Messages in this thread | | | From | Cong Wang <> | Subject | [Patch v3 0/3] iommu: reduce spinlock contention on fast path | Date | Fri, 6 Dec 2019 13:38:00 -0800 |
| |
This patchset contains three small optimizations for the global spinlock contention in IOVA cache. Our memcache perf test shows this reduced its p999 latency down by 45% on AMD when IOMMU is enabled.
Cong Wang (3): iommu: avoid unnecessary magazine allocations iommu: optimize iova_magazine_free_pfns() iommu: avoid taking iova_rbtree_lock twice --- drivers/iommu/iova.c | 75 ++++++++++++++++++++++++++------------------ 1 file changed, 45 insertions(+), 30 deletions(-)
-- 2.21.0
| |