From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-wm0-x234.google.com (mail-wm0-x234.google.com [IPv6:2a00:1450:400c:c09::234]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by lists.bufferbloat.net (Postfix) with ESMTPS id 458A93CB3C for ; Sat, 3 Feb 2018 14:54:17 -0500 (EST) Received: by mail-wm0-x234.google.com with SMTP id v71so18729505wmv.2 for ; Sat, 03 Feb 2018 11:54:17 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=mime-version:subject:from:in-reply-to:date:cc:message-id:references :to; bh=S2eTGfMTWpMHLqCn5YlcxasIvHHfVYqYyQnItvlBIy4=; b=J2M1Jy2/4rCpYf0bDyFZtZgjhofAixBQ9XprCBYtvxK7A1ZSSmzGU4l+IMlhIC+Hju AIsBHa7UPVCwdr78h9dtyapaW+DvLqs5HesRmwNqMIs2gS72or31sGv4L0P8qDfndzZ8 DPQMdzy81PM5SJeoIRgJtoQawb/ELkaPosbcwT8e/jrFUmitOvpF/27kj1thy58bCqgZ 6hFwYPCUN+Vyo/eSzqrE9hs8ttnU/o2Y4haI/4N9tGEyfJQw72ABfdTbveosR1ihS85l udvrU+0BCRQICKRz/Hj41mEvVgi7DPEvcy5TsiQFFUVCcIAq8kvM7u5kIYY1Ou3Obkhx NCPA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:subject:from:in-reply-to:date:cc :message-id:references:to; bh=S2eTGfMTWpMHLqCn5YlcxasIvHHfVYqYyQnItvlBIy4=; b=rlOxQ5nrZEjwRr3Wj0SzBLYhSoWoF6A80xArsy3p4U/Srm1tYWgqcSfX0T8S0IjI0u nq1kyo9GXvngt6sAtiq4ZmUkGe34Yf6Nx7qieYiM46qX7GWSOrXWnudc5bCJPc6G7Lg6 vl8LJTsFI2sz8Sk4Z4xTKqfoRNPGPRmWJ4+exiHUpphy4nwqUB1GVVSc2f0ywfNdJlqq zqWc7NwLw9mdQFCr6DNRLsY8TIFuqyGSmUMa/IMOqr534k6AZLuRjTP/tqZn7EZPzOpC l7deKlWPvY+mHACGReYrFQkxcHbvqnZHi+DDOCxbhrveXm23CWDpP/xyMQzZFPVbmN9h Uj4Q== X-Gm-Message-State: AKwxytd1AUM51FB0ioTl6eCTveOnwyghP65JpjeMz68PORBiRwTuA3PZ iNwKM3Py1J+zLhEXPZpXTgvkOYTC X-Google-Smtp-Source: AH8x226FDt0hEE1JNGkwPZzfIsYiQ1KVpFBKLGesHQjYJ5Swme5zSvYr6CXQiuiIm5/KjeoFcI3U+w== X-Received: by 10.28.234.200 with SMTP id g69mr30110923wmi.137.1517687656257; Sat, 03 Feb 2018 11:54:16 -0800 (PST) Received: from [10.72.0.20] (h-1169.lbcfree.net. [185.193.85.130]) by smtp.gmail.com with ESMTPSA id e67sm9807985wmf.7.2018.02.03.11.54.14 (version=TLS1 cipher=ECDHE-RSA-AES128-SHA bits=128/128); Sat, 03 Feb 2018 11:54:15 -0800 (PST) Content-Type: multipart/alternative; boundary="Apple-Mail=_FE1ECEE6-AE3B-45F9-AB90-8E70327F22F6" Mime-Version: 1.0 (Mac OS X Mail 9.3 \(3124\)) From: Pete Heist In-Reply-To: <87fu7avv0s.fsf@toke.dk> Date: Sat, 3 Feb 2018 20:54:12 +0100 Cc: make-wifi-fast@lists.bufferbloat.net Message-Id: References: <87o9lzqmsq.fsf@toke.dk> <1265AA25-398F-4FA1-9D6B-279178D52EEB@gmail.com> <87fu7avv0s.fsf@toke.dk> To: =?utf-8?Q?Toke_H=C3=B8iland-J=C3=B8rgensen?= X-Mailer: Apple Mail (2.3124) Subject: Re: [Make-wifi-fast] Estimating WiFi congestion using different-prio pings X-BeenThere: make-wifi-fast@lists.bufferbloat.net X-Mailman-Version: 2.1.20 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 03 Feb 2018 19:54:17 -0000 --Apple-Mail=_FE1ECEE6-AE3B-45F9-AB90-8E70327F22F6 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset=utf-8 > On Jan 13, 2018, at 12:49 PM, Toke H=C3=B8iland-J=C3=B8rgensen = wrote: >=20 > Any prioritisation of ICMP may just be because ICMP replies are > generated by the kernel, whereas other traffic goes all the way to the > userspace application generating it. However, it is certainly possible > that ICMP is being prioritised - some people do that in an effort to > game benchmarks... I somehow missed this comment from before. Here=E2=80=99s what makes me = think this is more than just kernel vs userspace, and something Ubiquiti = may be doing, at least in their M series firmware: - To measure overhead, between a RasPI (client) and an EdgeRouter-X = (server), I see only a 354=C2=B5s difference between ping=E2=80=99s mean = RTT and irtt's mean RTT when tested with 100 packets over direct cabled = Ethernet (865=C2=B5s - 511=C2=B5s). I assume that this overhead will = remain about the same for the same client and server devices, regardless = of what else lies between them. - Next, ping vs irtt (mean rtt of 100 packets) to the same EdgeRouter-X = over an unloaded Internet connection where the CPE is a Ubiquiti = PowerBeam M5-400: - ping: 17.03ms - irtt: 20.7ms - Next, ping vs irtt (mean rtt of 100 packets) to the same EdgeRouter-X, = same Internet connection, but with a saturated upload and no AQM: - ping: 22.9ms - irtt: 90.23ms Saturation seems to have a much larger impact on UDP than ICMP. This is only a rough test and I=E2=80=99ll need to reproduce this in my = lab setup when it=E2=80=99s up again. That will remove all devices along = the route as possible sources of this behavior. But since I know FreeNet = isn=E2=80=99t doing this in their backhaul I=E2=80=99m fairly certain = that=E2=80=99s what=E2=80=99s going on. I=E2=80=99ll update with some results later when repro=E2=80=99d in the = lab with NSM5s=E2=80=A6 --Apple-Mail=_FE1ECEE6-AE3B-45F9-AB90-8E70327F22F6 Content-Transfer-Encoding: quoted-printable Content-Type: text/html; charset=utf-8
On Jan 13, 2018, at 12:49 PM, Toke H=C3=B8iland-J=C3=B8rgensen = <toke@toke.dk> = wrote:

Any prioritisation of ICMP may just be = because ICMP replies are
generated by the kernel, whereas other = traffic goes all the way to the
userspace application generating it. = However, it is certainly possible
that ICMP is being prioritised - some = people do that in an effort to
game benchmarks...

I somehow missed this comment from before. = Here=E2=80=99s what makes me think this is more than just kernel vs = userspace, and something Ubiquiti may be doing, at least in their M = series firmware:

- To measure overhead, between a RasPI (client) and an = EdgeRouter-X (server), I see only a 354=C2=B5s difference between = ping=E2=80=99s mean RTT and irtt's mean RTT when tested with 100 packets = over direct cabled Ethernet (865=C2=B5s - 511=C2=B5s). I assume that = this overhead will remain about the same for the same client and server = devices, regardless of what else lies between them.

- Next, ping vs irtt = (mean rtt of 100 packets) to the same EdgeRouter-X over an unloaded = Internet connection where the CPE is a Ubiquiti PowerBeam = M5-400:
- ping: 17.03ms
= - irtt: 20.7ms

- Next, ping vs irtt (mean rtt of 100 packets) to the same = EdgeRouter-X, same Internet connection, but with a saturated upload and = no AQM:
- ping: 22.9ms
= - irtt: 90.23ms

Saturation seems to have a much larger impact on UDP than = ICMP.

This is = only a rough test and I=E2=80=99ll need to reproduce this in my lab = setup when it=E2=80=99s up again. That will remove all devices along the = route as possible sources of this behavior. But since I know FreeNet = isn=E2=80=99t doing this in their backhaul I=E2=80=99m fairly certain = that=E2=80=99s what=E2=80=99s going on.

I=E2=80=99ll update with some results = later when repro=E2=80=99d in the lab with NSM5s=E2=80=A6

= --Apple-Mail=_FE1ECEE6-AE3B-45F9-AB90-8E70327F22F6--