diff options
| author | Shay Drory <shayd@nvidia.com> | 2023-09-21 11:07:16 +0300 |
|---|---|---|
| committer | Leon Romanovsky <leon@kernel.org> | 2023-09-26 12:36:18 +0300 |
| commit | 57e7071683ef6148c9f5ea0ba84598d2ba681375 (patch) | |
| tree | f2b507f15a0bfce74206f2d1db49e4b0cb51bde0 /drivers/infiniband/hw/mlx5/umr.c | |
| parent | cb7ab7854bc70942abed62d19d8c16d0064bf7dc (diff) | |
| download | linux-57e7071683ef6148c9f5ea0ba84598d2ba681375.tar.xz | |
RDMA/mlx5: Implement mkeys management via LIFO queue
Currently, mkeys are managed via xarray. This implementation leads to
a degradation in cases many MRs are unregistered in parallel, due to xarray
internal implementation, for example: deregistration 1M MRs via 64 threads
is taking ~15% more time[1].
Hence, implement mkeys management via LIFO queue, which solved the
degradation.
[1]
2.8us in kernel v5.19 compare to 3.2us in kernel v6.4
Signed-off-by: Shay Drory <shayd@nvidia.com>
Link: https://lore.kernel.org/r/fde3d4cfab0f32f0ccb231cd113298256e1502c5.1695283384.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Diffstat (limited to 'drivers/infiniband/hw/mlx5/umr.c')
| -rw-r--r-- | drivers/infiniband/hw/mlx5/umr.c | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/drivers/infiniband/hw/mlx5/umr.c b/drivers/infiniband/hw/mlx5/umr.c index 234bf30db731..e76142f6fa88 100644 --- a/drivers/infiniband/hw/mlx5/umr.c +++ b/drivers/infiniband/hw/mlx5/umr.c @@ -332,8 +332,8 @@ static int mlx5r_umr_post_send_wait(struct mlx5_ib_dev *dev, u32 mkey, WARN_ON_ONCE(1); mlx5_ib_warn(dev, - "reg umr failed (%u). Trying to recover and resubmit the flushed WQEs\n", - umr_context.status); + "reg umr failed (%u). Trying to recover and resubmit the flushed WQEs, mkey = %u\n", + umr_context.status, mkey); mutex_lock(&umrc->lock); err = mlx5r_umr_recover(dev); mutex_unlock(&umrc->lock); |