From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-il1-x12b.google.com (mail-il1-x12b.google.com [IPv6:2607:f8b0:4864:20::12b]) (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 9D21C3B29D for ; Fri, 15 May 2020 12:25:43 -0400 (EDT) Received: by mail-il1-x12b.google.com with SMTP id w18so3081265ilm.13 for ; Fri, 15 May 2020 09:25:43 -0700 (PDT) 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=z+1BAUr4t1gX+s6Q+3NGur7BxvkXB0tQYT0u1DpO/+I=; b=Q+fMW9rpNTzUMgDvzP9maygCy2NnltNpkfQEO0kFgeRV2nZkbaO7npyZGOHSOqptMP CHAnzJjhxx7opn++eETNcLI+Hn5QKryCgTKPNKsYKoibi9UzP1FfaRkVSLEY7NFgQsx8 vUEvolyBOoVrrpmHUW1RLzBuAKGhdQftLz5FQZ16LecIB5LKzVvgcyJTql7rXLCZ0HX8 FLyNNG2hDL90AmKvtekmUi1Xj2PiDTxoThBP8mEELqiG2BekWprykIeDCTnGaM56NNXV A3D1g9hzTCYwP3v7rVp7VTGK/Q+SvXJklX2xNscEZFuXUcGpgHPLbMHnvyIyBFHsiOuY PIEQ== 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=z+1BAUr4t1gX+s6Q+3NGur7BxvkXB0tQYT0u1DpO/+I=; b=M/0oTEU+rEdQJazAaiDhCvlG6TyHBCR7yk4A4r/RL+N3ExrgADZeOrJvdtyo1pOfDK l6ZoUagaRUH+HY9ceRgZy2GKuGQ4/3Ins+5WaGvrCvJYoUas6K6ka9g4Ac/H8NazLhin Xfgov5ZjCSt+AyxOno4ugaPz1Tu8bPthS9EzqKSCScUYIKvUzddPgfgDpasZnC5BRAGc z6TDhQACi5pW8QsMoa+Gn6AHRZB0VKTXqv1pm+F97hEPLmw24XD9JG0oo3aGypEj0YYN DMXUrdqfXsqc9510q6VNSsBgoLW2fPYX7Lg7c9r0arIZmJXvZT3EblWDabz8NiOliPOR bj4Q== X-Gm-Message-State: AOAM532UIvPjoAdhaM8EMvL5KwyfPVMz6JANeHtefGs5GNZWI3vOf9C4 K9zr/5yzCTRLam2GV2sZPCdePTqMf8WvpNhnbf0= X-Google-Smtp-Source: ABdhPJxvyXeMBYnQHH/UnlElRvgUdBfoLixjTItjSrQSc7UqFitSDs68BKMC2S6HBtl+5/CqlLnDtajXqKkw9fAHNWI= X-Received: by 2002:a92:af84:: with SMTP id v4mr4382744ill.45.1589559943082; Fri, 15 May 2020 09:25:43 -0700 (PDT) MIME-Version: 1.0 References: <56a03e99-3337-bf4a-4743-deb93abb9592@smallnetbuilder.com> <29e9babb-b894-635d-4e60-332324d35565@timhiggins.com> In-Reply-To: <29e9babb-b894-635d-4e60-332324d35565@timhiggins.com> From: Dave Taht Date: Fri, 15 May 2020 09:25:31 -0700 Message-ID: To: Tim Higgins Cc: Erkki Lintunen , Make-Wifi-fast Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable Subject: Re: [Make-wifi-fast] SmallNetBuilder article: Does OFDMA Really Work? X-BeenThere: make-wifi-fast@lists.bufferbloat.net X-Mailman-Version: 2.1.20 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 15 May 2020 16:25:43 -0000 On Fri, May 15, 2020 at 8:34 AM Tim Higgins wrote: > > Hi Erkki, > > Thanks for your comments. > > A simple test is exactly what I'm after. The Part 1 article was basically= a look behind the scenes to describe why I used the benchmark I did for th= e Part2 article. It will compare an AC router and multiple AX routers. If t= here's an off-the-shelf consumer router with that implements SQM/cake on Wi= -Fi, I'm happy to try it. I have an evenroute IQrouter here, but I'm not su= re if it implements SQM on Wi-Fi. I'll ask. "SQM" isn't the thing. SQM is for better managing the ISP uplinks/downlinks= . it's the fq_codel and aqm scheduler for wifi. I'm under the impression that the evenroute v2 production version now has some of the aql/fq_codel related code backported to it. I've been off tuning that up over here: https://forum.openwrt.org/t/aql-and-the-ath10k-is-lovely/ but that code has not made it back into mainline. v3 has long had it, but was never optimized properly because I didn't have one. Still I've never had a testbed as nice as yours, it would be great, absolutely great, to get some feedback on your methods you are applying to see how decent it is today! :) The principal mis-feature in the current codebases for openwrt in wifi's case is some code we left in there keeping the codel target too high for 5ghz wifi, and far too large hw retries in the firmware and driver for these two chipsets. However there is no express supportfor mu-mimo in our versions as, like you, we discoverd the concept didn't work - and couldn't ever work as designed - so we discarded it in favor of better per station scheduling in the first place. https://arxiv.org/pdf/1703.00064.pdf There were so many things left unfinished in that project. We could have handled 802.11e much better than we do. --=20 "For a successful technology, reality must take precedence over public relations, for Mother Nature cannot be fooled" - Richard Feynman dave@taht.net CTO, TekLibre, LLC Tel: 1-831-435-0729