Intel-GFX-CI hosts are starting to run i915 selftests, and this bug is part of the series "Initial findings" igt@drv_selftest@live_objects hangs on SKL, BXT and GLK. Panic traces are available: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_4433/fi-glk-j4005/igt@drv_selftest@live_objects.html https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_4433/fi-glk-dsi/igt@drv_selftest@live_objects.html https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_4433/fi-bxt-j4205/igt@drv_selftest@live_objects.html https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_4433/fi-skl-6600u/igt@drv_selftest@live_objects.html
I'm not sure why the timeouts are picking on these machines and not others. There's no particular sign of stress (oomkiller), and the workload is identical to others. Mysterious, so lets look at how better we can accommodate igt_timeout inside live_objects.
commit e5d2435bfaeee3f4045e03441d3902c63254b618 Author: Chris Wilson <chris@chris-wilson.co.uk> Date: Fri Jul 6 07:53:07 2018 +0100 drm/i915/selftests: Destroy partial tiling vma after use As we keep VMA around until the object is destroyed, when testing partial tiling we instantiate many, many VMA (as the object is huge allowing for many different partial regions). We test elsewhere our handling of populating large objects with a full set of VMA and checking we can retrieve them afterwards, but in this test we incur the cost of flushing all VMA after every GTT write, dramatically slowing down the test. References: https://bugs.freedesktop.org/show_bug.cgi?id=107130 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Matthew Auld <matthew.auld@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20180706065332.15214-2-chris@chris-wilson.co.uk
(In reply to Chris Wilson from comment #2) > commit e5d2435bfaeee3f4045e03441d3902c63254b618 > Author: Chris Wilson <chris@chris-wilson.co.uk> > Date: Fri Jul 6 07:53:07 2018 +0100 > > drm/i915/selftests: Destroy partial tiling vma after use > > As we keep VMA around until the object is destroyed, when testing > partial tiling we instantiate many, many VMA (as the object is huge > allowing for many different partial regions). We test elsewhere our > handling of populating large objects with a full set of VMA and checking > we can retrieve them afterwards, but in this test we incur the cost of > flushing all VMA after every GTT write, dramatically slowing down the > test. > > References: https://bugs.freedesktop.org/show_bug.cgi?id=107130 > Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> > Reviewed-by: Matthew Auld <matthew.auld@intel.com> > Link: > https://patchwork.freedesktop.org/patch/msgid/20180706065332.15214-2- > chris@chris-wilson.co.uk Looks like it did the trick. Thanks!
Use of freedesktop.org services, including Bugzilla, is subject to our Code of Conduct. How we collect and use information is described in our Privacy Policy.