netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Alex Williamson <alex.williamson@hp.com>
To: Patrick McHardy <kaber@trash.net>
Cc: David Miller <davem@davemloft.net>,
	akpm@linux-foundation.org, buytenh@marvell.com,
	netdev@vger.kernel.org, bugme-daemon@bugzilla.kernel.org
Subject: Re: [Bugme-new] [Bug 11316] New: severe performance regression for iptables nat routing
Date: Thu, 14 Aug 2008 09:08:04 -0600	[thread overview]
Message-ID: <1218726484.23510.20.camel@2710p.home> (raw)
In-Reply-To: <48A41139.9080509@trash.net>

[-- Attachment #1: Type: text/plain, Size: 773 bytes --]

On Thu, 2008-08-14 at 13:04 +0200, Patrick McHardy wrote:
> I don't think so, its using skb_make_writable everywhere, which checks
> for skb_clone_writable, which should usually avoid COWing local TCP
> packets. It would also be unlikely to have that much of a performance
> impact (1MB/s -> 34kb/s).
> 
> > 
> > It seems, if anything, using GSO should make things go a little bit
> > faster not slower... Hmmm...
> 
> Alex, could you post a tcpdump from both loopback and the outgoing
> device from the machine you're doing NAT on?

Attached, let me know if you want more options, this is just -vv -n.
The NAT'ing system is at 10.0.2.15 and the ssh tunnel target is
192.168.1.60.  Thanks,

Alex

-- 
Alex Williamson                             HP Open Source & Linux Org.

[-- Attachment #2: eth0.log.bz2 --]
[-- Type: application/x-bzip, Size: 34521 bytes --]

[-- Attachment #3: lo.log.bz2 --]
[-- Type: application/x-bzip, Size: 10538 bytes --]

  reply	other threads:[~2008-08-14 15:08 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <bug-11316-10286@http.bugzilla.kernel.org/>
2008-08-13  5:12 ` [Bugme-new] [Bug 11316] New: severe performance regression for iptables nat routing Andrew Morton
2008-08-14  2:08   ` Alex Williamson
2008-08-14  2:21     ` David Miller
2008-08-14 11:04       ` Patrick McHardy
2008-08-14 15:08         ` Alex Williamson [this message]
2008-08-15  4:44           ` Herbert Xu
2008-08-15  5:35             ` Herbert Xu
2008-08-15  5:49               ` Alex Williamson
2008-08-15  6:17                 ` Herbert Xu
2008-08-15 21:56               ` David Miller
     [not found]             ` <1218778238.23510.22.camel@2710p.home>
2008-08-15  7:33               ` Herbert Xu
2008-08-15  8:14                 ` Herbert Xu
2008-08-15 10:32                   ` Herbert Xu
2008-08-15 10:53                     ` Herbert Xu
2008-08-15 15:34                       ` Alex Williamson
2008-08-15 21:55                         ` David Miller
2008-08-15 21:55                       ` David Miller
2008-08-15 20:58                     ` David Miller
2008-08-16  0:25                       ` Herbert Xu
2008-08-15 21:54                     ` David Miller
2008-08-14 22:00         ` David Miller
2008-08-15  4:34       ` Herbert Xu

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=1218726484.23510.20.camel@2710p.home \
    --to=alex.williamson@hp.com \
    --cc=akpm@linux-foundation.org \
    --cc=bugme-daemon@bugzilla.kernel.org \
    --cc=buytenh@marvell.com \
    --cc=davem@davemloft.net \
    --cc=kaber@trash.net \
    --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).