Intel-GFX Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Ben Widawsky <ben@bwidawsk.net>
To: Ben Widawsky <benjamin.widawsky@intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>,
	Intel GFX <intel-gfx@lists.freedesktop.org>
Subject: Re: [PATCH] drm/i915: Allocate atomically in execbuf path
Date: Tue, 26 Nov 2013 22:48:51 -0800	[thread overview]
Message-ID: <20131127064851.GA531@bwidawsk.net> (raw)
In-Reply-To: <20131127042346.GA601@bwidawsk.net>

On Tue, Nov 26, 2013 at 08:23:46PM -0800, Ben Widawsky wrote:
> On Tue, Nov 26, 2013 at 04:55:50PM -0800, Ben Widawsky wrote:
> > If we end up calling the shrinker, which in turn requires the OOM
> > killer, we may end up infinitely waiting for a process to die if the OOM
> > chooses. The case that this prevents occurs in execbuf. The forked
> > variants of gem_evict_everything is a good way to hit it. This is
> > exacerbated by Daniel's recent patch to give OOM precedence to the GEM
> > tests.
> > 
> > It's a twisted form of a deadlock.
> > 
> > What occurs is the following (assume just 2 procs)
> > 1. proc A gets to execbuf while out of memory, gets struct_mutex.
> > 2. OOM killer comes in and chooses proc B
> > 3. proc B closes it's fds, which requires struct mutex, blocks
> > 4, OOM killer waits for B to die before killing another process (this
> > part is speculative)
> > 
> > Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
> > Cc: Chris Wilson <chris@chris-wilson.co.uk>
> > Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
> 
> I'd still like to know if I am crazy, but I'm now trying to defer the
> stuff we do on file close without using any allocs. Just an update...
> 

workqueue still has similar problems. It could be because deferring the
context cleanup means we don't actually free much space, and so the OOM
isn't enough, or [more likely] something else is going on.

Maybe it's my bug. I am really out of ideas at the moment. The system
just becomes unresponsive after all threads end up blocked waiting for
struct mutex. I know I'd seen such problems in the past with
gem_evict_everything, but this time around I seem to be the sole cause
(and not all my machines hit it).

Sorry for the noise - just totally burning out on this one.

-- 
Ben Widawsky, Intel Open Source Technology Center

  parent reply	other threads:[~2013-11-27  6:49 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-11-27  0:55 [PATCH] drm/i915: Allocate atomically in execbuf path Ben Widawsky
2013-11-27  1:10 ` Ben Widawsky
2013-11-27  1:21   ` Ben Widawsky
2013-11-27  4:23 ` Ben Widawsky
2013-11-27  6:48   ` Daniel Vetter
2013-11-27  6:48   ` Ben Widawsky [this message]
2013-11-27  6:53 ` [PATCH] drm/i915: Optionally defer context closing Ben Widawsky

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=20131127064851.GA531@bwidawsk.net \
    --to=ben@bwidawsk.net \
    --cc=benjamin.widawsky@intel.com \
    --cc=daniel.vetter@ffwll.ch \
    --cc=intel-gfx@lists.freedesktop.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