public inbox for [email protected]
 help / color / mirror / Atom feed
From: Keith Busch <[email protected]>
To: Kanchan Joshi <[email protected]>
Cc: Keith Busch <[email protected]>,
	[email protected], [email protected], [email protected],
	[email protected], [email protected],
	[email protected], [email protected],
	[email protected]
Subject: Re: [PATCHv11 03/10] io_uring: add write stream attribute
Date: Fri, 6 Dec 2024 08:53:14 -0800	[thread overview]
Message-ID: <[email protected]> (raw)
In-Reply-To: <[email protected]>

On Fri, Dec 06, 2024 at 06:14:29PM +0530, Kanchan Joshi wrote:
> On 12/6/2024 7:23 AM, Keith Busch wrote:
> > From: Keith Busch <[email protected]>
> > 
> > Adds a new attribute type to specify a write stream per-IO.
> > 
> > Signed-off-by: Keith Busch <[email protected]>
> > ---
> >   include/uapi/linux/io_uring.h |  9 ++++++++-
> >   io_uring/rw.c                 | 28 +++++++++++++++++++++++++++-
> >   2 files changed, 35 insertions(+), 2 deletions(-)
> > 
> > diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
> > index 5fa38467d6070..263cd57aae72d 100644
> > --- a/include/uapi/linux/io_uring.h
> > +++ b/include/uapi/linux/io_uring.h
> > @@ -123,7 +123,14 @@ struct io_uring_attr_pi {
> >   	__u64	rsvd;
> >   };
> >   
> > -#define IORING_RW_ATTR_FLAGS_SUPPORTED (IORING_RW_ATTR_FLAG_PI)
> > +#define IORING_RW_ATTR_FLAG_WRITE_STREAM (1U << 1)
> > +struct io_uring_write_stream {
> > +	__u16	write_stream;
> > +	__u8	rsvd[6];
> > +};
> 
> So this needs 8 bytes. Maybe passing just 'u16 write_stream' is better? 
> Or do you expect future additions here (to keep rsvd).

I don't have any plans to use it. It's just padded for alignment. I am
not sure what future attributes might be proposed, but I don't want to
force them be align to a 2-byte boundary.
 
> Optimization is possible (now or in future) if it's 4 bytes or smaller, 
> as that can be placed in SQE along with a new RW attribute flag that 
> says it's placed inline. Like this -

Oh, that's definitely preferred IMO, because it is that much easier to
reach the capability. Previous versions of this proposal had the field
in the next union, so I for some reason this union you're showing here
was unavailable for new fields, but it looks like it's unused for
read/write. So, yeah, let's put it in the sqe if there's no conflict
here.

> --- a/include/uapi/linux/io_uring.h
> +++ b/include/uapi/linux/io_uring.h
> @@ -92,6 +92,10 @@ struct io_uring_sqe {
>                          __u16   addr_len;
>                          __u16   __pad3[1];
>                  };
> +               struct {
> +                       __u16   write_hint;
> +                       __u16   __rsvd[1];
> +               };
>          };
>          union {
>                  struct {

  reply	other threads:[~2024-12-06 16:53 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-12-06  1:52 [PATCHv11 00/10] block write streams with nvme fdp Keith Busch
2024-12-06  1:52 ` [PATCHv11 01/10] fs: add a write stream field to the kiocb Keith Busch
2024-12-06  1:53 ` [PATCHv11 02/10] io_uring: protection information enhancements Keith Busch
     [not found]   ` <CGME20241206095739epcas5p1ee968cb92c9d4ceb25a79ad80521601f@epcas5p1.samsung.com>
2024-12-06  9:49     ` Anuj Gupta
2024-12-06  1:53 ` [PATCHv11 03/10] io_uring: add write stream attribute Keith Busch
     [not found]   ` <CGME20241206100326epcas5p17d4dad663ccc6c6f40cfab98437e63f3@epcas5p1.samsung.com>
2024-12-06  9:55     ` Anuj Gupta
2024-12-06 12:44   ` Kanchan Joshi
2024-12-06 16:53     ` Keith Busch [this message]
2024-12-06  1:53 ` [PATCHv11 04/10] block: add a bi_write_stream field Keith Busch
2024-12-06  1:53 ` [PATCHv11 05/10] block: introduce max_write_streams queue limit Keith Busch
2024-12-06  1:53 ` [PATCHv11 06/10] block: introduce a write_stream_granularity " Keith Busch
2024-12-06  1:53 ` [PATCHv11 07/10] block: expose write streams for block device nodes Keith Busch
     [not found]   ` <CGME20241206091949epcas5p14a01e4cfe614ddd04e23b84f8f1036d5@epcas5p1.samsung.com>
2024-12-06  9:11     ` Nitesh Shetty
2024-12-06  1:53 ` [PATCHv11 08/10] nvme: add a nvme_get_log_lsi helper Keith Busch
2024-12-06  1:53 ` [PATCHv11 09/10] nvme: register fdp queue limits Keith Busch
2024-12-06  5:26   ` kernel test robot
2024-12-06  1:53 ` [PATCHv11 10/10] nvme: use fdp streams if write stream is provided Keith Busch
2024-12-06 13:18   ` kernel test robot
2024-12-06  2:18 ` [PATCHv11 00/10] block write streams with nvme fdp Keith Busch
2024-12-09 12:51 ` Christoph Hellwig
2024-12-09 15:57   ` Keith Busch
2024-12-09 17:14   ` [EXT] " Pierre Labat
2024-12-09 17:25     ` Keith Busch
2024-12-09 17:35       ` Pierre Labat

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 \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [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