[Intel-gfx] Memory leak in drm/i915?
Chris Wilson
chris at chris-wilson.co.uk
Wed Nov 3 17:02:26 CET 2010
On Wed, 3 Nov 2010 10:26:11 -0500, "Jason Detring" <jason.detring at navico.com> wrote:
> The problem observed is that performing this switch seems to grow system
> cache usage by about 1.5 to 2 MB per iteration. This is unbounded, and
> will fill both free memory and swap in the course of a few hours when
> running our app in its demonstration cycle. At this point, the system
> becomes unresponsive, eventually dumping the user to a text-mode kernel
> panic message. Killing the app before the hang causes the system cache
> and swap to be cleared on an intel-drm-next kernel, but not in the -rc3
> kernel (see software stacks later in this message).
This suggests that the leak is connected with:
commit 31dfbc93923c0aaa0440b809f80ff2830c6a531a
Author: Chris Wilson <chris at chris-wilson.co.uk>
Date: Mon Sep 27 21:28:30 2010 +0100
drm: Prune GEM vma entries
Hook the GEM vm open/close ops into the generic drm vm open/close so
that the private vma entries are created and destroy appropriately.
Fixes the leak of the drm_vma_entries during the lifetime of the filp.
Can you monitor /sys/debug/dri/0/i915_gem_objects and /proc/slabinfo and
see where the memory is going?
-Chris
--
Chris Wilson, Intel Open Source Technology Centre
More information about the Intel-gfx
mailing list