qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Kevin Wolf <kwolf@redhat.com>
To: Aarushi Mehta <mehta.aaru20@gmail.com>
Cc: qemu-block@nongnu.org, qemu-devel@nongnu.org,
	saket.sinha89@gmail.com, Stefan Hajnoczi <stefanha@redhat.com>,
	Julia Suvorova <jusual@mail.ru>
Subject: Re: [Qemu-devel] [Qemu-block] [RFC PATCH 1/9] qapi/block-core: add option for io_uring
Date: Wed, 22 May 2019 11:16:11 +0200	[thread overview]
Message-ID: <20190522091611.GA6087@localhost.localdomain> (raw)
In-Reply-To: <1c277edc76e47fbbaae0ecdd6774e24ac9a94ee5.camel@gmail.com>

Am 22.05.2019 um 02:51 hat Aarushi Mehta geschrieben:
> On Tue, 2019-05-21 at 19:39 -0500, Eric Blake wrote:
> > On 5/21/19 6:52 PM, Aarushi Mehta wrote:
> > > Signed-off-by: Aarushi Mehta <mehta.aaru20@gmail.com>
> > 
> > Sparse on the details. The subject line says what, but without a
> > 'why'
> > for how io_uring is different from existing aio options, it's hard to
> > see why I'd want to use it. Do you have any benchmark numbers?
> 
> For peak performance, io_uring helps us get to 1.7M 4k IOPS with
> polling. aio reaches a performance cliff much lower than that, at 608K.
> If we disable polling, io_uring is able to drive about 1.2M IOPS for
> the (otherwise) same test case.
> 
> More details, and the source for the above is at
> http://kernel.dk/io_uring.pdf
> 
> > > ---
> > >  qapi/block-core.json | 3 ++-
> > >  1 file changed, 2 insertions(+), 1 deletion(-)
> > > 
> > > diff --git a/qapi/block-core.json b/qapi/block-core.json
> > > index 7ccbfff9d0..116995810a 100644
> > > --- a/qapi/block-core.json
> > > +++ b/qapi/block-core.json
> > > @@ -2776,11 +2776,12 @@
> > >  #
> > >  # @threads:     Use qemu's thread pool
> > >  # @native:      Use native AIO backend (only Linux and Windows)
> > > +# @io_uring:    Use linux io_uring
> > 
> > Missing a '(since 4.1)' tag.
> > 
> > >  #
> > >  # Since: 2.9
> > >  ##
> > >  { 'enum': 'BlockdevAioOptions',
> > > -  'data': [ 'threads', 'native' ] }
> > > +  'data': [ 'threads', 'native','io_uring' ] }
> > 
> > Missing space after ',' (not essential, but matching style is nice).
> > Should the new element be defined conditionally, so that
> > introspection
> > only sees the new enum member when compiled for Linux?
> > 
> I'm not sure what would be the benefits of that? We already check for
> Linux at configure, and this would reduce readability. We aren't doing
> this for native.

BlockdevAioOptions is used in BlockdevOptionsFile, which contains the
options for two different drivers: file-posix and file-win32. Both of
them support both 'threads' and 'native'. However, I don't think you'll
add the new mode to the Windows driver. So I think making it conditional
on CONFIG_POSIX at least is necessary.

Kevin


  parent reply	other threads:[~2019-05-22  9:22 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-05-21 23:52 [Qemu-devel] [RFC PATCH 0/9] Add support for io_uring Aarushi Mehta
2019-05-21 23:52 ` [Qemu-devel] [RFC PATCH 1/9] qapi/block-core: add option " Aarushi Mehta
2019-05-22  0:39   ` Eric Blake
2019-05-22  0:51     ` Aarushi Mehta
2019-05-22  1:01       ` Eric Blake
2019-05-22  9:16       ` Kevin Wolf [this message]
2019-05-22 13:07       ` Stefan Hajnoczi
2019-05-21 23:52 ` [Qemu-devel] [RFC PATCH 2/9] block/block: add BDRV flag " Aarushi Mehta
2019-05-21 23:52 ` [Qemu-devel] [RFC PATCH 3/9] include/block: declare interfaces " Aarushi Mehta
2019-05-22 13:09   ` Stefan Hajnoczi
2019-05-21 23:52 ` [Qemu-devel] [RFC PATCH 4/9] stubs: add aio interface stubs " Aarushi Mehta
2019-05-22 13:10   ` Stefan Hajnoczi
2019-05-21 23:52 ` [Qemu-devel] [RFC PATCH 5/9] util/asyn: add aio interfaces " Aarushi Mehta
2019-05-22 13:16   ` Stefan Hajnoczi
2019-05-21 23:52 ` [Qemu-devel] [RFC PATCH 6/9] block/io_uring: implements " Aarushi Mehta
2019-05-22 15:43   ` Stefan Hajnoczi
2019-05-21 23:52 ` [Qemu-devel] [RFC PATCH 7/9] blockdev: accept io_uring as option Aarushi Mehta
2019-05-21 23:52 ` [Qemu-devel] [RFC PATCH 8/9] block/file-posix: extends to use with io_uring Aarushi Mehta
2019-05-22 15:45   ` Stefan Hajnoczi
2019-05-21 23:52 ` [Qemu-devel] [RFC PATCH 9/9] configure: permits use of io_uring with probe Aarushi Mehta
2019-05-22  0:09 ` [Qemu-devel] [RFC PATCH 0/9] Add support for io_uring no-reply
2019-05-22 15:46 ` Stefan Hajnoczi

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=20190522091611.GA6087@localhost.localdomain \
    --to=kwolf@redhat.com \
    --cc=jusual@mail.ru \
    --cc=mehta.aaru20@gmail.com \
    --cc=qemu-block@nongnu.org \
    --cc=qemu-devel@nongnu.org \
    --cc=saket.sinha89@gmail.com \
    --cc=stefanha@redhat.com \
    /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;
as well as URLs for NNTP newsgroup(s).