From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-we0-x229.google.com (mail-we0-x229.google.com [IPv6:2a00:1450:400c:c03::229]) (using TLSv1 with cipher RC4-SHA (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority G2" (verified OK)) by huchra.bufferbloat.net (Postfix) with ESMTPS id 68EF921F18C for ; Sun, 29 Dec 2013 05:52:25 -0800 (PST) Received: by mail-we0-f169.google.com with SMTP id w61so9564676wes.28 for ; Sun, 29 Dec 2013 05:52:23 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type:content-transfer-encoding; bh=fPNdE25kJYqLwzMZguKF4xJyDfLrSek8My8q4V1QOFE=; b=YhuWdhwSnBxXoyOYb1dOzEJGBtG5T5lZFuy3Mz+TbtKNmkOgF43Ui4puv6LIs6nTwh 6OEndtzSXwOnxMwgirXTrymcUFpESb6YlPwFZsApaF/GGR5cPE1RJGm3ENGETtwwwVXr wixqkgvE7Lut9yYJLEJPO0LiOL6H33dBEC4KnR61L5t5g2kZmtWfV8cXH+K08DmPsVYf M3CiZIcPbcpJhqOqr4L3y0lE1uRiveneLSgjBwKrIXcw2jJLbfPT8lH4golZDjlcZ96P zezZKoD3W2YW1xIJX12bY2bj5WgGrNtF9OIzEAILuSL5+SX8W1NzANNc467JRxhu5hOc YqGQ== MIME-Version: 1.0 X-Received: by 10.180.95.162 with SMTP id dl2mr40777057wib.17.1388325143474; Sun, 29 Dec 2013 05:52:23 -0800 (PST) Received: by 10.217.123.69 with HTTP; Sun, 29 Dec 2013 05:52:23 -0800 (PST) In-Reply-To: References: <54B228A1-9362-4CC5-BDC6-C8968A5DDE94@gmail.com> Date: Sun, 29 Dec 2013 05:52:23 -0800 Message-ID: From: Dave Taht To: Sebastian Moeller Content-Type: text/plain; charset=windows-1252 Content-Transfer-Encoding: quoted-printable Cc: cerowrt-devel Subject: Re: [Cerowrt-devel] SQM Question #3: How shall we recommend people set their upload/download speeds? X-BeenThere: cerowrt-devel@lists.bufferbloat.net X-Mailman-Version: 2.1.13 Precedence: list List-Id: Development issues regarding the cerowrt test router project List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 29 Dec 2013 13:52:25 -0000 On Sun, Dec 29, 2013 at 3:46 AM, Sebastian Moeller wrote: > Hi list, > On Dec 29, 2013, at 09:53 , Dave Taht wrote: > >> On Sat, Dec 28, 2013 at 8:33 PM, Rich Brown wr= ote: >>> QUESTION #3: How shall we recommend people set their upload/download sp= eeds? >>> >>> Although we have already spent a lot of time on the list batting around= ways to think about this, it seems to me that there are only two choices f= or recommendations, especially given that most people looking at CeroWrt ar= e in a =93TL;DR=94 mind set: >> >> What does TL;DR mean? > > Too Long; Didn't Read... Hah. I've seen this abbreviation a lot recently, but I thought it was wayward HTML! >> >>> 1) If you don=92t have an accurate sense of your actual link speed (e.g= ., you haven=92t done a link speed measurement), you should take your provi= der=92s published specs, knock them down by 15%, and enter those values in = the SQM Basic Settings tab. [Or should they take an additional 15% off that= already reduced value?] >> >> 92% on the up, 85% on the down are starting points. >> >>> >>> 2) If you have done measurements of your link speed, you should enter v= alues that are 95% of each direction=92s measured speed. >>> >>> Is this the right recommendation? > > That is what I thought, but it seems 95% was too optimistic=85 I = have found that ShaperProbe's (http://www.measurementlab.net/tools/shaperpr= obe) capacity estimate is pretty good at least for the low speeds I could t= est. > > >> A short rant on the inadaquacy of speedtest and other tests would be >> nice. Netanalyzr is the closest thing to a good test these days but it >> requires java and is inaccurate above 20mbit. > > The problem is that no one really wants to supply the large amoun= t of bandwidth required that everyone can max out their download long enoug= h for a reasonable test; this is why an often read recommendation is to use= curl or wget to concurrently down or up load large files from several beef= y servers, to actually be able to assess the local link capacity. The only = redeeming feature of seediest and friends is, that underestimating the avai= lable link capacity will lead to decent latency and lean buffers :). I do think the best way to get an estimate is to load up with multiple streams going to multiple servers. Needent be tcp.... but there I'd long hoped to get a grip on drop patterns and extrapolate from that. > > best > Sebastian > >> >>> >>> NB: In the Details=85 section, we can recommend ways to measure current= link speeds, encourage people to make the measurement during quiet times, = link to the =93Quick test for Bufferbloat=94 page, etc. for those who want = to dig further. >>> _______________________________________________ >>> Cerowrt-devel mailing list >>> Cerowrt-devel@lists.bufferbloat.net >>> https://lists.bufferbloat.net/listinfo/cerowrt-devel >> >> >> >> -- >> Dave T=E4ht >> >> Fixing bufferbloat with cerowrt: http://www.teklibre.com/cerowrt/subscri= be.html >> _______________________________________________ >> Cerowrt-devel mailing list >> Cerowrt-devel@lists.bufferbloat.net >> https://lists.bufferbloat.net/listinfo/cerowrt-devel > --=20 Dave T=E4ht Fixing bufferbloat with cerowrt: http://www.teklibre.com/cerowrt/subscribe.= html