From: Jamie Lokier <jamie@shareable.org>
To: Stephen Hemminger <shemminger@osdl.org>
Cc: "David S. Miller" <davem@redhat.com>, bert hubert <ahu@ds9a.nl>,
netdev@oss.sgi.com, linux-net@vger.kernel.org,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH] fix tcp_default_win_scale.
Date: Wed, 7 Jul 2004 20:31:25 +0100 [thread overview]
Message-ID: <20040707193125.GA17266@mail.shareable.org> (raw)
In-Reply-To: <20040707110653.7c49bef1@dell_ss3.pdx.osdl.net>
Stephen Hemminger wrote:
> But: isn't it better to have just one sysctl parameter set
> (tcp_rmem) and set the window scale as needed rather than increasing
> the already bewildering array of dials and knobs? I can't see why
> it would be advantageous to set a window scale of 7 if the largest
> possible window ever offered is limited to a smaller value?
That's a fair question.
It seems to me the only effects of a larger scale than necessary
are (a) the buffer size can be increased after the connection is
established, and (b) coarser granularity which can only degrade
performance over low mss links.
So why do we set a larger window scale than necessary?
Is it to support (a)?
-- Jamie
next prev parent reply other threads:[~2004-07-07 19:31 UTC|newest]
Thread overview: 39+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <32886.63.170.215.71.1088564087.squirrel@www.osdl.org>
[not found] ` <20040629222751.392f0a82.davem@redhat.com>
[not found] ` <20040630152750.2d01ca51@dell_ss3.pdx.osdl.net>
[not found] ` <20040630153049.3ca25b76.davem@redhat.com>
2004-07-01 20:37 ` [PATCH] TCP acts like it is always out of memory Stephen Hemminger
2004-07-01 21:04 ` David S. Miller
2004-07-02 1:32 ` Arnaldo Carvalho de Melo
2004-07-06 9:35 ` analysis of TCP window size issues still around - several reports / SACK involved? bert hubert
2004-07-06 18:47 ` [PATCH] fix tcp_default_win_scale Stephen Hemminger
2004-07-06 19:40 ` Jamie Lokier
2004-07-06 20:05 ` Stephen Hemminger
2004-07-06 20:28 ` David S. Miller
2004-07-06 20:36 ` Stephen Hemminger
2004-07-06 20:35 ` David S. Miller
2004-07-06 21:55 ` John Heffner
2004-07-06 22:50 ` David S. Miller
2004-07-07 1:32 ` John Heffner
2004-07-06 23:01 ` PLS help fix: recent 2.6.7 won't connect to anything " bert hubert
2004-07-06 20:12 ` David S. Miller
2004-07-06 22:44 ` bert hubert
2004-07-06 22:49 ` David S. Miller
2004-07-07 18:06 ` Stephen Hemminger
2004-07-07 19:31 ` Jamie Lokier [this message]
2004-07-07 19:38 ` bert hubert
2004-07-07 19:41 ` John Heffner
2004-07-09 23:14 ` David S. Miller
2004-07-06 20:00 ` Nivedita Singhvi
2004-07-06 20:16 ` David S. Miller
2004-07-06 20:26 ` David Ford
[not found] ` <20040706185856.GN18841@lug-owl.de>
2004-07-06 20:17 ` David S. Miller
2004-07-06 20:31 ` Stephen Hemminger
2004-07-06 20:33 ` David S. Miller
2004-07-06 20:24 ` David S. Miller
2004-07-06 23:16 ` Andi Kleen
2004-07-07 7:50 ` Chris Wedgwood
2004-07-06 23:19 ` Redeeman
2004-07-07 19:47 ` John Heffner
2004-07-06 20:19 ` analysis of TCP window size issues still around - several reports / SACK involved? David S. Miller
2004-07-06 20:27 ` bert hubert
2004-07-06 20:31 ` David S. Miller
2004-07-07 21:25 ` Alessandro Suardi
2004-07-06 20:35 [PATCH] fix tcp_default_win_scale Tim Berti
2004-07-06 20:54 ` David Ford
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=20040707193125.GA17266@mail.shareable.org \
--to=jamie@shareable.org \
--cc=ahu@ds9a.nl \
--cc=davem@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-net@vger.kernel.org \
--cc=netdev@oss.sgi.com \
--cc=shemminger@osdl.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).