From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from uplift.swm.pp.se (swm.pp.se [212.247.200.143]) (using TLSv1.2 with cipher ADH-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by lists.bufferbloat.net (Postfix) with ESMTPS id D842A3CB4B; Wed, 20 Mar 2019 10:28:32 -0400 (EDT) Received: by uplift.swm.pp.se (Postfix, from userid 501) id 6EFE7B0; Wed, 20 Mar 2019 15:28:31 +0100 (CET) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=swm.pp.se; s=mail; t=1553092111; bh=ufXTYVtIec75DCMKZZXCg30o8lTLNsLVqVnipyPDgt4=; h=Date:From:To:cc:Subject:In-Reply-To:References:From; b=M3P0hPsokVhl73RsaPy3ojNKS0plkpgn02ZZZPhfzNuGYcmFIzL1szWJdc+O5rpJd NG0QyCzCfDPbzOPxqd5t1PbwnUWcDznd+ifrZtSlvY6uVk7CWuMZP1UU5jujx5D0BO 4I8maJP3YTUgZ2zK14gPJvOZMQnxn3Gn24Oz2Nn0= Received: from localhost (localhost [127.0.0.1]) by uplift.swm.pp.se (Postfix) with ESMTP id 6CE1DAF; Wed, 20 Mar 2019 15:28:31 +0100 (CET) Date: Wed, 20 Mar 2019 15:28:31 +0100 (CET) From: Mikael Abrahamsson To: Dave Taht cc: ecn-sane@lists.bufferbloat.net, bloat , Cake List In-Reply-To: Message-ID: References: User-Agent: Alpine 2.20 (DEB 67 2015-01-07) Organization: People's Front Against WWW MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII; format=flowed Subject: Re: [Cake] [Ecn-sane] My (controversial) position paper on TCP 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: Wed, 20 Mar 2019 14:28:33 -0000 On Mon, 18 Mar 2019, Dave Taht wrote: > Another ietf idea that makes me crazy is the motto of "no host changes" > in homenet, and "dumb endpoints" - when we live in an age where we have > quad cores and AI coprocessors in everybody's hands. This isn't a resource problem, it's a code problem. The IETF wants 10-15 year old hosts to be able to connect to a network and perform basic networking. It might not be very optimized, but the basic function should be there. New functionality can optimize for different factors, but making older host stop working is frowned upon. If the endpoints are going to be smarter (and they will, question is how fast), how do we keep the smarts updated with new functionality? TCP does the same thing, it wants to be backwards compatible and that's why QUIC has been more free to innovate in some fashions. I also believe it's perhaps time to cut TCP off and come up with something new, the bad part is that it seems all innovation then has to be done over UDP which has its own drawbacks (because of NATs). -- Mikael Abrahamsson email: swmike@swm.pp.se