Date:   Tue, 7 Jul 2020 16:52:37 +0100
From:   Matthew Wilcox <willy@...radead.org>
To:     Kanchan Joshi <joshi.k@...sung.com>
Cc:     Jens Axboe <axboe@...nel.dk>, viro@...iv.linux.org.uk,
        bcrl@...ck.org, hch@...radead.org, Damien.LeMoal@....com,
        asml.silence@...il.com, linux-fsdevel@...r.kernel.org,
        mb@...htnvm.io, linux-kernel@...r.kernel.org, linux-aio@...ck.org,
        io-uring@...r.kernel.org, linux-block@...r.kernel.org,
        Selvakumar S <selvakuma.s1@...sung.com>,
        Nitesh Shetty <nj.shetty@...sung.com>,
        Javier Gonzalez <javier.gonz@...sung.com>
Subject: Re: [PATCH v3 4/4] io_uring: add support for zone-append

On Tue, Jul 07, 2020 at 08:41:05PM +0530, Kanchan Joshi wrote:
> On Mon, Jul 06, 2020 at 03:32:08PM +0100, Matthew Wilcox wrote:
> > On Mon, Jul 06, 2020 at 08:27:17AM -0600, Jens Axboe wrote:
> > > On 7/6/20 8:10 AM, Matthew Wilcox wrote:
> > > > On Sun, Jul 05, 2020 at 03:12:50PM -0600, Jens Axboe wrote:
> > > >> On 7/5/20 3:09 PM, Matthew Wilcox wrote:
> > > >>> On Sun, Jul 05, 2020 at 03:00:47PM -0600, Jens Axboe wrote:
> > > >>>> On 7/5/20 12:47 PM, Kanchan Joshi wrote:
> > > >>>>> From: Selvakumar S <selvakuma.s1@...sung.com>
> > > >>>>>
> > > >>>>> For zone-append, block-layer will return zone-relative offset via ret2
> > > >>>>> of ki_complete interface. Make changes to collect it, and send to
> > > >>>>> user-space using cqe->flags.
> > > >
> > > >>> I'm surprised you aren't more upset by the abuse of cqe->flags for the
> > > >>> address.
> 
> Documentation (https://kernel.dk/io_uring.pdf) mentioned cqe->flags can carry
> the metadata for the operation. I wonder if this should be called abuse.
> 
> > > >> Yeah, it's not great either, but we have less leeway there in terms of
> > > >> how much space is available to pass back extra data.
> > > >>
> > > >>> What do you think to my idea of interpreting the user_data as being a
> > > >>> pointer to somewhere to store the address?  Obviously other things
> > > >>> can be stored after the address in the user_data.
> > > >>
> > > >> I don't like that at all, as all other commands just pass user_data
> > > >> through. This means the application would have to treat this very
> > > >> differently, and potentially not have a way to store any data for
> > > >> locating the original command on the user side.
> > > >
> > > > I think you misunderstood me.  You seem to have thought I meant
> > > > "use the user_data field to return the address" when I actually meant
> > > > "interpret the user_data field as a pointer to where userspace
> > > > wants the address stored".
> > > 
> > > It's still somewhat weird to have user_data have special meaning, you're
> > > now having the kernel interpret it while every other command it's just
> > > an opaque that is passed through.
> > > 
> > > But it could of course work, and the app could embed the necessary
> > > u32/u64 in some other structure that's persistent across IO. If it
> > > doesn't have that, then it'd need to now have one allocated and freed
> > > across the lifetime of the IO.
> > > 
> > > If we're going that route, it'd be better to define the write such that
> > > you're passing in the necessary information upfront. In syscall terms,
> > > then that'd be something ala:
> > > 
> > > ssize_t my_append_write(int fd, const struct iovec *iov, int iovcnt,
> > > 			off_t *offset, int flags);
> > > 
> > > where *offset is copied out when the write completes. That removes the
> > > need to abuse user_data, with just providing the storage pointer for the
> > > offset upfront.
> > 
> > That works for me!  In io_uring terms, would you like to see that done
> > as adding:
> > 
> >        union {
> >                __u64   off;    /* offset into file */
> > +		__u64   *offp;	/* appending writes */
> >                __u64   addr2;
> >        };
> But there are peformance implications of this approach?
> If I got it right, the workflow is: - Application allocates 64bit of space,
> writes "off" into it and pass it
>  in the sqe->addr2
> - Kernel first reads sqe->addr2, reads the value to know the intended
>  write-location, and stores the address somewhere (?) to be used during
>  completion. Storing this address seems tricky as this may add one more
>  cacheline (in io_kiocb->rw)?

io_kiocb is:
        /* size: 232, cachelines: 4, members: 19 */
        /* forced alignments: 1 */
        /* last cacheline: 40 bytes */
so we have another 24 bytes before io_kiocb takes up another cacheline.
If that's a serious problem, I have an idea about how to shrink struct
kiocb by 8 bytes so struct io_rw would have space to store another
pointer.

> - During completion cqe res/flags are written as before, but extra step
>  to copy the append-completion-result into that user-space address.
> Extra steps are due to the pointer indirection.

... we've just done an I/O.  Concern about an extra pointer access
seems misplaced?

> And it seems application needs to be careful about managing this 64bit of
> space for a cluster of writes, especially if it wants to reuse the sqe
> before the completion.
> New one can handle 64bit result cleanly, but seems slower than current
> one.

But userspace has to _do_ something with that information anyway.  So
it must already have somewhere to put that information.

I do think that interpretation of that field should be a separate flag
from WRITE_APPEND so apps which genuinely don't care about where the I/O
ended up don't have to allocate some temporary storage.  eg a logging
application which just needs to know that it managed to append to the
end of the log and doesn't need to do anything if it's successful.

Powered by blists - more mailing lists