<div dir="ltr">There are horrible latencies observed on wired - including fiber, and FWA with good QoE solutions beats fiber (without it) anytime.<div>So it's not the function of the transport only, but rather the convergence between the transport (be it fiber, FWA, 5G or LEO) and it's latency/jitter/bufferbloat solution.</div><div><div><br></div><div><br clear="all"><div><div dir="ltr" class="gmail_signature" data-smartmail="gmail_signature"><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div dir="ltr"><div dir="ltr"><div dir="ltr"><div dir="ltr"><div dir="ltr"><div>All the best,</div><div><br></div><div><p class="MsoNormal" style="color:rgb(34,34,34)">Frank<u></u><u></u></p><p class="MsoNormal" style="color:rgb(34,34,34)"><u></u><u></u></p><p class="MsoNormal" style="color:rgb(34,34,34)">Frantisek (Frank) Borsik<u></u><u></u></p><p class="MsoNormal" style="color:rgb(34,34,34)"><u></u> <u></u></p><p class="MsoNormal" style="color:rgb(34,34,34)"><a href="https://www.linkedin.com/in/frantisekborsik" style="color:rgb(17,85,204)" target="_blank">https://www.linkedin.com/in/frantisekborsik</a><u></u><u></u></p><p class="MsoNormal" style="color:rgb(34,34,34)">Signal, Telegram, WhatsApp: +421919416714 <u></u><u></u></p><p class="MsoNormal" style="color:rgb(34,34,34)">iMessage, mobile: +420775230885<u></u><u></u></p><p class="MsoNormal" style="color:rgb(34,34,34)">Skype: casioa5302ca<u></u><u></u></p><p class="MsoNormal" style="color:rgb(34,34,34)"><a href="mailto:frantisek.borsik@gmail.com" style="color:rgb(17,85,204)" target="_blank">frantisek.borsik@gmail.com</a></p></div></div></div></div></div></div></div></div></div></div></div></div></div><br></div></div></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Mon, Sep 25, 2023 at 10:59 AM David Lang via Starlink <<a href="mailto:starlink@lists.bufferbloat.net">starlink@lists.bufferbloat.net</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left-width:1px;border-left-style:solid;border-left-color:rgb(204,204,204);padding-left:1ex">On Mon, 25 Sep 2023, Alexandre Petrescu wrote:<br>
<br>
> Apart the AI's inability aspect, it stays interesting if future LEO Internet <br>
> access systems competes to fiber in the right range.<br>
<br>
wired (including fiber) is going to beat wireless pretty much anywhere it's <br>
available. Wireless (and LEO) have the advantage that it's EXPENSIVE to run <br>
wires, so they start to shine when the use density decreases (and even there, <br>
there will be areas where 'fiber is bing run down this road anyway, so let's <br>
offer service to people along the way to earn a few penny's and some good PR)<br>
<br>
the quirk where very long range communication can be slightly lower round-trip <br>
time by first hopping up into space is balanced by the more limited bandwidth <br>
available through that space connection (you have to get through miles of <br>
atmosphere, and that's going to limit your throughput compared to millimeters to <br>
get into the fiber)<br>
<br>
> The timestamped technologies should be compared. Starlink today's 20ms <br>
> should be compared to today's advanced 5G 1ms, and not to 4G 50ms. Future <br>
> LEO Internet access should be compared to future 6G terrestrial and future <br>
> FTTH, because they also evolve.<br>
<br>
True, but when you are looking at limits imposed by known physics, it's a pretty <br>
safe bet. Yes, it is possible that quantum entanglement will translate into FTL <br>
communications that can be used to replace everything we know, but that's rather <br>
unlikely for at least a LONG time.<br>
<br>
David Lang<br>
<br>
> Alex<br>
><br>
><br>
>> The laser communication system is about *40% faster* than fiber due to the <br>
>> speed of light in vacuum <br>
>> <<a href="https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html" rel="noreferrer" target="_blank">https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html</a>>^1 <br>
>> <<a href="https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html" rel="noreferrer" target="_blank">https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html</a>>. <br>
>> The number of laser transponders in a second-generation Starlink satellite <br>
>> is not mentioned in the information I found. However, it is worth noting <br>
>> that the second-generation Starlink satellites are expected to be <br>
>> significantly more capable than their predecessors <br>
>> <<a href="https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html" rel="noreferrer" target="_blank">https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html</a>>^1 <br>
>> <<a href="https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html" rel="noreferrer" target="_blank">https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html</a>>. <br>
>> They will be larger and much faster, with a capacity of up to *80 Gbps per <br>
>> satellite*, compared to *18 Gbps* in the current version <br>
>> <<a href="https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html" rel="noreferrer" target="_blank">https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html</a>>^1 <br>
>> <<a href="https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html" rel="noreferrer" target="_blank">https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html</a>>. <br>
>> The proposed Starlink Gen2 constellation, consisting of approximately <br>
>> 30,000 satellites, would have a total instantaneous bandwidth of at least <br>
>> *500 terabits per second (Tbps) over land*, which is around 1800 Tbps <br>
>> including ocean coverage <br>
>> <<a href="https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html" rel="noreferrer" target="_blank">https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html</a>>^1 <br>
>> <<a href="https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html" rel="noreferrer" target="_blank">https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html</a>>.<br>
>> <br>
>> Please note that the information I provided is based on available sources <br>
>> and may not cover all the details about the second-generation Starlink <br>
>> satellites. For more specific information, it is recommended to refer to <br>
>> official sources or SpaceX’s announcements.<br>
>> <br>
>> Is there anything else I can help you with? 😊<br>
>> <br>
>> Learn more:<br>
>> 1. <a href="http://nextbigfuture.com" rel="noreferrer" target="_blank">nextbigfuture.com</a> <br>
>> <<a href="https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html" rel="noreferrer" target="_blank">https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html</a>><br>
>> 2. <a href="http://arstechnica.com" rel="noreferrer" target="_blank">arstechnica.com</a> <br>
>> <<a href="https://arstechnica.com/information-technology/2021/01/spacex-adds-laser-links-to-starlink-satellites-to-serve-earths-polar-areas/" rel="noreferrer" target="_blank">https://arstechnica.com/information-technology/2021/01/spacex-adds-laser-links-to-starlink-satellites-to-serve-earths-polar-areas/</a>><br>
>> 3. <a href="http://spaceflightnow.com" rel="noreferrer" target="_blank">spaceflightnow.com</a> <br>
>> <<a href="https://spaceflightnow.com/2021/09/14/spacex-launches-first-full-batch-of-laser-equipped-starlink-satellites/" rel="noreferrer" target="_blank">https://spaceflightnow.com/2021/09/14/spacex-launches-first-full-batch-of-laser-equipped-starlink-satellites/</a>>— see <br>
>> less<br>
>> <br>
>> " *(End of BING Response)*<br>
>> <br>
>> Hesham<br>
>> <br>
>> <br>
>> <br>
>> On Sat, Sep 23, 2023, 2:55 PM Larry Press via Starlink <br>
>> <<a href="mailto:starlink@lists.bufferbloat.net" target="_blank">starlink@lists.bufferbloat.net</a>> wrote:<br>
>><br>
>> In his first Starlink simulation, Mark Hadley assumed five<br>
>> transponders per satellite -- Two in-plane, two adjacent, and one<br>
>> crossing:<br>
>> <a href="https://www.youtube.com/watch?v=3479tkagiNo&list=PLrRMhEONgz06oMXQOljB5BoZxZw6cShLN&index=3" rel="noreferrer" target="_blank">https://www.youtube.com/watch?v=3479tkagiNo&list=PLrRMhEONgz06oMXQOljB5BoZxZw6cShLN&index=3</a><br>
>> <<a href="https://www.youtube.com/watch?v=3479tkagiNo&list=PLrRMhEONgz06oMXQOljB5BoZxZw6cShLN&index=3" rel="noreferrer" target="_blank">https://www.youtube.com/watch?v=3479tkagiNo&list=PLrRMhEONgz06oMXQOljB5BoZxZw6cShLN&index=3</a>><br>
>><br>
>> In his next Starlink simulation, Mark Hadley assumed four:<br>
>> <a href="https://www.youtube.com/watch?v=QEIUdMiColU&list=PLrRMhEONgz06oMXQOljB5BoZxZw6cShLN&index=2" rel="noreferrer" target="_blank">https://www.youtube.com/watch?v=QEIUdMiColU&list=PLrRMhEONgz06oMXQOljB5BoZxZw6cShLN&index=2</a><br>
>> <<a href="https://www.youtube.com/watch?v=QEIUdMiColU&list=PLrRMhEONgz06oMXQOljB5BoZxZw6cShLN&index=2" rel="noreferrer" target="_blank">https://www.youtube.com/watch?v=QEIUdMiColU&list=PLrRMhEONgz06oMXQOljB5BoZxZw6cShLN&index=2</a>><br>
>><br>
>> I guess he assumed the relative velocities were too high for the<br>
>> crossing connection.<br>
>><br>
>> I asked Bard "How many laser transponders are in a<br>
>> second-generation Starlink satellite?" and it said "four."<br>
>> I asked ChatGPT "How many laser transponders are in a<br>
>> second-generation Starlink satellite?" and it said it did not know.<br>
>> I asked Bard again and the second time it said it did not know.<br>
>> When I pointed out that it had told me "four" the first time I<br>
>> asked, Bard apologized for its previous answer.<br>
>><br>
>> I remain an "AI" skeptic:<br>
>> <a href="https://circleid.com/posts/20230721-google-bard-fails-to-answer-satellite-internet-questions" rel="noreferrer" target="_blank">https://circleid.com/posts/20230721-google-bard-fails-to-answer-satellite-internet-questions</a><br>
>><br>
>> *From:* Starlink <<a href="mailto:starlink-bounces@lists.bufferbloat.net" target="_blank">starlink-bounces@lists.bufferbloat.net</a>> on<br>
>> behalf of David Lang via Starlink <<a href="mailto:starlink@lists.bufferbloat.net" target="_blank">starlink@lists.bufferbloat.net</a>><br>
>> *Sent:* Friday, September 22, 2023 1:41 AM<br>
>> *To:* Alexandre Petrescu <<a href="mailto:alexandre.petrescu@gmail.com" target="_blank">alexandre.petrescu@gmail.com</a>><br>
>> *Cc:* <a href="mailto:starlink@lists.bufferbloat.net" target="_blank">starlink@lists.bufferbloat.net</a> <<a href="mailto:starlink@lists.bufferbloat.net" target="_blank">starlink@lists.bufferbloat.net</a>><br>
>> *Subject:* Re: [Starlink] APNIC56 last week<br>
>> I believe that I read that STarlink has 5 lasers per sat. but<br>
>> whatever the<br>
>> number, it's a tiny number compared to the number of satellites<br>
>> that they have<br>
>> up there.<br>
>><br>
>> As you are looking at 'trains', check their altitude. They aren't<br>
>> going to<br>
>> shuffle sats around much, it's expensive in terms of fuel and they<br>
>> are only<br>
>> allowed to provide service when they are in their proper orbits.<br>
>><br>
>> We know the lasers are in operation as they are providing service<br>
>> to places more<br>
>> than one sat hop away from ground stations. We also know they have<br>
>> a lot of<br>
>> ground stations around to share the load.<br>
>><br>
>> We have almost no details on the specific modules they are using,<br>
>> and none on<br>
>> what routing they are using.<br>
>><br>
>> David Lang<br>
>> <br>
>><br>
>> On Fri, 22 Sep 2023,<br>
>> Alexandre Petrescu via Starlink wrote:<br>
>><br>
>> > Date: Fri, 22 Sep 2023 10:26:26 +0200<br>
>> > From: Alexandre Petrescu via Starlink<br>
>> <<a href="mailto:starlink@lists.bufferbloat.net" target="_blank">starlink@lists.bufferbloat.net</a>><br>
>> > Reply-To: Alexandre Petrescu <<a href="mailto:alexandre.petrescu@gmail.com" target="_blank">alexandre.petrescu@gmail.com</a>><br>
>> > To: <a href="mailto:starlink@lists.bufferbloat.net" target="_blank">starlink@lists.bufferbloat.net</a><br>
>> > Subject: Re: [Starlink] APNIC56 last week<br>
>> ><br>
>> ><br>
>> > Le 21/09/2023 à 21:05, Inemesit Affia via Starlink a écrit :<br>
>> >> Not going to go into details but lasers have been identified in<br>
>> photos<br>
>> >> of the sats and one of the component suppliers is known. (The<br>
>> scale is<br>
>> >> novel, not the tech, demisabiliy is new though)<br>
>> ><br>
>> > 4 or 2 lasers on each sat (N-S, E-W) is potentially a very<br>
>> different<br>
>> > matter from an IP routing standpoint. It still is a reduced set of<br>
>> > variables, for a routing protocol (it is not like there being an<br>
>> > arbitrary number of IP interfaces, it's just 2 or 4).<br>
>> ><br>
>> > For component manufacturers: yes, I heard about a few<br>
>> manufacturers of<br>
>> > such equipment for laser comms for LEO sats, experimented. <br>
>> There is<br>
>> > public information about a few of them. I dont know which is<br>
>> considered<br>
>> > by starlink, but there is not my worry. There is also a difference<br>
>> > between laser links between sats on different orbit altitudes (e.g.<br>
>> > laser for ISL for GEO to MEO) and lasers between sats on a same<br>
>> orbit<br>
>> > altitude, or on a same orbit. It's three different things, with<br>
>> > different sets of requirements: focusing, power levels, distance<br>
>> ranges.<br>
>> ><br>
>> > At the lowest limit (cheapest, less powerful, less range<br>
>> distance), I<br>
>> > suppose it is possible to use simply LiFi optical links (a sort<br>
>> of WiFi<br>
>> > but with light). If so, then it is very easy to have IP on it.<br>
>> ><br>
>> > There is also an 'optical' spec that was circulated here on this<br>
>> list<br>
>> ><br>
>> (<a href="https://urldefense.com/v3/__https://www.sda.mil/wp-content/uploads/2022/04/SDA-OCT-Standard-v3.0.pdf__;!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYhXDWmzfQ$" rel="noreferrer" target="_blank">https://urldefense.com/v3/__https://www.sda.mil/wp-content/uploads/2022/04/SDA-OCT-Standard-v3.0.pdf__;!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYhXDWmzfQ$</a><br>
>> ),<br>
>> > although it seemed to me to figure on kepler's website, not on<br>
>> > starlink's. In that spec, it is said Ethernet, among other<br>
>> things. On<br>
>> > Ethernet, IP can run easily.<br>
>> ><br>
>> >><br>
>> >> Starlink can't deliver to Antarctica or Northern parts of Alaska,<br>
>> >> Ascension Island, Diego Garcia, Easter Island, Vanuatu, Iran<br>
>> without<br>
>> >> ISL's etc<br>
>> ><br>
>> > I'll have to look where these places are.<br>
>> ><br>
>> > When looking at starlink satellites I often see trains forming and<br>
>> > lasting for a while. Someone said these sats are like that<br>
>> (trains)<br>
>> > prior to be put on a more evenly distanced, in-orbit; but some time<br>
>> > passed, and they continue this kind of behaviour: form denser<br>
>> trains,<br>
>> > then distance more evenly, and back again. So I am not sure these<br>
>> > 'trains' are ephemeral. They seem to be in such 'train'<br>
>> structure while<br>
>> > above some particular continents or areas, but not sure. It<br>
>> takes a lot<br>
>> > of time to make a meaning of it.<br>
>> ><br>
>> > Also, now here are at least two kinds of starlink subscription<br>
>> plans:<br>
>> > 40EUR/month and 287EUR/month, for fixed vs mobile.<br>
>> ><br>
>> >><br>
>> >> North South links seem to work but not East West (if they exist)<br>
>> ><br>
>> > Yes, good question. It makes a lot of difference whether there<br>
>> are 2 or<br>
>> > 4 laser links on each sat. It also makes a lot of difference if<br>
>> trying<br>
>> > to make IP routing work there (assuming there could be 2 or 4 IP<br>
>> > interfaces for lasers).<br>
>> ><br>
>> > This (number of ISL links on a starlink sat) can have an impact<br>
>> on how<br>
>> > people show LEO satellite topologies in Internet Drafts at IETF.<br>
>> ><br>
>> > Alex<br>
>> ><br>
>> >><br>
>> >> On Thu, Sep 21, 2023, 2:20 PM Alexandre Petrescu via Starlink<br>
>> >> <<a href="mailto:starlink@lists.bufferbloat.net" target="_blank">starlink@lists.bufferbloat.net</a>> wrote:<br>
>> >><br>
>> >><br>
>> >> Le 19/09/2023 à 06:39, Ulrich Speidel via Starlink a écrit :<br>
>> >> > FWIW, I gave a talk about Starlink - insights from a year<br>
>> in -<br>
>> >> at last<br>
>> >> > week's APNIC56 conference in Kyoto:<br>
>> >> ><br>
>> >> ><br>
>> <a href="https://urldefense.com/v3/__https://conference.apnic.net/56/program/program/*/day/6/technical-2/__;Iw!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYjUChNXHQ$" rel="noreferrer" target="_blank">https://urldefense.com/v3/__https://conference.apnic.net/56/program/program/*/day/6/technical-2/__;Iw!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYjUChNXHQ$</a><br>
>><br>
>> >><br>
>> >><br>
>> >> Thanks for the presentation.<br>
>> >><br>
>> >> I would like to ask what do you mean by "Method #2: "space<br>
>> >> lasers""and<br>
>> >> "Not all Starlink satellites have<br>
>> >> lasers" on slide 5?<br>
>> >><br>
>> >> It seems to be saying there is inter-satellite<br>
>> communications. The<br>
>> >> need<br>
>> >> of that seems to stem from the lack of ground 'teleport'<br>
>> that is<br>
>> >> necessary for DISHY-SAT-Internet communications, so a<br>
>> SAT-to-SAT<br>
>> >> communication is apparently used with lasers. I can agree with<br>
>> >> the need.<br>
>> >><br>
>> >> What standard is used for these lasers?<br>
>> >><br>
>> >> Is this ISL communicaiton within the starlink constellation a<br>
>> >> supposition or a sure thing?<br>
>> >><br>
>> >> Other presentations of starlink mentioned on this list dont<br>
>> talk<br>
>> >> about<br>
>> >> this lasers between sats (dont show lasers on the sats),<br>
>> but kepler<br>
>> >> talks about optical links, and also there is talk about<br>
>> ISOC LEO<br>
>> >> Internet about such 'lasers from space'.<br>
>> >><br>
>> >> (I must say that I thought previously that there were only<br>
>> 2 or 3<br>
>> >> ground<br>
>> >> teleports overall in EU and USA, but I see now there is a<br>
>> teleport<br>
>> >> in NZ<br>
>> >> too).<br>
>> >><br>
>> >> (for price comparison: it is said 100USD monthly, but in<br>
>> France right<br>
>> >> now the monthly subscription is at around 40 Euros; this<br>
>> competes<br>
>> >> very<br>
>> >> advantageously to other satcoms ISPs for rural areas<br>
>> non-covered<br>
>> >> by 5G;<br>
>> >> the cellular monthly subscriptions are still much more<br>
>> advantageous,<br>
>> >> where there is 5G, of course).<br>
>> >><br>
>> >> Alex<br>
>> >><br>
>> >> ><br>
>> >> > Also well worth looking at is Geoff Huston's excellent<br>
>> piece on the<br>
>> >> > foreseeable demise of TCP in favour of QUIC in the same<br>
>> session.<br>
>> >> One<br>
>> >> > of Geoff's main arguments is that the Internet is<br>
>> becoming local,<br>
>> >> > i.e., most traffic goes between a CDN server and you, and<br>
>> most<br>
>> >> data is<br>
>> >> > becoming proprietary to the application owner, meaning it<br>
>> suits the<br>
>> >> > Googles and Facebooks of this world very well not to be using<br>
>> >> TCP for<br>
>> >> > its transport, but rather pull the transport specifics<br>
>> into the<br>
>> >> > application layer where the have full control.<br>
>> >> ><br>
>> >> > Food for thought, especially since LEO networks are a<br>
>> >> particularly bad<br>
>> >> > place to put local content caches, since the concept of<br>
>> what's<br>
>> >> "local"<br>
>> >> > in a LEO network changes constantly, at around 20,000<br>
>> miles an<br>
>> >> hour or<br>
>> >> > so. Spoke to a Rwandan colleague who installs Starlink<br>
>> there and<br>
>> >> sees<br>
>> >> > all traffic to anywhere go via the US with RTTs of nearly 2<br>
>> >> seconds,<br>
>> >> > even if the Rwandan user is trying to access a Rwandan<br>
>> service.<br>
>> >> ><br>
>> >> > About to hop onto a plane (ZK-NZJ) tonight with free WiFi<br>
>> (Ka band<br>
>> >> > GEO) enroute to Auckland in the hope of getting a better<br>
>> experience<br>
>> >> > than last time when the system seemed to run out of IP<br>
>> addresses on<br>
>> >> > its DHCP.<br>
>> >> ><br>
>> >> _______________________________________________<br>
>> >> Starlink mailing list<br>
>> >> <a href="mailto:Starlink@lists.bufferbloat.net" target="_blank">Starlink@lists.bufferbloat.net</a><br>
>> >><br>
>> <a href="https://urldefense.com/v3/__https://lists.bufferbloat.net/listinfo/starlink__;!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYgJ4na9hA$" rel="noreferrer" target="_blank">https://urldefense.com/v3/__https://lists.bufferbloat.net/listinfo/starlink__;!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYgJ4na9hA$</a><br>
>><br>
>> >><br>
>> >><br>
>> >> _______________________________________________<br>
>> >> Starlink mailing list<br>
>> >> <a href="mailto:Starlink@lists.bufferbloat.net" target="_blank">Starlink@lists.bufferbloat.net</a><br>
>> >><br>
>> <a href="https://urldefense.com/v3/__https://lists.bufferbloat.net/listinfo/starlink__;!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYgJ4na9hA$" rel="noreferrer" target="_blank">https://urldefense.com/v3/__https://lists.bufferbloat.net/listinfo/starlink__;!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYgJ4na9hA$</a><br>
>><br>
>> > _______________________________________________<br>
>> > Starlink mailing list<br>
>> > <a href="mailto:Starlink@lists.bufferbloat.net" target="_blank">Starlink@lists.bufferbloat.net</a><br>
>> ><br>
>> <a href="https://urldefense.com/v3/__https://lists.bufferbloat.net/listinfo/starlink__;!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYgJ4na9hA$" rel="noreferrer" target="_blank">https://urldefense.com/v3/__https://lists.bufferbloat.net/listinfo/starlink__;!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYgJ4na9hA$</a><br>
>><br>
>> ><br>
>> _______________________________________________<br>
>> Starlink mailing list<br>
>> <a href="mailto:Starlink@lists.bufferbloat.net" target="_blank">Starlink@lists.bufferbloat.net</a><br>
>> <a href="https://lists.bufferbloat.net/listinfo/starlink" rel="noreferrer" target="_blank">https://lists.bufferbloat.net/listinfo/starlink</a><br>
>> <br>
>_______________________________________________<br>
Starlink mailing list<br>
<a href="mailto:Starlink@lists.bufferbloat.net" target="_blank">Starlink@lists.bufferbloat.net</a><br>
<a href="https://lists.bufferbloat.net/listinfo/starlink" rel="noreferrer" target="_blank">https://lists.bufferbloat.net/listinfo/starlink</a><br>
</blockquote></div>