From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mout.gmx.net (mout.gmx.net [212.227.17.20]) (using TLSv1 with cipher DHE-RSA-AES128-SHA (128/128 bits)) (Client CN "mout.gmx.net", Issuer "TeleSec ServerPass DE-1" (verified OK)) by huchra.bufferbloat.net (Postfix) with ESMTPS id 1C64521F19C for ; Sat, 11 Jan 2014 11:57:52 -0800 (PST) Received: from hms-beagle-3.home.lan ([217.254.130.56]) by mail.gmx.com (mrgmx001) with ESMTPSA (Nemesis) id 0MIe0O-1W4Hc43xTk-002DTf for ; Sat, 11 Jan 2014 20:57:41 +0100 Content-Type: text/plain; charset=windows-1252 Mime-Version: 1.0 (Mac OS X Mail 6.6 \(1510\)) From: Sebastian Moeller In-Reply-To: <10B5A5C1-A4D7-429D-A57D-21612B5169E1@gmail.com> Date: Sat, 11 Jan 2014 20:57:40 +0100 Content-Transfer-Encoding: quoted-printable Message-Id: <4E5E2FFE-3842-4E83-AEC7-B77E690BFB1D@gmx.de> References: <4B0976EC-5224-4E81-B5DF-96A85424FB6E@gmail.com> <49DBDBE7-BF76-4823-B723-670935A55833@gmx.de> <10B5A5C1-A4D7-429D-A57D-21612B5169E1@gmail.com> To: Rich Brown X-Mailer: Apple Mail (2.1510) X-Provags-ID: V03:K0:rSmGPvnVPAD4n7YyfaHXrgvSm4FgYWsKR/JYrQLJ13uZ1NKkZkj J/N55fRj6tV7No0KtyIG7V5XoVkRIp0J3L2cTWWGSQ6oHxWeTian/wRvolS4HX4ql4WHAxo scmAPMR212MBB0RgzxdaMArphIs5VOTueEgXJAhkbz9Cew795kQhRVj4VHXTGLIr4bQ7E94 uSIL6Oa8POc/oBga59kjw== Cc: cerowrt-devel Subject: Re: [Cerowrt-devel] VDSL 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: Sat, 11 Jan 2014 19:57:57 -0000 X-List-Received-Date: Sat, 11 Jan 2014 19:57:57 -0000 Hi Rich, On Jan 11, 2014, at 20:06 , Rich Brown wrote: > Hi Sebastian, >=20 >>>> Well, that looks like a decent recommendation for the wiki. The = SQM configuration page still needs to expose all three values, atm, = ethernet, and none so that people can actually change things... >>>=20 >>> So two questions really: >>>=20 >>> 1) (=46rom my previous note) What=92s the difference between the = current =93Ethernet=94 (for VDSL) and =93None=94 link layer adaptations? >>=20 >> Currently, "none" completely disables the link layer = adjustments, "ethernet" enables them, but will only use the overhead = (unless you specify an tcMPU, but that is truly exotic). >>=20 >>>=20 >>> 2) When we distinguish the Ethernet/VDSL case, I would really like = to use a different name from =93Ethernet=94 because it seems confusingly = similar to having a real Ethernet path/link (e.g., direct connection to = internet backbone without any ADSL, cable modem, etc.)=20 >>=20 >> On the one hand I agree, but the two options are called "ATM" = (well for tc "adsl" is a valid alias for ATM) and "ethernet" if you pass = them to tc (what we do), and I would really hate it to hide this under = fancy names. I see no chance of renaming those options in tc, so we are = sort of stuck with them and adding another layer of indirection seems = too opaque to me. This is why I put some explanation behind the option = names in the list box=85 >=20 > Now I see how it works. (I didn=92t understand that =93None=94 really = meant NONE.) Ah, I see, the reason most likely is that initially I had it set = up differently, and only later I realized that there are only three = relevant states... > The following choices in the Link Layer Adaptation would have eased my = confusion: >=20 > - ATM (almost every type of ADSL or DSL) Question, for me DSL is short hand for SDSL, ADSL, and VDSL, but = i take it too mean whatever the ISP put in the product name so most = likely ADSL, is that correct? > - Ethernet with overhead > - None (default) >=20 > Then the text can say: >=20 > =97 > You must set the Link Layer Adaptation options so that CeroWrt can = perform its best with video and audio chat, gaming, and other protocols = that rely on short packets. The general rule for selecting the Link = Layer Adaption is:=20 >=20 > * If you use any kind of DSL/ADSL connection to the Internet (that is, = if you get your internet service through the telephone line), you should = choose the =93ATM (almost every type of ADSL or DSL)" item. Set the = Per-packet Overhead to 44.=20 Sounds like a reasonable default, we only sacrifice a bit of = bandwidth but keep the latency spiffy. >=20 > * If you know you have a VDSL connection, you should choose =93Ethernet = with overhead" and set the Per-packet Overhead to 8.=20 This depends on whether there is PPPoE in use (then 8 seems = correct), I do not know about potential ethernet heads or VLAN headers, = so * might be too small. Also I have not seen much data whatsoever from = a VDSL link so I really have no good handle on this (except Germany's = lardiest ISP uses PPPoE). Note I might switch to VDSL later this year, = then I can see (if I manage to get anything useful out of non ATM links, = my overhead detector critically relies on ATM cell quantization) >=20 > * If you use Cable modem, Fiber, or another kind of connection to the = Internet, you should choose =93None (default)=94. All other parameters = will be ignored. I think this is the status quo; I have no data to argue any = change here (I have an intuition though that most likely all of these = will also suffer from additional per packet overhead by virtue of being = shared media). >=20 > If you cannot tell what kind of link you have, first try using "None", = then run the [[Quick Test for Bufferbloat]]. If the results are good, = you=92re done. I will ned to test this with link layer disabled, to better = describe what to expect. I fear a typical speediest.net test will not = show ATMs small packet volatility; so there might be need for a = dedicated test... > Next, try the ADSL/ATM choice, then the VDSL choice to see which = performs best. Read the **Details** (below) to learn more about tuning = the parameters for your link.=20 > =97 >=20 > Would that be better? Thanks. Oh, I think that is quite reasonable and helpful. Now I need to = put more information into the **Details** Best Sebastian >=20 > Rich