From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <toke@toke.dk>
Received: from mail.toke.dk (mail.toke.dk [IPv6:2a0c:4d80:42:2001::664])
 (using TLSv1.2 with cipher ADH-AES256-GCM-SHA384 (256/256 bits))
 (No client certificate requested)
 by lists.bufferbloat.net (Postfix) with ESMTPS id D32963CB38
 for <rpm@lists.bufferbloat.net>; Thu, 21 Oct 2021 07:46:01 -0400 (EDT)
From: Toke =?utf-8?Q?H=C3=B8iland-J=C3=B8rgensen?= <toke@toke.dk>
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=toke.dk; s=20161023;
 t=1634816759; bh=ojxlwBVPV6xtNY4zx9taqWCg96ULSkFrOjuaoqfLs3U=;
 h=From:To:Cc:Subject:In-Reply-To:References:Date:From;
 b=uD/wpCTvwCt6HJ+Gy374TEIQMwKmAtxFQcDnm2dVjKBgh/i+V0SpF8aCjyzDSZgEa
 n6tnJaAsEI9YciDpFiVR3YoGkfq02+BzmX6m49paduRnK1ybAdMrQQPERF/2e5Npqp
 mnxfni6dqHk3xhLGG0uTUifXuRhPruedYAwM8qUqj5f4aCiSQqVO8mjIDroyIWDFDo
 S4FLybb4B1BsHvvlwKhhbVutNi328DPFOz97lwwTPVeBPONvmb0HgX05/D1jJWxVb+
 Uj3/TzwrDuqyuFLIgOcNdC0vLXJnZ/FSW7MxKfcT3zt5tKsayKXwzmySqagVrc8bGF
 og/0gv/MrjwVA==
To: Omer Shapira <omer_shapira@apple.com>, Christoph Paasch
 <cpaasch@apple.com>, Rich Brown <richb.hanover@gmail.com>
Cc: Rpm <rpm@lists.bufferbloat.net>
In-Reply-To: <4C9625A0-6276-4073-A43F-A57C22F268C6@apple.com>
References: <ED8D819B-BB2A-4538-A8A8-955D85824474@gmail.com>
 <6B7910A6-9157-40DD-8C50-FE42AEDB7797@apple.com>
 <8F8B59C1-9FB7-4B3E-9C15-14180721FEA8@gmail.com>
 <YWiSmRqTSzBQxvxU@MacBook-Pro-2.local>
 <D54D12B4-9DF1-4CEC-A68F-2D57F7CA7250@gmail.com>
 <DA158695-9A5F-4CAE-8675-7D04988F61F4@apple.com>
 <4C9625A0-6276-4073-A43F-A57C22F268C6@apple.com>
Date: Thu, 21 Oct 2021 13:45:58 +0200
X-Clacks-Overhead: GNU Terry Pratchett
Message-ID: <87y26md2ix.fsf@toke.dk>
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: quoted-printable
Subject: Re: [Rpm] Does RPM measurement *require* a valid SSL certificate
X-BeenThere: rpm@lists.bufferbloat.net
X-Mailman-Version: 2.1.20
Precedence: list
List-Id: revolutions per minute - a new metric for measuring responsiveness
 <rpm.lists.bufferbloat.net>
List-Unsubscribe: <https://lists.bufferbloat.net/options/rpm>,
 <mailto:rpm-request@lists.bufferbloat.net?subject=unsubscribe>
List-Archive: <https://lists.bufferbloat.net/pipermail/rpm>
List-Post: <mailto:rpm@lists.bufferbloat.net>
List-Help: <mailto:rpm-request@lists.bufferbloat.net?subject=help>
List-Subscribe: <https://lists.bufferbloat.net/listinfo/rpm>,
 <mailto:rpm-request@lists.bufferbloat.net?subject=subscribe>
X-List-Received-Date: Thu, 21 Oct 2021 11:46:02 -0000

Omer Shapira via Rpm <rpm@lists.bufferbloat.net> writes:

> 2. The notion that =E2=80=9Cit=E2=80=99s easy enough to stand up code to =
respond to
> HTTP=E2=80=9D - this may be true, but the role of the server is not to ju=
st
> respond, it will have to actually saturate the link. This requires
> sufficient processing power to send the data at the required rate.
> Hence, the boxes that rely on a SOC to move the bytes, and have low
> power master CPU may not be able to saturate the link.

I'll add another complication to this, at least for Linux: TCP Small
Queues (TSQ). If the server responding to the requests is the AP, TSQ
can do a quite good job of keeping those streams from saturating the
queues of the WiFi interface, meaning you won't expose any bloat that
may be hiding there. This varies between implementations, but it's quite
possible to have an AP that has no bufferbloat when running a test
against a server on the AP itself, but is severely bloated when
forwarding packets.

-Toke