From: Bill Davidsen <davidsen@tmr.com>
To: Ed W <lists@wildgooses.com>
Cc: linux-kernel@vger.kernel.org
Subject: Re: Raise initial congestion window size / speedup slow start?
Date: Wed, 14 Jul 2010 11:21:15 -0400 [thread overview]
Message-ID: <4C3DD5EB.9070908@tmr.com> (raw)
In-Reply-To: <4C3D94E3.9080103@wildgooses.com>
Ed W wrote:
> Hi, my network connection looks like 500Kbits with a round trip latency
> of perhaps 1s+ (it's a satellite link).
>
> From what I can see the linux initial congestion window is signficantly
> limiting me here, with slow start taking many many seconds to open up
> the window wide enough to get the data flowing? For protocols like http
> this is really hurting with all the short lived connections never really
> getting up to speed. (throw in some random packet loss and things
> really screech to a halt)
>
> Reading around there appear to be several previous attempts to modify
> the kernel to start with a slightly wider initial congestion window, say
> 10 packets. (Seems even google did some work on this and agreed that a
> small of initial cwd to 10 ish, would help even many non satellite
> users?) However, all the work I can find is quite old and doesn't seem
> to give me much of a leg up in terms of experimenting with such changes
> on a modern kernel?
>
> Does someone have some pointers on where to look to modify initial
> congestion window please?
>
Are you sure that's the issue? The backlog is in incoming, is it not?
Having dealt with moderately long delays push TB between timezones, have you set
your window size up? Set /proc/sys/net/ipv4/tcp_adv_win_scale to 5 or 6 and see
if that helps. You may have to go into /proc/sys/net/core and crank up the
rmem_* settings, depending on your distribution.
This allows the server to push a lot of data without an ack, which is what you
want, the ack will be delayed by the long latency, so this helps. You can
calculate how large to make the setting, but "make it bigger until tcpdump never
shows the window size < 2k" is the best way, even a bit larger than that wont
hurt, although it will take a bit of memory.
--
Bill Davidsen <davidsen@tmr.com>
"We have more to fear from the bungling of the incompetent than from
the machinations of the wicked." - from Slashdot
next prev parent reply other threads:[~2010-07-14 15:21 UTC|newest]
Thread overview: 43+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-07-14 10:43 Raise initial congestion window size / speedup slow start? Ed W
2010-07-14 11:58 ` Alan Cox
2010-07-14 15:21 ` Bill Davidsen [this message]
2010-07-14 18:15 ` David Miller
2010-07-14 18:48 ` Ed W
2010-07-14 19:10 ` Stephen Hemminger
2010-07-14 21:47 ` Mitchell Erblich
2010-07-14 20:17 ` Rick Jones
2010-07-14 20:39 ` Hagen Paul Pfeifer
2010-07-14 21:55 ` David Miller
2010-07-14 22:13 ` Hagen Paul Pfeifer
2010-07-14 22:19 ` Rick Jones
2010-07-14 22:40 ` Hagen Paul Pfeifer
2010-07-14 22:52 ` Ed W
2010-07-14 23:01 ` Hagen Paul Pfeifer
2010-07-14 23:05 ` Ed W
2010-07-15 3:49 ` Bill Fink
2010-07-15 5:29 ` H.K. Jerry Chu
2010-07-15 19:51 ` Rick Jones
2010-07-15 20:48 ` Stephen Hemminger
2010-07-16 0:23 ` H.K. Jerry Chu
2010-07-16 9:03 ` Hagen Paul Pfeifer
2010-07-15 10:33 ` Alan Cox
2010-07-14 22:05 ` Ed W
2010-07-14 22:36 ` Hagen Paul Pfeifer
2010-07-14 23:01 ` Ed W
2010-07-15 4:12 ` Tom Herbert
2010-07-15 7:48 ` Ed W
2010-07-15 17:36 ` Jerry Chu
2010-07-15 5:09 ` H.K. Jerry Chu
2010-07-15 2:52 ` Bill Fink
2010-07-15 4:51 ` H.K. Jerry Chu
2010-07-16 17:01 ` Patrick McManus
2010-07-16 17:41 ` Ed W
2010-07-17 1:23 ` H.K. Jerry Chu
2010-07-17 0:36 ` H.K. Jerry Chu
2010-07-19 17:08 ` Rick Jones
2010-07-19 22:51 ` H.K. Jerry Chu
2010-07-19 23:42 ` Hagen Paul Pfeifer
2010-07-15 23:14 ` Bill Davidsen
2010-07-14 18:32 ` Ed W
2010-07-15 15:10 ` Bill Davidsen
2010-07-16 2:58 ` Henrique de Moraes Holschuh
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=4C3DD5EB.9070908@tmr.com \
--to=davidsen@tmr.com \
--cc=linux-kernel@vger.kernel.org \
--cc=lists@wildgooses.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