Skip to content

anv: allocate bigger batches as we grow command buffers

Lionel Landwerlin requested to merge llandwerlin/mesa:review/anv-out-of-mmap-issue into main

This is the first time we see an application running out of mmap().

We essentially allocate too many batches (+65k) and end up not being able to mmap them, at which point we can't mmap anything anymore and things go sideways.

This change allocates bigger batch BOs as we grow an existing command buffer. This drastically reduces the number of BOs we need to allocate (the benchmark that reported the issue now reaches a max of ~630 BOs, instead of reaching 65k and failing previously).

Signed-off-by: Lionel Landwerlin lionel.g.landwerlin@intel.com Closes: #4956 (closed) Cc: mesa-stable

Merge request reports