Quoting Tvrtko Ursulin (2020-07-17 13:38:01)
>
> On 15/07/2020 12:50, Chris Wilson wrote:
> > + /* Even if we have not used the cache, we may still have a barrier */
> > + if (!ref->cache)
> > + ref->cache = fetch_node(ref->tree.rb_node);
> > +
> > + /* Keep the MRU cached
On 2020-07-15 13:50, Chris Wilson wrote:
Whenever an i915_active idles, we prune its tree of old fence slots to
prevent a gradual leak should it be used to track many, many timelines.
The downside is that we then have to frequently reallocate the rbtree.
A compromise is that we keep the most
On 15/07/2020 12:50, Chris Wilson wrote:
Whenever an i915_active idles, we prune its tree of old fence slots to
prevent a gradual leak should it be used to track many, many timelines.
The downside is that we then have to frequently reallocate the rbtree.
A compromise is that we keep the most
Whenever an i915_active idles, we prune its tree of old fence slots to
prevent a gradual leak should it be used to track many, many timelines.
The downside is that we then have to frequently reallocate the rbtree.
A compromise is that we keep the most recently used fence slot, and
reuse that for