netdev - Re: [PATCH rfc 3/3] virtio-net: support transmit timestamp

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <CAF=yD-Ly3cdpj+B25Zgu+KYCE8ijV0+fQ_ssgjBAG2w8=iAp-Q@mail.gmail.com>
Date:   Wed, 30 Dec 2020 10:25:46 -0500
From:   Willem de Bruijn <willemdebruijn.kernel@...il.com>
To:     Richard Cochran <richardcochran@...il.com>
Cc:     virtualization@...ts.linux-foundation.org,
        Network Development <netdev@...r.kernel.org>,
        "Michael S. Tsirkin" <mst@...hat.com>,
        Jason Wang <jasowang@...hat.com>,
        Willem de Bruijn <willemb@...gle.com>
Subject: Re: [PATCH rfc 3/3] virtio-net: support transmit timestamp

On Wed, Dec 30, 2020 at 7:38 AM Richard Cochran
<richardcochran@...il.com> wrote:
>
> On Mon, Dec 28, 2020 at 11:22:33AM -0500, Willem de Bruijn wrote:
> > From: Willem de Bruijn <willemb@...gle.com>
> >
> > Add optional delivery time (SO_TXTIME) offload for virtio-net.
> >
> > The Linux TCP/IP stack tries to avoid bursty transmission and network
> > congestion through pacing: computing an skb delivery time based on
> > congestion information. Userspace protocol implementations can achieve
> > the same with SO_TXTIME. This may also reduce scheduling jitter and
> > improve RTT estimation.
>
> This description is clear, but the Subject line is confusing.  It made
> me wonder whether this series is somehow about host/guest synchronization
> (but your comments do explain that that isn't the case).
>
> How about this instead?
>
>    virtio-net: support future packet transmit time

Yes, that's clearer. As is, this could easily be mistaken for
SOF_TIMESTAMPING_TX_*, which it is not. Will update, thanks.

Related terms already in use are SO_TXTIME, Earliest Delivery Time
(EDT) and Earliest TxTime First (ETF).

I should probably also s/TX_TSTAMP/TX_TIME/  in the code for the same reason.