Re: [Intel-gfx] [PATCH i-g-t] igt/gem_ringfill: Adds ringbuffer full preemption test

2017-08-24 Thread Chris Wilson
Quoting Michał Winiarski (2017-08-24 13:13:30) > > +static void alarm_handler(int sig) > > +{ > > +} > > + > > +static int __execbuf(int fd, struct drm_i915_gem_execbuffer2 *execbuf) > > +{ > > + return ioctl(fd, DRM_IOCTL_I915_GEM_EXECBUFFER2, execbuf); > > +} > > + > > So... __gem_execbuf?

Re: [Intel-gfx] [PATCH i-g-t] igt/gem_ringfill: Adds ringbuffer full preemption test

2017-08-24 Thread Michał Winiarski
On Wed, Aug 23, 2017 at 05:11:23PM -0700, Antonio Argenziano wrote: > The testcase added here, stimulates this scenario where a high priority > request is sent while another process keeps submitting requests and > filling its ringbuffer. s/stimulates/simulates You're no longer changing igt/gem_ri

[Intel-gfx] [PATCH i-g-t] igt/gem_ringfill: Adds ringbuffer full preemption test

2017-08-23 Thread Antonio Argenziano
The testcase added here, stimulates this scenario where a high priority request is sent while another process keeps submitting requests and filling its ringbuffer. From RFC (Chris): - Use two FDs, one for each priority submission. - Move from gem_ringfill to gem_exec_schedule.