null_blk: unalign call_single_data

Commit 966a967116e6 randomly added alignment to this structure, but
it's actually detrimental to performance of null_blk. Test case:

Running on both the home and remote node shows a ~5% degradation
in performance.

While in there, move blk_status_t to the hole after the integer tag
in the nullb_cmd structure. After this patch, we shrink the size
from 192 to 152 bytes.

Fixes: 966a967116e69 ("smp: Avoid using two cache lines for struct call_single_data")
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index ccb9975a97fa3f214d658776450ab618bae26643..ad0477ae820f040affe54f4368d3a02d9da63350 100644 (file)
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -35,13 +35,13 @@ static inline u64 mb_per_tick(int mbps)
 struct nullb_cmd {
        struct list_head list;
        struct llist_node ll_list;
-       call_single_data_t csd;
+       struct __call_single_data csd;
        struct request *rq;
        struct bio *bio;
        unsigned int tag;
+       blk_status_t error;
        struct nullb_queue *nq;
        struct hrtimer timer;
-       blk_status_t error;
 };
 
 struct nullb_queue {