All of lore.kernel.org
 help / color / mirror / Atom feed
From: Stefan Hajnoczi <stefanha@redhat.com>
To: Bernd Schubert <bschubert@ddn.com>
Cc: Brian Song <hibriansong@gmail.com>,
	"qemu-block@nongnu.org" <qemu-block@nongnu.org>,
	"qemu-devel@nongnu.org" <qemu-devel@nongnu.org>,
	"armbru@redhat.com" <armbru@redhat.com>,
	"fam@euphon.net" <fam@euphon.net>,
	"hreitz@redhat.com" <hreitz@redhat.com>,
	"kwolf@redhat.com" <kwolf@redhat.com>
Subject: Re: [PATCH RFC 1/1] block/export: FUSE-over-io_uring Support for QEMU FUSE Exports
Date: Mon, 21 Jul 2025 14:26:21 -0400	[thread overview]
Message-ID: <20250721182621.GA69677@fedora> (raw)
In-Reply-To: <e13f8119-7c60-4aa6-91b0-860ac0a462f5@ddn.com>

[-- Attachment #1: Type: text/plain, Size: 1059 bytes --]

On Mon, Jul 21, 2025 at 01:51:44PM +0000, Bernd Schubert wrote:
> I need test these flags again, might be worthful for qemu as well
> 
> 	/* These flags should help to increase performance, but actually
> 	 * make it a bit slower - reason should get investigated.
> 	 */
> 	if (0) {
> 		/* Has the main slow down effect */
> 		params.flags |= IORING_SETUP_SINGLE_ISSUER;
> 
> 		// params.flags |= IORING_SETUP_DEFER_TASKRUN;
> 		params.flags |= IORING_SETUP_TASKRUN_FLAG;
> 
> 		/* Second main effect to make it slower */
> 		params.flags |= IORING_SETUP_COOP_TASKRUN;
> 	}

Yes, they are interesting. Thanks for mentioning them!

An earlier attempt at enabling IORING_SETUP_SINGLE_ISSUER in QEMU (still
needs benchmarking):
https://lore.kernel.org/qemu-devel/174293621917.22751.11381319865102029969-0%40git.sr.ht/T/#t

Let's consider these flags as a separate patch series. I have a
benchmarking setup that can be used for measurement, so I'll take this
as a TODO item for myself to work on over the coming days.

Thanks,
Stefan

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

  reply	other threads:[~2025-07-21 18:28 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-07-16 18:38 [PATCH RFC 0/1] block/export: FUSE-over-io_uring Support for QEMU FUSE Exports Brian Song
2025-07-16 18:38 ` [PATCH RFC 1/1] " Brian Song
2025-07-17  6:03   ` Markus Armbruster
2025-07-22 12:00     ` Brian Song
2025-07-21  0:53   ` Stefan Hajnoczi
2025-07-22 12:00     ` Brian Song
2025-07-22 15:17       ` Kevin Wolf
2025-07-22 14:06     ` Bernd Schubert
2025-07-22 15:43       ` Stefan Hajnoczi
2025-07-22 16:20         ` Bernd Schubert
2025-07-21 13:51   ` Bernd Schubert
2025-07-21 18:26     ` Stefan Hajnoczi [this message]
2025-07-22 12:00     ` Brian Song
2025-07-22 14:51       ` Stefan Hajnoczi
2025-07-24 20:36     ` Stefan Hajnoczi
2025-07-22 13:32   ` Kevin Wolf
2025-12-10 22:10   ` Bernd Schubert
2025-12-11  4:40     ` Brian Song
2025-07-20 16:13 ` [PATCH RFC 0/1] " Stefan Hajnoczi
2025-07-22 12:00   ` Brian Song
2025-07-22 14:47     ` 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=20250721182621.GA69677@fedora \
    --to=stefanha@redhat.com \
    --cc=armbru@redhat.com \
    --cc=bschubert@ddn.com \
    --cc=fam@euphon.net \
    --cc=hibriansong@gmail.com \
    --cc=hreitz@redhat.com \
    --cc=kwolf@redhat.com \
    --cc=qemu-block@nongnu.org \
    --cc=qemu-devel@nongnu.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.