From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-it0-x22c.google.com (mail-it0-x22c.google.com [IPv6:2607:f8b0:4001:c0b::22c]) (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 64E873CB50 for ; Fri, 9 Feb 2018 10:56:43 -0500 (EST) Received: by mail-it0-x22c.google.com with SMTP id n206so11193819itg.1 for ; Fri, 09 Feb 2018 07:56:43 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=subject:to:references:from:message-id:date:user-agent:mime-version :in-reply-to:content-language; bh=B2DqXAs/Y2ELpTaZdLNOCVqq3garRIblRenQ6+5UgIs=; b=k0LY8phEcs4jPLN0uXPyZxI22hjlnVKb5vYwHNuX+HxEb+S9WsHqKbmnwoMMQY0NHM moLvWVFxw1JHyu9PQ1RigpN0d+pte0YPKlJT6sXXi7Z29EuE8tgL1P2vN1b+Y3HUDJXn i5KWen9C+hNKw/Iuyatjbw6DkbFy9hLrD25IkjMrLgJB1XGH5J86BjGd/ba+rSZjjFoJ W+F5gCS1FLTPLjU/CwUeLQ1Oa4xy+9+bFT/lx1ChgyDycmegzTm6c3kJ03YeeT+Y/eOg bSmrLJn+yv7hVVRtir2IjxNcn9QqCh7B5I+0g4FacRNCOUZRx+eKRMF3QEMwg+BQ6se5 3n8A== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:subject:to:references:from:message-id:date :user-agent:mime-version:in-reply-to:content-language; bh=B2DqXAs/Y2ELpTaZdLNOCVqq3garRIblRenQ6+5UgIs=; b=I+uwP16L3Bt/ZMZ0MpFi7KhQVJLx9SsmJPA1dLmzJa5GIy3W4wOqLO5U46vckWGAKj CyitXlWmb5/jHC9Ql6HnOeqtZvgh4sCEMmg+arcB8UoICowVakiP7HP/i4nMMLy9DfbJ FZsxZwWVuxvQjT/cCznlsgRqIyhsRcy/Fxxn6wW3tOJe9cE6kevNKlKtdlBPEhpUf2cD xGjzKCkhUfwj2lPyhOi2qGU/yx9dFO2womSv63kD4+A9pQgIEPfXiGvl+4jjRiilhtmw NyyUC/+Sz46FOydeiG3UZSCapq24yvX1mpNhaqOx4K8KYDmDyYUj8e4PYxzHtUVXcoXs g0qQ== X-Gm-Message-State: APf1xPBNypp5MZW5+8wkodQRqJQpOmOeXmM1w5W8ArCH6RLj842jw9Gd xVk6iTHgyinownUbCDi0+dQjJ+6V X-Google-Smtp-Source: AH8x225HHeoaPPw6JFTVn4OfFkpHaZdcoOrwSNxetqj66CFetyiXjeN2n1jEUbyKxpaojTgVzuDpbw== X-Received: by 10.36.41.76 with SMTP id p73mr3874473itp.127.1518191802713; Fri, 09 Feb 2018 07:56:42 -0800 (PST) Received: from ?IPv6:2601:404:300:fdea:55f2:e4de:3d4d:d8aa? ([2601:404:300:fdea:55f2:e4de:3d4d:d8aa]) by smtp.gmail.com with ESMTPSA id t76sm3246858iof.87.2018.02.09.07.56.41 for (version=TLS1_2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Fri, 09 Feb 2018 07:56:41 -0800 (PST) To: make-wifi-fast@lists.bufferbloat.net References: <87zia1n0zi.fsf@toke.dk> <87mv61mnhw.fsf@toke.dk> <87k215mn1u.fsf@toke.dk> <8eb5d9ff-ce18-b314-cfbe-ee4a6815ac9c@darbyshire-bryant.me.uk> <8760comfxj.fsf@toke.dk> <87o9qgutx3.fsf@toke.dk> From: Noah Causin Message-ID: <58c8a193-8452-6cd2-3e57-c28309afd858@gmail.com> Date: Fri, 9 Feb 2018 10:56:38 -0500 User-Agent: Mozilla/5.0 (Windows NT 10.0; WOW64; rv:52.0) Gecko/20100101 Thunderbird/52.6.0 MIME-Version: 1.0 In-Reply-To: <87o9qgutx3.fsf@toke.dk> Content-Type: multipart/alternative; boundary="------------B25FD341D66B3618C060AC84" Content-Language: en-US Subject: [Make-wifi-fast] ath10k latency under load? 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, 09 Feb 2018 15:56:43 -0000 This is a multi-part message in MIME format. --------------B25FD341D66B3618C060AC84 Content-Type: text/plain; charset=utf-8; format=flowed Content-Transfer-Encoding: 8bit Last year, mac80211 softqueues were re-enabled for ath10k devices in LEDE, which brought back fq_codel support, but did not improve latency under load. Is this latency under load still an issue today? Noah On 9/12/2017 5:51 AM, Toke Høiland-Jørgensen wrote: > Toke Høiland-Jørgensen writes: > >> Kevin Darbyshire-Bryant writes: >> >>> On 11/09/17 19:33, Adrian Popescu wrote: >>>> I've tried a bunch of setups: standard firmware, CT firmware, CT >>>> firmware with the patch and standard firmware with the patch. >>>> >>>> Both CT and default firmware have low throughput with this patch. >>> It's been committed in LEDE >>> https://git.lede-project.org/?p=source.git;a=commit;h=76c3a033f63aba10047a141ccdae303bc9db571e >> Ah! So it should be in current nightlies. I'll flash an Archer C7 and >> see if there are any issues. Anyone else care to test out the current >> nightly? :) > So testing it, I see no difference in throughput on my Archer C7; my > 802.11ac-capable phone gets ~200 Mbps and my 802.11n laptop around 80. > However, there's no improvement in latency under load either. Meh... > > Plot attached. > > -Toke > > > > _______________________________________________ > Make-wifi-fast mailing list > Make-wifi-fast@lists.bufferbloat.net > https://lists.bufferbloat.net/listinfo/make-wifi-fast --------------B25FD341D66B3618C060AC84 Content-Type: text/html; charset=utf-8 Content-Transfer-Encoding: 8bit Last year, mac80211 softqueues were re-enabled for ath10k devices in LEDE, which brought back fq_codel support, but did not improve latency under load.

Is this latency under load still an issue today?

Noah

On 9/12/2017 5:51 AM, Toke Høiland-Jørgensen wrote:
Toke Høiland-Jørgensen <toke@toke.dk> writes:


Kevin Darbyshire-Bryant <kevin@darbyshire-bryant.me.uk> writes:


On 11/09/17 19:33, Adrian Popescu wrote:

I've tried a bunch of setups: standard firmware, CT firmware, CT
firmware with the patch and standard firmware with the patch.

Both CT and default firmware have low throughput with this patch.

It's been committed in LEDE 
https://git.lede-project.org/?p=source.git;a=commit;h=76c3a033f63aba10047a141ccdae303bc9db571e

Ah! So it should be in current nightlies. I'll flash an Archer C7 and
see if there are any issues. Anyone else care to test out the current
nightly? :)

So testing it, I see no difference in throughput on my Archer C7; my
802.11ac-capable phone gets ~200 Mbps and my 802.11n laptop around 80.
However, there's no improvement in latency under load either. Meh...

Plot attached.

-Toke




_______________________________________________
Make-wifi-fast mailing list
Make-wifi-fast@lists.bufferbloat.net
https://lists.bufferbloat.net/listinfo/make-wifi-fast

--------------B25FD341D66B3618C060AC84--