From: Dominik Kaspar <dokaspar.ietf@gmail.com>
To: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Carsten Wolff <carsten@wolffcarsten.de>, netdev@vger.kernel.org
Subject: Re: Linux TCP's Robustness to Multipath Packet Reordering
Date: Tue, 26 Apr 2011 18:58:58 +0200 [thread overview]
Message-ID: <BANLkTikcn832pXzxPjM032ZuRi8o0SQ++Q@mail.gmail.com> (raw)
In-Reply-To: <1303745915.2747.151.camel@edumazet-laptop>
Hi Eric,
On Mon, Apr 25, 2011 at 5:38 PM, Eric Dumazet <eric.dumazet@gmail.com> wrote:
>
> Since you have at sender a rule to spoof destination address of packets,
> you should make sure you dont send "super packets (up to 64Kbytes)",
> because it would stress the multipath more than you wanted to. This way,
> you send only normal packets (1500 MTU).
>
> ethtool -K eth0 tso off
> ethtool -K eth0 gso off
>
> I am pretty sure it should help your (atypic) workload.
I made new experiments with the exact same multipath setup as before,
but disabled TSO and GSO on all involved Ethernet interfaces. However,
this did not seem to change much about TCP's behavior when packets are
striped over heterogeneous paths. You can see the results of four
20-minute experiments on this plot:
http://home.simula.no/~kaspar/static/mptcp-emu-wlan-hspa-01-tos0.png
Cheers,
Dominik
next prev parent reply other threads:[~2011-04-26 16:59 UTC|newest]
Thread overview: 33+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-04-25 10:37 Linux TCP's Robustness to Multipath Packet Reordering Dominik Kaspar
2011-04-25 11:25 ` Eric Dumazet
2011-04-25 14:35 ` Dominik Kaspar
2011-04-25 15:38 ` Eric Dumazet
2011-04-26 16:58 ` Dominik Kaspar [this message]
2011-04-26 17:10 ` Eric Dumazet
2011-04-26 18:00 ` Dominik Kaspar
2011-04-26 20:16 ` John Heffner
2011-04-26 21:27 ` Dominik Kaspar
2011-04-27 9:57 ` Carsten Wolff
2011-04-27 16:22 ` Dominik Kaspar
2011-04-27 16:36 ` Alexander Zimmermann
2011-06-21 11:25 ` Ilpo Järvinen
2011-06-21 11:34 ` Carsten Wolff
2011-06-21 11:46 ` Ilpo Järvinen
2011-04-27 16:48 ` Eric Dumazet
2011-04-27 17:39 ` Yuchung Cheng
2011-04-27 17:53 ` Alexander Zimmermann
2011-04-27 19:56 ` Dominik Kaspar
2011-04-27 21:41 ` Yuchung Cheng
2011-04-28 6:11 ` Alexander Zimmermann
2011-06-19 15:22 ` Dominik Kaspar
2011-06-19 15:38 ` Alexander Zimmermann
2011-06-19 16:25 ` Dominik Kaspar
2011-06-20 10:42 ` Ilpo Järvinen
2011-06-20 12:52 ` Dominik Kaspar
2011-06-21 11:35 ` Ilpo Järvinen
2011-04-26 20:43 ` Eric Dumazet
2011-04-26 21:04 ` Dominik Kaspar
2011-04-26 21:08 ` Eric Dumazet
2011-04-26 21:16 ` Dominik Kaspar
2011-04-26 21:17 ` Eric Dumazet
2011-04-25 12:59 ` Carsten Wolff
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=BANLkTikcn832pXzxPjM032ZuRi8o0SQ++Q@mail.gmail.com \
--to=dokaspar.ietf@gmail.com \
--cc=carsten@wolffcarsten.de \
--cc=eric.dumazet@gmail.com \
--cc=netdev@vger.kernel.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).