Netdev List
 help / color / mirror / Atom feed
From: Eric Dumazet <eric.dumazet@gmail.com>
To: Andrew Vagin <avagin@parallels.com>
Cc: netdev@vger.kernel.org, vvs@parallels.com,
	"Michał Mirosław" <mirq-linux@rere.qmqm.pl>
Subject: Re: Slow speed of tcp connections in a network namespace
Date: Sat, 29 Dec 2012 11:41:02 -0800	[thread overview]
Message-ID: <1356810062.21409.4991.camel@edumazet-glaptop> (raw)
In-Reply-To: <1356807516.4102.4.camel@edumazet-laptop>

On Sat, 2012-12-29 at 19:58 +0100, Eric Dumazet wrote:
> Le samedi 29 décembre 2012 à 09:40 -0800, Eric Dumazet a écrit :
> 
> > 
> > Please post your new tcpdump then ;)
> > 
> > also post "netstat -s" from root and test ns after your wgets
> 
> Also try following bnx2 patch.
> 
> It should help GRO / TCP coalesce
> 
> bnx2 should be the last driver not using skb head_frag

And of course, you should make sure all your bnx2 interrupts are handled
by the same cpu.

Or else, packets might be reordered because the way dev_forward_skb()
works.

(CPU X gets a bunch of packets from eth0, forward them via netif_rx() in
the local CPU X queue, NAPI is ended on eth0)

CPU Y gets a bunch of packets from eth0, forward them via netif_rx() in
the local CPU Y queue.

CPU X and Y process their local queue in // -> packets are delivered Out
of order to TCP stack

Alternative is to setup RPS on your veth1 device, to force packets being
delivered/handled by a given cpu

  reply	other threads:[~2012-12-29 19:41 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-12-29  9:24 Slow speed of tcp connections in a network namespace Andrew Vagin
2012-12-29 13:53 ` Eric Dumazet
2012-12-29 14:50   ` Andrew Vagin
2012-12-29 17:40     ` Eric Dumazet
2012-12-29 18:29       ` Andrew Vagin
2012-12-29 18:58       ` Eric Dumazet
2012-12-29 19:41         ` Eric Dumazet [this message]
2012-12-29 20:08           ` Andrew Vagin
2012-12-29 20:20             ` Eric Dumazet
2012-12-29 21:07               ` Andrew Vagin
2012-12-29 21:12             ` Eric Dumazet
2012-12-29 21:19               ` Andrew Vagin
2012-12-29 21:15         ` Andrew Vagin
2012-12-29 16:01   ` Michał Mirosław
2012-12-30  2:26     ` [PATCH] veth: extend device features Eric Dumazet
2012-12-30 10:32       ` 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=1356810062.21409.4991.camel@edumazet-glaptop \
    --to=eric.dumazet@gmail.com \
    --cc=avagin@parallels.com \
    --cc=mirq-linux@rere.qmqm.pl \
    --cc=netdev@vger.kernel.org \
    --cc=vvs@parallels.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox