From: Christian Schmid <webmaster@rapidforum.com>
To: Ben Greear <greearb@candelatech.com>
Cc: linux-kernel@vger.kernel.org
Subject: Re: BUG: Slowdown on 3000 socket-machines tracked down
Date: Mon, 07 Mar 2005 15:35:36 +0100 [thread overview]
Message-ID: <422C66B8.2060605@rapidforum.com> (raw)
In-Reply-To: <422BC303.9060907@candelatech.com>
Ben Greear wrote:
>> Its a full-duplex. Its a download-service with 3000 downloaders all
>> over the world.
>
>
> So actually it's really mostly one-way traffic, ie in the download
> direction.
> Anything significant at all going upstream, other than ACKs, etc?
Not much. See on the graph. The red is the downstream ;)
>> Yes. send-buffer to 64 kbytes and receive buffer to 16 kbytes.
>
>
> With regard to this note in the 'man 7 socket' man page:
>
> NOTES
> Linux assumes that half of the send/receive buffer is used for
> internal kernel struc-
> tures; thus the sysctls are twice what can be observed on the wire.
>
> What value are you using for the sockopt call?
First I used 64 * 1024 but some months ago I checked with getsockopt and realized that it always
gives twice of the value back. So I just have done 64 * 512 ;)
Chris
next prev parent reply other threads:[~2005-03-07 14:35 UTC|newest]
Thread overview: 39+ messages / expand[flat|nested] mbox.gz Atom feed top
2005-03-05 17:10 BUG: Slowdown on 3000 socket-machines tracked down Christian Schmid
2005-03-07 0:45 ` Nick Piggin
2005-03-07 1:13 ` Ben Greear
2005-03-07 1:58 ` Christian Schmid
2005-03-07 2:57 ` Ben Greear
2005-03-07 5:14 ` Nick Piggin
2005-03-07 5:30 ` Willy Tarreau
2005-03-07 5:41 ` Nick Piggin
2005-03-07 5:42 ` Nick Piggin
2005-03-07 5:46 ` Willy Tarreau
2005-03-07 9:22 ` Ben Greear
2005-03-07 9:28 ` Nick Piggin
2005-03-08 6:30 ` Ben Greear
2005-03-08 16:41 ` Christian Schmid
2005-03-09 23:45 ` Ben Greear
2005-03-09 23:52 ` Christian Schmid
2005-03-10 0:18 ` Ben Greear
2005-03-10 0:24 ` Christian Schmid
2005-03-10 5:17 ` Andrew Morton
2005-03-10 9:00 ` Andi Kleen
2005-03-10 9:09 ` Andrew Morton
2005-03-10 9:12 ` Andi Kleen
2005-03-10 9:38 ` Andrew Morton
2005-03-10 19:03 ` Ben Greear
2005-03-10 18:51 ` Christian Schmid
2005-03-10 19:06 ` Christian Schmid
2005-03-11 15:29 ` Christian Schmid
2005-03-11 19:10 ` Ben Greear
2005-03-11 19:27 ` Christian Schmid
2005-03-14 4:40 ` Nick Piggin
2005-03-14 4:53 ` Christian Schmid
2005-03-14 5:04 ` Nick Piggin
2005-05-28 3:17 ` Christian Schmid
2005-06-08 2:26 ` Christian Schmid
2005-06-08 2:39 ` Nick Piggin
2005-06-08 2:44 ` Andrew Morton
2005-03-07 14:35 ` Christian Schmid [this message]
2005-03-07 23:37 ` Ben Greear
2005-03-07 2:07 ` Christian Schmid
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=422C66B8.2060605@rapidforum.com \
--to=webmaster@rapidforum.com \
--cc=greearb@candelatech.com \
--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