[Intel-gfx] [RFC] tests/gem_ring_sync_copy: reduce memory usage

[Gore, Tim]

> -----Original Message-----
> From: Lespiau, Damien
> Sent: Friday, November 28, 2014 3:39 PM
> To: Gore, Tim
> Cc: intel-gfx at lists.freedesktop.org
> Subject: Re: [RFC] tests/gem_ring_sync_copy: reduce memory usage
> 
> On Fri, Nov 28, 2014 at 02:46:24PM +0000, tim.gore at intel.com wrote:
> > From: Tim Gore <tim.gore at intel.com>
> >
> > gem_ring_sync_copy uses a lot of memory and gets OOM killed on smaller
> > systems (eg android devices).
> > Most of the allocation is for "busy work" to keep the render rings
> > busy and for this we can just re-use the same few buffers over and
> > over. This enables the test to be run on low end devices.
> >
> > Signed-off-by: Tim Gore <tim.gore at intel.com>
> 
> The one thing I'm wondering is how we can ensure that 32 is indeed enough
> to create a dependency between the two rings.
> 
> I'm not sure why you've chosen to remove n_buffers_load (without actually
> removing it from the test data. How about:
> 
> diff --git a/tests/gem_ring_sync_copy.c b/tests/gem_ring_sync_copy.c
> index 4a732d2..2561bac 100644
> --- a/tests/gem_ring_sync_copy.c
> +++ b/tests/gem_ring_sync_copy.c
> @@ -331,7 +331,7 @@ igt_main
>                 data.drm_fd = drm_open_any_render();
>                 data.devid = intel_get_drm_devid(data.drm_fd);
> 
> -               data.n_buffers_load = 1000;
> +               data.n_buffers_load = 32;
> 
>                 data.bufmgr = drm_intel_bufmgr_gem_init(data.drm_fd, 4096);
>                 igt_assert(data.bufmgr);
> 
> --
> Damien
> 

N_buffers_load is still used. I am still submitting 1000 buffers to the ring, its just
that I use the same buffers over and over (hence the "i % NUM_BUSY_BUFFERS").
So I only allocate 32 buffers, and each gets copied 1000/32 times, so the ring is kept
busy for as long as previously.

  Tim

> > ---
> >  tests/gem_ring_sync_copy.c | 25 +++++++++++++++----------
> >  1 file changed, 15 insertions(+), 10 deletions(-)
> >
> > diff --git a/tests/gem_ring_sync_copy.c b/tests/gem_ring_sync_copy.c
> > index 4a732d2..7257188 100644
> > --- a/tests/gem_ring_sync_copy.c
> > +++ b/tests/gem_ring_sync_copy.c
> > @@ -57,6 +57,7 @@
> >
> >  #define WIDTH	512
> >  #define HEIGHT	512
> > +#define NUM_BUSY_BUFFERS 32
> >
> >  typedef struct {
> >  	int drm_fd;
> > @@ -163,11 +164,13 @@ static void render_busy(data_t *data)
> >  	size_t array_size;
> >  	int i;
> >
> > -	array_size = data->n_buffers_load * sizeof(struct igt_buf);
> > +	/* allocate 32 buffer objects and re-use them as needed */
> > +	array_size = NUM_BUSY_BUFFERS * sizeof(struct igt_buf);
> > +
> >  	data->render.srcs = malloc(array_size);
> >  	data->render.dsts = malloc(array_size);
> >
> > -	for (i = 0; i < data->n_buffers_load; i++) {
> > +	for (i = 0; i < NUM_BUSY_BUFFERS; i++) {
> >  		scratch_buf_init(data, &data->render.srcs[i], WIDTH,
> HEIGHT,
> >  				 0xdeadbeef);
> >  		scratch_buf_init(data, &data->render.dsts[i], WIDTH,
> HEIGHT, @@
> > -177,10 +180,10 @@ static void render_busy(data_t *data)
> >  	for (i = 0; i < data->n_buffers_load; i++) {
> >  		data->render.copy(data->batch,
> >  				  NULL,			/* context */
> > -				  &data->render.srcs[i],
> > +				  &data->render.srcs[i %
> NUM_BUSY_BUFFERS],
> >  				  0, 0,			/* src_x, src_y */
> >  				  WIDTH, HEIGHT,
> > -				  &data->render.dsts[i],
> > +				  &data->render.dsts[i %
> NUM_BUSY_BUFFERS],
> >  				  0, 0			/* dst_x, dst_y */);
> >  	}
> >  }
> > @@ -189,7 +192,7 @@ static void render_busy_fini(data_t *data)  {
> >  	int i;
> >
> > -	for (i = 0; i < data->n_buffers_load; i++) {
> > +	for (i = 0; i < NUM_BUSY_BUFFERS; i++) {
> >  		drm_intel_bo_unreference(data->render.srcs[i].bo);
> >  		drm_intel_bo_unreference(data->render.dsts[i].bo);
> >  	}
> > @@ -225,11 +228,13 @@ static void blitter_busy(data_t *data)
> >  	size_t array_size;
> >  	int i;
> >
> > -	array_size = data->n_buffers_load * sizeof(drm_intel_bo *);
> > +	/* allocate 32 buffer objects and re-use them as needed */
> > +	array_size = NUM_BUSY_BUFFERS * sizeof(drm_intel_bo *);
> > +
> >  	data->blitter.srcs = malloc(array_size);
> >  	data->blitter.dsts = malloc(array_size);
> >
> > -	for (i = 0; i < data->n_buffers_load; i++) {
> > +	for (i = 0; i < NUM_BUSY_BUFFERS; i++) {
> >  		data->blitter.srcs[i] = bo_create(data,
> >  						  WIDTH, HEIGHT,
> >  						  0xdeadbeef);
> > @@ -240,8 +245,8 @@ static void blitter_busy(data_t *data)
> >
> >  	for (i = 0; i < data->n_buffers_load; i++) {
> >  		intel_copy_bo(data->batch,
> > -			      data->blitter.srcs[i],
> > -			      data->blitter.dsts[i],
> > +			      data->blitter.srcs[i % NUM_BUSY_BUFFERS],
> > +			      data->blitter.dsts[i % NUM_BUSY_BUFFERS],
> >  			      WIDTH*HEIGHT*4);
> >  	}
> >  }
> > @@ -250,7 +255,7 @@ static void blitter_busy_fini(data_t *data)  {
> >  	int i;
> >
> > -	for (i = 0; i < data->n_buffers_load; i++) {
> > +	for (i = 0; i < NUM_BUSY_BUFFERS; i++) {
> >  		drm_intel_bo_unreference(data->blitter.srcs[i]);
> >  		drm_intel_bo_unreference(data->blitter.dsts[i]);
> >  	}
> > --
> > 2.1.3
> >