From: "Michael S. Tsirkin" <mst@redhat.com>
To: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
Cc: virtualization@lists.linux-foundation.org,
Network Development <netdev@vger.kernel.org>,
Jason Wang <jasowang@redhat.com>
Subject: Re: [PATCH rfc 0/3] virtio-net: add tx-hash, rx-tstamp and tx-tstamp
Date: Mon, 28 Dec 2020 16:38:33 -0500 [thread overview]
Message-ID: <20201228163809-mutt-send-email-mst@kernel.org> (raw)
In-Reply-To: <CA+FuTScXQ0U1+rFFpKxB1Qn73pG8jmFuujONov_9yEEKyyer_g@mail.gmail.com>
On Mon, Dec 28, 2020 at 02:51:09PM -0500, Willem de Bruijn wrote:
> On Mon, Dec 28, 2020 at 12:29 PM Michael S. Tsirkin <mst@redhat.com> wrote:
> >
> > On Mon, Dec 28, 2020 at 11:22:30AM -0500, Willem de Bruijn wrote:
> > > From: Willem de Bruijn <willemb@google.com>
> > >
> > > RFC for three new features to the virtio network device:
> > >
> > > 1. pass tx flow hash and state to host, for routing + telemetry
> > > 2. pass rx tstamp to guest, for better RTT estimation
> > > 3. pass tx tstamp to host, for accurate pacing
> > >
> > > All three would introduce an extension to the virtio spec.
> > > I assume this would require opening three ballots against v1.2 at
> > > https://www.oasis-open.org/committees/ballots.php?wg_abbrev=virtio
> > >
> > > This RFC is to informally discuss the proposals first.
> > >
> > > The patchset is against v5.10. Evaluation additionally requires
> > > changes to qemu and at least one back-end. I implemented preliminary
> > > support in Linux vhost-net. Both patches available through github at
> > >
> > > https://github.com/wdebruij/linux/tree/virtio-net-txhash-1
> > > https://github.com/wdebruij/qemu/tree/virtio-net-txhash-1
> >
> > Any data on what the benefits are?
>
> For the general method, yes. For this specific implementation, not yet.
>
> Swift congestion control is delay based. It won the best paper award
> at SIGCOMM this year. That paper has a lot of data:
> https://dl.acm.org/doi/pdf/10.1145/3387514.3406591 . Section 3.1 talks
> about the different components that contribute to delay and how to
> isolate them.
And for the hashing part?
> BBR and BBRv2 also have an explicit ProbeRTT phase as part of the design.
>
> The specific additional benefits for VM-based TCP depends on many
> conditions, e.g., whether a vCPU is exclusively owned and pinned. But
> the same reasoning should be even more applicable to this even longer
> stack, especially in the worst case conditions.
WARNING: multiple messages have this Message-ID (diff)
From: "Michael S. Tsirkin" <mst@redhat.com>
To: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
Cc: Network Development <netdev@vger.kernel.org>,
virtualization@lists.linux-foundation.org
Subject: Re: [PATCH rfc 0/3] virtio-net: add tx-hash, rx-tstamp and tx-tstamp
Date: Mon, 28 Dec 2020 16:38:33 -0500 [thread overview]
Message-ID: <20201228163809-mutt-send-email-mst@kernel.org> (raw)
In-Reply-To: <CA+FuTScXQ0U1+rFFpKxB1Qn73pG8jmFuujONov_9yEEKyyer_g@mail.gmail.com>
On Mon, Dec 28, 2020 at 02:51:09PM -0500, Willem de Bruijn wrote:
> On Mon, Dec 28, 2020 at 12:29 PM Michael S. Tsirkin <mst@redhat.com> wrote:
> >
> > On Mon, Dec 28, 2020 at 11:22:30AM -0500, Willem de Bruijn wrote:
> > > From: Willem de Bruijn <willemb@google.com>
> > >
> > > RFC for three new features to the virtio network device:
> > >
> > > 1. pass tx flow hash and state to host, for routing + telemetry
> > > 2. pass rx tstamp to guest, for better RTT estimation
> > > 3. pass tx tstamp to host, for accurate pacing
> > >
> > > All three would introduce an extension to the virtio spec.
> > > I assume this would require opening three ballots against v1.2 at
> > > https://www.oasis-open.org/committees/ballots.php?wg_abbrev=virtio
> > >
> > > This RFC is to informally discuss the proposals first.
> > >
> > > The patchset is against v5.10. Evaluation additionally requires
> > > changes to qemu and at least one back-end. I implemented preliminary
> > > support in Linux vhost-net. Both patches available through github at
> > >
> > > https://github.com/wdebruij/linux/tree/virtio-net-txhash-1
> > > https://github.com/wdebruij/qemu/tree/virtio-net-txhash-1
> >
> > Any data on what the benefits are?
>
> For the general method, yes. For this specific implementation, not yet.
>
> Swift congestion control is delay based. It won the best paper award
> at SIGCOMM this year. That paper has a lot of data:
> https://dl.acm.org/doi/pdf/10.1145/3387514.3406591 . Section 3.1 talks
> about the different components that contribute to delay and how to
> isolate them.
And for the hashing part?
> BBR and BBRv2 also have an explicit ProbeRTT phase as part of the design.
>
> The specific additional benefits for VM-based TCP depends on many
> conditions, e.g., whether a vCPU is exclusively owned and pinned. But
> the same reasoning should be even more applicable to this even longer
> stack, especially in the worst case conditions.
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
next prev parent reply other threads:[~2020-12-28 23:17 UTC|newest]
Thread overview: 67+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-12-28 16:22 [PATCH rfc 0/3] virtio-net: add tx-hash, rx-tstamp and tx-tstamp Willem de Bruijn
2020-12-28 16:22 ` Willem de Bruijn
2020-12-28 16:22 ` [PATCH rfc 1/3] virtio-net: support transmit hash report Willem de Bruijn
2020-12-28 16:22 ` Willem de Bruijn
2020-12-28 16:28 ` Michael S. Tsirkin
2020-12-28 16:28 ` Michael S. Tsirkin
2020-12-28 16:47 ` Willem de Bruijn
2020-12-28 16:47 ` Willem de Bruijn
2020-12-28 17:22 ` Michael S. Tsirkin
2020-12-28 17:22 ` Michael S. Tsirkin
2020-12-29 1:19 ` Willem de Bruijn
2020-12-29 1:19 ` Willem de Bruijn
2020-12-28 21:36 ` Michael S. Tsirkin
2020-12-28 21:36 ` Michael S. Tsirkin
2020-12-29 1:23 ` Willem de Bruijn
2020-12-29 1:23 ` Willem de Bruijn
2020-12-28 16:22 ` [PATCH rfc 2/3] virtio-net: support receive timestamp Willem de Bruijn
2020-12-28 16:22 ` Willem de Bruijn
2020-12-28 17:28 ` Michael S. Tsirkin
2020-12-28 17:28 ` Michael S. Tsirkin
2020-12-28 19:30 ` Willem de Bruijn
2020-12-28 19:30 ` Willem de Bruijn
2020-12-28 21:32 ` Michael S. Tsirkin
2020-12-28 21:32 ` Michael S. Tsirkin
2020-12-29 1:05 ` Willem de Bruijn
2020-12-29 1:05 ` Willem de Bruijn
2020-12-29 9:17 ` Jason Wang
2020-12-29 9:17 ` Jason Wang
2020-12-29 14:20 ` Willem de Bruijn
2020-12-29 14:20 ` Willem de Bruijn
2020-12-30 8:38 ` Jason Wang
2020-12-30 8:38 ` Jason Wang
2020-12-28 22:59 ` Jakub Kicinski
2020-12-29 0:57 ` Willem de Bruijn
2020-12-29 0:57 ` Willem de Bruijn
2020-12-30 8:44 ` Jason Wang
2020-12-30 8:44 ` Jason Wang
2020-12-30 12:30 ` Richard Cochran
2021-02-02 13:05 ` kernel test robot
2021-02-02 13:05 ` kernel test robot
2021-02-02 13:05 ` kernel test robot
2021-02-02 14:08 ` Michael S. Tsirkin
2021-02-02 14:08 ` Michael S. Tsirkin
2021-02-02 22:17 ` Willem de Bruijn
2021-02-02 22:17 ` Willem de Bruijn
2021-02-02 23:02 ` Michael S. Tsirkin
2021-02-02 23:02 ` Michael S. Tsirkin
2021-02-02 23:43 ` Willem de Bruijn
2021-02-02 23:43 ` Willem de Bruijn
2020-12-28 16:22 ` [PATCH rfc 3/3] virtio-net: support transmit timestamp Willem de Bruijn
2020-12-28 16:22 ` Willem de Bruijn
2020-12-30 12:38 ` Richard Cochran
2020-12-30 15:25 ` Willem de Bruijn
2020-12-30 15:25 ` Willem de Bruijn
2021-02-02 13:47 ` kernel test robot
2021-02-02 13:47 ` kernel test robot
2021-02-02 13:47 ` kernel test robot
2020-12-28 17:29 ` [PATCH rfc 0/3] virtio-net: add tx-hash, rx-tstamp and tx-tstamp Michael S. Tsirkin
2020-12-28 17:29 ` Michael S. Tsirkin
2020-12-28 19:51 ` Willem de Bruijn
2020-12-28 19:51 ` Willem de Bruijn
2020-12-28 21:38 ` Michael S. Tsirkin [this message]
2020-12-28 21:38 ` Michael S. Tsirkin
2020-12-29 1:14 ` Willem de Bruijn
2020-12-29 1:14 ` Willem de Bruijn
2021-01-06 20:32 ` Willem de Bruijn
2021-01-06 20:32 ` Willem de Bruijn
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=20201228163809-mutt-send-email-mst@kernel.org \
--to=mst@redhat.com \
--cc=jasowang@redhat.com \
--cc=netdev@vger.kernel.org \
--cc=virtualization@lists.linux-foundation.org \
--cc=willemdebruijn.kernel@gmail.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 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.