From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-pf0-x234.google.com (mail-pf0-x234.google.com [IPv6:2607:f8b0:400e:c00::234]) (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 83B143BA8E; Wed, 29 Nov 2017 19:21:28 -0500 (EST) Received: by mail-pf0-x234.google.com with SMTP id d23so2318311pfe.9; Wed, 29 Nov 2017 16:21:28 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=message-id:subject:from:to:cc:date:in-reply-to:references :mime-version:content-transfer-encoding; bh=1JowrMKaxHINRuzYU5OevVRVe7nLyvA6qMiXmPz6q6U=; b=BVma6oCyzHBObYyZXVoiDOpjKYps7cnujCwt87kjmmY+NQV3oPEjzsKrFgn/Rw8FfF Eqf4QQw/nbixJF0Eei+FITmtWZ1ymwyAlxo0kAcEOmRET/Rn9Bokc9Nfhx9b8z/Loxap Y7W9dDLqZ3TY5IGGaqYGpRg7cj4Y4EArFsxROeauJ9wuVGBWiuNvlZ3mlnoI4P//QIQr +UNiWp/qfHpIyUHzvs2YsnZdxNUc4f7v92Hc6IX8iFSRvmQUJuSxq0+9iekaBZi/6dHW GSWl1ob9HYmGu9HhEPeXGWcNgh4iUieQBHEeZt0bkyYaSTlpbRqfrzEAqoNqaZl85I8c ApEQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:message-id:subject:from:to:cc:date:in-reply-to :references:mime-version:content-transfer-encoding; bh=1JowrMKaxHINRuzYU5OevVRVe7nLyvA6qMiXmPz6q6U=; b=Gmh11w9BxF28PQfaXXaHm12GZvbSWfXE8bNLfNxahoMG5u4Alvu2tVQgV/aTnoVXD3 nhFSMe1ZRsCWgcpIs9M4/uoXxmUEoH0+bbgA7CucR9cMKq/UX0dG/I59TdDM/bViqZXl hXdHtCTKs4gIucMkefWbeX2KBwyS2zpNtkhNo7SKYow9fNbYb4R3SatDzh+H0ZeGeP5F X+EF6LsKE7UlIeZ4Dr0VJbxcWXdthgqvQGSj1qjm99xaYNC6PISeBr0zEt90/MfmkhUz hc/En8frpYumjVg2AlQX8Y+iubvZ2650Wz00C/3wvJiUYFWI6PvC1H7sFCBTWD8bs0We rsyg== X-Gm-Message-State: AJaThX5rbIv6NYkumhaz2KDC23r7PrNJkIpcO55MuUFOlW4znGMgLYD4 ij+lkq8cKznl8Lv7BLWfGdA= X-Google-Smtp-Source: AGs4zMZGj1cXiPoLlOBhz8iBsoEcQfnehH6w24WHZVtwwLuY6dV0sYvBMgVe+xMZgkomcyWGr2IMdQ== X-Received: by 10.101.82.65 with SMTP id q1mr631714pgp.55.1512001287702; Wed, 29 Nov 2017 16:21:27 -0800 (PST) Received: from [10.1.104.90] ([207.198.105.19]) by smtp.googlemail.com with ESMTPSA id b6sm3953110pfe.57.2017.11.29.16.21.26 (version=TLS1_2 cipher=ECDHE-RSA-CHACHA20-POLY1305 bits=256/256); Wed, 29 Nov 2017 16:21:27 -0800 (PST) Message-ID: <1512001284.19682.1.camel@gmail.com> From: Eric Dumazet To: Stephen Hemminger , Dave Taht Cc: Cake List , Juliusz Chroboczek , bloat Date: Wed, 29 Nov 2017 16:21:24 -0800 In-Reply-To: <20171129155917.63d51add@xeon-e3> References: <7i1skhrln1.wl-jch@irif.fr> <20171129155917.63d51add@xeon-e3> Content-Type: text/plain; charset="UTF-8" X-Mailer: Evolution 3.22.6-1+deb9u1 Mime-Version: 1.0 Content-Transfer-Encoding: 8bit Subject: Re: [Bloat] benefits of ack filtering 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: Thu, 30 Nov 2017 00:21:28 -0000 On Wed, 2017-11-29 at 15:59 -0800, Stephen Hemminger wrote: > On Wed, 29 Nov 2017 10:41:41 -0800 > Dave Taht wrote: > > > On Wed, Nov 29, 2017 at 10:21 AM, Juliusz Chroboczek > > wrote: > > > > The better solution would of course be to have the TCP peeps > > > > change the > > > > way TCP works so that it sends fewer ACKs.   > > > > > > Which tends to perturb the way the TCP self-clocking feedback > > > loop works, > > > and to break Nagle.   > > > > Linux TCP is no longer particularly ack-clocked. In the post > > pacing, > > post sch_fq world, packets are released (currently) on a 1ms > > schedule. > > Support was recently released for modifying that schedule on a per > > driver basis, which turns out to be helpful for wifi. > > > > see: https://www.spinics.net/lists/netdev/msg466312.html > > Also TCP BBR has lost its initial luster since it is unfair and > ignores > losses and ECN (see recent netdev paper). Recent netdev paper (from Larry) mentioned that fq_codel is used. fq_codel is stochastic, so not a fairness champion with many flows. There is a reason we use fq [1] instead ;) We asked Larry how to reproduce his (surprising) results, because we suspect some setup error or bias. He has to update his github trees. netem can be tricky to use properly. [1] Although the choice of packet scheduler is no longer an issue with BBR now TCP can fallback to internal pacing implementation. About ECN : We do not enable ECN for edge communications, so BBR runs without ECN being negotiated/accepted. We will probably take care of this point soon, but we had more urgent problems.