From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-pl0-x241.google.com (mail-pl0-x241.google.com [IPv6:2607:f8b0:400e:c01::241]) (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 E33693BA8E for ; Fri, 18 May 2018 11:20:02 -0400 (EDT) Received: by mail-pl0-x241.google.com with SMTP id az12-v6so4767599plb.8 for ; Fri, 18 May 2018 08:20:02 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=subject:to:cc:references:from:message-id:date:user-agent :mime-version:in-reply-to:content-language:content-transfer-encoding; bh=v09rNxW7mo85JBxNM68p7wT8VYpcaRc+cFV+vsJTWfc=; b=u8BimWtv9u1kp+lIed8Zl7DDRvTpTXuQb2OBqrdKbIqWgZ+dw5igRPv+TDwOdwCfnQ BRM1/Ss6uuzec+YwGJ281fEhXj+1oj+zHz4RvlryI3CmR4e+wtFwhx+fw4tV9P8oe3rN CigFvjzQPxmZSIWqfmlxnQZ0j7TLrrVSG7wUwaVy5xYdw5+Gg856FcIf0GvoTzg38Xlr 02NPAOdPdTopISoyLe/fEEZwkvdTarr/SI0BMEynXeADUENdWKq6C5ECPG5U3s8MsDWe rnG7z8G880MHtdQLa5gW7CsvBhfZQG8X9fJotzFr4OsUHY0aUBdjlEJ9rCeMl5QXNX/Y tnqA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:subject:to:cc:references:from:message-id:date :user-agent:mime-version:in-reply-to:content-language :content-transfer-encoding; bh=v09rNxW7mo85JBxNM68p7wT8VYpcaRc+cFV+vsJTWfc=; b=iw+TGZMrIvBt4DcSIgwmH3uOtCngXQYu81ekjPA9Q5ZAE9j1CFR9WGAoCpofSNQFe8 bDqxIKzPoFA/2EKe0HlgpK2sR0Vni/a5v+wZ2UaNAQ1FXzmOjxxdqr+L1G6NgIBfJbB8 xKHa0sX6SAk+im9kHIRko/fSVBTrSpEFZveco37/PlC+4EylBpSJ/+lhkb5eEBKvymAk fjb4JvE4J56p4xthDqkIqEAn9yWHcdnroKWdcHyAKkbB0296EsCDh0niiP3lfA86RIpZ ePQ5MPi2uw6k4mvboa319Tml1cS20q23zuzNRtfNkN30+ch3VzINcOsiu50PX6QpPJBN dBoQ== X-Gm-Message-State: ALKqPwf1goqRwi0Pn4H1GbOjUjhWK6kk5zhnTrivJYSMw41Wf+v0sbBG Xl6/X5L/vke5liRbl9WCD98= X-Google-Smtp-Source: AB8JxZqrky/dxefumg5WuJsrzBHAXgN0dBUAax1qgcCHjBBiqihvKK6+QUBUb5bc7Gmx+i6mFUAnRw== X-Received: by 2002:a17:902:2826:: with SMTP id e35-v6mr9960385plb.348.1526656802225; Fri, 18 May 2018 08:20:02 -0700 (PDT) Received: from [192.168.86.235] (c-67-180-167-114.hsd1.ca.comcast.net. [67.180.167.114]) by smtp.gmail.com with ESMTPSA id n10-v6sm17756603pfj.68.2018.05.18.08.20.00 (version=TLS1_2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Fri, 18 May 2018 08:20:01 -0700 (PDT) To: Kevin Darbyshire-Bryant , Cong Wang Cc: =?UTF-8?Q?Toke_H=c3=b8iland-J=c3=b8rgensen?= , Cake List , Linux Kernel Network Developers , Eric Dumazet References: <152650253056.25701.10138252969621361651.stgit@alrua-kau> <152650254614.25701.1377066681230937234.stgit@alrua-kau> <87in7my196.fsf@toke.dk> <05E1D675-B73B-4409-8991-EB89D5538EAB@darbyshire-bryant.me.uk> From: Eric Dumazet Message-ID: <9a29f298-410e-c8cb-9b7a-8e80c0450f71@gmail.com> Date: Fri, 18 May 2018 08:20:00 -0700 User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:52.0) Gecko/20100101 Thunderbird/52.6.0 MIME-Version: 1.0 In-Reply-To: <05E1D675-B73B-4409-8991-EB89D5538EAB@darbyshire-bryant.me.uk> Content-Type: text/plain; charset=utf-8 Content-Language: en-US Content-Transfer-Encoding: 8bit Subject: Re: [Cake] [PATCH net-next v12 3/7] sch_cake: Add optional ACK filter X-BeenThere: cake@lists.bufferbloat.net X-Mailman-Version: 2.1.20 Precedence: list List-Id: Cake - FQ_codel the next generation List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 18 May 2018 15:20:03 -0000 On 05/18/2018 04:18 AM, Kevin Darbyshire-Bryant wrote: > > Speaking as a user of cake’s ack filtering, although it may be an odd place, it is incredibly useful in my linux based home router middle box that usefully extracts extra usable bandwidth from my asymmetric link. And whilst ack compression/reduction/filtering call it what you will, will come to the linux TCP stack, as yet other OS stacks are less enlightened and benefit from the router’s tweaking/meddling/interference. > > Kevin, there is no doubt the feature might be useful. But it has to be properly implemented, or we risk to block future TCP improvements. An ACK filter MUST parse the TCP options. 1) If some options can not be understood, ACK MUST not be dropped. 2) SACK options MUST be carefully analyzed 3) Timestamps also need some care. Too many middle-boxes are breaking TCP, we do not want to carry another TCP blackhole in upstream linux, that would be a shame. conntrack had bugs that seriously impacted TCP Fastopen deployment for example.