From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail.lang.hm (unknown [66.167.227.145]) (using TLSv1.2 with cipher ADH-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by lists.bufferbloat.net (Postfix) with ESMTPS id 8F3183B29D for ; Sat, 2 Apr 2022 21:05:56 -0400 (EDT) Received: from dlang-mobile (unknown [10.2.2.69]) by mail.lang.hm (Postfix) with ESMTP id 6BBFA129119; Sat, 2 Apr 2022 18:05:55 -0700 (PDT) Date: Sat, 2 Apr 2022 18:05:55 -0700 (PDT) From: David Lang To: Dave Taht cc: biz.tinalee@gmail.com, bloat In-Reply-To: Message-ID: References: MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII; format=flowed Subject: Re: [Bloat] less than best effort: TCP - flexis - A New Approach To Incipient Congestion Detection and Control 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: Sun, 03 Apr 2022 01:05:56 -0000 On Sat, 2 Apr 2022, Dave Taht wrote: > I have always disagreed with the "don't reduce segment size" crowd, > btw. If you have a rate where you need to go below 2mss, it doesn't > hurt the network to reduce the size of the packet, and you can keep > the signal strength up by reducing that size and continuing to sample > rtt, to respond quickly. > > Even if you are only passing a single byte of data, by lowering this > below everyone else's 2mss noise floor, you still eventually win, and > also you occupy space in packet fifos, reducing overall latency, as > bytes=time. IMHO. this ignores per-packet overhead (which is headers + inter-packet time). As data rates get faster, the inter-packet time is not shrinking to match. This is especially true in wifi where the headers are transmitted at a much slower speed than the data for compatibility reasons (as there may be many different data rates on any channel), but it still applies to wired networks. David Lang