ublk: cache-align struct ublk_io

struct ublk_io is already 56 bytes on 64-bit architectures, so round it
up to a full cache line (typically 64 bytes). This ensures a single
ublk_io doesn't span multiple cache lines and prevents false sharing if
consecutive ublk_io's are accessed by different daemon tasks.

Signed-off-by: Caleb Sander Mateos <csander@purestorage.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250620151008.3976463-15-csander@purestorage.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This commit is contained in:
Caleb Sander Mateos 2025-06-20 09:10:08 -06:00 committed by Jens Axboe
parent c9d066ebfd
commit 857f431824
1 changed files with 1 additions and 1 deletions

View File

@ -188,7 +188,7 @@ struct ublk_io {
/* auto-registered buffer, valid if UBLK_IO_FLAG_AUTO_BUF_REG is set */
u16 buf_index;
void *buf_ctx_handle;
};
} ____cacheline_aligned_in_smp;
struct ublk_queue {
int q_id;