From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-qk1-x744.google.com (mail-qk1-x744.google.com [IPv6:2607:f8b0:4864:20::744]) (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 3E9EF3B29E for ; Fri, 11 Oct 2019 00:05:25 -0400 (EDT) Received: by mail-qk1-x744.google.com with SMTP id 201so7660311qkd.13 for ; Thu, 10 Oct 2019 21:05:25 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=from:content-transfer-encoding:mime-version:subject:date:references :to:in-reply-to:message-id; bh=eFx4aYgFOcSlQNqL875v0XQC3r4cywMCmLqgqYf2mac=; b=tL3sGiWcJxdOwHkDE6ZlwaKQC7vH5fLdfJHb63mY51rgfFB3MeKzT6iISE+3ipds6U bjmKApMG6S2kxUAugCz1tuIMQQiY02NrJGv6Y5/MQpDskowQQT0tynoav9qNWJ2fVBFA grRJmWpa3+vT9+sKvW0hLNpU5bbOQtlnl1S55nuHfiPx8FAv83mKlnI8ijN/bwrSqtye lMaYNtXHRP1HLr5fW/mlloqUyDXE0JuKdhDgvJtTMYAk3QPztMFLhNG1wuWMFSvFtK80 MFIs6IMRtZiYcV+3uG0gb4xZZSXeuk6Oh/GdyiE2hfSmMlYU99brCoS6eN2sW3FiUPko jQ8w== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:content-transfer-encoding:mime-version :subject:date:references:to:in-reply-to:message-id; bh=eFx4aYgFOcSlQNqL875v0XQC3r4cywMCmLqgqYf2mac=; b=YXnUBVqiWhx/8tFiXOtn84UH3SUiQz7MYGwQz4uqoP1tMs0lh/BA0tih2t9eCG+rl9 E0gscjZs+mGq63Y3d6InlG5vhp7I6D7sMA1RAMAezG+jil3xNv7ZDgckBe2boQ4ddob2 OK5GIOjD+6RbgFpfYniaoxpdbsme0PsTTdKv7HVn5A26oAoulK7eaE43MdB3UXQFl9hy NHECOlGb9mp2A1yt1pCCZwjJZmysLqSPwTTJz/9ZintBZj28XbXkLC0n/cqG5oSLuzEE OB2ZcdTItpSv40iKzs50vapGkS103bGNXHSiNPjbL/1GdKkGUDDTRdIc3UBucgdLWmUV IGQg== X-Gm-Message-State: APjAAAVRMFXWcHr5X7k8vmNKAtdr6BV0bCIORz9uFU07mC2tw14mk55p fKlhSas4JZye7KTPMVbcz73JDDfjCWQ= X-Google-Smtp-Source: APXvYqzOeCtsZ0FkNoeXTAHjRuZOTrO/MCGWXgpgGaVPa4cnb6SE5lVeHP9f7yeMM+QMNRV8vmBrMw== X-Received: by 2002:a05:620a:1645:: with SMTP id c5mr13614553qko.473.1570766724337; Thu, 10 Oct 2019 21:05:24 -0700 (PDT) Received: from richs-mbp-10337.lan ([64.223.225.201]) by smtp.gmail.com with ESMTPSA id s50sm4430024qth.92.2019.10.10.21.05.23 for (version=TLS1_2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Thu, 10 Oct 2019 21:05:23 -0700 (PDT) From: Rich Brown Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: quoted-printable Mime-Version: 1.0 (Mac OS X Mail 10.3 \(3273\)) Date: Fri, 11 Oct 2019 00:05:22 -0400 References: To: make-wifi-fast@lists.bufferbloat.net In-Reply-To: Message-Id: <90BB0D49-4C4C-4CC0-A014-73DD00C58A70@gmail.com> X-Mailer: Apple Mail (2.3273) Subject: Re: [Make-wifi-fast] [PATCH v3 1/2] mac80211: Implement Airtime-based Queue Limit (AQL) 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: Fri, 11 Oct 2019 04:05:25 -0000 I have been bothered by small ambiguities in the comments below. (I = assume underlying code is correct.) I have tweaked the text below to make it a bit more clear. Please feel = free to correct it if I've missed what's really happening. (And please = forgive my pseudo-patch code - I hope you can see the changes I am = suggesting.) Thank you all for this great work making Wi-Fi Fast! Rich - In order for the Fq_CoDel integrated in mac80211 layer operates = effectively + In order for the Fq_CoDel algorithm integrated into the mac80211 = layer to control excessive queueing latency, the CoDel algorithm = requires an - accurate measure of how long the packets stays in the queue, aka = sojourn + accurate measure of how long packets stay in the queue, aka their = sojourn - time. The sojourn time measured at mac80211 layer doesn't include = queueing + time. The sojourn time measured at the mac80211 layer doesn't = include queueing - latency in lower layer (firmware/hardware) and CoDel expects lower = layer to + latency in the lower layer (firmware/hardware) and CoDel expects the = lower layer to have a short queue. However, most 802.11ac chipsets offload = tasks such TX aggregation to firmware or hardware, thus have a deep lower = layer queue. +=20 Without a mechanism to control the lower layer queue size, = packets only - stays in mac80211 layer transiently before being sent to firmware = queue. + stay in mac80211 layer transiently before being sent to firmware = queue. As a result, the sojourn time measured by CoDel in the mac80211 = layer is almost always lower than the CoDel latency target, hence CoDel = does little to control the latency, even when the lower layer queue causes = excessive latency. - Byte Queue limits (BQL) is commonly used to address the similar = issue with + Byte Queue Limits (BQL) are commonly used to address the similar = issue with wired network interface. However, this method cannot be applied = directly - to the wireless network interface. Byte is not a suitable measure of = queue + to the wireless network interface. "Bytes" is not a suitable measure = of queue depth in the wireless network, as the data rate can vary = dramatically from station to station in the same network, from a few Mbps to over = Gbps. - This patch implemented an Airtime-based Queue Limit (AQL) to make = CoDel + This patch implements an Airtime-based Queue Limit (AQL) to make = CoDel - works effectively with wireless drivers that utilized = firmware/hardware + work effectively with wireless drivers that utilize = firmware/hardware - offloading. AQL only allows each txq to release just enough packets = to the + offloading. AQL allows each txq to release only enough packets to = the lower layer to form 1-2 large aggregations to keep hardware = fully utilized - and keep the rest of frames in mac80211 layer to be controlled by = the CoDel + and retains the rest of frames in the mac80211 layer to be = controlled by the CoDel algorithm.