To: Olivier.Bonaventure@uclouvain.be, =?UTF-8?B?546L5biF?=
 <13211134@bjtu.edu.cn>, multipathtcp <multipathtcp@ietf.org>
References: <2e5562a3.3efcf.15af4ee489c.Coremail.13211134@bjtu.edu.cn>
 <d81b7cf0-67ff-9a2b-31ee-63c44fbe7643@uclouvain.be>
From: Joe Touch <touch@isi.edu>
Message-ID: <77ee43ab-cab9-586b-b40e-e53fb0bb9a47@isi.edu>
Date: Wed, 22 Mar 2017 08:42:05 -0700
User-Agent: Mozilla/5.0 (Windows NT 10.0; WOW64; rv:45.0) Gecko/20100101
 Thunderbird/45.8.0
MIME-Version: 1.0
In-Reply-To: <d81b7cf0-67ff-9a2b-31ee-63c44fbe7643@uclouvain.be>
Content-Type: multipart/alternative;
 boundary="------------C1837304602704B115098D73"
Archived-At: <https://mailarchive.ietf.org/arch/msg/multipathtcp/wWWEB6SnmRlspVzF69X1gouc5F8>
Subject: Re: [multipathtcp] how to deal with GRO when we use MPTCP?
Precedence: list

This is a multi-part message in MIME format.
--------------C1837304602704B115098D73
Content-Type: text/plain; charset=windows-1252
Content-Transfer-Encoding: quoted-printable

FYI - we had experience with GRO on Linux where it acted against spec,
coalescing packets with EDO headers even when these options were
different between adjacent packets. We also saw performance plummet when
GRO was enabled even when it was not supposed to coalesce packets.

See Sec 5.2 of the following:

H. Trieu, J. Touch, T. Faber, =93Implementation of the TCP Extended Data
Offset Option <http://www.isi.edu/touch/pubs/isi-tr-2015-696.pdf>,=94
USC/ISI Tech. Report ISI-TR-696, Mar. 2015.

Note that we were unable to pinpoint the issue, which might have been in
our implementation.

Joe


On 3/22/2017 1:54 AM, Olivier Bonaventure wrote:
> ...
>
> GRO should not coalesce packets from an MPTCP sender that does not use
> TSO and thus send packets with different DSN values. If you see a
> network interface that behaves badly, please report this on the
> mptcp-dev mailing list
>
>
> Olivier
>
> _______________________________________________
> multipathtcp mailing list
> multipathtcp@ietf.org
> https://www.ietf.org/mailman/listinfo/multipathtcp


--------------C1837304602704B115098D73
Content-Type: text/html; charset=windows-1252
Content-Transfer-Encoding: 8bit

<html>
  <head>
    <meta content="text/html; charset=windows-1252"
      http-equiv="Content-Type">
  </head>
  <body bgcolor="#FFFFFF" text="#000000">
    <p>FYI - we had experience with GRO on Linux where it acted against
      spec, coalescing packets with EDO headers even when these options
      were different between adjacent packets. We also saw performance
      plummet when GRO was enabled even when it was not supposed to
      coalesce packets.<br>
    </p>
    <p>See Sec 5.2 of the following:</p>
    <p>H. Trieu, J. Touch, T. Faber, “<a
        href="http://www.isi.edu/touch/pubs/isi-tr-2015-696.pdf"
        style="">Implementation of the TCP Extended Data Offset Option</a>,”
      USC/ISI Tech. Report ISI-TR-696, Mar. 2015.</p>
    <p>Note that we were unable to pinpoint the issue, which might have
      been in our implementation. <br>
    </p>
    <p>Joe<br>
    </p>
    <br>
    <div class="moz-cite-prefix">On 3/22/2017 1:54 AM, Olivier
      Bonaventure wrote:<br>
    </div>
    <blockquote
      cite="mid:d81b7cf0-67ff-9a2b-31ee-63c44fbe7643@uclouvain.be"
      type="cite">...<br>
      <br>
      GRO should not coalesce packets from an MPTCP sender that does not
      use TSO and thus send packets with different DSN values. If you
      see a network interface that behaves badly, please report this on
      the mptcp-dev mailing list
      <br>
      <br>
      <br>
      Olivier
      <br>
      <br>
      _______________________________________________
      <br>
      multipathtcp mailing list
      <br>
      <a class="moz-txt-link-abbreviated" href="mailto:multipathtcp@ietf.org">multipathtcp@ietf.org</a>
      <br>
      <a class="moz-txt-link-freetext" href="https://www.ietf.org/mailman/listinfo/multipathtcp">https://www.ietf.org/mailman/listinfo/multipathtcp</a>
      <br>
    </blockquote>
    <br>
  </body>
</html>

--------------C1837304602704B115098D73--