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 6/9] fs: add IOCB flags related to passing back dio completions
Date: Fri, 21 Jul 2023 09:28:07 -0700 [thread overview]
Message-ID: <20230721162807.GT11352@frogsfrogsfrogs> (raw)
In-Reply-To: <[email protected]>
On Fri, Jul 21, 2023 at 10:16:47AM -0600, Jens Axboe wrote:
> Async dio completions generally happen from hard/soft IRQ context, which
> means that users like iomap may need to defer some of the completion
> handling to a workqueue. This is less efficient than having the original
> issuer handle it, like we do for sync IO, and it adds latency to the
> completions.
>
> Add IOCB_DIO_CALLER_COMP, which the issuer can set if it is able to
> safely punt these completions to a safe context. If the dio handler is
> aware of this flag, assign a callback handler in kiocb->dio_complete and
> associated data io kiocb->private. The issuer will then call this
> handler with that data from task context.
>
> No functional changes in this patch.
>
> Reviewed-by: Christoph Hellwig <[email protected]>
> Signed-off-by: Jens Axboe <[email protected]>
> ---
> include/linux/fs.h | 35 +++++++++++++++++++++++++++++++++--
> 1 file changed, 33 insertions(+), 2 deletions(-)
>
> diff --git a/include/linux/fs.h b/include/linux/fs.h
> index 6867512907d6..60e2b4ecfc4d 100644
> --- a/include/linux/fs.h
> +++ b/include/linux/fs.h
> @@ -338,6 +338,20 @@ enum rw_hint {
> #define IOCB_NOIO (1 << 20)
> /* can use bio alloc cache */
> #define IOCB_ALLOC_CACHE (1 << 21)
> +/*
> + * IOCB_DIO_CALLER_COMP can be set by the iocb owner, to indicate that the
> + * iocb completion can be passed back to the owner for execution from a safe
> + * context rather than needing to be punted through a workqueue.If this If this
"...through a workqueue. If this flag is set..."
Need a space after the period, and delete one of the "If this".
With that fixed,
Reviewed-by: Darrick J. Wong <[email protected]>
--D
> + * flag is set, the bio completion handling may set iocb->dio_complete to a
> + * handler function and iocb->private to context information for that handler.
> + * The issuer should call the handler with that context information from task
> + * context to complete the processing of the iocb. Note that while this
> + * provides a task context for the dio_complete() callback, it should only be
> + * used on the completion side for non-IO generating completions. It's fine to
> + * call blocking functions from this callback, but they should not wait for
> + * unrelated IO (like cache flushing, new IO generation, etc).
> + */
> +#define IOCB_DIO_CALLER_COMP (1 << 22)
>
> /* for use in trace events */
> #define TRACE_IOCB_STRINGS \
> @@ -351,7 +365,8 @@ enum rw_hint {
> { IOCB_WRITE, "WRITE" }, \
> { IOCB_WAITQ, "WAITQ" }, \
> { IOCB_NOIO, "NOIO" }, \
> - { IOCB_ALLOC_CACHE, "ALLOC_CACHE" }
> + { IOCB_ALLOC_CACHE, "ALLOC_CACHE" }, \
> + { IOCB_DIO_CALLER_COMP, "CALLER_COMP" }
>
> struct kiocb {
> struct file *ki_filp;
> @@ -360,7 +375,23 @@ struct kiocb {
> void *private;
> int ki_flags;
> u16 ki_ioprio; /* See linux/ioprio.h */
> - struct wait_page_queue *ki_waitq; /* for async buffered IO */
> + union {
> + /*
> + * Only used for async buffered reads, where it denotes the
> + * page waitqueue associated with completing the read. Valid
> + * IFF IOCB_WAITQ is set.
> + */
> + struct wait_page_queue *ki_waitq;
> + /*
> + * Can be used for O_DIRECT IO, where the completion handling
> + * is punted back to the issuer of the IO. May only be set
> + * if IOCB_DIO_CALLER_COMP is set by the issuer, and the issuer
> + * must then check for presence of this handler when ki_complete
> + * is invoked. The data passed in to this handler must be
> + * assigned to ->private when dio_complete is assigned.
> + */
> + ssize_t (*dio_complete)(void *data);
> + };
> };
>
> static inline bool is_sync_kiocb(struct kiocb *kiocb)
> --
> 2.40.1
>
next prev parent reply other threads:[~2023-07-21 16:31 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-07-21 16:16 [PATCHSET v5 0/9] Improve async iomap DIO performance Jens Axboe
2023-07-21 16:16 ` [PATCH 1/9] iomap: cleanup up iomap_dio_bio_end_io() Jens Axboe
2023-07-21 16:16 ` [PATCH 2/9] iomap: add IOMAP_DIO_INLINE_COMP Jens Axboe
2023-07-21 16:16 ` [PATCH 3/9] iomap: treat a write through cache the same as FUA Jens Axboe
2023-07-21 16:25 ` Darrick J. Wong
2023-07-21 16:27 ` Jens Axboe
2023-07-21 16:47 ` Darrick J. Wong
2023-07-21 16:52 ` Jens Axboe
2023-07-21 16:16 ` [PATCH 4/9] iomap: completed polled IO inline Jens Axboe
2023-07-21 16:16 ` [PATCH 5/9] iomap: only set iocb->private for polled bio Jens Axboe
2023-07-21 16:16 ` [PATCH 6/9] fs: add IOCB flags related to passing back dio completions Jens Axboe
2023-07-21 16:28 ` Darrick J. Wong [this message]
2023-07-21 16:30 ` Jens Axboe
2023-07-21 16:43 ` Jens Axboe
2023-07-21 16:16 ` [PATCH 7/9] io_uring/rw: add write support for IOCB_DIO_CALLER_COMP Jens Axboe
2023-07-21 16:29 ` Darrick J. Wong
2023-07-21 16:16 ` [PATCH 8/9] iomap: support IOCB_DIO_CALLER_COMP Jens Axboe
2023-07-21 16:16 ` [PATCH 9/9] iomap: use an unsigned type for IOMAP_DIO_* defines Jens Axboe
2023-07-21 16:29 ` Darrick J. Wong
2023-07-24 16:36 ` Christoph Hellwig
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=20230721162807.GT11352@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