From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-lf1-x12a.google.com (mail-lf1-x12a.google.com [IPv6:2a00:1450:4864:20::12a]) (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 E1A953B2A4 for ; Sun, 24 Sep 2023 08:00:39 -0400 (EDT) Received: by mail-lf1-x12a.google.com with SMTP id 2adb3069b0e04-503065c4b25so7191329e87.1 for ; Sun, 24 Sep 2023 05:00:39 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20230601; t=1695556838; x=1696161638; darn=lists.bufferbloat.net; h=cc:to:subject:message-id:date:from:in-reply-to:references :mime-version:from:to:cc:subject:date:message-id:reply-to; bh=6BwfuzEfgly9YW1gu/+OFWojOUqSAKJNSGJYtsZNenk=; b=gDg9Q9/rPS7kBlqi8jKKdxG+gcjvJzFTGB9lnD4arq1ULo2Ks+WkneQhWXHLXw6gZy VT2EaK1fs/aqk1f1sJItMvm15EzM+k1nCw2feMMw9LMfd6lOM57GfI9RVoU6Tc6aP2rJ VenUdWNa1Qzqc0nkzEb1yz6FQBcAHOuMMLk5d+sqjp1LMrkQJGW1wuPT0/4oStw3uYNE efy46X5ERmz0oQiXpuVQ+btaeZQjUuslsCe4xw9WUvRPa9YPQ06r+qAed7xb6gPNaJLn X4qyrNQ1spmO3ioY9xHcTqFDd5HA1t08tVipKJRfEyoyCd3DDkOzmZ4+nwmsVic8qUCv JO4g== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1695556838; x=1696161638; h=cc:to:subject:message-id:date:from:in-reply-to:references :mime-version:x-gm-message-state:from:to:cc:subject:date:message-id :reply-to; bh=6BwfuzEfgly9YW1gu/+OFWojOUqSAKJNSGJYtsZNenk=; b=XsEb1VuTzv0v+HoYXGlm5LTXpOQgNGgui+CbAdjornRb8I4u/LjuA1OLh0V5GXqUmT R/hLrTC/wihbhwpkSrMIl+5HJPKvMrJFypDe1L3ibl2oyWerKT9EGAKL8l1Yjewf2Kdf ZlRa7tnGcPcHe7yLghPOZwuoDyJ/ScF55ywthf9cNXjFRB9u723/xkMxO5t8kEkXlc6V wf6c5FoejHOMMmHyjc6kOt2ehgHtc8VwJZxLl3BJF3YhenV4Cs65OSXGhdidb15Dr/Ud p/JSFyTYYT0bTLgpF4NHU5mHFO+FohnHIzJIrYkx7h2m5PBdvKG1IMwlMxnwcGW0E6Bb TI2w== X-Gm-Message-State: AOJu0YwAlRWni8YYQ1fwLacj2RPLUXytVB3uIwob8q2wVSrm2erHHw/L S7S8XFgns7ucolhbtOIln7Li5+8iRc6pRU2J4lU= X-Google-Smtp-Source: AGHT+IExXPSNmC0QFuRr800rslR/W9yfrJf7AqGrRmngvTlPO1+3yLpiHgt8jMsqPbX3wTiXe6/gXIMXyLCYJaVMIgU= X-Received: by 2002:a19:4f10:0:b0:4fd:d92e:31ca with SMTP id d16-20020a194f10000000b004fdd92e31camr3537752lfb.36.1695556837906; Sun, 24 Sep 2023 05:00:37 -0700 (PDT) MIME-Version: 1.0 References: <9d96e8d6-8a40-4353-b7a3-49881742f1a7@auckland.ac.nz> <04809a35-4c06-43b6-bc2e-b69de3214946@gmail.com> <9283a186-e960-4106-ad87-ff5c6a97da7e@gmail.com> <1oor055r-p02p-3o25-9056-p257s819q308@ynat.uz> In-Reply-To: From: Hesham ElBakoury Date: Sun, 24 Sep 2023 05:00:23 -0700 Message-ID: To: Larry Press Cc: Alexandre Petrescu , David Lang , Dave Taht via Starlink Content-Type: multipart/alternative; boundary="000000000000051c950606199709" Subject: Re: [Starlink] APNIC56 last week 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: Sun, 24 Sep 2023 12:00:40 -0000 --000000000000051c950606199709 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable I asked BING the same question, I got the following response. *Start of BING Response* "The second-generation *Starlink satellites* are equipped with *laser communication* between satellites, which helps reduce latency to about *10-= 20 milliseconds*, compared to *17 milliseconds* for fiber 1 . The laser communication system is about *40% faster* than fiber due to the speed of light in vacuum 1 . The number of laser transponders in a second-generation Starlink satellite is not mentioned in the information I found. However, it is worth noting that the second-generation Starlink satellites are expected to be significantly more capable than their predecessors 1 . They will be larger and much faster, with a capacity of up to *80 Gbps per satellite*, compared to *18 Gbps* in the current version 1 . The proposed Starlink Gen2 constellation, consisting of approximately 30,000 satellites, would have a total instantaneous bandwidth of at least *= 500 terabits per second (Tbps) over land*, which is around 1800 Tbps including ocean coverage 1 . Please note that the information I provided is based on available sources and may not cover all the details about the second-generation Starlink satellites. For more specific information, it is recommended to refer to official sources or SpaceX=E2=80=99s announcements. Is there anything else I can help you with? =F0=9F=98=8A Learn more: 1. nextbigfuture.com 2. arstechnica.com 3. spaceflightnow.com =E2=80=94 see less " *(End of BING Response)* Hesham On Sat, Sep 23, 2023, 2:55 PM Larry Press via Starlink < starlink@lists.bufferbloat.net> wrote: > In his first Starlink simulation, Mark Hadley assumed five transponders > per satellite -- Two in-plane, two adjacent, and one crossing: > > https://www.youtube.com/watch?v=3D3479tkagiNo&list=3DPLrRMhEONgz06oMXQOlj= B5BoZxZw6cShLN&index=3D3 > > In his next Starlink simulation, Mark Hadley assumed four: > > https://www.youtube.com/watch?v=3DQEIUdMiColU&list=3DPLrRMhEONgz06oMXQOlj= B5BoZxZw6cShLN&index=3D2 > > I guess he assumed the relative velocities were too high for the crossing > connection. > > I asked Bard "How many laser transponders are in a second-generation > Starlink satellite?" and it said "four." > I asked ChatGPT "How many laser transponders are in a second-generation > Starlink satellite?" and it said it did not know. > I asked Bard again and the second time it said it did not know. > When I pointed out that it had told me "four" the first time I asked, Bar= d > apologized for its previous answer. > > I remain an "AI" skeptic: > > https://circleid.com/posts/20230721-google-bard-fails-to-answer-satellite= -internet-questions > > *From:* Starlink on behalf of > David Lang via Starlink > *Sent:* Friday, September 22, 2023 1:41 AM > *To:* Alexandre Petrescu > *Cc:* starlink@lists.bufferbloat.net > *Subject:* Re: [Starlink] APNIC56 last week > > I believe that I read that STarlink has 5 lasers per sat. but whatever th= e > number, it's a tiny number compared to the number of satellites that they > have > up there. > > As you are looking at 'trains', check their altitude. They aren't going t= o > shuffle sats around much, it's expensive in terms of fuel and they are > only > allowed to provide service when they are in their proper orbits. > > We know the lasers are in operation as they are providing service to > places more > than one sat hop away from ground stations. We also know they have a lot > of > ground stations around to share the load. > > We have almost no details on the specific modules they are using, and non= e > on > what routing they are using. > > David Lang > > > On Fri, 22 Sep 2023, > Alexandre Petrescu via Starlink wrote: > > > Date: Fri, 22 Sep 2023 10:26:26 +0200 > > From: Alexandre Petrescu via Starlink > > Reply-To: Alexandre Petrescu > > To: starlink@lists.bufferbloat.net > > Subject: Re: [Starlink] APNIC56 last week > > > > > > Le 21/09/2023 =C3=A0 21:05, Inemesit Affia via Starlink a =C3=A9crit : > >> Not going to go into details but lasers have been identified in photos > >> of the sats and one of the component suppliers is known. (The scale is > >> novel, not the tech, demisabiliy is new though) > > > > 4 or 2 lasers on each sat (N-S, E-W) is potentially a very different > > matter from an IP routing standpoint. It still is a reduced set of > > variables, for a routing protocol (it is not like there being an > > arbitrary number of IP interfaces, it's just 2 or 4). > > > > For component manufacturers: yes, I heard about a few manufacturers of > > such equipment for laser comms for LEO sats, experimented. There is > > public information about a few of them. I dont know which is considere= d > > by starlink, but there is not my worry. There is also a difference > > between laser links between sats on different orbit altitudes (e.g. > > laser for ISL for GEO to MEO) and lasers between sats on a same orbit > > altitude, or on a same orbit. It's three different things, with > > different sets of requirements: focusing, power levels, distance ranges= . > > > > At the lowest limit (cheapest, less powerful, less range distance), I > > suppose it is possible to use simply LiFi optical links (a sort of WiFi > > but with light). If so, then it is very easy to have IP on it. > > > > There is also an 'optical' spec that was circulated here on this list > > ( > https://urldefense.com/v3/__https://www.sda.mil/wp-content/uploads/2022/0= 4/SDA-OCT-Standard-v3.0.pdf__;!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip= 5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYhXDWmzfQ$ > ), > > although it seemed to me to figure on kepler's website, not on > > starlink's. In that spec, it is said Ethernet, among other things. On > > Ethernet, IP can run easily. > > > >> > >> Starlink can't deliver to Antarctica or Northern parts of Alaska, > >> Ascension Island, Diego Garcia, Easter Island, Vanuatu, Iran without > >> ISL's etc > > > > I'll have to look where these places are. > > > > When looking at starlink satellites I often see trains forming and > > lasting for a while. Someone said these sats are like that (trains) > > prior to be put on a more evenly distanced, in-orbit; but some time > > passed, and they continue this kind of behaviour: form denser trains, > > then distance more evenly, and back again. So I am not sure these > > 'trains' are ephemeral. They seem to be in such 'train' structure whil= e > > above some particular continents or areas, but not sure. It takes a lo= t > > of time to make a meaning of it. > > > > Also, now here are at least two kinds of starlink subscription plans: > > 40EUR/month and 287EUR/month, for fixed vs mobile. > > > >> > >> North South links seem to work but not East West (if they exist) > > > > Yes, good question. It makes a lot of difference whether there are 2 o= r > > 4 laser links on each sat. It also makes a lot of difference if trying > > to make IP routing work there (assuming there could be 2 or 4 IP > > interfaces for lasers). > > > > This (number of ISL links on a starlink sat) can have an impact on how > > people show LEO satellite topologies in Internet Drafts at IETF. > > > > Alex > > > >> > >> On Thu, Sep 21, 2023, 2:20 PM Alexandre Petrescu via Starlink > >> wrote: > >> > >> > >> Le 19/09/2023 =C3=A0 06:39, Ulrich Speidel via Starlink a =C3=A9cr= it : > >> > FWIW, I gave a talk about Starlink - insights from a year in - > >> at last > >> > week's APNIC56 conference in Kyoto: > >> > > >> > > https://urldefense.com/v3/__https://conference.apnic.net/56/program/progr= am/*/day/6/technical-2/__;Iw!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K= 7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYjUChNXHQ$ > >> > >> > >> Thanks for the presentation. > >> > >> I would like to ask what do you mean by "Method #2: "space > >> lasers""and > >> "Not all Starlink satellites have > >> lasers" on slide 5? > >> > >> It seems to be saying there is inter-satellite communications. The > >> need > >> of that seems to stem from the lack of ground 'teleport' that is > >> necessary for DISHY-SAT-Internet communications, so a SAT-to-SAT > >> communication is apparently used with lasers. I can agree with > >> the need. > >> > >> What standard is used for these lasers? > >> > >> Is this ISL communicaiton within the starlink constellation a > >> supposition or a sure thing? > >> > >> Other presentations of starlink mentioned on this list dont talk > >> about > >> this lasers between sats (dont show lasers on the sats), but kepl= er > >> talks about optical links, and also there is talk about ISOC LEO > >> Internet about such 'lasers from space'. > >> > >> (I must say that I thought previously that there were only 2 or 3 > >> ground > >> teleports overall in EU and USA, but I see now there is a teleport > >> in NZ > >> too). > >> > >> (for price comparison: it is said 100USD monthly, but in France > right > >> now the monthly subscription is at around 40 Euros; this competes > >> very > >> advantageously to other satcoms ISPs for rural areas non-covered > >> by 5G; > >> the cellular monthly subscriptions are still much more advantageou= s, > >> where there is 5G, of course). > >> > >> Alex > >> > >> > > >> > Also well worth looking at is Geoff Huston's excellent piece on > the > >> > foreseeable demise of TCP in favour of QUIC in the same session. > >> One > >> > of Geoff's main arguments is that the Internet is becoming local= , > >> > i.e., most traffic goes between a CDN server and you, and most > >> data is > >> > becoming proprietary to the application owner, meaning it suits > the > >> > Googles and Facebooks of this world very well not to be using > >> TCP for > >> > its transport, but rather pull the transport specifics into the > >> > application layer where the have full control. > >> > > >> > Food for thought, especially since LEO networks are a > >> particularly bad > >> > place to put local content caches, since the concept of what's > >> "local" > >> > in a LEO network changes constantly, at around 20,000 miles an > >> hour or > >> > so. Spoke to a Rwandan colleague who installs Starlink there and > >> sees > >> > all traffic to anywhere go via the US with RTTs of nearly 2 > >> seconds, > >> > even if the Rwandan user is trying to access a Rwandan service. > >> > > >> > About to hop onto a plane (ZK-NZJ) tonight with free WiFi (Ka ba= nd > >> > GEO) enroute to Auckland in the hope of getting a better > experience > >> > than last time when the system seemed to run out of IP addresses > on > >> > its DHCP. > >> > > >> _______________________________________________ > >> Starlink mailing list > >> Starlink@lists.bufferbloat.net > >> > https://urldefense.com/v3/__https://lists.bufferbloat.net/listinfo/starli= nk__;!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4Et= POvEhS9XoLRaKS8QbVoEgYgJ4na9hA$ > >> > >> > >> _______________________________________________ > >> Starlink mailing list > >> Starlink@lists.bufferbloat.net > >> > https://urldefense.com/v3/__https://lists.bufferbloat.net/listinfo/starli= nk__;!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4Et= POvEhS9XoLRaKS8QbVoEgYgJ4na9hA$ > > _______________________________________________ > > Starlink mailing list > > Starlink@lists.bufferbloat.net > > > https://urldefense.com/v3/__https://lists.bufferbloat.net/listinfo/starli= nk__;!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4Et= POvEhS9XoLRaKS8QbVoEgYgJ4na9hA$ > > > _______________________________________________ > Starlink mailing list > Starlink@lists.bufferbloat.net > https://lists.bufferbloat.net/listinfo/starlink > --000000000000051c950606199709 Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable
I asked BING the same question, I got the following=C2=A0= response.=C2=A0

Start of BI= NG Response

"The second-generation Starlink satellites ar= e equipped with laser communication between satellites, wh= ich helps reduce latency to about 10-20 milliseconds, comp= ared to 17 milliseconds for fiber1. The laser communication system is about 40% faster than fiber due to the speed of light in vacuum= 1. Th= e number of laser transponders in a second-generation Starlink satellite is= not mentioned in the information I found. However, it is worth noting that the second-generati= on Starlink satellites are expected to be significantly more capable than t= heir predecessors1. T= hey will be larger and much faster, with a capacity of up to 80 Gbp= s per satellite, compared to 18 Gbps in the curre= nt version1= . The prop= osed Starlink Gen2 constellation, consisting of approximately 30,000 satell= ites, would have a total instantaneous bandwidth of at least 500 te= rabits per second (Tbps) over land, which is around 1800 Tbps incl= uding ocean coverage1.

Please note that the information I provided is = based on available sources and may not cover all the details about the seco= nd-generation Starlink satellites. For more specific information, it is rec= ommended to refer to official sources or SpaceX=E2=80=99s announcements.

Is there anything else I can help you with? =F0=9F=98=8A

Learn more:
=

" (End of BING Response)

Hesham

=


On Sa= t, Sep 23, 2023, 2:55 PM Larry Press via Starlink <starlink@lists.bufferbloat.net> wrote:<= br>
In his first Starlink simulation, Mark Hadley assumed five transponders per= satellite -- Two in-plane, two adjacent, and one crossing:

In his next Starlink simulation, Mark Hadley assumed four:

I guess he assumed the relative velocities were too high for the cross= ing connection.

I asked Bard "How many laser transponders are in a second-generat= ion Starlink satellite?" and it said "four."
I asked ChatGPT "How many laser transponders are in a second-gene= ration Starlink satellite?" and it said it did not know.
I asked Bard again and the second time it said it did not know.
When I pointed out that it had told me "four" the first time= I asked, Bard apologized for its previous answer.

I remain an "AI" skeptic:

From: S= tarlink <starlink-bounces@lists.bufferbloat.net&= gt; on behalf of David Lang via Starlink <starlink@lists.buf= ferbloat.net>
Sent: Friday, September 22, 2023 1:41 AM
To: Alexandre Petrescu <alexandre.petrescu@gmail.com>
Cc: starlink@lists.bufferbloat.net <s= tarlink@lists.bufferbloat.net>
Subject: Re: [Starlink] APNIC56 last week
=C2=A0
I believe that I read that STarlink has 5 lasers per sat. but whatever= the
number, it's a tiny number compared to the number of satellites that th= ey have
up there.

As you are looking at 'trains', check their altitude. They aren'= ;t going to
shuffle sats around much, it's expensive in terms of fuel and they are = only
allowed to provide service when they are in their proper orbits.

We know the lasers are in operation as they are providing service to places= more
than one sat hop away from ground stations. We also know they have a lot of=
ground stations around to share the load.

We have almost no details on the specific modules they are using, and none = on
what routing they are using.

David Lang


=C2=A0 On Fri, 22 Sep 2023,
Alexandre Petrescu via Starlink wrote:

> Date: Fri, 22 Sep 2023 10:26:26 +0200
> From: Alexandre Petrescu via Starlink <starlink@lists.b= ufferbloat.net>
> Reply-To: Alexandre Petrescu <alexandre.petrescu@gmail.co= m>
> To: starlink@lists.bufferbloat.net
> Subject: Re: [Starlink] APNIC56 last week
>
>
> Le 21/09/2023 =C3=A0 21:05, Inemesit Affia via Starlink a =C3=A9crit= =C2=A0:
>> Not going to go into details but lasers have been identified in ph= otos
>> of the sats and one of the component suppliers is known. (The scal= e is
>> novel, not the tech, demisabiliy is new though)
>
> 4 or 2 lasers on each sat=C2=A0 (N-S, E-W) is potentially a very diffe= rent
> matter from an IP routing standpoint.=C2=A0 It still is a reduced set = of
> variables, for a routing protocol (it is not like there being an
> arbitrary number of IP interfaces, it's just 2 or 4).
>
> For component manufacturers: yes, I heard about a few manufacturers of=
> such equipment for laser comms for LEO sats, experimented.=C2=A0 There= is
> public information about a few of them.=C2=A0 I dont know which is con= sidered
> by starlink, but there is not my worry.=C2=A0 There is also a differen= ce
> between laser links between sats on different orbit altitudes (e.g. > laser for ISL for GEO to MEO) and lasers between sats on a same orbit =
> altitude, or on a same orbit.=C2=A0 It's three different things, w= ith
> different sets of requirements: focusing, power levels, distance range= s.
>
> At the lowest limit (cheapest, less powerful, less range distance), I =
> suppose it is possible to use simply LiFi optical links (a sort of WiF= i
> but with light).=C2=A0 If so, then it is very easy to have IP on it. >
> There is also an 'optical' spec that was circulated here on th= is list
> (https://urldefense.com/v3/__https://www.= sda.mil/wp-content/uploads/2022/04/SDA-OCT-Standard-v3.0.pdf__;!!P7nkOOY!ps= o4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8Qb= VoEgYhXDWmzfQ$ ),
> although it seemed to me to figure on kepler's website, not on > starlink's.=C2=A0 In that spec, it is said Ethernet, among other t= hings.=C2=A0 On
> Ethernet, IP can run easily.
>
>>
>> Starlink can't deliver to Antarctica or Northern parts of Alas= ka,
>> Ascension Island, Diego Garcia, Easter Island, Vanuatu, Iran witho= ut
>> ISL's etc
>
> I'll have to look where these places are.
>
> When looking at starlink satellites I often see trains forming and > lasting for a while.=C2=A0 Someone said these sats are like that (trai= ns)
> prior to be put on a more evenly distanced, in-orbit; but some time > passed, and they continue this kind of behaviour: form denser trains, =
> then distance more evenly, and back again.=C2=A0 So I am not sure thes= e
> 'trains' are ephemeral.=C2=A0 They seem to be in such 'tra= in' structure while
> above some particular continents or areas, but not sure.=C2=A0 It take= s a lot
> of time to make a meaning of it.
>
> Also, now here are at least two kinds of starlink subscription plans: =
> 40EUR/month and 287EUR/month, for fixed vs mobile.
>
>>
>> North South links seem to work but not East West (if they exist) >
> Yes, good question.=C2=A0 It makes a lot of difference whether there a= re 2 or
> 4 laser links on each sat.=C2=A0 It also makes a lot of difference if = trying
> to make IP routing work there (assuming there could be 2 or 4 IP
> interfaces for lasers).
>
> This (number of ISL links on a starlink sat) can have an impact on how=
> people show LEO satellite topologies in Internet Drafts at IETF.
>
> Alex
>
>>
>> On Thu, Sep 21, 2023, 2:20 PM Alexandre Petrescu via Starlink
>> <starlink@lists.bufferbloat.net> wrote:
>>
>>
>>=C2=A0=C2=A0=C2=A0=C2=A0 Le 19/09/2023 =C3=A0 06:39, Ulrich Speidel= via Starlink a =C3=A9crit=C2=A0:
>>=C2=A0=C2=A0=C2=A0=C2=A0 > FWIW, I gave a talk about Starlink - = insights from a year in -
>>=C2=A0=C2=A0=C2=A0=C2=A0 at last
>>=C2=A0=C2=A0=C2=A0=C2=A0 > week's APNIC56 conference in Kyot= o:
>>=C2=A0=C2=A0=C2=A0=C2=A0 >
>>=C2=A0=C2=A0=C2=A0=C2=A0 > https://urldefense.com/v3/__https://conference.apnic.net/56/program/program= /*/day/6/technical-2/__;Iw!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7p= xmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYjUChNXHQ$
>>
>>
>>=C2=A0=C2=A0=C2=A0=C2=A0 Thanks for the presentation.
>>
>>=C2=A0=C2=A0=C2=A0=C2=A0 I would like to ask what do you mean by &q= uot;Method #2: "space
>>=C2=A0=C2=A0=C2=A0=C2=A0 lasers""and
>>=C2=A0=C2=A0=C2=A0=C2=A0 "Not all Starlink satellites have
>>=C2=A0=C2=A0=C2=A0=C2=A0 lasers" on slide 5?
>>
>>=C2=A0=C2=A0=C2=A0=C2=A0 It seems to be saying there is inter-satel= lite communications. The
>>=C2=A0=C2=A0=C2=A0=C2=A0 need
>>=C2=A0=C2=A0=C2=A0=C2=A0 of that seems to stem from the lack of gro= und 'teleport' that is
>>=C2=A0=C2=A0=C2=A0=C2=A0 necessary for DISHY-SAT-Internet communica= tions, so a SAT-to-SAT
>>=C2=A0=C2=A0=C2=A0=C2=A0 communication is apparently used with lase= rs.=C2=A0 I can agree with
>>=C2=A0=C2=A0=C2=A0=C2=A0 the need.
>>
>>=C2=A0=C2=A0=C2=A0=C2=A0 What standard is used for these lasers? >>
>>=C2=A0=C2=A0=C2=A0=C2=A0 Is this ISL communicaiton within the starl= ink constellation a
>>=C2=A0=C2=A0=C2=A0=C2=A0 supposition or a sure thing?
>>
>>=C2=A0=C2=A0=C2=A0=C2=A0 Other presentations of starlink mentioned = on this list dont talk
>>=C2=A0=C2=A0=C2=A0=C2=A0 about
>>=C2=A0=C2=A0=C2=A0=C2=A0 this lasers between sats (dont show=C2=A0 = lasers on the sats), but kepler
>>=C2=A0=C2=A0=C2=A0=C2=A0 talks about optical links, and also there = is talk about ISOC LEO
>>=C2=A0=C2=A0=C2=A0=C2=A0 Internet about such 'lasers from space= '.
>>
>>=C2=A0=C2=A0=C2=A0=C2=A0 (I must say that I thought previously that= there were only 2 or 3
>>=C2=A0=C2=A0=C2=A0=C2=A0 ground
>>=C2=A0=C2=A0=C2=A0=C2=A0 teleports overall in EU and USA, but I see= now there is a teleport
>>=C2=A0=C2=A0=C2=A0=C2=A0 in NZ
>>=C2=A0=C2=A0=C2=A0=C2=A0 too).
>>
>>=C2=A0=C2=A0=C2=A0=C2=A0 (for price comparison: it is said 100USD m= onthly, but in France right
>>=C2=A0=C2=A0=C2=A0=C2=A0 now the monthly subscription is at around = 40 Euros;=C2=A0 this competes
>>=C2=A0=C2=A0=C2=A0=C2=A0 very
>>=C2=A0=C2=A0=C2=A0=C2=A0 advantageously to other satcoms ISPs for r= ural areas non-covered
>>=C2=A0=C2=A0=C2=A0=C2=A0 by 5G;
>>=C2=A0=C2=A0=C2=A0=C2=A0 the cellular monthly subscriptions are sti= ll much more advantageous,
>>=C2=A0=C2=A0=C2=A0=C2=A0 where there is 5G, of course).
>>
>>=C2=A0=C2=A0=C2=A0=C2=A0 Alex
>>
>>=C2=A0=C2=A0=C2=A0=C2=A0 >
>>=C2=A0=C2=A0=C2=A0=C2=A0 > Also well worth looking at is Geoff H= uston's excellent piece on the
>>=C2=A0=C2=A0=C2=A0=C2=A0 > foreseeable demise of TCP in favour o= f QUIC in the same session.
>>=C2=A0=C2=A0=C2=A0=C2=A0 One
>>=C2=A0=C2=A0=C2=A0=C2=A0 > of Geoff's main arguments is that= the Internet is becoming local,
>>=C2=A0=C2=A0=C2=A0=C2=A0 > i.e., most traffic goes between a CDN= server and you, and most
>>=C2=A0=C2=A0=C2=A0=C2=A0 data is
>>=C2=A0=C2=A0=C2=A0=C2=A0 > becoming proprietary to the applicati= on owner, meaning it suits the
>>=C2=A0=C2=A0=C2=A0=C2=A0 > Googles and Facebooks of this world v= ery well not to be using
>>=C2=A0=C2=A0=C2=A0=C2=A0 TCP for
>>=C2=A0=C2=A0=C2=A0=C2=A0 > its transport, but rather pull the tr= ansport specifics into the
>>=C2=A0=C2=A0=C2=A0=C2=A0 > application layer where the have full= control.
>>=C2=A0=C2=A0=C2=A0=C2=A0 >
>>=C2=A0=C2=A0=C2=A0=C2=A0 > Food for thought, especially since LE= O networks are a
>>=C2=A0=C2=A0=C2=A0=C2=A0 particularly bad
>>=C2=A0=C2=A0=C2=A0=C2=A0 > place to put local content caches, si= nce the concept of what's
>>=C2=A0=C2=A0=C2=A0=C2=A0 "local"
>>=C2=A0=C2=A0=C2=A0=C2=A0 > in a LEO network changes constantly, = at around 20,000 miles an
>>=C2=A0=C2=A0=C2=A0=C2=A0 hour or
>>=C2=A0=C2=A0=C2=A0=C2=A0 > so. Spoke to a Rwandan colleague who = installs Starlink there and
>>=C2=A0=C2=A0=C2=A0=C2=A0 sees
>>=C2=A0=C2=A0=C2=A0=C2=A0 > all traffic to anywhere go via the US= with RTTs of nearly 2
>>=C2=A0=C2=A0=C2=A0=C2=A0 seconds,
>>=C2=A0=C2=A0=C2=A0=C2=A0 > even if the Rwandan user is trying to= access a Rwandan service.
>>=C2=A0=C2=A0=C2=A0=C2=A0 >
>>=C2=A0=C2=A0=C2=A0=C2=A0 > About to hop onto a plane (ZK-NZJ) to= night with free WiFi (Ka band
>>=C2=A0=C2=A0=C2=A0=C2=A0 > GEO) enroute to Auckland in the hope = of getting a better experience
>>=C2=A0=C2=A0=C2=A0=C2=A0 > than last time when the system seemed= to run out of IP addresses on
>>=C2=A0=C2=A0=C2=A0=C2=A0 > its DHCP.
>>=C2=A0=C2=A0=C2=A0=C2=A0 >
>>=C2=A0=C2=A0=C2=A0=C2=A0 __________________________________________= _____
>>=C2=A0=C2=A0=C2=A0=C2=A0 Starlink mailing list
>>=C2=A0=C2=A0=C2=A0=C2=A0 Starlink@lists.bufferbloat.net=
>>=C2=A0=C2=A0=C2=A0=C2=A0 https://urldefense.com/v3/__https://lists.bufferbloat.net/listinfo/starlink= __;!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPO= vEhS9XoLRaKS8QbVoEgYgJ4na9hA$
>>
>>
>> _______________________________________________
>> Starlink mailing list
>> Starlink@lists.bufferbloat.net
>> https://urldefense.com/v3/__https://lists.bufferbloat.net/listinfo/starlink= __;!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPO= vEhS9XoLRaKS8QbVoEgYgJ4na9hA$
> _______________________________________________
> Starlink mailing list
> Starlink@lists.bufferbloat.net
> https://urldefense.com/v3/__https://lists.bufferbloat.net/listinfo/starlink= __;!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPO= vEhS9XoLRaKS8QbVoEgYgJ4na9hA$
>
_______________________________________________
Starlink mailing list
Starlink@lists.bufferbloat.net
https://lists.bufferbloat.net/listinfo/sta= rlink
--000000000000051c950606199709--