From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-lf0-x22f.google.com (mail-lf0-x22f.google.com [IPv6:2a00:1450:4010:c07::22f]) (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 313533B2A4 for ; Sat, 4 Mar 2017 15:28:02 -0500 (EST) Received: by mail-lf0-x22f.google.com with SMTP id a6so59246533lfa.0 for ; Sat, 04 Mar 2017 12:28:02 -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 :content-transfer-encoding:message-id:references:to; bh=YTmedSyLqPnzcvnTitdU2upvpW23aFDTWozYR/wA7k8=; b=p5CHllxQTF0JpE61wGNO2vdePmphdpOL1bu4Ecg2ptqquJjt++5Zp/klTY66eJwiiV hVDZGil8NPq6mpqBEkywIn3WqMI/S+J7LV2LW6G4GtPDXn1vOEwdIp/hCRTgrGdPF4jW sglwSm0ipU9fFmwv2nnR3qu+buANo53YxATagk/D3hNuKz+1GnMZFgrHNDNz/Wkz3UU4 0mp9TNaCM/HfcvzIIEIC/BZFdf4WWcdgJj21P+l99CkiNSFisLYYRED6WLvwCmqMRE/2 xl25m2YI5bG8mjTFrk5pEv4CZe0TgY4YdvsNlRnCRuiu413EtXLVyN1ZuHaT7ItE+SIw YvrA== 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 :content-transfer-encoding:message-id:references:to; bh=YTmedSyLqPnzcvnTitdU2upvpW23aFDTWozYR/wA7k8=; b=qeLbFl9aHxzw3+8FjJMzR8PtTOmkb+dmydKI6fFziSPOIrS/9Rk/GGYNwrKlD85sac HWm+RDdTaZwF6sTRQBwq25MzvG7doT6By0+V0AyzNzN+T4cF0aUfoMUITMLI0cQbxO/g S8tj5xoZLckzyXhfbjNxXKsgClPcj/x5900u0XZfvi7buIouI848G4Cindnp12OFyE5p BuphtQ+AEvrXx3BjW7rn6mVEXBTFKIUsx3zeGUVaNXD5dD72BexQ0qNW+MhbNPgAfu00 NSKqlVXOWEMxm6RmL5JCObLqTGHcy5m1z8XjFbVeXm1tWqlJrGr1h3a5eRlAAMv0r/70 Ifew== X-Gm-Message-State: AMke39kAUYfWnHjQDM6Ow4swJLWo61GeajwHAHQ99Sc3ArRTyHUbofIF0O4jm+HvBedUTw== X-Received: by 10.46.0.65 with SMTP id 62mr3155354lja.115.1488659280982; Sat, 04 Mar 2017 12:28:00 -0800 (PST) Received: from [192.168.100.16] (37-219-206-78.nat.bb.dnainternet.fi. [37.219.206.78]) by smtp.gmail.com with ESMTPSA id 9sm3136168ljn.1.2017.03.04.12.27.59 (version=TLS1 cipher=ECDHE-RSA-AES128-SHA bits=128/128); Sat, 04 Mar 2017 12:28:00 -0800 (PST) Content-Type: text/plain; charset=utf-8 Mime-Version: 1.0 (Mac OS X Mail 9.3 \(3124\)) From: Jonathan Morton In-Reply-To: <752ad487-0826-ba92-6bbf-a46d031a10ee@gmail.com> Date: Sat, 4 Mar 2017 22:27:57 +0200 Cc: Cake@lists.bufferbloat.net Content-Transfer-Encoding: quoted-printable Message-Id: <95D56BA5-0C5E-4D2E-B28F-A8C957B5F65D@gmail.com> References: <752ad487-0826-ba92-6bbf-a46d031a10ee@gmail.com> To: Andy Furniss X-Mailer: Apple Mail (2.3124) Subject: Re: [Cake] low bandwidth default params best effort vs voice latency. X-BeenThere: cake@lists.bufferbloat.net X-Mailman-Version: 2.1.20 Precedence: list List-Id: Cake - FQ_codel the next generation List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 04 Mar 2017 20:28:02 -0000 Okay, I think I=E2=80=99ve worked out what is happening. At 250KB/s, it takes 6ms to get one 1500-byte bulk packet down the pipe. = This is unavoidable, so having a bulk flow competing with your game = traffic will always increase your peak latency by that much. With three independent game streams in play, it=E2=80=99s possible for = them all to transmit simultaneously *and* to coincide with a bulk packet = having just been sent. With overheads, it will take a total of 8.5ms to = get all four packets through. This corresponds nicely to your = best-effort results; you=E2=80=99re getting very close to the = theoretical best performance there. So Diffserv marking actually can=E2=80=99t improve your performance in = this particular case. But it shouldn=E2=80=99t make it worse either. = You=E2=80=99re actually seeing a nearly 6ms increase in peak latency, = which corresponds neatly to an additional bulk packet ending up ahead of = the game traffic in the queue. That=E2=80=99s not supposed to happen, but I think I can see how it = *can* happen with the current Diffserv logic. It=E2=80=99s a weighted = DRR, much like what is used between flow queues a little further down - = but it *doesn=E2=80=99t* have a special bonus for sparse tins. That=E2=80= =99s something I clearly need to fix. To help remind me, please do open an issue on the Github project. - Jonathan Morton