From mboxrd@z Thu Jan  1 00:00:00 1970
Authentication-Results: mail.toke.dk; spf=pass (mailfrom) smtp.mailfrom=webweaving.org (client-ip=148.251.234.232; helo=weser.webweaving.org; envelope-from=dirkx@webweaving.org; receiver=<UNKNOWN>)
Authentication-Results: mail.toke.dk;
	dkim=pass (1024-bit key; unprotected) header.d=webweaving.org header.i=@webweaving.org header.a=rsa-sha256 header.s=shared header.b=Ame/3KnS
Received: from weser.webweaving.org (weser.webweaving.org [148.251.234.232])
	by mail.toke.dk (Postfix) with ESMTPS id 3C59FB02E3A
	for <galene@lists.galene.org>; Sat, 22 Mar 2025 21:41:34 +0100 (CET)
Received: from smtpclient.apple (fiber.static.cbizz.nl [185.142.248.117] (may be forged))
	(authenticated bits=0)
	by weser.webweaving.org (8.18.1/8.18.1) with ESMTPSA id 52MKblRU017732
	(version=TLSv1.2 cipher=ECDHE-ECDSA-AES256-GCM-SHA384 bits=256 verify=NO);
	Sat, 22 Mar 2025 21:37:48 +0100 (CET)
	(envelope-from dirkx@webweaving.org)
DKIM-Signature: v=1; a=rsa-sha256; c=simple/simple; d=webweaving.org;
	s=shared; t=1742675868;
	bh=ONZ0wFFW82to3FHDcB+FErhXi3bmCXglS8PALiRPFjc=;
	h=Subject:From:In-Reply-To:Date:Cc:References:To;
	b=Ame/3KnSZd2wEYd1bPH9/FjrnwV8O5rnshtiyowK2g/0kRqJ7e28+rjaH0vEsFTAb
	 PYxgSA6Uk+brB8ue+pSX/n9IW3PCSLMS+4RCDnLuq/D3whC5CT5APVujlrqn3pZ9xZ
	 48zyNQDIYgdRKEpl/Ik2wkPszDBMDdgPgAfmJ4Tk=
X-Authentication-Warning: weser.webweaving.org: Host fiber.static.cbizz.nl [185.142.248.117] (may be forged) claimed to be smtpclient.apple
Content-Type: text/plain;
	charset=utf-8
Mime-Version: 1.0 (Mac OS X Mail 16.0 \(3826.400.131.1.6\))
From: Dirk-Willem van Gulik <dirkx@webweaving.org>
In-Reply-To: <87sen4onf7.wl-jch@irif.fr>
Date: Sat, 22 Mar 2025 21:36:47 +0100
Content-Transfer-Encoding: quoted-printable
Message-Id: <25DD360D-2A18-411B-A50B-F82670B6A562@webweaving.org>
References: <87sen4onf7.wl-jch@irif.fr>
To: Juliusz Chroboczek <jch@irif.fr>
X-Mailer: Apple Mail (2.3826.400.131.1.6)
X-Greylist: Sender succeeded SMTP AUTH, not delayed by milter-greylist-4.6.4 (weser.webweaving.org [148.251.234.232]); Sat, 22 Mar 2025 21:37:48 +0100 (CET)
Message-ID-Hash: G7SDD5V7SK5MTKXJ4UD6YE6BMYCPZIBG
X-Message-ID-Hash: G7SDD5V7SK5MTKXJ4UD6YE6BMYCPZIBG
X-MailFrom: dirkx@webweaving.org
X-Mailman-Rule-Hits: member-moderation
X-Mailman-Rule-Misses: dmarc-mitigation; no-senders; approved; loop; banned-address; emergency
CC: galene@lists.galene.org
X-Mailman-Version: 3.3.10
Precedence: list
Subject: [Galene] Re: UDP muxing: a completely unscientific benchmark
List-Id: =?utf-8?q?Gal=C3=A8ne_videoconferencing_server_discussion_list?= <galene.lists.galene.org>
Archived-At: <https://lists.galene.org/galene/25DD360D-2A18-411B-A50B-F82670B6A562@webweaving.org/>
List-Archive: <https://lists.galene.org/galene/>
List-Help: <mailto:galene-request@lists.galene.org?subject=help>
List-Owner: <mailto:galene-owner@lists.galene.org>
List-Post: <mailto:galene@lists.galene.org>
List-Subscribe: <mailto:galene-join@lists.galene.org>
List-Unsubscribe: <mailto:galene-leave@lists.galene.org>


On 22 Mar 2025, at 20:50, Juliusz Chroboczek <jch@irif.fr> wrote:

> I think we may conclude that the overhead of UDP muxing is negligible.

Same here - I tried a standard 1 minute 256 streams x 10 tests against =
it - and could (on a low end VPS) not measure the difference.=20

This is with Galene `behind=E2=80=99 an apache reverse proxy and package =
in a FreeBSD jail; and comparing all CPU taken by that jail. Where the =
latter is either configured to take it through NAT with the -udp mux =
option; or `normal=E2=80=99 with its IP directly exposed.

Dw.=