Re: [PATCH v2 1/8] io_uring/uring_cmd: add io_uring_cmd_import_fixed_full()

[Joanne Koong <joannelkoong@gmail.com>]

On Thu, Oct 30, 2025 at 3:24 PM Bernd Schubert <bschubert@ddn.com> wrote:
>
>
>
> On 10/30/25 19:06, Pavel Begunkov wrote:
> > On 10/29/25 18:37, Joanne Koong wrote:
> >> On Wed, Oct 29, 2025 at 7:01 AM Pavel Begunkov <asml.silence@gmail.com> wrote:
> >>>
> >>> On 10/27/25 22:28, Joanne Koong wrote:
> >>>> Add an API for fetching the registered buffer associated with a
> >>>> io_uring cmd. This is useful for callers who need access to the buffer
> >>>> but do not have prior knowledge of the buffer's user address or length.
> >>>
> >>> Joanne, is it needed because you don't want to pass {offset,size}
> >>> via fuse uapi? It's often more convenient to allocate and register
> >>> one large buffer and let requests to use subchunks. Shouldn't be
> >>> different for performance, but e.g. if you try to overlay it onto
> >>> huge pages it'll be severely overaccounted.
> >>>
> >>
> >> Hi Pavel,
> >>
> >> Yes, I was thinking this would be a simpler interface than the
> >> userspace caller having to pass in the uaddr and size on every
> >> request. Right now the way it is structured is that userspace
> >> allocates a buffer per request, then registers all those buffers. On
> >> the kernel side when it fetches the buffer, it'll always fetch the
> >> whole buffer (eg offset is 0 and size is the full size).
> >>
> >> Do you think it is better to allocate one large buffer and have the
> >> requests use subchunks?
> >
> > I think so, but that's general advice, I don't know the fuse
> > implementation details, and it's not a strong opinion. It'll be great
> > if you take a look at what other server implementations might want and
> > do, and if whether this approach is flexible enough, and how amendable
> > it is if you change it later on. E.g. how many registered buffers it
> > might need? io_uring caps it at some 1000s. How large buffers are?
> > Each separate buffer has memory footprint. And because of the same
> > footprint there might be cache misses as well if there are too many.
> > Can you always predict the max number of buffers to avoid resizing
> > the table? Do you ever want to use huge pages while being
> > restricted by mlock limits? And so on.
> >
> > In either case, I don't have a problem with this patch, just
> > found it a bit off.
>
> Maybe we could address that later on, so far I don't like the idea
> of a single buffer size for all ring entries. Maybe it would make
> sense to introduce buffer pools of different sizes and let ring
> entries use a needed buffer size dynamically.
>
> The part I'm still not too happy about is the need for fuse server
> changes - my alternative patch didn't need that at all.
>

With pinning through io-uring registered buffers, this lets us also
automatically use pinned pages for writing it out (eg if we're writing
it out to local disk, we can pass that sqe directly to
io_uring_prep_rw() and since it's marked as a registered buffer in io
uring, it'll skip that pinning/translation overhead).

Thanks,
Joanne

> Thanks,
> Bernd