From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-wm1-x32c.google.com (mail-wm1-x32c.google.com [IPv6:2a00:1450:4864:20::32c]) (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 BBCFF3CB37 for ; Mon, 26 Sep 2022 21:12:42 -0400 (EDT) Received: by mail-wm1-x32c.google.com with SMTP id r10-20020a1c440a000000b003b494ffc00bso384474wma.0 for ; Mon, 26 Sep 2022 18:12:42 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20210112; h=content-transfer-encoding:cc:to:subject:message-id:date:from :in-reply-to:references:mime-version:from:to:cc:subject:date; bh=6OGR9pV80b5sXJrienNrxXqQlIk0Wvpvi7/dJ1oEGm4=; b=oY3D+llfKN9M0FB+31+fqy3F1doSozvZMY9UNYWf9egNGRbiAxX40u2/GCzS+dO7+d nLiHckYJfz4kQkZ0FNhEjR9CJEqvJ/ILU9MNLGxbKJE66Fq4Mbba5T45sL68QucpocCn JwA5YN600YplkyZ9AUXtY7UZzUXpOCpdWkhO3hO+F7kxzou9czY/EtJ0FScsN3znEPhj chfqO6CznYROm+JRcux7pvAVtAl19aoadxN6demjx3DLsxdUelSJyVVEPAk5Gu1DMKDK 7MRZHBcbyJjOV5GGoYwP7y7sDQI5xdMildtirCs1WqWDEM8vR+0pyo7LC90j2CIb67qE eCcQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=content-transfer-encoding:cc:to:subject:message-id:date:from :in-reply-to:references:mime-version:x-gm-message-state:from:to:cc :subject:date; bh=6OGR9pV80b5sXJrienNrxXqQlIk0Wvpvi7/dJ1oEGm4=; b=ZRFcSPBMWDUGg69KEsjjRL/eZXfF5wt60Ytru0O3CdNtS6ZwmgXCyc67ycyT+NPgGW wCagzDQbD0kcRCkfDDt/Jr+iUd3AhA3LyNDIfRlN2SO238ulVH7s9aE1g4s7Riv6nd7t FzIffySwsZDm3DCLIB0v5bZfWQwDFdA0v5G6WN2ysTKHXBZy3Dr1bLO/iWQDXv8loteD TrGFfvzPv9Ol+u9UwvIP+HDAI43o5u07DY5CyUNGfgdpvIRviSHAzHQDFZTE7OTJDaJH q8Jt0FGfL9h+rOrgGa4i2ojxoje/L6IYTPeKSBEgPES+tGLOXCphmqldb5MRZxbsJ+9P FSqA== X-Gm-Message-State: ACrzQf3SfF87gfquF2+nolb4bzFP5o63V4TVIb3MQVNOUfCx2RcvKr9s CSTzpEdaMZpnEHanjjmC0QKc623Og8rDFtYFtszWlrsyrVo= X-Google-Smtp-Source: AMsMyM7Hwsly84xOQgvRDNA2zik2eKgu8TwqaCrzmQDW3A0G215UQukw/mmVJDS6Yv36DNv0NqE6guiwVsbBh1C4ZkI= X-Received: by 2002:a7b:cc99:0:b0:3b4:76f2:192b with SMTP id p25-20020a7bcc99000000b003b476f2192bmr855856wma.138.1664241161431; Mon, 26 Sep 2022 18:12:41 -0700 (PDT) MIME-Version: 1.0 References: <060F7695-D48E-413C-9501-54ECC651ABEB@cable.comcast.com> <07C46DD5-7359-410E-8820-82B319944618@alum.mit.edu> <39E525B8-D356-4F76-82FF-F1F0B3183908@ieee.org> <498p2p23-on1q-op89-p518-1874r3r6rpo@ynat.uz> <8DC6E5EE-2B46-4815-A909-E326507E95B1@ieee.org> <9D97FB02-58A5-48B0-9B43-6B7BD2A24099@gmx.de> In-Reply-To: From: Dave Taht Date: Mon, 26 Sep 2022 18:12:28 -0700 Message-ID: To: Bruce Perens Cc: Eugene Y Chang , Dave Taht via Starlink Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable Subject: Re: [Starlink] It's still the starlink latency... X-BeenThere: starlink@lists.bufferbloat.net X-Mailman-Version: 2.1.20 Precedence: list List-Id: "Starlink has bufferbloat. Bad." List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 27 Sep 2022 01:12:43 -0000 On Mon, Sep 26, 2022 at 5:55 PM Bruce Perens wrote: > > Why not write an RFC on internet metrics? Then evangelize customers to re= ly on metrics compliant with the RFC. Glad you asked. :) Apple's current IETF IPPM draft is here:https://datatracker.ietf.org/doc/draft-ietf-ippm-responsiveness/ github here: https://github.com/network-quality/draft-ietf-ippm-responsiven= ess and distributed now as networkQuality on OSX and available under developer settings for ios. Given that the methods and metrics are not final, it is not being pushed all that much except into the developer userbase as yet. https://github.com/network-quality has a go version of the client which runs on everything and how to set up your own ngix server. A nice thing about it is that it is designed to stress out our more common protocols (https, quic) and servers, unlike my flent tests which test tcp only. I think the present go implementation stresses out a low speed network too hard, actually, and needs to get more deeply and often into sampling the TCP_INFO statistics - and really needs a section for my most desired metric which is a simultaneous up and download to be at least available, if optional, but haven't written that up yet). A noted problem with up/down is that you are also stressing the device drivers of the local system.... which is important to fix, but There has been a LOT of other work on better metric producing tools in the past year - iperf2 gained a few new tests like "bounce-back", and crusader - written in rust and notable for it's speed and portability - appeared here: https://github.com/Zoxc/crusader I am a lot behind on tracking all this stuff, and putting it in my cloud. Although I was deeply involved in the beginning, spent most of the last 9 months heads down fixing regression after regression in openwrt's wifi code. I wanted to have a sterling example of how to do wifi buffering more right, and only in late august, got there. > On Mon, Sep 26, 2022 at 5:36 PM Dave Taht wrote: >> >> On Mon, Sep 26, 2022 at 2:45 PM Bruce Perens via Starlink >> wrote: >> > >> > That's a good maxim: Don't believe a speed test that is hosted by your= own ISP. >> >> A network designed for speedtest.net, is a network... designed for >> speedtest. Starlink seemingly was designed for speedtest - the 15 >> second "cycle" to sense/change their bandwidth setting is just within >> the 20s cycle speedtest terminates at, and speedtest returns the last >> number for the bandwidth. It is a brutal test - using 8 or more flows >> - much harder on the network than your typical web page load which, >> while that is often 15 or so, most never run long enough to get out of >> slow start. At least some of qualifying for the RDOF money was >> achieving 100mbits down on "speedtest". >> >> A knowledgeable user concerned about web PLT should be looking a the >> first 3 s of a given test, and even then once the bandwidth cracks >> 20Mbit, it's of no help for most web traffic ( we've been citing mike >> belshe's original work here a lot, >> and more recent measurements still show that ) >> >> Speedtest also does nothing to measure how well a given >> videoconference or voip session might go. There isn't a test (at least >> not when last I looked) in the FCC broadband measurements for just >> videoconferencing, and their latency under load test for many years >> now, is buried deep in the annual report. >> >> I hope that with both ookla and samknows more publicly recording and >> displaying latency under load (still, sigh, I think only displaying >> the last number and only sampling every 250ms) that we can shift the >> needle on this, but I started off this thread complaining nobody was >> picking up on those numbers... and neither service tests the worst >> case scenario of a simultaneous up/download, which was the principal >> scenario we explored with the flent "rrul" series of tests, which were >> originally designed to emulate and deeply understand what bittorrent >> was doing to networks, and our principal tool in designing new fq and >> aqm and transport CCs, along with the rtt_fair test for testing near >> and far destinations at the same time. >> >> My model has always been a family of four, one person uploading, >> another doing web, one doing videoconferencing, >> and another doing voip or gaming, and no test anyone has emulates >> that. With 16 wifi devices >> per household, the rrul scenario is actually not "worst case", but >> increasingly the state of things "normally". >> >> Another irony about speedtest is that users are inspired^Wtrained to >> use it when the "network feels slow", and self-initiate something that >> makes it worse, for both them and their portion of the network. >> >> Since the internet architecture board met last year, ( >> https://www.iab.org/activities/workshops/network-quality/ ) there >> seems to be an increasing amount of work on better metrics and tests >> for QoE, with stuff like apple's responsiveness test, etc. >> >> I have a new one - prototyped in some starlink tests so far, and >> elsewhere - called "SPOM" - steady packets over milliseconds, which, >> when run simultaneously with capacity seeking traffic, might be a >> better predictor of videoconferencing performance. >> >> There's also a really good "P99" conference coming up for those, that >> like me, are OCD about a few sigmas. >> >> > >> > On Mon, Sep 26, 2022 at 2:36 PM Eugene Y Chang via Starlink wrote: >> >> >> >> Thank you for the dialog,. >> >> This discussion with regards to Starlink is interesting as it confirm= s my guesses about the gap between Starlinks overly simplified, over optimi= stic marketing and the reality as they acquire subscribers. >> >> >> >> I am actually interested in a more perverse issue. I am seeing latenc= y and bufferbloat as a consequence from significant under provisioning. It = doesn=E2=80=99t matter that the ISP is selling a fiber drop, if (parts) of = their network is under provisioned. Two end points can be less than 5 mile = apart and realize 120+ ms latency. Two Labor Days ago (a holiday) the max l= atency was 230+ ms. The pattern I see suggest digital redlining. The older = communities appear to have much more severe under provisioning. >> >> >> >> Another observation. Running speedtest appears to go from the edge of= the network by layer 2 to the speedtest host operated by the ISP. Yup, byp= asses the (suspected overloaded) routers. >> >> >> >> Anyway, just observing. >> >> >> >> Gene >> >> ---------------------------------------------- >> >> Eugene Chang >> >> IEEE Senior Life Member >> >> eugene.chang@ieee.org >> >> 781-799-0233 (in Honolulu) >> >> >> >> >> >> >> >> On Sep 26, 2022, at 11:20 AM, Sebastian Moeller wro= te: >> >> >> >> Hi Gene, >> >> >> >> >> >> On Sep 26, 2022, at 23:10, Eugene Y Chang wro= te: >> >> >> >> Comments inline below. >> >> >> >> Gene >> >> ---------------------------------------------- >> >> Eugene Chang >> >> IEEE Senior Life Member >> >> eugene.chang@ieee.org >> >> 781-799-0233 (in Honolulu) >> >> >> >> >> >> >> >> On Sep 26, 2022, at 11:01 AM, Sebastian Moeller wro= te: >> >> >> >> Hi Eugene, >> >> >> >> >> >> On Sep 26, 2022, at 22:54, Eugene Y Chang via Starlink wrote: >> >> >> >> Ok, we are getting into the details. I agree. >> >> >> >> Every node in the path has to implement this to be effective. >> >> >> >> >> >> Amazingly the biggest bang for the buck is gotten by fixing those nod= es that actually contain a network path's bottleneck. Often these are prett= y stable. So yes for fully guaranteed service quality all nodes would need = to participate, but for improving things noticeably it is sufficient to imp= rove the usual bottlenecks, e.g. for many internet access links the home ga= teway is a decent point to implement better buffer management. (In short th= e problem are over-sized and under-managed buffers, and one of the best sol= ution is better/smarter buffer management). >> >> >> >> >> >> This is not completely true. >> >> >> >> >> >> [SM] You are likely right, trying to summarize things leads to partia= lly incorrect generalizations. >> >> >> >> >> >> Say the bottleneck is at node N. During the period of congestion, the= upstream node N-1 will have to buffer. When node N recovers, the bufferblo= at at N-1 will be blocking until the bufferbloat drains. Etc. etc. Making = node N better will reduce the extent of the backup at N-1, but N-1 should i= mplement the better code. >> >> >> >> >> >> [SM] It is the node that builds up the queue that profits most from b= etter queue management.... (again I generalize, the node with the queue its= elf probably does not care all that much, but the endpoints will profit if = the queue experiencing node deals with that queue more gracefully). >> >> >> >> >> >> >> >> >> >> >> >> In fact, every node in the path has to have the same prioritization o= r the scheme becomes ineffective. >> >> >> >> >> >> Yes and no, one of the clearest winners has been flow queueing, IMHO = not because it is the most optimal capacity sharing scheme, but because it = is the least pessimal scheme, allowing all (or none) flows forward progress= . You can interpret that as a scheme in which flows below their capacity sh= are are prioritized, but I am not sure that is the best way to look at thes= e things. >> >> >> >> >> >> The hardest part is getting competing ISPs to implement and coordinat= e. >> >> >> >> >> >> [SM] Yes, but it turned out even with non-cooperating ISPs there is a= lot end-users can do unilaterally on their side to improve both ingress an= d egress congestion. Admittedly especially ingress congestion would be even= better handled with cooperation of the ISP. >> >> >> >> Bufferbloat and handoff between ISPs will be hard. The only way to fi= x this is to get the unwashed public to care. Then they can say =E2=80=9Cwe= don=E2=80=99t care about the technical issues, just fix it.=E2=80=9D Until= then =E2=80=A6.. >> >> >> >> >> >> [SM] Well we do this one home network at a time (not because that is = efficient or ideal, but simply because it is possible). Maybe, if you have = not done so already try OpenWrt with sqm-scripts (and maybe cake-autorate i= n addition) on your home internet access link for say a week and let us kno= w ih/how your experience changed? >> >> >> >> Regards >> >> Sebastian >> >> >> >> >> >> >> >> >> >> >> >> >> >> Regards >> >> Sebastian >> >> >> >> >> >> >> >> Gene >> >> ---------------------------------------------- >> >> Eugene Chang >> >> IEEE Senior Life Member >> >> eugene.chang@ieee.org >> >> 781-799-0233 (in Honolulu) >> >> >> >> >> >> >> >> On Sep 26, 2022, at 10:48 AM, David Lang wrote: >> >> >> >> software updates can do far more than just improve recovery. >> >> >> >> In practice, large data transfers are less sensitive to latency than = smaller data transfers (i.e. downloading a CD image vs a video conference),= software can ensure better fairness in preventing a bulk transfer from hur= ting the more latency sensitive transfers. >> >> >> >> (the example below is not completely accurate, but I think it gets th= e point across) >> >> >> >> When buffers become excessivly large, you have the situation where a = video call is going to generate a small amount of data at a regular interva= l, but a bulk data transfer is able to dump a huge amount of data into the = buffer instantly. >> >> >> >> If you just do FIFO, then you get a small chunk of video call, then s= everal seconds worth of CD transfer, followed by the next small chunk of th= e video call. >> >> >> >> But the software can prevent the one app from hogging so much of the = connection and let the chunk of video call in sooner, avoiding the impact t= o the real time traffic. Historically this has required the admin classify = all traffic and configure equipment to implement different treatment based = on the classification (and this requires trust in the classification proces= s), the bufferbloat team has developed options (fq_codel and cake) that can= ensure fairness between applications/servers with little or no configurati= on, and no trust in other systems to properly classify their traffic. >> >> >> >> The one thing that Cake needs to work really well is to be able to kn= ow what the data rate available is. With Starlink, this changes frequently = and cake integrated into the starlink dish/router software would be far bet= ter than anything that can be done externally as the rate changes can be fe= d directly into the settings (currently they are only indirectly detected) >> >> >> >> David Lang >> >> >> >> >> >> On Mon, 26 Sep 2022, Eugene Y Chang via Starlink wrote: >> >> >> >> You already know this. Bufferbloat is a symptom and not the cause. Bu= fferbloat grows when there are (1) periods of low or no bandwidth or (2) pe= riods of insufficient bandwidth (aka network congestion). >> >> >> >> If I understand this correctly, just a software update cannot make bu= fferbloat go away. It might improve the speed of recovery (e.g. throw away = all time sensitive UDP messages). >> >> >> >> Gene >> >> ---------------------------------------------- >> >> Eugene Chang >> >> IEEE Senior Life Member >> >> eugene.chang@ieee.org >> >> 781-799-0233 (in Honolulu) >> >> >> >> >> >> >> >> On Sep 26, 2022, at 10:04 AM, Bruce Perens wrote: >> >> >> >> Please help to explain. Here's a draft to start with: >> >> >> >> Starlink Performance Not Sufficient for Military Applications, Say Sc= ientists >> >> >> >> The problem is not availability: Starlink works where nothing but ano= ther satellite network would. It's not bandwidth, although others have ques= tions about sustaining bandwidth as the customer base grows. It's latency a= nd jitter. As load increases, latency, the time it takes for a packet to ge= t through, increases more than it should. The scientists who have fought bu= fferbloat, a major cause of latency on the internet, know why. SpaceX needs= to upgrade their system to use the scientist's Open Source modifications t= o Linux to fight bufferbloat, and thus reduce latency. This is mostly just = using a newer version, but there are some tunable parameters. Jitter is a c= hange in the speed of getting a packet through the network during a connect= ion, which is inevitable in satellite networks, but will be improved by mak= ing use of the bufferbloat-fighting software, and probably with the additio= n of more satellites. >> >> >> >> We've done all of the work, SpaceX just needs to adopt it by upgradin= g their software, said scientist Dave Taht. Jim Gettys, Taht's collaborator= and creator of the X Window System, chimed in: >> >> Open Source luminary Bruce Perens said: sometimes Starlink's latency = and jitter make it inadequate to remote-control my ham radio station. But t= he military is experimenting with remote-control of vehicles on the battlef= ield and other applications that can be demonstrated, but won't happen at s= cale without adoption of bufferbloat-fighting strategies. >> >> >> >> On Mon, Sep 26, 2022 at 12:59 PM Eugene Chang > wrote: >> >> The key issue is most people don=E2=80=99t understand why latency mat= ters. They don=E2=80=99t see it or feel it=E2=80=99s impact. >> >> >> >> First, we have to help people see the symptoms of latency and how it = impacts something they care about. >> >> - gamers care but most people may think it is frivolous. >> >> - musicians care but that is mostly for a hobby. >> >> - business should care because of productivity but they don=E2=80=99t= know how to =E2=80=9Csee=E2=80=9D the impact. >> >> >> >> Second, there needs to be a =E2=80=9COMG, I have been seeing the acti= on of latency all this time and never knew it! I was being shafted.=E2=80= =9D Once you have this awakening, you can get all the press you want for fr= ee. >> >> >> >> Most of the time when business apps are developed, =E2=80=9Cwe=E2=80= =9D hide the impact of poor performance (aka latency) or they hide from the= discussion because the developers don=E2=80=99t have a way to fix the late= ncy. Maybe businesses don=E2=80=99t care because any employees affected are= just considered poor performers. (In bad economic times, the poor performe= rs are just laid off.) For employees, if they happen to be at a location wi= th bad latency, they don=E2=80=99t know that latency is hurting them. Unfai= r but most people don=E2=80=99t know the issue is latency. >> >> >> >> Talking and explaining why latency is bad is not as effective as show= ing why latency is bad. Showing has to be with something that has a person = impact. >> >> >> >> Gene >> >> ----------------------------------- >> >> Eugene Chang >> >> eugene.chang@alum.mit.edu >> >> +1-781-799-0233 (in Honolulu) >> >> >> >> >> >> >> >> >> >> >> >> On Sep 26, 2022, at 6:32 AM, Bruce Perens via Starlink > wrote: >> >> >> >> If you want to get attention, you can get it for free. I can place ar= ticles with various press if there is something interesting to say. Did thi= s all through the evangelism of Open Source. All we need to do is write, si= gn, and publish a statement. What they actually write is less relevant if t= hey publish a link to our statement. >> >> >> >> Right now I am concerned that the Starlink latency and jitter is goin= g to be a problem even for remote controlling my ham station. The US Milita= ry is interested in doing much more, which they have demonstrated, but I do= n't see happening at scale without some technical work on the network. Bein= g able to say this isn't ready for the government's application would be an= attention-getter. >> >> >> >> Thanks >> >> >> >> Bruce >> >> >> >> On Mon, Sep 26, 2022 at 9:21 AM Dave Taht via Starlink > wrote: >> >> These days, if you want attention, you gotta buy it. A 50k half page >> >> ad in the wapo or NYT riffing off of It's the latency, Stupid!", >> >> signed by the kinds of luminaries we got for the fcc wifi fight, woul= d >> >> go a long way towards shifting the tide. >> >> >> >> On Mon, Sep 26, 2022 at 8:29 AM Dave Taht > wrote: >> >> >> >> >> >> On Mon, Sep 26, 2022 at 8:20 AM Livingood, Jason >> >> > wr= ote: >> >> >> >> >> >> The awareness & understanding of latency & impact on QoE is nearly un= known among reporters. IMO maybe there should be some kind of background br= iefings for reporters - maybe like a simple YouTube video explainer that is= short & high level & visual? Otherwise reporters will just continue to foc= us on what they know... >> >> >> >> >> >> That's a great idea. I have visions of crashing the washington >> >> correspondents dinner, but perhaps >> >> there is some set of gatherings journalists regularly attend? >> >> >> >> >> >> =EF=BB=BFOn 9/21/22, 14:35, "Starlink on behalf of Dave Taht via Star= link" on behalf of starlink@lists.bufferbloat.net > wrote: >> >> >> >> I still find it remarkable that reporters are still missing the >> >> meaning of the huge latencies for starlink, under load. >> >> >> >> >> >> >> >> >> >> -- >> >> FQ World Domination pending: https://blog.cerowrt.org/post/state_of_f= q_codel/ >> >> Dave T=C3=A4ht CEO, TekLibre, LLC >> >> >> >> >> >> >> >> >> >> -- >> >> FQ World Domination pending: https://blog.cerowrt.org/post/state_of_f= q_codel/ >> >> Dave T=C3=A4ht CEO, TekLibre, LLC >> >> _______________________________________________ >> >> Starlink mailing list >> >> Starlink@lists.bufferbloat.net >> >> https://lists.bufferbloat.net/listinfo/starlink >> >> >> >> >> >> -- >> >> Bruce Perens K6BP >> >> _______________________________________________ >> >> Starlink mailing list >> >> Starlink@lists.bufferbloat.net >> >> https://lists.bufferbloat.net/listinfo/starlink >> >> >> >> >> >> >> >> >> >> -- >> >> Bruce Perens K6BP >> >> >> >> >> >> _______________________________________________ >> >> Starlink mailing list >> >> Starlink@lists.bufferbloat.net >> >> https://lists.bufferbloat.net/listinfo/starlink >> >> >> >> >> >> _______________________________________________ >> >> Starlink mailing list >> >> Starlink@lists.bufferbloat.net >> >> https://lists.bufferbloat.net/listinfo/starlink >> > >> > >> > >> > -- >> > Bruce Perens K6BP >> > _______________________________________________ >> > Starlink mailing list >> > Starlink@lists.bufferbloat.net >> > https://lists.bufferbloat.net/listinfo/starlink >> >> >> >> -- >> FQ World Domination pending: https://blog.cerowrt.org/post/state_of_fq_c= odel/ >> Dave T=C3=A4ht CEO, TekLibre, LLC > > > > -- > Bruce Perens K6BP --=20 FQ World Domination pending: https://blog.cerowrt.org/post/state_of_fq_code= l/ Dave T=C3=A4ht CEO, TekLibre, LLC