On Tue, Feb 22, 2022 at 03:14:39PM +0100, Christoph Hellwig wrote:
> I/O accounting buckets I/O into the read/write/discard categories into
> which passthrough I/O does not fit at all. It also accounts to the
> block_device, which may not even exist for passthrough I/O.
>
> Signed-off-by: Christoph Hellwig <hch@xxxxxx>
> ---
> block/blk-mq.c | 6 +-----
> block/blk.h | 2 +-
> 2 files changed, 2 insertions(+), 6 deletions(-)
>
> diff --git a/block/blk-mq.c b/block/blk-mq.c
> index a05ce77250316..ee80853473d1e 100644
> --- a/block/blk-mq.c
> +++ b/block/blk-mq.c
> @@ -883,11 +883,7 @@ static inline void blk_account_io_done(struct request *req, u64 now)
>
> static void __blk_account_io_start(struct request *rq)
> {
> - /* passthrough requests can hold bios that do not have ->bi_bdev set */
> - if (rq->bio && rq->bio->bi_bdev)
> - rq->part = rq->bio->bi_bdev;
> - else if (rq->q->disk)
> - rq->part = rq->q->disk->part0;
> + rq->part = rq->bio->bi_bdev;
>
> part_stat_lock();
> update_io_ticks(rq->part, jiffies, false);
> diff --git a/block/blk.h b/block/blk.h
> index ebaa59ca46ca6..6f21859c7f0ff 100644
> --- a/block/blk.h
> +++ b/block/blk.h
> @@ -325,7 +325,7 @@ int blk_dev_init(void);
> */
> static inline bool blk_do_io_stat(struct request *rq)
> {
> - return (rq->rq_flags & RQF_IO_STAT) && rq->q->disk;
> + return (rq->rq_flags & RQF_IO_STAT) && !blk_rq_is_passthrough(rq);
I guess this way may cause regression for workloads with lots of userspace IO
from user viewpoint?
Thanks,
Ming
