From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from smtp105.iad3a.emailsrvr.com (smtp105.iad3a.emailsrvr.com [173.203.187.105]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by lists.bufferbloat.net (Postfix) with ESMTPS id E40A73CB35 for ; Wed, 20 Jun 2018 10:28:05 -0400 (EDT) Received: from smtp22.relay.iad3a.emailsrvr.com (localhost [127.0.0.1]) by smtp22.relay.iad3a.emailsrvr.com (SMTP Server) with ESMTP id A622C68AF; Wed, 20 Jun 2018 10:28:05 -0400 (EDT) X-SMTPDoctor-Processed: csmtpprox beta Received: from smtp22.relay.iad3a.emailsrvr.com (localhost [127.0.0.1]) by smtp22.relay.iad3a.emailsrvr.com (SMTP Server) with ESMTP id 9D8AC68CF; Wed, 20 Jun 2018 10:28:05 -0400 (EDT) Received: from app56.wa-webapps.iad3a (relay-webapps.rsapps.net [172.27.255.140]) by smtp22.relay.iad3a.emailsrvr.com (SMTP Server) with ESMTP id 7E82068AF; Wed, 20 Jun 2018 10:28:05 -0400 (EDT) X-Sender-Id: MAILER-DAEMON Received: from app56.wa-webapps.iad3a (relay-webapps.rsapps.net [172.27.255.140]) by 0.0.0.0:25 (trex/5.7.12); Wed, 20 Jun 2018 10:28:05 -0400 Received: from deepplum.com (localhost.localdomain [127.0.0.1]) by app56.wa-webapps.iad3a (Postfix) with ESMTP id 69AB4A0461; Wed, 20 Jun 2018 10:28:05 -0400 (EDT) Received: by apps.rackspace.com (Authenticated sender: dpreed@deepplum.com, from: dpreed@deepplum.com) with HTTP; Wed, 20 Jun 2018 10:28:05 -0400 (EDT) Date: Wed, 20 Jun 2018 10:28:05 -0400 (EDT) From: "dpreed@deepplum.com" To: "Sebastian Moeller" Cc: "Kevin Darbyshire-Bryant" , "Jonathan Morton" , "cerowrt-devel@lists.bufferbloat.net" , "bloat" MIME-Version: 1.0 Content-Type: text/plain;charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Message-ID: <1529504885.43062717@apps.rackspace.com> X-Mailer: mobile/6.0.2 Subject: Re: [Cerowrt-devel] [Bloat] Invisibility of bufferbloat andits remedies X-BeenThere: cerowrt-devel@lists.bufferbloat.net X-Mailman-Version: 2.1.20 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: Wed, 20 Jun 2018 14:28:06 -0000 The best is the enemy of the pretty good. Isn't there some cumulative lag under load statistic that can be maintained= by a pinger sampling lag as a function of current rate (upload and downloa= d)? The Pinger would only ping when load is above a threshold, and only cou= nt data as valid if load during ping remains above threshold. If you scatter plot lag times as a function of current load load, there sho= uld be a very obvious knee very visible at just above the optimal control l= imit.=20 In Luci, this plot could be shown, covering time since last adjustment. The= user then can see what rate to use, and also evidence of the problem. Just= one plot and one setting. -----Original Message----- From: "Sebastian Moeller" Sent: Wed, Jun 20, 2018 at 4:07 am To: "Kevin Darbyshire-Bryant" Cc: "Kevin Darbyshire-Bryant" , "Jonathan Mo= rton" , "cerowrt-devel@lists.bufferbloat.net" , "bloat" Subject: Re: [Cerowrt-devel] [Bloat] Invisibility of bufferbloat andits=09r= emedies Hi Kevin, > On Jun 20, 2018, at 09:12, Kevin Darbyshire-Bryant wrote: >=20 >=20 >=20 >> On 20 Jun 2018, at 00:41, Jonathan Morton wrote: >>=20 >>> On 19 Jun, 2018, at 11:34 pm, valdis.kletnieks@vt.edu wrote: >>>=20 >>> Do we have a good cookbook on how to determine the set-rate? >>=20 >> On DSL, the sync rates in each direction should usually be readable from= the modem; they are typically reported on the router's status page. The a= dvertised rate is less reliable, to say the least. >=20 > I=E2=80=99ve been experimenting with this hack in sqm-scripts to do just = that https://github.com/ldir-EDB0/sqm-scripts/commit/a71ab1c9acd75d6e925436= 0e832ac7b6f9514e88 originally on my parents DGN3500 and currently on my on = BT HomeHub5a test line. =09Clever (I see how you chiseled data_rates() into shape here, respect)! E= ven though I believe that this is not pppoa specific and should probably ch= eck whether /lib/functions/lantiq_dsl.sh exists. Actually this code will al= so work on VDSL2 links... (and we should also be able to extract the encaps= ulation atm or ptm). if [ "pppoa-wan" =3D "$IFACE" ]; then =09if [ -f "/lib/functions/lantiq_dsl.sh" ] : then =09=09... =09fi fi But would it not be simpler to call /etc/init.d/dsl_control status | grep -= e "Data Rate:" or somesuch? Cureently openwrt only supports lantiq/intel mo= dems, but if broadcom modems should ever be supported I venture a guess the= y will not use /lib/functions/lantiq_dsl.sh to generate the stats output ;)= (not that there is a guarantee that dsl_control would exost and generate c= ompatible output). But I believe that this is not that helpful as a mode to automatically set = the bandwidth*, as I assume that most ISPs will shape the downstream bandwi= dth upstream of the DSLAM (if just to avoid having a DDOS against one user = taking down the whole DSLAM). In my case my ISP even shapes the upstream, w= hich is somewhat more puzzling. It looks like a cool way to deal with varia= ble sync (either after a re-sync due to say DLM action or due to SRA) so ho= w about polishing this a bit and including this as pure informational line = in the log?=20 *) if this is to be made automatic by say allowing to scrape bandwidth from= the modem we would need additional setting for setting the shaper percenta= ge. I wonder whether all of this is worth it though, given that the number = of users running sqm on devices in control of the dsl-modem is going to be = miniscule, no? >=20 > It fails to work if the ISP does rate banding (BT 20CN does this, BT 21CN= doesn=E2=80=99t) where downstream is limited to a rate below downstream sy= nc rate. I guess a lookup table could be implemented. =09I predict that a lookup table is going to be constantly out of date, esp= ecially since at least my ISP is a moving target in both the shaper setting= s as well as the actual overheads (on the plus side they started to send th= e applicable net bandwidth as part of the pppoe negotiations (but failed to= document how those rates are actually to be interpreted ;) win some loose = some)).=20 Final thought, how about just using this on the luci side to give hints abo= ut the sync bandwidth in the GUI (like displaying the value of either sync = for xdsl or the speed for ethernet devices (speed in ethtool parlance, so 1= 0Mb/s, 100Mb/s, ...)) that will not be as smooth as your solution, but shou= ld also be more robust against doing the wrmg thing automatically? Or am I = overcomplicating things again. Final final thought ;) since lantig_dsl.sh is quite openwrt specific, maybe= we should do the automatic mode inside of the equally openwrt specific /us= r/lib/sqm/run instead of in start-sqm that will might also be executed on o= ther platforms? Best Regards =09Sebastian >=20 > Kevin > _______________________________________________ > Bloat mailing list > Bloat@lists.bufferbloat.net > https://lists.bufferbloat.net/listinfo/bloat _______________________________________________ Cerowrt-devel mailing list Cerowrt-devel@lists.bufferbloat.net https://lists.bufferbloat.net/listinfo/cerowrt-devel