615FFA8A@hdsmsx403.hd.intel.com>
2004-07-11 2:36 ` 2.6.7-mm7 Len Brown
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=20040717191903.GA1801@zion.rivenstone.net \
--to=jhf@rivenstone.net \
--cc=akpm@osdl.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linuxppc-dev@lists.linuxppc.org \
--cc=paulus@samba.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.