| Message ID | 20180712115729.3506-1-chris@chris-wilson.co.uk (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
Quoting Patchwork (2018-08-11 11:51:15) > igt@kms_cursor_legacy@all-pipes-torture-move: > shard-snb: DMESG-WARN (fdo#107122) -> PASS > shard-glk: DMESG-WARN (fdo#107122) -> PASS > shard-apl: DMESG-WARN (fdo#107122) -> PASS > shard-hsw: DMESG-WARN (fdo#107122) -> PASS They have been reasonably consistent failures for the last few runs, so this looks like indication of success. -Chris
Quoting Chris Wilson (2018-07-12 12:57:29) > We require that we keep the list of outstanding work short so that we do > not "leak" memory while pageflipping under stress. However that system > stress may delay kernel workers virtually indefinitely, which incurs the > pageflips stall and eventually hit a timeout waiting for the cleanup. > > Try to combat CPU starvation of our short-lived cleanup workers by > switching to a high priority workqueue. > > Testcase: igt/kms_cursor_legacy/all-pipes-torture-move > References: https://bugs.freedesktop.org/show_bug.cgi?id=107122 > Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> > Cc: Daniel Vetter <daniel.vetter@ffwll.ch> > --- > Not sure if highpri is enough to combat our RT torture... CI thinks it is. -Chris
Chris Wilson <chris@chris-wilson.co.uk> writes: > Quoting Chris Wilson (2018-07-12 12:57:29) >> We require that we keep the list of outstanding work short so that we do >> not "leak" memory while pageflipping under stress. However that system >> stress may delay kernel workers virtually indefinitely, which incurs the >> pageflips stall and eventually hit a timeout waiting for the cleanup. >> >> Try to combat CPU starvation of our short-lived cleanup workers by >> switching to a high priority workqueue. >> >> Testcase: igt/kms_cursor_legacy/all-pipes-torture-move >> References: https://bugs.freedesktop.org/show_bug.cgi?id=107122 >> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> >> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> >> --- >> Not sure if highpri is enough to combat our RT torture... > > CI thinks it is. Not so familiar with the atomic commit. But it makes sense and now there is evidence supporting it. Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> > -Chris > _______________________________________________ > Intel-gfx mailing list > Intel-gfx@lists.freedesktop.org > https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Quoting Mika Kuoppala (2018-08-13 13:49:43) > Chris Wilson <chris@chris-wilson.co.uk> writes: > > > Quoting Chris Wilson (2018-07-12 12:57:29) > >> We require that we keep the list of outstanding work short so that we do > >> not "leak" memory while pageflipping under stress. However that system > >> stress may delay kernel workers virtually indefinitely, which incurs the > >> pageflips stall and eventually hit a timeout waiting for the cleanup. > >> > >> Try to combat CPU starvation of our short-lived cleanup workers by > >> switching to a high priority workqueue. > >> > >> Testcase: igt/kms_cursor_legacy/all-pipes-torture-move > >> References: https://bugs.freedesktop.org/show_bug.cgi?id=107122 > >> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> > >> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> > >> --- > >> Not sure if highpri is enough to combat our RT torture... > > > > CI thinks it is. > > Not so familiar with the atomic commit. But it makes > sense and now there is evidence supporting it. Proof is indeed in the pudding; the CI stress case is about the worst it can be so, with any luck the starvation issue is prevented. Thanks, pushed. -Chris
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 8a07de5ac740..626dea685b84 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -12741,7 +12741,7 @@ static void intel_atomic_commit_tail(struct drm_atomic_state *state) * down. */ INIT_WORK(&state->commit_work, intel_atomic_cleanup_work); - schedule_work(&state->commit_work); + queue_work(system_highpri_wq, &state->commit_work); } static void intel_atomic_commit_work(struct work_struct *work)
We require that we keep the list of outstanding work short so that we do not "leak" memory while pageflipping under stress. However that system stress may delay kernel workers virtually indefinitely, which incurs the pageflips stall and eventually hit a timeout waiting for the cleanup. Try to combat CPU starvation of our short-lived cleanup workers by switching to a high priority workqueue. Testcase: igt/kms_cursor_legacy/all-pipes-torture-move References: https://bugs.freedesktop.org/show_bug.cgi?id=107122 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> --- Not sure if highpri is enough to combat our RT torture... --- drivers/gpu/drm/i915/intel_display.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)