From: Jesper Dangaard Brouer <brouer@redhat.com>
To: Saeed Mahameed <saeedm@mellanox.com>
Cc: "dsahern@gmail.com" <dsahern@gmail.com>,
"thoiland@redhat.com" <thoiland@redhat.com>,
"virtualization@lists.linux-foundation.org"
<virtualization@lists.linux-foundation.org>,
"borkmann@iogearbox.net" <borkmann@iogearbox.net>,
Tariq Toukan <tariqt@mellanox.com>,
"john.fastabend@gmail.com" <john.fastabend@gmail.com>,
"mst@redhat.com" <mst@redhat.com>,
"jakub.kicinski@netronome.com" <jakub.kicinski@netronome.com>,
"netdev@vger.kernel.org" <netdev@vger.kernel.org>,
"jasowang@redhat.com" <jasowang@redhat.com>,
"davem@davemloft.net" <davem@davemloft.net>,
"makita.toshiaki@lab.ntt.co.jp" <makita.toshiaki@lab.ntt.co.jp>,
brouer@redhat.com
Subject: Re: [PATCH net] virtio_net: Account for tx bytes and packets on sending xdp_frames
Date: Wed, 6 Feb 2019 14:48:14 +0100 [thread overview]
Message-ID: <20190206144814.46996933@carbon> (raw)
In-Reply-To: <140ecbe1e25f54f90d859cc696c4119aa96bc6eb.camel@mellanox.com>
On Wed, 6 Feb 2019 00:06:33 +0000
Saeed Mahameed <saeedm@mellanox.com> wrote:
> 3) Unrelated, In non XDP case, if skb allocation fails or driver fails
> to pass the skb up to the stack for somereason, should the driver
> increase rx packets ? IMHO the answer should be yes if we want to have
> similar behavior between XDP and non XDP cases.
I don't think "skb allocation fails" should increase rx packets
counter. The difference is that these events are outside sysadm/users
control, and is an error detected inside the driver. The XDP program
takes a policy choice to XDP_DROP a packet, which can be accounted
inside the XDP prog (as the samples show) or as we also discuss via a
more generic XDP-action counters.
That said, I took at quick look at driver code, and it seems this
behavior differs per driver... ixgbe and mlx5 does not count "skb
allocation fails" as RX-ed packets, while mlx4 seems to count them.
> But this could result in netdev->stats.rx_packets +
> netdev->stats.rx_dropped to be more than the actual rx-ed packets, is
> this acceptable ?
This is one reasons I think this is wrong.
--Jesper
next prev parent reply other threads:[~2019-02-06 13:48 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-01-31 11:40 [PATCH net] virtio_net: Account for tx bytes and packets on sending xdp_frames Toshiaki Makita
2019-01-31 15:25 ` Michael S. Tsirkin
2019-01-31 17:45 ` David Miller
2019-01-31 20:15 ` Jesper Dangaard Brouer
2019-02-01 1:53 ` Toshiaki Makita
2019-02-02 21:27 ` David Ahern
2019-02-04 11:53 ` Jesper Dangaard Brouer
2019-02-05 3:13 ` David Ahern
2019-02-06 0:06 ` Saeed Mahameed
2019-02-06 13:48 ` Jesper Dangaard Brouer [this message]
2019-02-06 15:52 ` Jakub Kicinski
2019-02-07 7:48 ` Resource management for ndo_xdp_xmit (Was: [PATCH net] virtio_net: Account for tx bytes and packets on sending xdp_frames) Jesper Dangaard Brouer
2019-02-07 19:08 ` Saeed Mahameed
2019-02-08 16:55 ` Toke Høiland-Jørgensen
2019-02-08 22:49 ` Saeed Mahameed
2019-02-08 23:17 ` Saeed Mahameed
2019-02-09 0:18 ` Saeed Mahameed
2019-02-09 2:05 ` Jakub Kicinski
2019-02-09 16:56 ` Toke Høiland-Jørgensen
2019-02-09 16:56 ` Toke Høiland-Jørgensen
2019-02-08 16:02 ` [PATCH net] virtio_net: Account for tx bytes and packets on sending xdp_frames Jesper Dangaard Brouer
2019-04-18 14:24 ` Stats for XDP actions (was: Re: [PATCH net] virtio_net: Account for tx bytes and packets on sending xdp_frames) Toke Høiland-Jørgensen
2019-04-21 0:16 ` Stats for XDP actions David Ahern
2019-06-20 20:42 ` Toke Høiland-Jørgensen
2019-06-21 0:42 ` David Ahern
2019-06-21 13:57 ` Toke Høiland-Jørgensen
2019-02-04 4:18 ` [PATCH net] virtio_net: Account for tx bytes and packets on sending xdp_frames David Miller
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=20190206144814.46996933@carbon \
--to=brouer@redhat.com \
--cc=borkmann@iogearbox.net \
--cc=davem@davemloft.net \
--cc=dsahern@gmail.com \
--cc=jakub.kicinski@netronome.com \
--cc=jasowang@redhat.com \
--cc=john.fastabend@gmail.com \
--cc=makita.toshiaki@lab.ntt.co.jp \
--cc=mst@redhat.com \
--cc=netdev@vger.kernel.org \
--cc=saeedm@mellanox.com \
--cc=tariqt@mellanox.com \
--cc=thoiland@redhat.com \
--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 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).