blk-stat: Optimise blk_stat_add()

blk_stat_add() calls {get,put}_cpu_ptr() in a loop, which entails
overhead of disabling/enabling preemption. The loop is under RCU
(i.e.short) anyway, so do get_cpu() in advance.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This commit is contained in:
Pavel Begunkov 2019-10-08 00:16:51 +03:00 committed by Jens Axboe
parent a2e80f6f04
commit 8148f0b564
1 changed files with 4 additions and 3 deletions

View File

@ -53,7 +53,7 @@ void blk_stat_add(struct request *rq, u64 now)
struct request_queue *q = rq->q;
struct blk_stat_callback *cb;
struct blk_rq_stat *stat;
int bucket;
int bucket, cpu;
u64 value;
value = (now >= rq->io_start_time_ns) ? now - rq->io_start_time_ns : 0;
@ -61,6 +61,7 @@ void blk_stat_add(struct request *rq, u64 now)
blk_throtl_stat_add(rq, value);
rcu_read_lock();
cpu = get_cpu();
list_for_each_entry_rcu(cb, &q->stats->callbacks, list) {
if (!blk_stat_is_active(cb))
continue;
@ -69,10 +70,10 @@ void blk_stat_add(struct request *rq, u64 now)
if (bucket < 0)
continue;
stat = &get_cpu_ptr(cb->cpu_stat)[bucket];
stat = &per_cpu_ptr(cb->cpu_stat, cpu)[bucket];
blk_rq_stat_add(stat, value);
put_cpu_ptr(cb->cpu_stat);
}
put_cpu();
rcu_read_unlock();
}