Re: [PATCH 4/6] block/io_uring: convert to blk_io_plug_call() API

From: Stefan Hajnoczi <stefanha@redhat.com>
To: Eric Blake <eblake@redhat.com>
Cc: qemu-devel@nongnu.org, xen-devel@lists.xenproject.org,
	"Julia Suvorova" <jusual@redhat.com>,
	"Michael S. Tsirkin" <mst@redhat.com>,
	"Stefano Stabellini" <sstabellini@kernel.org>,
	"Stefano Garzarella" <sgarzare@redhat.com>,
	"Kevin Wolf" <kwolf@redhat.com>, "Fam Zheng" <fam@euphon.net>,
	"Philippe Mathieu-Daudé" <philmd@linaro.org>,
	"Paolo Bonzini" <pbonzini@redhat.com>,
	qemu-block@nongnu.org, "Paul Durrant" <paul@xen.org>,
	"Anthony Perard" <anthony.perard@citrix.com>,
	"Aarushi Mehta" <mehta.aaru20@gmail.com>,
	"Hanna Reitz" <hreitz@redhat.com>
Subject: Re: [PATCH 4/6] block/io_uring: convert to blk_io_plug_call() API
Date: Tue, 23 May 2023 11:48:54 -0400	[thread overview]
Message-ID: <20230523154854.GF96478@fedora> (raw)
In-Reply-To: <7xerljqzrhzvl73beu7dboq3d6jbxbkrxbhs25xzcw5ozopgbn@3olwj3w5fil5>

[-- Attachment #1: Type: text/plain, Size: 1213 bytes --]

On Thu, May 18, 2023 at 07:18:42PM -0500, Eric Blake wrote:
> On Wed, May 17, 2023 at 06:10:20PM -0400, Stefan Hajnoczi wrote:
> > Stop using the .bdrv_co_io_plug() API because it is not multi-queue
> > block layer friendly. Use the new blk_io_plug_call() API to batch I/O
> > submission instead.
> > 
> > Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
> > ---
> >  include/block/raw-aio.h |  7 -------
> >  block/file-posix.c      | 10 ---------
> >  block/io_uring.c        | 45 ++++++++++++++++-------------------------
> >  block/trace-events      |  5 ++---
> >  4 files changed, 19 insertions(+), 48 deletions(-)
> > 
> 
> > @@ -337,7 +325,6 @@ void luring_io_unplug(void)
> >   * @type: type of request
> >   *
> >   * Fetches sqes from ring, adds to pending queue and preps them
> > - *
> >   */
> >  static int luring_do_submit(int fd, LuringAIOCB *luringcb, LuringState *s,
> >                              uint64_t offset, int type)
> > @@ -370,14 +357,16 @@ static int luring_do_submit(int fd, LuringAIOCB *luringcb, LuringState *s,
> 
> Looks a bit like a stray hunk, but you are touching the function, so
> it's okay.

I'm respinning, so I'll drop this.

Stefan

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]