The current BO cache puts BOs back into the recycle bucket the moment the refcount hits zero. If the BO is busy, we just don't re-use it until it isn't or we re-use it for a render target which we assume will be used first for drawing. This patch series reworks the way the BO cache works a bit so that we don't ever recycle a busy BO. On the down side, it means that we don't get the "keep busy BOs busy" heuristic (which we have no proof actually helps). On the up side, we can now easily use a MRU heuristic instead of round-robin for all buffers and not just the busy ones. Will this be an improvement, a regression or a wash? I don't know but I doubt it will have a major effect one way or another.
Jason Ekstrand (8): i965/bufmgr: Bail early in bo_busy if the BO is flagged idle i965/miptree: Stop setting BO_ALLOC_BUSY i965/bufmgr: Drop the BO_ALLOC_BUSY flag i965/bufmgr: Add a garbage collection mechanism i965/batch: Use brw_bo_unreference_bos_when_idle i965: Call intel_finish before destroying the context i965/bufmgr: Don't allow busy BOs to be returned to the pool i965/bufmgr: Allocate from the tail of the bucket free list src/mesa/drivers/dri/i965/brw_bufmgr.c | 186 +++++++++++++----- src/mesa/drivers/dri/i965/brw_bufmgr.h | 18 +- src/mesa/drivers/dri/i965/brw_context.c | 8 + src/mesa/drivers/dri/i965/intel_batchbuffer.c | 8 +- src/mesa/drivers/dri/i965/intel_fbo.c | 2 +- src/mesa/drivers/dri/i965/intel_mipmap_tree.c | 29 ++- src/mesa/drivers/dri/i965/intel_mipmap_tree.h | 9 - src/mesa/drivers/dri/i965/intel_screen.c | 2 +- .../drivers/dri/i965/intel_tex_validate.c | 2 +- 9 files changed, 182 insertions(+), 82 deletions(-) -- 2.17.1 _______________________________________________ mesa-dev mailing list mesa-dev@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/mesa-dev
