From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-qt1-x843.google.com (mail-qt1-x843.google.com [IPv6:2607:f8b0:4864:20::843]) (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 4038B3B29E for ; Tue, 11 Dec 2018 13:38:05 -0500 (EST) Received: by mail-qt1-x843.google.com with SMTP id i7so17554877qtj.10 for ; Tue, 11 Dec 2018 10:38:05 -0800 (PST) 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=lLSH8CvUMgztVNyhPrbW5x0nQCt63cZ25ve8ABam30Q=; b=Ze2mUAER3F7Nnsrof6ETc/iLhPe64Z1US7qX0jMl/kEfj11frwGH7p+SosusyHANjt Mj4OgREmesNFmREGhJMR+Pk5cQMG0AAZk4SbEUH4Ca7x8hlKVqABUJ53kvyTWyHvO1rs stjbnfMMF1AJumCVJb8Q7khZGW29MceobK36cWT+8iRNp1kt2mBixuTdPJj8MJd21k2G kaThicb6ZINVRkPVBOgJmmWjNqjgajQw0KFU9p2E25ol37qGMM9B7ghEqOOYatqCPpeu QLOIAJEmUvzSag9JkOX/F9pVB3eadcVjIOiMoLFD9XK6h5Xq1Fu9xvk4o9+IG/IQQ/2G 302A== 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=lLSH8CvUMgztVNyhPrbW5x0nQCt63cZ25ve8ABam30Q=; b=OvXFaQNuZfi/qqF0CgurUCcUHVYUwyr0bMX5pzLMHPF1LCFn5jqktneo69HbbXd25W 4prBC7CXIZ/rCGU/5uRkD7rRJlnj0PIjQ1bgo7Yd1G2TTP7Buq2nwjDoKeSfIyg/QOaY Fe6Vp59jwEXjiR77FKSGoaDF7rxQTLfRQXuy50J8jUwdUnRY2ImLrkrTcToAfwPOvdKF DR27TXcyUbn0kM7aLww3j1CJJdGVMtTV9Fk7oWDwfmnyDuBo1VEJ7X7f1scicSGG/fMx pn2Gysn2J8Oc9gvBt9avwrNW531+UgGfrVzD/viwb6GFNLmJ1eP3KAqArZ04HkWs5gDF eyWg== X-Gm-Message-State: AA+aEWblkvklTbGDEt49tg8dE3uos/7JlXB8Afz/34QvUtoHjxeqnohE wD8mfwVAetrgpTY7QsOyAK5th4KhQH4OSfHenOA= X-Google-Smtp-Source: AFSGD/Unk1uBcKWHRkETsjGR+odLlWMt11wEFfXKuiv/kpitKHQVwAzkx8Lm81UXGSYNfFpvqf31USvBHiCF95VW1AY= X-Received: by 2002:ac8:326a:: with SMTP id y39mr17386838qta.175.1544553484671; Tue, 11 Dec 2018 10:38:04 -0800 (PST) MIME-Version: 1.0 References: <87bm5zgkkg.fsf@toke.dk> In-Reply-To: From: Dave Taht Date: Tue, 11 Dec 2018 10:37:51 -0800 Message-ID: To: Aaron Wood Cc: =?UTF-8?B?VG9rZSBIw7hpbGFuZC1Kw7hyZ2Vuc2Vu?= , cerowrt-devel Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable Subject: Re: [Cerowrt-devel] fq_pie for linux X-BeenThere: cerowrt-devel@lists.bufferbloat.net X-Mailman-Version: 2.1.20 Precedence: list List-Id: Development issues regarding the cerowrt test router project List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 11 Dec 2018 18:38:05 -0000 On Tue, Dec 11, 2018 at 10:32 AM Aaron Wood wrote: > > On Wed, Dec 5, 2018 at 11:51 PM Toke H=C3=B8iland-J=C3=B8rgensen wrote: >> >> Dave Taht writes: >> >> > https://github.com/gautamramk/FQ-PIE-for-Linux-Kernel/issues/2 >> >> With all the variants of fq+AQM, maybe decoupling the FQ part and the >> AQM part would be worthwhile, instead of reimplementing it for each >> variant... > > > That's a great idea, Toke. There are a lot of places where I think it co= uld work well, especially if it took a pluggable hash function for the hash= ing (at which point it's very general-purpose, and works on all sorts of di= fferent kinds of packets and workloads). That would let it be used for use= rspace VPN links (as an example), or within QUIC (or similar), where the ke= rnel can't see the embedded flows that are hidden by the TLS encryption. > > And having it pluggable in the kernel would also allow IPSec to work with= out bloat (last I checked it was horribly bufferbloated, but that was ~5 ye= ars ago). ipsec terminating on the router was made to work beautifully with fq_codel with this commit, below. Before: http://www.taht.net/~d/ipsec_fq_codel/oldqos.png After: http://www.taht.net/~d/ipsec_fq_codel/newqos.png It's why we keep hoping to do the same thing to wireguard. commit 264b87fa617e758966108db48db220571ff3d60e Author: Andrew Collins Date: Wed Jan 18 14:04:28 2017 -0700 fq_codel: Avoid regenerating skb flow hash unless necessary The fq_codel qdisc currently always regenerates the skb flow hash. This wastes some cycles and prevents flow seperation in cases where the traffic has been encrypted and can no longer be understood by the flow dissector. Change it to use the prexisting flow hash if one exists, and only regenerate if necessary. --=20 Dave T=C3=A4ht CTO, TekLibre, LLC http://www.teklibre.com Tel: 1-831-205-9740