On Thu, Nov 20, 2025 at 6:00 PM Ming Lei <ming.lei@redhat.com> wrote:
>
> Reduce overhead when completing multiple requests in batch I/O mode by
> accumulating them in an io_comp_batch structure and completing them
> together via blk_mq_end_request_batch(). This minimizes per-request
> completion overhead and improves performance for high IOPS workloads.
>
> The implementation adds an io_comp_batch pointer to struct ublk_io and
> initializes it in __ublk_fetch(). For batch I/O, the pointer is set to
> the batch structure in ublk_batch_commit_io(). The __ublk_complete_rq()
> function uses io->iob to call blk_mq_add_to_batch() for batch mode.
> After processing all batch I/Os, the completion callback is invoked in
> ublk_handle_batch_commit_cmd() to complete all accumulated requests
> efficiently.
>
> So far just covers direct completion. For deferred completion(zero copy,
> auto buffer reg), ublk_io_release() is often delayed in freeing buffer
> consumer io_uring request's code path, so this patch often doesn't work,
> also it is hard to pass the per-task 'struct io_comp_batch' for deferred
> completion.
>
> Signed-off-by: Ming Lei <ming.lei@redhat.com>
> ---
>  drivers/block/ublk_drv.c | 30 ++++++++++++++++++++++--------
>  1 file changed, 22 insertions(+), 8 deletions(-)
>
> diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
> index 90cd1863bc83..a5606c7111a4 100644
> --- a/drivers/block/ublk_drv.c
> +++ b/drivers/block/ublk_drv.c
> @@ -130,6 +130,7 @@ struct ublk_batch_io_data {
>         struct io_uring_cmd *cmd;
>         struct ublk_batch_io header;
>         unsigned int issue_flags;
> +       struct io_comp_batch *iob;
>  };
>
>  /*
> @@ -642,7 +643,12 @@ static blk_status_t ublk_setup_iod_zoned(struct ublk_queue *ubq,
>  #endif
>
>  static inline void __ublk_complete_rq(struct request *req, struct ublk_io *io,
> -                                     bool need_map);
> +                                     bool need_map, struct io_comp_batch *iob);
> +
> +static void ublk_complete_batch(struct io_comp_batch *iob)
> +{
> +       blk_mq_end_request_batch(iob);
> +}

Don't see the need for this function, just use blk_mq_end_request_batch instead?

Otherwise,
Reviewed-by: Caleb Sander Mateos <csander@purestorage.com>

>
>  static dev_t ublk_chr_devt;
>  static const struct class ublk_chr_class = {
> @@ -912,7 +918,7 @@ static inline void ublk_put_req_ref(struct ublk_io *io, struct request *req)
>                 return;
>
>         /* ublk_need_map_io() and ublk_need_req_ref() are mutually exclusive */
> -       __ublk_complete_rq(req, io, false);
> +       __ublk_complete_rq(req, io, false, NULL);
>  }
>
>  static inline bool ublk_sub_req_ref(struct ublk_io *io)
> @@ -1251,7 +1257,7 @@ static inline struct ublk_uring_cmd_pdu *ublk_get_uring_cmd_pdu(
>
>  /* todo: handle partial completion */
>  static inline void __ublk_complete_rq(struct request *req, struct ublk_io *io,
> -                                     bool need_map)
> +                                     bool need_map, struct io_comp_batch *iob)
>  {
>         unsigned int unmapped_bytes;
>         blk_status_t res = BLK_STS_OK;
> @@ -1288,8 +1294,11 @@ static inline void __ublk_complete_rq(struct request *req, struct ublk_io *io,
>
>         if (blk_update_request(req, BLK_STS_OK, io->res))
>                 blk_mq_requeue_request(req, true);
> -       else if (likely(!blk_should_fake_timeout(req->q)))
> +       else if (likely(!blk_should_fake_timeout(req->q))) {
> +               if (blk_mq_add_to_batch(req, iob, false, ublk_complete_batch))
> +                       return;
>                 __blk_mq_end_request(req, BLK_STS_OK);
> +       }
>
>         return;
>  exit:
> @@ -2249,7 +2258,7 @@ static void __ublk_fail_req(struct ublk_device *ub, struct ublk_io *io,
>                 blk_mq_requeue_request(req, false);
>         else {
>                 io->res = -EIO;
> -               __ublk_complete_rq(req, io, ublk_dev_need_map_io(ub));
> +               __ublk_complete_rq(req, io, ublk_dev_need_map_io(ub), NULL);
>         }
>  }
>
> @@ -2986,7 +2995,7 @@ static int ublk_ch_uring_cmd_local(struct io_uring_cmd *cmd,
>                 if (req_op(req) == REQ_OP_ZONE_APPEND)
>                         req->__sector = addr;
>                 if (compl)
> -                       __ublk_complete_rq(req, io, ublk_dev_need_map_io(ub));
> +                       __ublk_complete_rq(req, io, ublk_dev_need_map_io(ub), NULL);
>
>                 if (ret)
>                         goto out;
> @@ -3321,11 +3330,11 @@ static int ublk_batch_commit_io(struct ublk_queue *ubq,
>         if (req_op(req) == REQ_OP_ZONE_APPEND)
>                 req->__sector = ublk_batch_zone_lba(uc, elem);
>         if (compl)
> -               __ublk_complete_rq(req, io, ublk_dev_need_map_io(data->ub));
> +               __ublk_complete_rq(req, io, ublk_dev_need_map_io(data->ub), data->iob);
>         return 0;
>  }
>
> -static int ublk_handle_batch_commit_cmd(const struct ublk_batch_io_data *data)
> +static int ublk_handle_batch_commit_cmd(struct ublk_batch_io_data *data)
>  {
>         const struct ublk_batch_io *uc = &data->header;
>         struct io_uring_cmd *cmd = data->cmd;
> @@ -3334,10 +3343,15 @@ static int ublk_handle_batch_commit_cmd(const struct ublk_batch_io_data *data)
>                 .total = uc->nr_elem * uc->elem_bytes,
>                 .elem_bytes = uc->elem_bytes,
>         };
> +       DEFINE_IO_COMP_BATCH(iob);
>         int ret;
>
> +       data->iob = &iob;
>         ret = ublk_walk_cmd_buf(&iter, data, ublk_batch_commit_io);
>
> +       if (iob.complete)
> +               iob.complete(&iob);
> +
>         return iter.done == 0 ? ret : iter.done;
>  }
>
> --
> 2.47.0
>