All of lore.kernel.org
 help / color / mirror / Atom feed
From: Willy Tarreau <w@1wt.eu>
To: David Miller <davem@davemloft.net>
Cc: herbert@gondor.hengli.com.au, netdev@vger.kernel.org
Subject: Re: TCP: orphans broken by RFC 2525 #2.17
Date: Tue, 28 Sep 2010 07:37:47 +0200	[thread overview]
Message-ID: <20100928053747.GF12373@1wt.eu> (raw)
In-Reply-To: <20100927.223231.179927955.davem@davemloft.net>

On Mon, Sep 27, 2010 at 10:32:31PM -0700, David Miller wrote:
> From: Willy Tarreau <w@1wt.eu>
> Date: Tue, 28 Sep 2010 07:12:58 +0200
> 
> > Once again, for now, I will only handle this precise case of the extra
> > CRLF, but this will not fix the issue with pipelined requests.
> 
> You might want to read server/connection.c in the apache httpd
> sources.
>
> It does exactly what Eric Dumazet and I have suggested to you.

I've seen that. Though nginx, squid, thttpd, haproxy and lighttpd all
make use of the standard orphans and are all affected by the same issue.

> But, I guess the entire world is wrong and you're right Willy.

Given the figures above, that's not how I analyze it, I'm sorry.

Willy


  reply	other threads:[~2010-09-28  5:37 UTC|newest]

Thread overview: 39+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-09-26 13:17 TCP: orphans broken by RFC 2525 #2.17 Willy Tarreau
2010-09-26 17:02 ` Eric Dumazet
2010-09-26 17:40   ` Willy Tarreau
2010-09-26 18:35     ` Eric Dumazet
2010-09-26 18:49       ` Willy Tarreau
2010-09-26 21:01         ` Eric Dumazet
2010-09-26 21:46           ` Willy Tarreau
2010-09-26 22:19             ` David Miller
2010-09-26 22:10         ` David Miller
2010-09-26 19:16     ` Willy Tarreau
2010-09-26 22:14       ` David Miller
2010-09-26 22:13 ` David Miller
2010-09-26 22:34   ` Willy Tarreau
2010-09-26 22:38     ` David Miller
2010-09-26 22:54       ` Willy Tarreau
2010-09-26 23:08         ` David Miller
2010-09-26 23:25           ` Willy Tarreau
2010-09-27  1:12             ` David Miller
2010-09-27  5:39               ` Willy Tarreau
2010-09-27  5:48                 ` Eric Dumazet
2010-09-27  6:04                   ` Willy Tarreau
2010-09-27  6:44                   ` David Miller
2010-09-27  6:42                 ` David Miller
2010-09-27  7:34                   ` Willy Tarreau
2010-09-27  7:42                     ` David Miller
2010-09-27 19:21                       ` Willy Tarreau
2010-09-27 23:28                         ` Herbert Xu
2010-09-28  5:12                           ` Willy Tarreau
2010-09-28  5:32                             ` David Miller
2010-09-28  5:37                               ` Willy Tarreau [this message]
2010-09-27  9:12                     ` Julian Anastasov
2010-09-27 19:24                       ` Willy Tarreau
2010-09-27 20:00                         ` Eric Dumazet
2010-09-28  9:01                         ` Julian Anastasov
2010-09-28  9:26                           ` Willy Tarreau
2010-09-27  8:02 ` Herbert Xu
2010-09-27 20:00   ` Willy Tarreau
2010-09-27 20:08     ` Rick Jones
2010-09-27 20:20       ` Willy Tarreau

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=20100928053747.GF12373@1wt.eu \
    --to=w@1wt.eu \
    --cc=davem@davemloft.net \
    --cc=herbert@gondor.hengli.com.au \
    --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 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.