From: Jens Axboe <axboe@kernel.dk>
To: Keith Busch <kbusch@kernel.org>
Cc: Caleb Sander Mateos <csander@purestorage.com>, io-uring@vger.kernel.org
Subject: Re: [PATCHSET v2 0/8] Add support for mixed sized CQEs
Date: Thu, 21 Aug 2025 11:47:33 -0600 [thread overview]
Message-ID: <1bbb3425-557d-4c6b-be41-2ae67336e413@kernel.dk> (raw)
In-Reply-To: <aKdZ8TUE811CBrSn@kbusch-mbp>
On 8/21/25 11:40 AM, Keith Busch wrote:
> On Thu, Aug 21, 2025 at 11:12:28AM -0600, Jens Axboe wrote:
>>
>> For the SQE case, I think it's a bit different. At least the cases I
>> know of, it's mostly 100% 64b SQEs or 128b SQEs. I'm certainly willing
>> to be told otherwise! Because that is kind of the key question that
>> needs answering before even thinking about doing that kind of work.
>
> The main use case I can think of is if an application allocates one ring
> for uring_cmd with the 128b SQEs, and then a separate ring for normal
> file and network stuff. Mixed SQE's would allow that application to have
> just one ring without being wasteful, but I'm just not sure if the
> separate rings is undesirable enough to make the effort worth it.
Indeed! And like Caleb mentioned, their use case already does this in
fact, just passthrough with housekeeping buffer commands.
>> But yes, it could be supported, and Keith (kind of) signed himself up to
>> do that. One oddity I see on that side is that while with CQE32 the
>> kernel can manage the potential wrap-around gap, for SQEs that's
>> obviously on the application to do. That could just be a NOP or
>> something like that, but you do need something to fill/skip that space.
>> I guess that could be as simple as having an opcode that is simply "skip
>> me", so on the kernel side it'd be easy as it'd just drop it on the
>> floor. You still need to app side to fill one, however, and then deal
>> with "oops SQ ring is now full" too.
>
> Yep, I think it's doable, and your implementation for mixed CQEs
> provides a great reference. I trust we can get liburing using it
> correctly, but would be afraid for anyone not using the library.
That's the same with the mixed CQEs though - as you can see from the
liburing changes, it's really not hard to support. If you're using the
raw interface, well then things are already a bit more complicated for
you. Not too worried about that use case.
--
Jens Axboe
next prev parent reply other threads:[~2025-08-21 17:47 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-08-21 14:18 [PATCHSET v2 0/8] Add support for mixed sized CQEs Jens Axboe
2025-08-21 14:18 ` [PATCH 1/8] io_uring: remove io_ctx_cqe32() helper Jens Axboe
2025-08-21 14:18 ` [PATCH 2/8] io_uring: add UAPI definitions for mixed CQE postings Jens Axboe
2025-08-21 14:18 ` [PATCH 3/8] io_uring/fdinfo: handle mixed sized CQEs Jens Axboe
2025-08-21 14:18 ` [PATCH 4/8] io_uring/trace: support completion tracing of mixed 32b CQEs Jens Axboe
2025-08-21 14:18 ` [PATCH 5/8] io_uring: add support for IORING_SETUP_CQE_MIXED Jens Axboe
2025-08-21 14:18 ` [PATCH 6/8] io_uring/nop: " Jens Axboe
2025-08-21 14:18 ` [PATCH 7/8] io_uring/uring_cmd: " Jens Axboe
2025-08-21 14:18 ` [PATCH 8/8] io_uring/zcrx: " Jens Axboe
2025-08-21 17:02 ` [PATCHSET v2 0/8] Add support for mixed sized CQEs Caleb Sander Mateos
2025-08-21 17:12 ` Jens Axboe
2025-08-21 17:40 ` Keith Busch
2025-08-21 17:47 ` Jens Axboe [this message]
2025-08-21 17:41 ` Caleb Sander Mateos
2025-08-21 17:46 ` Jens Axboe
2025-08-21 18:19 ` Caleb Sander Mateos
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=1bbb3425-557d-4c6b-be41-2ae67336e413@kernel.dk \
--to=axboe@kernel.dk \
--cc=csander@purestorage.com \
--cc=io-uring@vger.kernel.org \
--cc=kbusch@kernel.org \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.