From: "Darrick J. Wong" <[email protected]>
To: Jens Axboe <[email protected]>
Cc: [email protected], [email protected], [email protected],
[email protected], [email protected]
Subject: Re: [PATCH 7/8] io_uring/rw: add write support for IOCB_DIO_DEFER
Date: Fri, 21 Jul 2023 08:50:34 -0700 [thread overview]
Message-ID: <20230721155034.GP11352@frogsfrogsfrogs> (raw)
In-Reply-To: <[email protected]>
On Thu, Jul 20, 2023 at 12:13:09PM -0600, Jens Axboe wrote:
> If the filesystem dio handler understands IOCB_DIO_DEFER, we'll get
> a kiocb->ki_complete() callback with kiocb->dio_complete set. In that
> case, rather than complete the IO directly through task_work, queue
> up an intermediate task_work handler that first processes this
> callback and then immediately completes the request.
>
> For XFS, this avoids a punt through a workqueue, which is a lot less
> efficient and adds latency to lower queue depth (or sync) O_DIRECT
> writes.
>
> Only do this for non-polled IO, as polled IO doesn't need this kind
> of deferral as it always completes within the task itself. This then
> avoids a check for deferral in the polled IO completion handler.
>
> Signed-off-by: Jens Axboe <[email protected]>
Seems pretty obvious to me, though I'm famous for not being an
experienced io_uring user yet...
Reviewed-by: Darrick J. Wong <[email protected]>
--D
> ---
> io_uring/rw.c | 27 ++++++++++++++++++++++++---
> 1 file changed, 24 insertions(+), 3 deletions(-)
>
> diff --git a/io_uring/rw.c b/io_uring/rw.c
> index 1bce2208b65c..f4f700383b4e 100644
> --- a/io_uring/rw.c
> +++ b/io_uring/rw.c
> @@ -285,6 +285,14 @@ static inline int io_fixup_rw_res(struct io_kiocb *req, long res)
>
> void io_req_rw_complete(struct io_kiocb *req, struct io_tw_state *ts)
> {
> + struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw);
> +
> + if (rw->kiocb.dio_complete) {
> + long res = rw->kiocb.dio_complete(rw->kiocb.private);
> +
> + io_req_set_res(req, io_fixup_rw_res(req, res), 0);
> + }
> +
> io_req_io_end(req);
>
> if (req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)) {
> @@ -300,9 +308,11 @@ static void io_complete_rw(struct kiocb *kiocb, long res)
> struct io_rw *rw = container_of(kiocb, struct io_rw, kiocb);
> struct io_kiocb *req = cmd_to_io_kiocb(rw);
>
> - if (__io_complete_rw_common(req, res))
> - return;
> - io_req_set_res(req, io_fixup_rw_res(req, res), 0);
> + if (!rw->kiocb.dio_complete) {
> + if (__io_complete_rw_common(req, res))
> + return;
> + io_req_set_res(req, io_fixup_rw_res(req, res), 0);
> + }
> req->io_task_work.func = io_req_rw_complete;
> __io_req_task_work_add(req, IOU_F_TWQ_LAZY_WAKE);
> }
> @@ -916,6 +926,17 @@ int io_write(struct io_kiocb *req, unsigned int issue_flags)
> }
> kiocb->ki_flags |= IOCB_WRITE;
>
> + /*
> + * For non-polled IO, set IOCB_DIO_DEFER, stating that our handler
> + * groks deferring the completion to task context. This isn't
> + * necessary and useful for polled IO as that can always complete
> + * directly.
> + */
> + if (!(kiocb->ki_flags & IOCB_HIPRI)) {
> + kiocb->ki_flags |= IOCB_DIO_DEFER;
> + kiocb->dio_complete = NULL;
> + }
> +
> if (likely(req->file->f_op->write_iter))
> ret2 = call_write_iter(req->file, kiocb, &s->iter);
> else if (req->file->f_op->write)
> --
> 2.40.1
next prev parent reply other threads:[~2023-07-21 15:51 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-07-20 18:13 [PATCHSET v4 0/8] Improve async iomap DIO performance Jens Axboe
2023-07-20 18:13 ` [PATCH 1/8] iomap: cleanup up iomap_dio_bio_end_io() Jens Axboe
2023-07-21 6:14 ` Christoph Hellwig
2023-07-21 15:13 ` Darrick J. Wong
2023-07-20 18:13 ` [PATCH 2/8] iomap: add IOMAP_DIO_INLINE_COMP Jens Axboe
2023-07-21 6:14 ` Christoph Hellwig
2023-07-21 15:16 ` Darrick J. Wong
2023-07-20 18:13 ` [PATCH 3/8] iomap: treat a write through cache the same as FUA Jens Axboe
2023-07-21 6:15 ` Christoph Hellwig
2023-07-21 14:04 ` Jens Axboe
2023-07-21 15:55 ` Darrick J. Wong
2023-07-21 16:03 ` Jens Axboe
2023-07-20 18:13 ` [PATCH 4/8] iomap: completed polled IO inline Jens Axboe
2023-07-21 6:16 ` Christoph Hellwig
2023-07-21 15:19 ` Darrick J. Wong
2023-07-21 21:43 ` Dave Chinner
2023-07-22 3:10 ` Jens Axboe
2023-07-22 23:05 ` Dave Chinner
2023-07-24 22:35 ` Jens Axboe
2023-07-22 16:54 ` Jens Axboe
2023-07-20 18:13 ` [PATCH 5/8] iomap: only set iocb->private for polled bio Jens Axboe
2023-07-21 6:18 ` Christoph Hellwig
2023-07-21 15:35 ` Darrick J. Wong
2023-07-21 15:37 ` Jens Axboe
2023-07-20 18:13 ` [PATCH 6/8] fs: add IOCB flags related to passing back dio completions Jens Axboe
2023-07-21 6:18 ` Christoph Hellwig
2023-07-21 15:48 ` Darrick J. Wong
2023-07-21 15:53 ` Jens Axboe
2023-07-20 18:13 ` [PATCH 7/8] io_uring/rw: add write support for IOCB_DIO_DEFER Jens Axboe
2023-07-21 6:19 ` Christoph Hellwig
2023-07-21 15:50 ` Darrick J. Wong [this message]
2023-07-21 15:53 ` Jens Axboe
2023-07-20 18:13 ` [PATCH 8/8] iomap: support IOCB_DIO_DEFER Jens Axboe
2023-07-21 6:19 ` Christoph Hellwig
2023-07-21 16:01 ` Darrick J. Wong
2023-07-21 16:30 ` Jens Axboe
2023-07-21 22:05 ` Dave Chinner
2023-07-22 3:12 ` Jens Axboe
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20230721155034.GP11352@frogsfrogsfrogs \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox