From: Bill Davidsen <davidsen@tmr.com>
To: 7eggert@gmx.de
Cc: Linux-kernel <linux-kernel@vger.kernel.org>
Subject: Re: 2.6.9 NAT problem
Date: Tue, 21 Dec 2004 11:40:54 -0500 [thread overview]
Message-ID: <41C85216.1070304@tmr.com> (raw)
In-Reply-To: <E1CgfT5-0000Zh-00@be1.7eggert.dyndns.org>
Bodo Eggert wrote:
> Bill Davidsen wrote:
>
>>Antonio Pérez wrote:
>
>
>>>add this:
>>>echo 0 > /proc/sys/net/ipv4/tcp_bic
>>>echo 0 > /proc/sys/net/ipv4/tcp_ecn
>>>echo 0 > /proc/sys/net/ipv4/tcp_vegas_conf_avoid
>>
>>I've seen this and similar advice for other problems, and have disabled=
>>
>>ecn for several systems with networking ailments myself. Would it be
>>better to have some of these off by default rather than have multiple
>>versions of these problems appear into the future?
>
>
> Disabeling ecn is a workaround for b0rken firewalls and may result in
> using more bandwidth than nescensary. If disabeling ecn helps, dump the
> firewall and get something that supports basic internet standards (or
> ask the owner to do this).
>
Like many other parameters, ecn can improve performance but may result
in a non-functional network. Based on that I still think it's better for
the default to be "works" and use of ecn or other tuning parameters such
as reducing timeouts should be "tuning" instead.
Adding a few printk's seems to show that ecn is not so common that it
needs to be on by default. I suspect that the main use of ecn code is in
fighting with those broken routers and firewalls rather than improving
performance.
--
-bill davidsen (davidsen@tmr.com)
"The secret to procrastination is to put things off until the
last possible moment - but no longer" -me
next prev parent reply other threads:[~2004-12-21 16:41 UTC|newest]
Thread overview: 11+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <fa.en17uqu.1r1odgm@ifi.uio.no>
[not found] ` <fa.b00sk8v.12lus29@ifi.uio.no>
2004-12-21 8:34 ` 2.6.9 NAT problem Bodo Eggert
2004-12-21 16:40 ` Bill Davidsen [this message]
2004-12-13 20:26 Giuliano Pochini
2004-12-13 22:11 ` Antonio Pérez
2004-12-14 21:20 ` Giuliano Pochini
2004-12-16 20:41 ` Bill Davidsen
2004-12-14 9:31 ` Martin Josefsson
2004-12-14 9:53 ` Giuliano Pochini
2004-12-14 21:26 ` Giuliano Pochini
2004-12-15 6:53 ` Martin Josefsson
2004-12-15 19:18 ` Giuliano Pochini
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=41C85216.1070304@tmr.com \
--to=davidsen@tmr.com \
--cc=7eggert@gmx.de \
--cc=linux-kernel@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