From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from relay2-d.mail.gandi.net (relay2-d.mail.gandi.net [IPv6:2001:4b98:c:538::194]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by lists.bufferbloat.net (Postfix) with ESMTPS id BEC7D3B29E for ; Wed, 22 Nov 2017 06:58:27 -0500 (EST) X-Originating-IP: 74.125.82.42 Received: from mail-wm0-f42.google.com (mail-wm0-f42.google.com [74.125.82.42]) (Authenticated sender: nctu@louie.lu) by relay2-d.mail.gandi.net (Postfix) with ESMTPSA id 8BB98C5A4F for ; Wed, 22 Nov 2017 12:58:26 +0100 (CET) Received: by mail-wm0-f42.google.com with SMTP id u83so9828858wmb.5 for ; Wed, 22 Nov 2017 03:58:26 -0800 (PST) X-Gm-Message-State: AJaThX4TduMj9Ieo1tUrqfsXGEj24A52f8Auggo2v1VUtUm/mP96s925 Z/zZdMG3oJMSkwNLHpngTgwuivz64qcDN8+3pXI= X-Google-Smtp-Source: AGs4zMYgDnCArj5p76uBmV1LUSTYAiPvpcQkQIOyVQtcYvq4rcsXRcwKQI0CUR2IoPNiSeY5vuPJ25z8nGw9m3jeqg0= X-Received: by 10.80.141.9 with SMTP id s9mr28424014eds.238.1511351905713; Wed, 22 Nov 2017 03:58:25 -0800 (PST) MIME-Version: 1.0 Received: by 10.80.141.205 with HTTP; Wed, 22 Nov 2017 03:58:25 -0800 (PST) From: Louie Lu Date: Wed, 22 Nov 2017 19:58:25 +0800 X-Gmail-Original-Message-ID: Message-ID: To: Make-wifi-fast@lists.bufferbloat.net Content-Type: text/plain; charset="UTF-8" X-Mailman-Approved-At: Wed, 22 Nov 2017 07:10:34 -0500 Subject: [Make-wifi-fast] How to figure out Linux wifi queue and ath10k queue scheduling? 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: Wed, 22 Nov 2017 11:58:27 -0000 Hi all, I'm a graduate student in NCTU, Taiwan. I'm working on making VoWIFI performance more better on ath10k driver, my first thought is that I can modify queue scheduling algorithm inside ath10k. After tracking the commit log, it seems currently ath10k is using mac80211 as an intermidieate queue[1][2], and as [2] indicate, ath10k is not able to do airtime fairness now. After reading the source code and [2], what I think about the queue in Linux to ath10k is: 1. Mac layer queue (mac80211) 2. ath10k 802.11e priority queues (4 queues, with different 802.11e ToS level) 3. ath10k firmware (HW) queue Am I right on this? Also, I saw the make-wifi-fast google docs[3], it has a plan for obsolete VO queue, is that still in the roadmap, or it is implemented, if not, where can I help for it? Thanks, Louie. [1]: https://www.linuxplumbersconf.org/2016/ocw/system/presentations/3963/original/linuxplumbers_wifi_latency-3Nov.pdf [2]: https://arxiv.org/abs/1703.00064 [3]: https://docs.google.com/document/d/1Se36svYE1Uzpppe1HWnEyat_sAGghB3kE285LElJBW4/edit#