All of lore.kernel.org
 help / color / mirror / Atom feed
From: Matteo Croce <mcroce@redhat.com>
To: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>,
	netdev <netdev@vger.kernel.org>,
	Jay Vosburgh <j.vosburgh@gmail.com>,
	Veaceslav Falico <vfalico@gmail.com>,
	Andy Gospodarek <andy@greyhouse.net>,
	"David S . Miller" <davem@davemloft.net>,
	Stanislav Fomichev <sdf@google.com>,
	Daniel Borkmann <daniel@iogearbox.net>,
	Song Liu <songliubraving@fb.com>,
	Alexei Starovoitov <ast@kernel.org>,
	Paul Blakey <paulb@mellanox.com>,
	LKML <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH net-next v2 4/4] bonding: balance ICMP echoes in layer3+4 mode
Date: Thu, 31 Oct 2019 17:22:21 +0100	[thread overview]
Message-ID: <CAGnkfhxvOdZgS90PittFgAtYnPzfQNVFsxsTpadzBcr1-mnD=Q@mail.gmail.com> (raw)
In-Reply-To: <CAGnkfhyaXzMx608jZqqjdywv6BZst97QSmGe++aSc=-xOQSWzg@mail.gmail.com>

On Wed, Oct 30, 2019 at 12:19 AM Matteo Croce <mcroce@redhat.com> wrote:
>
> On Wed, Oct 30, 2019 at 12:14 AM Eric Dumazet <eric.dumazet@gmail.com> wrote:
> >
> >
> >
> > On 10/29/19 4:03 PM, Matteo Croce wrote:
> >
> > > Hi Eric,
> > >
> > > this would work for locally generated echoes, but what about forwarded packets?
> > > The point behind my changeset is to provide consistent results within
> > > a session by using the same path for request and response,
> > > but avoid all sessions flowing to the same path.
> > > This should resemble what happens with TCP and UDP: different
> > > connections, different port, probably a different path. And by doing
> > > this in the flow dissector, other applications could benefit it.
> >
> > In principle it is fine, but I was not sure of overall impact of your change
> > on performance for 99.9% of packets that are not ICMP :)
> >
>
> Good point. I didn't measure it (I will) but all the code additions
> are under some if (proto == ICMP) or similar.
> My guess is that performance shouldn't change for non ICMP traffic,
> but I'm curious to test it.
>

Indeed if there is some impact it's way below the measurement uncertainty.
I've bonded two veth pairs and added a tc drop to the peers, then
started mausezahn to generate UDP traffic.
Traffic is measured on the veth peers:

Stock 5.4-rc5:

rx: 261.5 Mbps 605.4 Kpps
rx: 261.2 Mbps 604.6 Kpps
rx: 261.6 Mbps 605.5 Kpps

patched:

rx: 261.4 Mbps 605.1 Kpps
rx: 261.1 Mbps 604.4 Kpps
rx: 260.3 Mbps 602.5 Kpps

perf top shows no significatn change in bond* and skb_flow* functions

Regards,
-- 
Matteo Croce
per aspera ad upstream


  reply	other threads:[~2019-10-31 16:23 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-10-29 13:50 [PATCH net-next v2 0/4] ICMP flow improvements Matteo Croce
2019-10-29 13:50 ` [PATCH net-next v2 1/4] flow_dissector: add meaningful comments Matteo Croce
2019-10-29 13:50 ` [PATCH net-next v2 2/4] flow_dissector: skip the ICMP dissector for non ICMP packets Matteo Croce
2019-10-29 13:50 ` [PATCH net-next v2 3/4] flow_dissector: extract more ICMP information Matteo Croce
2019-10-29 13:50 ` [PATCH net-next v2 4/4] bonding: balance ICMP echoes in layer3+4 mode Matteo Croce
2019-10-29 18:35   ` Nikolay Aleksandrov
2019-10-29 18:41     ` Nikolay Aleksandrov
2019-10-29 19:45       ` Matteo Croce
2019-10-29 20:07         ` Nikolay Aleksandrov
2019-10-29 21:03     ` Eric Dumazet
2019-10-29 21:50       ` Nikolay Aleksandrov
2019-10-29 23:04         ` Eric Dumazet
2019-10-30 12:48           ` Nikolay Aleksandrov
2019-10-29 23:03       ` Matteo Croce
2019-10-29 23:14         ` Eric Dumazet
2019-10-29 23:19           ` Matteo Croce
2019-10-31 16:22             ` Matteo Croce [this message]
2019-10-31  0:21 ` [PATCH net-next v2 0/4] ICMP flow improvements 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='CAGnkfhxvOdZgS90PittFgAtYnPzfQNVFsxsTpadzBcr1-mnD=Q@mail.gmail.com' \
    --to=mcroce@redhat.com \
    --cc=andy@greyhouse.net \
    --cc=ast@kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=davem@davemloft.net \
    --cc=eric.dumazet@gmail.com \
    --cc=j.vosburgh@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=nikolay@cumulusnetworks.com \
    --cc=paulb@mellanox.com \
    --cc=sdf@google.com \
    --cc=songliubraving@fb.com \
    --cc=vfalico@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.