summaryrefslogtreecommitdiff
path: root/tools/perf/scripts/python/stackcollapse.py
diff options
context:
space:
mode:
authorMatthew Brost <matthew.brost@intel.com>2026-06-11 16:58:44 -0700
committerMatthew Brost <matthew.brost@intel.com>2026-06-12 15:23:34 -0700
commit0d81db90d364cb3d733410829118759f28957c5a (patch)
tree71f96a9269ad60706d35ef6a0c521153e9724bcc /tools/perf/scripts/python/stackcollapse.py
parent02b7f6c326b7283fec94e44f9118a791a2477bf3 (diff)
drm/xe: Set TTM device beneficial_order to 9 (2M)
Set the TTM device beneficial_order to 9 (2M), which is the sweet spot for Xe when attempting reclaim on system memory BOs, as it matches the large GPU page size. This ensures reclaim is attempted at the most effective order for the driver. This fixes an issue where an order-10 (4M) allocation cannot be found despite an abundance of memory. The 4M allocation triggers reclaim, unnecessarily evicting the working set and hurting performance. Since the TTM infrastructure was introduced recently, we are tagging the TTM patch as the Fixes target, even though this resolves an Xe-side problem. Fixes: 7e9c548d3709 ("drm/ttm: Allow drivers to specify maximum beneficial TTM pool size") Cc: stable@vger.kernel.org Signed-off-by: Matthew Brost <matthew.brost@intel.com> Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com> Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com> Link: https://patch.msgid.link/20260611235844.3725147-1-matthew.brost@intel.com
Diffstat (limited to 'tools/perf/scripts/python/stackcollapse.py')
0 files changed, 0 insertions, 0 deletions