From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-il1-x12d.google.com (mail-il1-x12d.google.com [IPv6:2607:f8b0:4864:20::12d]) (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 AA3BB3B29E for ; Sat, 25 Apr 2020 14:19:29 -0400 (EDT) Received: by mail-il1-x12d.google.com with SMTP id e8so12649187ilm.7 for ; Sat, 25 Apr 2020 11:19:29 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=mime-version:references:in-reply-to:from:date:message-id:subject:to :cc:content-transfer-encoding; bh=9fq91o0UUdUONgsy5r++eiciqPR3N1GYNzvc1DDIBb8=; b=Gjo97ZZZNaZjBFDnTmkBh496pW9b3eg3PhUfY/52B+bt8gvpgmel1Gvms42JQ75YIM bUC75gOlSIvFki3PvCnPX/BmzrIjh5Z9yz22UmkHQ+Usarz2yTFal0dWy/5kZ7YqYcFh h7xbetODiY6HAjrub1MNqqOGbQTRjiTXG/NNYp/6QnosiKPIjdv266/0RScd6h0YRsns nXmF/A4VX+lhjEweTgvnOLAoBPf2C1OeMAHJ4H1jNuKgRS+X+vOd6Q1s5Vi6URygHHLn /5nttH27B+f8JSrrR9uHVn1EXi00lr142vbjPwt70eimzTMgIXNvcQJVyhvxRThwytI4 VkiQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:references:in-reply-to:from:date :message-id:subject:to:cc:content-transfer-encoding; bh=9fq91o0UUdUONgsy5r++eiciqPR3N1GYNzvc1DDIBb8=; b=ap29SU2Gp31IhmHflI49e3Fc96nWgpipGo3nhzHCt3S+xtMHleCsF8kIqdtnf6kSSf 2Ms7GG7JR9TP6Osb580w6DpYbuuBURNRVqxQ88n7mtvb80yKkVSqEtkVsKtYt/FUl+lf IBOtGKnINKxniqEGJTrK2+9Mkj8T/ZB99kUaia+vEsvvMNtC+EU7+sln1olfrnvzB0I8 ZGSZfTQl1SkLRtJTUBn0kYfpot39wS6MNRoVj87snOX/YeQ71MkjMXpLIkzecDCB5UAj 99wKvPJQcRA8KIGdMGlDQJ1kRekM6/gVukOJkdjxASbuPuyCMVsInvZThr86uA1pBy6p +pEw== X-Gm-Message-State: AGi0PuYyK/HEm0kugc8VhFE6QoYO/NClf9WfFSSmaZ+yvIucEcYFa8Kh Yr7ig9H731LUbbEb0rCralGTO4nr8nmWa41GCng= X-Google-Smtp-Source: APiQypJ2g1YmAGWK4q4P3MLhY9rF3WWpeVeyvoZ04YzfbJayAnK00pzO+vvZnovXn0hXdiN+dNRzZyOC1fyEWafTQDo= X-Received: by 2002:a92:dccf:: with SMTP id b15mr13804270ilr.246.1587838769020; Sat, 25 Apr 2020 11:19:29 -0700 (PDT) MIME-Version: 1.0 References: <431A84397F3D9C1EB097BCCE@[172.27.17.193]> <6F1F3C646A7DFD2CC8C9E79E@172.27.17.193> <0B51625096F92AF18CD397D9@[172.27.17.193]> <8f4566dd-def0-cd97-45db-577784f90efd@sewingwitch.com> <9FDDBB5C-68CF-45B1-85D8-3A7BD6CB9F31@gmail.com> <3D2F4A70BAB1774D1EFDC641@[172.27.17.193]> <18E93BF9-44B0-444D-8B01-8210C9C85B5F@gmail.com> In-Reply-To: <18E93BF9-44B0-444D-8B01-8210C9C85B5F@gmail.com> From: Dave Taht Date: Sat, 25 Apr 2020 11:19:17 -0700 Message-ID: To: Jonathan Morton Cc: Y , bloat Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable Subject: Re: [Bloat] this explains speedtest stuff X-BeenThere: bloat@lists.bufferbloat.net X-Mailman-Version: 2.1.20 Precedence: list List-Id: General list for discussing Bufferbloat List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 25 Apr 2020 18:19:29 -0000 in /etc/config/sqm, with fq_codel, you need to uncomment or enter the following lines option ingress_ecn 'ECN' option egress_ecn 'ECN' I still am not much of an ecn fan. I use it primarily for debugging codel. :/ When I see marking, I know its working, and if I see loss where I shouldn't, I know something else in the stack is broken somewhere. Example - I ran into this while trying to get the ath10k performing sanely: https://forum.openwrt.org/t/aql-and-the-ath10k-is-lovely/59002/92 - dropping packets elsewhere in the stack. The "fix" got bidir throughput up by 10x, and it's still 4x lower than it could be for... unknown reasons. I worry a lot about checksummng problems and incorrect encapsulation. Hit that multiple times myself, and most recently a ddpk person hit it. "Look ecn's enabled!" but the actual receiver was dropping it instead because the checksum was wrong. I also hit it with 6 months of data from all over the world on osx. The second and successive runs of the rrul test disabled ecn neg attempts entirely for those ip addresses. I didn't figure it out until I sat down to write the paper and was agast at my packet captures. osx is completely useless for evaluating ecn behaviors given the heuristics in place on it today. Would love to have one valid windows + openvpn + fq_codel result. On Sat, Apr 25, 2020 at 10:37 AM Jonathan Morton wr= ote: > > > On 25 Apr, 2020, at 8:24 pm, Y via Bloat = wrote: > > > > ECN on > > http://www.dslreports.com/speedtest/62823326 > > ECN off > > http://www.dslreports.com/speedtest/62823112 > > Yup, that's what I mean. > > > doesn't appear to have worked. retransmits are still high. > > Ken, it might be that your version of fq_codel doesn't actually have ECN = support on by default. So try adding the "ecn" keyword to the qdisc. > > - Jonathan Morton > _______________________________________________ > Bloat mailing list > Bloat@lists.bufferbloat.net > https://lists.bufferbloat.net/listinfo/bloat --=20 Make Music, Not War Dave T=C3=A4ht CTO, TekLibre, LLC http://www.teklibre.com Tel: 1-831-435-0729