All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Michael S. Tsirkin" <mst@redhat.com>
To: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: axboe@kernel.dk, brauner@kernel.org,
	linux-kernel@vger.kernel.org, Oleg Nesterov <oleg@redhat.com>,
	linux@leemhuis.info, stefanha@redhat.com,
	nicolas.dichtel@6wind.com,
	virtualization@lists.linux-foundation.org,
	torvalds@linux-foundation.org
Subject: Re: Can vhost translate to io_uring?
Date: Wed, 14 Jun 2023 10:20:44 -0400	[thread overview]
Message-ID: <20230614101951-mutt-send-email-mst@kernel.org> (raw)
In-Reply-To: <87mt12oa25.fsf_-_@email.froward.int.ebiederm.org>

On Wed, Jun 14, 2023 at 01:02:58AM -0500, Eric W. Biederman wrote:
> 
> I am sad my idea for simplifying things did not work out.
> 
> 
> Let's try an even bigger idea to reduce maintenance and simplify things.
> 
> Could vhost depend on io_uring?
> 
> Could vhost just be a translation layer of existing vhost requests to
> io_uring requests?

I expect that's going to have a measureable performance impact.

> At a quick glance it looks like io_uring already supports the
> functionality that vhost supports (which I think is networking and
> scsi).
> 
> If vhost could become a translation layer that would allow removing
> the vhost worker and PF_USER_WORKER could be removed completely,
> leaving only PF_IO_WORKER.
> 
> 
> I suggest this because a significant vhost change is needed because in
> the long term the hacks in exec and coredump are not a good idea.  Which
> means something like my failed "[PATCH v3] fork, vhost: Use CLONE_THREAD
> to fix freezer/ps regression".
> 
> If we have to go to all of the trouble of reworking things it why can't
> we just make io_uring do all of the work?
> 
> Eric

_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization

WARNING: multiple messages have this Message-ID (diff)
From: "Michael S. Tsirkin" <mst@redhat.com>
To: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Mike Christie <michael.christie@oracle.com>,
	Oleg Nesterov <oleg@redhat.com>,
	linux@leemhuis.info, nicolas.dichtel@6wind.com, axboe@kernel.dk,
	torvalds@linux-foundation.org, linux-kernel@vger.kernel.org,
	virtualization@lists.linux-foundation.org, sgarzare@redhat.com,
	jasowang@redhat.com, stefanha@redhat.com, brauner@kernel.org
Subject: Re: Can vhost translate to io_uring?
Date: Wed, 14 Jun 2023 10:20:44 -0400	[thread overview]
Message-ID: <20230614101951-mutt-send-email-mst@kernel.org> (raw)
In-Reply-To: <87mt12oa25.fsf_-_@email.froward.int.ebiederm.org>

On Wed, Jun 14, 2023 at 01:02:58AM -0500, Eric W. Biederman wrote:
> 
> I am sad my idea for simplifying things did not work out.
> 
> 
> Let's try an even bigger idea to reduce maintenance and simplify things.
> 
> Could vhost depend on io_uring?
> 
> Could vhost just be a translation layer of existing vhost requests to
> io_uring requests?

I expect that's going to have a measureable performance impact.

> At a quick glance it looks like io_uring already supports the
> functionality that vhost supports (which I think is networking and
> scsi).
> 
> If vhost could become a translation layer that would allow removing
> the vhost worker and PF_USER_WORKER could be removed completely,
> leaving only PF_IO_WORKER.
> 
> 
> I suggest this because a significant vhost change is needed because in
> the long term the hacks in exec and coredump are not a good idea.  Which
> means something like my failed "[PATCH v3] fork, vhost: Use CLONE_THREAD
> to fix freezer/ps regression".
> 
> If we have to go to all of the trouble of reworking things it why can't
> we just make io_uring do all of the work?
> 
> Eric


  parent reply	other threads:[~2023-06-14 14:20 UTC|newest]

Thread overview: 49+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-06-01 18:32 [PATCH 1/1] fork, vhost: Use CLONE_THREAD to fix freezer/ps regression Mike Christie
2023-06-01 18:32 ` Mike Christie
2023-06-01 19:11 ` Michael S. Tsirkin
2023-06-01 19:11   ` Michael S. Tsirkin
2023-06-02  0:43 ` Eric W. Biederman
2023-06-02  0:43   ` Eric W. Biederman
2023-06-02 14:34 ` Nicolas Dichtel
2023-06-02 19:22 ` Oleg Nesterov
2023-06-02 19:22   ` Oleg Nesterov
2023-06-03  3:44   ` Eric W. Biederman
2023-06-03  3:44     ` Eric W. Biederman
2023-06-05 13:26     ` Oleg Nesterov
2023-06-05 13:26       ` Oleg Nesterov
2023-06-03  4:15   ` [CFT][PATCH v3] " Eric W. Biederman
2023-06-03  4:15     ` Eric W. Biederman
2023-06-04  3:28     ` michael.christie
2023-06-04  3:28       ` michael.christie
2023-06-05 15:10       ` Oleg Nesterov
2023-06-05 15:10         ` Oleg Nesterov
2023-06-05 15:46         ` Mike Christie
2023-06-05 15:46           ` Mike Christie
2023-06-06 12:16           ` Oleg Nesterov
2023-06-06 12:16             ` Oleg Nesterov
2023-06-06 15:57             ` Mike Christie
2023-06-06 15:57               ` Mike Christie
2023-06-06 19:39               ` Oleg Nesterov
2023-06-06 19:39                 ` Oleg Nesterov
2023-06-06 20:38                 ` Mike Christie
2023-06-06 20:38                   ` Mike Christie
2023-06-14  6:02                   ` Can vhost translate to io_uring? Eric W. Biederman
2023-06-14  6:02                     ` Eric W. Biederman
2023-06-14  6:25                     ` michael.christie
2023-06-14  6:25                       ` michael.christie
2023-06-14 14:30                       ` Jens Axboe
2023-06-14 14:30                         ` Jens Axboe
2023-06-14 17:59                       ` Mike Christie
2023-06-14 17:59                         ` Mike Christie
2023-06-14 14:20                     ` Michael S. Tsirkin [this message]
2023-06-14 14:20                       ` Michael S. Tsirkin
2023-06-14 15:02                     ` Michael S. Tsirkin
2023-06-14 15:02                       ` Michael S. Tsirkin
2023-06-11 20:27                 ` [CFT][PATCH v3] fork, vhost: Use CLONE_THREAD to fix freezer/ps regression Eric W. Biederman
2023-06-11 20:27                   ` Eric W. Biederman
2023-06-14 17:08                   ` Oleg Nesterov
2023-06-14 17:08                     ` Oleg Nesterov
2023-06-05 12:38     ` Oleg Nesterov
2023-06-05 12:38       ` Oleg Nesterov
2023-06-05 13:48 ` [PATCH 1/1] " Oleg Nesterov
2023-06-05 13:48   ` Oleg Nesterov

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=20230614101951-mutt-send-email-mst@kernel.org \
    --to=mst@redhat.com \
    --cc=axboe@kernel.dk \
    --cc=brauner@kernel.org \
    --cc=ebiederm@xmission.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux@leemhuis.info \
    --cc=nicolas.dichtel@6wind.com \
    --cc=oleg@redhat.com \
    --cc=stefanha@redhat.com \
    --cc=torvalds@linux-foundation.org \
    --cc=virtualization@lists.linux-foundation.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.