Re: [Intel-gfx] [PATCH 2/2] drm/i915: Make GPU pages movable

2016-11-23 Thread Hugh Dickins
On Wed, 23 Nov 2016, Daniel Vetter wrote: > On Tue, Nov 22, 2016 at 09:26:11PM -0800, Hugh Dickins wrote: > > On Tue, 22 Nov 2016, Matthew Auld wrote: > > > On 9 November 2016 at 18:36, Hugh Dickins wrote: > > > > On Wed, 9 Nov 2016, Daniel Vetter wrote: > > > >> > > > >> Hi all

Re: [Intel-gfx] [PATCH 2/2] drm/i915: Make GPU pages movable

2016-11-23 Thread Daniel Vetter
On Tue, Nov 22, 2016 at 09:26:11PM -0800, Hugh Dickins wrote: > On Tue, 22 Nov 2016, Matthew Auld wrote: > > On 9 November 2016 at 18:36, Hugh Dickins wrote: > > > On Wed, 9 Nov 2016, Daniel Vetter wrote: > > >> > > >> Hi all -mm folks! > > >> > > >> Any feedback on these two?

Re: [Intel-gfx] [PATCH 2/2] drm/i915: Make GPU pages movable

2016-11-22 Thread Hugh Dickins
On Tue, 22 Nov 2016, Matthew Auld wrote: > On 9 November 2016 at 18:36, Hugh Dickins wrote: > > On Wed, 9 Nov 2016, Daniel Vetter wrote: > >> > >> Hi all -mm folks! > >> > >> Any feedback on these two? It's kinda an intermediate step towards a > >> full-blown gemfs, and I think

Re: [Intel-gfx] [PATCH 2/2] drm/i915: Make GPU pages movable

2016-11-22 Thread Matthew Auld
On 9 November 2016 at 18:36, Hugh Dickins wrote: > On Wed, 9 Nov 2016, Daniel Vetter wrote: >> >> Hi all -mm folks! >> >> Any feedback on these two? It's kinda an intermediate step towards a >> full-blown gemfs, and I think useful for that. Or do we need to go >> directly to our

Re: [Intel-gfx] [PATCH 2/2] drm/i915: Make GPU pages movable

2016-11-15 Thread akash goel
On Wed, Nov 16, 2016 at 6:55 AM, Hugh Dickins wrote: > On Mon, 14 Nov 2016, akash goel wrote: >> On Thu, Nov 10, 2016 at 1:00 PM, Goel, Akash wrote: >> > On 11/10/2016 12:09 PM, Hugh Dickins wrote: >> >> On Fri, 4 Nov 2016, akash.g...@intel.com wrote: >>

Re: [Intel-gfx] [PATCH 2/2] drm/i915: Make GPU pages movable

2016-11-15 Thread Hugh Dickins
On Mon, 14 Nov 2016, akash goel wrote: > On Thu, Nov 10, 2016 at 1:00 PM, Goel, Akash wrote: > > On 11/10/2016 12:09 PM, Hugh Dickins wrote: > >> On Fri, 4 Nov 2016, akash.g...@intel.com wrote: > >>> @@ -4185,6 +4189,8 @@ struct drm_i915_gem_object * > >>> > >>> mask

Re: [Intel-gfx] [PATCH 2/2] drm/i915: Make GPU pages movable

2016-11-13 Thread akash goel
On Thu, Nov 10, 2016 at 1:00 PM, Goel, Akash wrote: > > > On 11/10/2016 12:09 PM, Hugh Dickins wrote: >> >> On Fri, 4 Nov 2016, akash.g...@intel.com wrote: >>> >>> From: Chris Wilson >>> >>> On a long run of more than 2-3 days, physical memory

Re: [Intel-gfx] [PATCH 2/2] drm/i915: Make GPU pages movable

2016-11-09 Thread Goel, Akash
On 11/10/2016 12:09 PM, Hugh Dickins wrote: On Fri, 4 Nov 2016, akash.g...@intel.com wrote: From: Chris Wilson On a long run of more than 2-3 days, physical memory tends to get fragmented severely, which considerably slows down the system. In such a scenario, the

Re: [Intel-gfx] [PATCH 2/2] drm/i915: Make GPU pages movable

2016-11-09 Thread Hugh Dickins
On Fri, 4 Nov 2016, akash.g...@intel.com wrote: > From: Chris Wilson > > On a long run of more than 2-3 days, physical memory tends to get > fragmented severely, which considerably slows down the system. In such a > scenario, the shrinker is also unable to help as lack

Re: [Intel-gfx] [PATCH 2/2] drm/i915: Make GPU pages movable

2016-11-09 Thread Hugh Dickins
On Wed, 9 Nov 2016, Daniel Vetter wrote: > > Hi all -mm folks! > > Any feedback on these two? It's kinda an intermediate step towards a > full-blown gemfs, and I think useful for that. Or do we need to go > directly to our own backing storage thing? Aside from ack/nack from -mm I > think this is

Re: [Intel-gfx] [PATCH 2/2] drm/i915: Make GPU pages movable

2016-11-09 Thread Daniel Vetter
On Fri, Nov 04, 2016 at 08:32:56PM +0530, akash.g...@intel.com wrote: > From: Chris Wilson > > On a long run of more than 2-3 days, physical memory tends to get > fragmented severely, which considerably slows down the system. In such a > scenario, the shrinker is also

[Intel-gfx] [PATCH 2/2] drm/i915: Make GPU pages movable

2016-11-04 Thread akash . goel
From: Chris Wilson On a long run of more than 2-3 days, physical memory tends to get fragmented severely, which considerably slows down the system. In such a scenario, the shrinker is also unable to help as lack of memory is not the actual problem, since it has been

Re: [Intel-gfx] [PATCH 2/2] drm/i915: Make GPU pages movable

2016-11-04 Thread Goel, Akash
On 11/4/2016 7:07 PM, Chris Wilson wrote: Best if we send these as a new series to unconfuse CI. Okay will send as a new series. On Fri, Nov 04, 2016 at 06:18:26PM +0530, akash.g...@intel.com wrote: +static int do_migrate_page(struct drm_i915_gem_object *obj) +{ + struct

Re: [Intel-gfx] [PATCH 2/2] drm/i915: Make GPU pages movable

2016-11-04 Thread Chris Wilson
Best if we send these as a new series to unconfuse CI. On Fri, Nov 04, 2016 at 06:18:26PM +0530, akash.g...@intel.com wrote: > +static int do_migrate_page(struct drm_i915_gem_object *obj) > +{ > + struct drm_i915_private *dev_priv = to_i915(obj->base.dev); > + int ret = 0; > + > + if

[Intel-gfx] [PATCH 2/2] drm/i915: Make GPU pages movable

2016-11-04 Thread akash . goel
From: Chris Wilson On a long run of more than 2-3 days, physical memory tends to get fragmented severely, which considerably slows down the system. In such a scenario, the shrinker is also unable to help as lack of memory is not the actual problem, since it has been