From: Dave Chinner <david@fromorbit.com>
To: Dave Jones <davej@redhat.com>, Al Viro <viro@ZenIV.linux.org.uk>,
Linus Torvalds <torvalds@linux-foundation.org>,
Eric Sandeen <sandeen@sandeen.net>,
Linux Kernel <linux-kernel@vger.kernel.org>,
xfs@oss.sgi.com
Subject: Re: 3.14-rc2 XFS backtrace because irqs_disabled.
Date: Wed, 12 Feb 2014 17:31:50 +1100 [thread overview]
Message-ID: <20140212063150.GD13997@dastard> (raw)
In-Reply-To: <20140212061038.GC13997@dastard>
On Wed, Feb 12, 2014 at 05:10:38PM +1100, Dave Chinner wrote:
> On Wed, Feb 12, 2014 at 12:50:27AM -0500, Dave Jones wrote:
> > On Wed, Feb 12, 2014 at 04:40:43PM +1100, Dave Chinner wrote:
> >
> > > None of the XFS code disables interrupts in that path, not does is
> > > call outside XFS except to dispatch IO. The stack is pretty deep at
> > > this point and I know that the standard (non stacked) IO stack can
> > > consume >3kb of stack space when it gets down to having to do memory
> > > reclaim during GFP_NOIO allocation at the lowest level of SCSI
> > > drivers. Stack overruns typically show up with symptoms like we are
> > > seeing.
> > > ..
> > >
> > > Dave, before chasing ghosts, can you (like Eric originally asked)
> > > turn on stack overrun detection?
> >
> > CONFIG_DEBUG_STACKOVERFLOW ? Already turned on.
>
> That only checks stack usage when an interrupt is taken. If no
> interrupts are taken when stack usage is within 128 bytes of
> overflow, then it doesn't catch it.
>
> I tend to use CONFIG_DEBUG_STACK_USAGE=y as it records the maximum
> stack usage of a process via canary overwrites and it records it in
> do_exit(). I also use the stack tracer to record the largest stack
> usage seen so I know exactly what code paths are approaching stack
> overruns...
FYI, just creating lots of files with open(O_CREAT):
[ 348.718357] fs_mark (4828) used greatest stack depth: 2968 bytes left
[ 348.769846] fs_mark (4814) used greatest stack depth: 2312 bytes left
[ 349.777717] fs_mark (4826) used greatest stack depth: 2280 bytes left
[ 418.139415] fs_mark (4928) used greatest stack depth: 1936 bytes left
[ 460.492282] fs_mark (4993) used greatest stack depth: 1336 bytes left
[ 544.825418] fs_mark (5104) used greatest stack depth: 1112 bytes left
[ 689.503970] fs_mark (5265) used greatest stack depth: 1000 bytes left
We've got absolutely no spare stack space anymore in the IO path.
And the IO path can't get much simpler than filesystem -> virtio
block device.
Cheers,
Dave.
--
Dave Chinner
david@fromorbit.com
next prev parent reply other threads:[~2014-02-12 6:31 UTC|newest]
Thread overview: 65+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-02-11 17:27 3.14-rc2 XFS backtrace because irqs_disabled Dave Jones
2014-02-11 21:08 ` Dave Chinner
2014-02-11 21:49 ` Eric Sandeen
2014-02-12 0:44 ` Dave Jones
2014-02-12 1:09 ` Al Viro
2014-02-12 2:52 ` Linus Torvalds
2014-02-12 4:03 ` Dave Jones
2014-02-12 4:22 ` Al Viro
2014-02-12 5:40 ` Dave Chinner
2014-02-12 5:50 ` Dave Jones
2014-02-12 6:10 ` Dave Chinner
2014-02-12 6:31 ` Dave Chinner [this message]
2014-02-12 6:59 ` Linus Torvalds
2014-02-12 8:13 ` Tejun Heo
2014-02-12 12:44 ` Steven Rostedt
2014-02-12 8:35 ` Dave Chinner
2014-02-12 12:50 ` Steven Rostedt
2014-02-12 12:40 ` Steven Rostedt
2014-02-12 13:29 ` Peter Zijlstra
2014-02-12 14:25 ` Dave Jones
2014-02-12 21:14 ` Dave Chinner
2014-02-12 15:57 ` Eric Sandeen
2014-02-12 6:28 ` Linus Torvalds
2014-02-12 7:18 ` Dave Chinner
2014-02-14 0:24 ` Dave Chinner
2014-02-14 16:01 ` Dave Jones
2014-02-15 22:23 ` Dave Chinner
2014-02-15 22:28 ` Dave Jones
2014-02-15 22:43 ` Linus Torvalds
2014-02-15 23:50 ` Linus Torvalds
2014-02-18 1:27 ` Dave Chinner
2014-02-12 11:39 ` Al Viro
2014-02-12 20:13 ` Linus Torvalds
2014-02-12 21:14 ` Al Viro
2014-02-12 21:32 ` Linus Torvalds
2014-02-12 21:44 ` Al Viro
2014-02-13 20:51 ` Al Viro
2014-02-14 0:09 ` Al Viro
2014-02-14 13:25 ` Christoph Hellwig
2014-02-14 13:29 ` Richard Weinberger
2014-02-14 15:20 ` Al Viro
2014-02-14 16:08 ` Oleg Nesterov
2014-02-13 17:40 ` Oleg Nesterov
2014-02-13 17:58 ` Linus Torvalds
2014-02-13 18:10 ` Oleg Nesterov
2014-02-13 18:37 ` Oleg Nesterov
2014-02-15 5:25 ` Al Viro
2014-02-15 14:27 ` Oleg Nesterov
2014-02-15 15:22 ` Al Viro
2014-02-15 15:33 ` Oleg Nesterov
2014-02-15 15:36 ` Al Viro
2014-02-15 15:58 ` Al Viro
2014-02-15 16:59 ` Al Viro
2014-02-15 17:43 ` Oleg Nesterov
2014-02-15 18:05 ` Al Viro
2014-02-15 18:45 ` Oleg Nesterov
2014-02-17 16:57 ` Oleg Nesterov
2014-02-17 17:40 ` Al Viro
2014-02-17 17:46 ` Oleg Nesterov
2014-02-17 17:54 ` Al Viro
2014-02-14 16:13 ` Christoph Hellwig
2014-02-14 16:16 ` Al Viro
2014-02-14 16:18 ` Al Viro
2014-02-14 16:19 ` Christoph Hellwig
2014-02-15 14:46 ` Oleg Nesterov
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=20140212063150.GD13997@dastard \
--to=david@fromorbit.com \
--cc=davej@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=sandeen@sandeen.net \
--cc=torvalds@linux-foundation.org \
--cc=viro@ZenIV.linux.org.uk \
--cc=xfs@oss.sgi.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).