[Starlink] APNIC56 last week

[Starlink] APNIC56 last week

[Ulrich Speidel]

FWIW, I gave a talk about Starlink - insights from a year in - at last 
week's APNIC56 conference in Kyoto:

https://conference.apnic.net/56/program/program/#/day/6/technical-2/

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 band 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.

-- 
****************************************************************
Dr. Ulrich Speidel

School of Computer Science

Room 303S.594 (City Campus)

The University of Auckland
u.speidel@auckland.ac.nz
http://www.cs.auckland.ac.nz/~ulrich/
****************************************************************

Re: [Starlink] APNIC56 last week

[Dave Taht]

[-- Attachment #1: Type: text/plain, Size: 4174 bytes --]

On Mon, Sep 18, 2023 at 9:39 PM Ulrich Speidel via Starlink <
starlink@lists.bufferbloat.net> wrote:

> FWIW, I gave a talk about Starlink - insights from a year in - at last
> week's APNIC56 conference in Kyoto:
>
> https://conference.apnic.net/56/program/program/#/day/6/technical-2/
>
> 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.


I worked through both presentations just now, thank you.

As vs Geoffs presentation on QUIC eating the universe in terms of traffic
volume, and the world becoming a giant content distribution network, I
still hold, that the internet is a communications network, and that despite
content moving ever closer to the edges, more private content, and
connecting people to people, and vpns to corporations, will remain an
important use case. Ssh as one example, still holds the underpinnings of
the network together, and is very low traffic volume, and there is no such
thing as a "voip caching server". Also, big providers of replicated
content, such as steam, are experimenting with bittorrent-like techniques
again. QUIC makes torrent extremely feasible once again.

I liked that geoff left traffic shaping as a question at the end. I have
long opposed DPI based methods! However, inserting well defined drop and
marking and fq-ing behaviors into the network has long seemed to be a major
step forward.

In the case of quic, despite its ability to multiplex flows on one
connection to the google mainframe, I still usually see many connections
opened to collect various assets.

It was also interesting to see higher adoption of Quic in south america,
rather than America. why is that? Whatsapp dominates down there...


> 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.
>

Africa I hope is moving towards localizing its content also. More IXPs are
needed worldwide. Despite the siloing of content into apple, google,
facebook burbclaves, and wars between the telcos, they need to interconnect
somewhere.


> About to hop onto a plane (ZK-NZJ) tonight with free WiFi (Ka band 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.
>
>
How did it go? The world record for bufferbloat related delay on a plane is
held by dave reed, at 860 seconds. I would love to see a plane flent trace
that held it below 30ms.

https://paxex.aero/jsx-starlink-spacex-review/ did pretty well.

I hope in qualifying the wifi gear for a plane, they manage the bloat
better, and actually test what happens when 300 passengers are attempting
to stream both local videocontent and use the web.





> --
> ****************************************************************
> Dr. Ulrich Speidel
>
> School of Computer Science
>
> Room 303S.594 (City Campus)
>
> The University of Auckland
> u.speidel@auckland.ac.nz
> http://www.cs.auckland.ac.nz/~ulrich/
> ****************************************************************
>
>
>
> _______________________________________________
> Starlink mailing list
> Starlink@lists.bufferbloat.net
> https://lists.bufferbloat.net/listinfo/starlink
>


-- 
Oct 30: https://netdevconf.info/0x17/news/the-maestro-and-the-music-bof.html
Dave Täht CSO, LibreQos

[-- Attachment #2: Type: text/html, Size: 6034 bytes --]

Re: [Starlink] APNIC56 last week

[Alexandre Petrescu]

Le 19/09/2023 à 06:39, Ulrich Speidel via Starlink a écrit :
> FWIW, I gave a talk about Starlink - insights from a year in - at last 
> week's APNIC56 conference in Kyoto:
>
> https://conference.apnic.net/56/program/program/#/day/6/technical-2/


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 kepler 
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 advantageous, 
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 band 
> 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.
>

Re: [Starlink] APNIC56 last week

[Inemesit Affia]

[-- Attachment #1: Type: text/plain, Size: 3593 bytes --]

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)

Starlink can't deliver to Antarctica or Northern parts of Alaska, Ascension
Island, Diego Garcia, Easter Island, Vanuatu, Iran without ISL's etc

North South links seem to work but not East West (if they exist)

On Thu, Sep 21, 2023, 2:20 PM Alexandre Petrescu via Starlink <
starlink@lists.bufferbloat.net> wrote:

>
> Le 19/09/2023 à 06:39, Ulrich Speidel via Starlink a écrit :
> > FWIW, I gave a talk about Starlink - insights from a year in - at last
> > week's APNIC56 conference in Kyoto:
> >
> > https://conference.apnic.net/56/program/program/#/day/6/technical-2/
>
>
> 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 kepler
> 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 advantageous,
> 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 band
> > 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://lists.bufferbloat.net/listinfo/starlink
>

[-- Attachment #2: Type: text/html, Size: 4599 bytes --]

Re: [Starlink] APNIC56 last week

[Dave Taht]

[-- Attachment #1: Type: text/plain, Size: 4312 bytes --]

One of the things that amazes me is how do they go about focusing the ISLs?

There was a really neat laser MEMs switch chip that google showed off in
some recent presentation that I forget the name of and a few interesting
patents.



On Thu, Sep 21, 2023 at 12:05 PM Inemesit Affia via Starlink <
starlink@lists.bufferbloat.net> wrote:

> 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)
>
> Starlink can't deliver to Antarctica or Northern parts of Alaska,
> Ascension Island, Diego Garcia, Easter Island, Vanuatu, Iran without ISL's
> etc
>
> North South links seem to work but not East West (if they exist)
>
> On Thu, Sep 21, 2023, 2:20 PM Alexandre Petrescu via Starlink <
> starlink@lists.bufferbloat.net> wrote:
>
>>
>> Le 19/09/2023 à 06:39, Ulrich Speidel via Starlink a écrit :
>> > FWIW, I gave a talk about Starlink - insights from a year in - at last
>> > week's APNIC56 conference in Kyoto:
>> >
>> > https://conference.apnic.net/56/program/program/#/day/6/technical-2/
>>
>>
>> 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 kepler
>> 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 advantageous,
>> 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 band
>> > 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://lists.bufferbloat.net/listinfo/starlink
>>
> _______________________________________________
> Starlink mailing list
> Starlink@lists.bufferbloat.net
> https://lists.bufferbloat.net/listinfo/starlink
>


-- 
Oct 30: https://netdevconf.info/0x17/news/the-maestro-and-the-music-bof.html
Dave Täht CSO, LibreQos

[-- Attachment #2: Type: text/html, Size: 6026 bytes --]

Re: [Starlink] APNIC56 last week

[Alexandre Petrescu]

Le 21/09/2023 à 21:05, Inemesit Affia via Starlink a écrit :
> 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 considered 
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://www.sda.mil/wp-content/uploads/2022/04/SDA-OCT-Standard-v3.0.pdf), 
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 while 
above some particular continents or areas, but not sure.  It takes 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.  It makes a lot of difference whether there are 2 or 
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 
> <starlink@lists.bufferbloat.net> wrote:
>
>
>     Le 19/09/2023 à 06:39, Ulrich Speidel via Starlink a écrit :
>     > FWIW, I gave a talk about Starlink - insights from a year in -
>     at last
>     > week's APNIC56 conference in Kyoto:
>     >
>     > https://conference.apnic.net/56/program/program/#/day/6/technical-2/
>
>
>     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 kepler
>     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 advantageous,
>     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 band
>     > 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://lists.bufferbloat.net/listinfo/starlink
>
>
> _______________________________________________
> Starlink mailing list
> Starlink@lists.bufferbloat.net
> https://lists.bufferbloat.net/listinfo/starlink

Re: [Starlink] APNIC56 last week

[David Lang]

[-- Attachment #1: Type: text/plain, Size: 7919 bytes --]

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 they 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


  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.bufferbloat.net>
> Reply-To: Alexandre Petrescu <alexandre.petrescu@gmail.com>
> To: starlink@lists.bufferbloat.net
> Subject: Re: [Starlink] APNIC56 last week
> 
>
> Le 21/09/2023 à 21:05, Inemesit Affia via Starlink a écrit :
>> 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 considered 
> 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://www.sda.mil/wp-content/uploads/2022/04/SDA-OCT-Standard-v3.0.pdf), 
> 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 while 
> above some particular continents or areas, but not sure.  It takes 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.  It makes a lot of difference whether there are 2 or 
> 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 
>> <starlink@lists.bufferbloat.net> wrote:
>>
>>
>>     Le 19/09/2023 à 06:39, Ulrich Speidel via Starlink a écrit :
>>     > FWIW, I gave a talk about Starlink - insights from a year in -
>>     at last
>>     > week's APNIC56 conference in Kyoto:
>>     >
>>     > https://conference.apnic.net/56/program/program/#/day/6/technical-2/
>>
>>
>>     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 kepler
>>     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 advantageous,
>>     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 band
>>     > 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://lists.bufferbloat.net/listinfo/starlink
>>
>>
>> _______________________________________________
>> 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
>

Re: [Starlink] APNIC56 last week

[Michael Richardson]

[-- Attachment #1: Type: text/plain, Size: 419 bytes --]


David Lang via Starlink <starlink@lists.bufferbloat.net> wrote:
    > 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.

But, is it still bent pipe (long, kinked, fine) solution?
There are no L2 or L3 decisions being made in the satellites themselves yet?


[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 511 bytes --]

Re: [Starlink] APNIC56 last week

[David Lang]

We don't know what their routing in space is. But we know that it isn't just up 
to a single satellite and back down to a ground station.

But I will say that since they NAT the connection at the ground station (or 
Internet peering point), and not allowing dishy-to-dishy direct communications 
yet, they aren't sending different packets to different destinations, they are 
sending them all to the single internet gateway

David Lang

On Fri, 22 Sep 2023, Michael Richardson wrote:

> David Lang via Starlink <starlink@lists.bufferbloat.net> wrote:
>    > 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.
>
> But, is it still bent pipe (long, kinked, fine) solution?
> There are no L2 or L3 decisions being made in the satellites themselves yet?
>
>

Re: [Starlink] APNIC56 last week

[Michael Richardson]

[-- Attachment #1: Type: text/plain, Size: 1032 bytes --]


David Lang <david@lang.hm> wrote:
    > We don't know what their routing in space is. But we know that it isn't just
    > up to a single satellite and back down to a ground station.

If the "routing" was all based upon a connecting a circuit from a dishy
to a ground station, and they never look into the packets, then it sounds
like bent pipe to me.  Even though the specific physical path would change
every ~15 minutes.
One could do this with a variety of technologies, but I'd probably use MPLS.

OTH, if a dishy could be moved from one ground station to another, then
that's a different matter.

    > But I will say that since they NAT the connection at the ground station (or
    > Internet peering point), and not allowing dishy-to-dishy direct

I don't think that the l3 NAT44 is particularly relevant in this case.
One could easily allow for dishy-to-dishy "behind" the NAT, but it requires
an L3 decision point before the NAT44/Internet-Peering-Point.

I thought that there was many with working IPv6?
(but not all)




[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 511 bytes --]

Re: [Starlink] APNIC56 last week

[Noel Butler]

[-- Attachment #1: Type: text/plain, Size: 1871 bytes --]

On 20/09/2023 11:13, Dave Taht via Starlink wrote:

> As vs Geoffs presentation on QUIC eating the universe in terms of 
> traffic volume, and the world becoming a giant content distribution 
> network, I still hold, that the internet is a communications network, 
> and that despite content moving ever closer to the edges, more private 
> content, and connecting people to people, and vpns to corporations, 
> will remain an important use case. Ssh as one example, still holds the 
> underpinnings of the network together, and is very low traffic volume, 
> and there is no such thing as a "voip caching server". Also, big 
> providers of replicated content, such as steam, are experimenting with 
> bittorrent-like techniques again. QUIC makes torrent extremely feasible 
> once again.

Despite my high level of respect for Geoff, he, and others like him, 
often talk things up to push things their way of thinking, we only need 
look at the FUD they came out with in mid 90's about IPv4's imminent 
demise giving it three to five years before depletion, and here we are 
30 years later and it is still the most dominant transport protocol by a 
long long mile despite allegedly  running out only a few years ago and 
not in early 2000's as they tried to claim. (Even today there are still 
reserve stocks on /24's for newbies from some regions, and the bigger 
networks have years of stockpiled addresses in reserve).

It's also like the local water board here who last week came out saying 
a whopping 70% of people surveyed said they'd drink recycled water, of 
course it was the local water board that conducted this alleged survey, 
because >90% of the more independent polling shows a totally different 
story.

"Ohh, everybody's doing it"  "must be safe" "we should do it"  ... 
nah... TCP isn't going anywhere, nor is UDP, not in my lifetime anyway 
:)

Cheers

[-- Attachment #2: Type: text/html, Size: 2409 bytes --]

Re: [Starlink] APNIC56 last week

[Vint Cerf]

[-- Attachment #1.1: Type: text/plain, Size: 2714 bytes --]

Noel, IPv4 is only managing to work because it is NATted - going to IPv6
let's us get back to point-to-point in either direction including
rendezvous.
The present IPv4 situation is NOT good - people are paying $35-50 per IPv4
address to acquire or even to lease them. For all practical purposes, IPv4
has run out.

vint


On Fri, Sep 22, 2023 at 9:33 PM Noel Butler via Starlink <
starlink@lists.bufferbloat.net> wrote:

> On 20/09/2023 11:13, Dave Taht via Starlink wrote:
>
>
>
> As vs Geoffs presentation on QUIC eating the universe in terms of traffic
> volume, and the world becoming a giant content distribution network, I
> still hold, that the internet is a communications network, and that despite
> content moving ever closer to the edges, more private content, and
> connecting people to people, and vpns to corporations, will remain an
> important use case. Ssh as one example, still holds the underpinnings of
> the network together, and is very low traffic volume, and there is no such
> thing as a "voip caching server". Also, big providers of replicated
> content, such as steam, are experimenting with bittorrent-like techniques
> again. QUIC makes torrent extremely feasible once again.
>
>
> Despite my high level of respect for Geoff, he, and others like him, often
> talk things up to push things their way of thinking, we only need look at
> the FUD they came out with in mid 90's about IPv4's imminent demise giving
> it three to five years before depletion, and here we are 30 years later and
> it is still the most dominant transport protocol by a long long mile
> despite allegedly  running out only a few years ago and not in early 2000's
> as they tried to claim. (Even today there are still reserve stocks on /24's
> for newbies from some regions, and the bigger networks have years of
> stockpiled addresses in reserve).
>
> It's also like the local water board here who last week came out saying a
> whopping 70% of people surveyed said they'd drink recycled water, of course
> it was the local water board that conducted this alleged survey, because
> >90% of the more independent polling shows a totally different story.
>
> "Ohh, everybody's doing it"  "must be safe" "we should do it"  ... nah...
> TCP isn't going anywhere, nor is UDP, not in my lifetime anyway :)
>
> Cheers
>
>
> _______________________________________________
> Starlink mailing list
> Starlink@lists.bufferbloat.net
> https://lists.bufferbloat.net/listinfo/starlink
>


-- 
Please send any postal/overnight deliveries to:
Vint Cerf
Google, LLC
1900 Reston Metro Plaza, 16th Floor
Reston, VA 20190
+1 (571) 213 1346


until further notice

[-- Attachment #1.2: Type: text/html, Size: 3982 bytes --]

[-- Attachment #2: S/MIME Cryptographic Signature --]
[-- Type: application/pkcs7-signature, Size: 3995 bytes --]

Re: [Starlink] APNIC56 last week

[Noel Butler]

[-- Attachment #1: Type: text/plain, Size: 1212 bytes --]

Hi Vint,

On 23/09/2023 11:47, Vint Cerf wrote:

> Noel, IPv4 is only managing to work because it is NATted - going to 
> IPv6 let's us get back to point-to-point in either direction including 
> rendezvous.
> The present IPv4 situation is NOT good - people are paying $35-50 per 
> IPv4 address to acquire or even to lease them. For all practical 
> purposes, IPv4 has run out.
> 
> vint

Oh I agree it's not a good situation, but my point was it's still most 
dominant 30 years after they claimed we had about 5 years, it's like the 
little boy who cried wolf, if they held off the hysterics until it was 
proved imminent, I've no doubt the update would be greater and taken 
more seriously (I've used IPv6 for over 10 years myself), but the global 
low uptake is what causes ISP's and Telco's to use CGNAT, its free and 
plentiful, so it still wont be laid to rest for a while yet.

IPv6 is only 4% of traffic that hits my Mail Servers, it's less than 1% 
on my Web servers.

Just like TCP, it wont be going anywhere, not quietly, and if it were 
to, likely be long after I'm gone, QUIC seems an interesting project, 
and I guess only the decades ahead of us will tell of it becomes a 
raging success.

Cheers

[-- Attachment #2: Type: text/html, Size: 1743 bytes --]

Re: [Starlink] APNIC56 last week

[Gert Doering]

Hi,

On Sat, Sep 23, 2023 at 02:22:58PM +1000, Noel Butler via Starlink wrote:
> Oh I agree it's not a good situation, but my point was it's still most
> dominant 30 years after they claimed we had about 5 years, 

This is not actually a contradiction.

IPv4 *has* run out - but that does not mean (and never meant) "the existing
IPv4 network will stop working over night".

It just means "building new IPv4 networks is way more expensive" and
"doing anything useful with IPv4 heaps up more and more technical dept"
(like, multiple layers of NAT44 inside Enterprise networks).

Moving more actively towards IPv6 would have avoided many of the costs
we're facing today.

> it's like the
> little boy who cried wolf, if they held off the hysterics until it was
> proved imminent, I've no doubt the update would be greater and taken more
> seriously (I've used IPv6 for over 10 years myself), but the global low
> uptake is what causes ISP's and Telco's to use CGNAT, its free and
> plentiful, so it still wont be laid to rest for a while yet.

Well, CGNAT is far from "free".  Have you had a look what vendors charge
for a 100G-capable CGNAT box?

But indeed, IPv6 deployment is still spotty.  Some countries are doing
well (like, Germany, with all major access and mobile providers providing
IPv6 as normal part of the service), others try to ignore it away (Italy)...

Gert Doering
        -- NetMaster
-- 
have you enabled IPv6 on something today...?

SpaceNet AG                      Vorstand: Sebastian v. Bomhard, Michael Emmer
Joseph-Dollinger-Bogen 14        Aufsichtsratsvors.: A. Grundner-Culemann
D-80807 Muenchen                 HRB: 136055 (AG Muenchen)
Tel: +49 (0)89/32356-444         USt-IdNr.: DE813185279

Re: [Starlink] APNIC56 last week

[Ulrich Speidel]

On 23/09/2023 4:22 pm, Noel Butler via Starlink wrote:
> IPv6 is only 4% of traffic that hits my Mail Servers, it's less than 
> 1% on my Web servers.
> Just like TCP, it wont be going anywhere, not quietly, and if it were 
> to, likely be long after I'm gone, QUIC seems an interesting project, 
> and I guess only the decades ahead of us will tell of it becomes a 
> raging success.

Now what that tells me is that you and those that use your mail / web 
servers are within networks that are either in networks that are old and 
have legacy IPv4 allocations, or that are new, desparate, and rich. And 
Geoff, if you asked him, would tell you that this is perfectly fine by 
him - as long as you're happy with it. In fact, I can recall a 
presentation of his not too long ago (APNIC54, AINTEC22?) where he said 
pretty much exactly that he didn't foresee a rapid demise of IPv4.

But if you look at the Internet as a whole - and Geoff does, in a very 
ingenious way, I might add - then we notice that the percentage of IPv6 
out there has been growing steadily. IPv6 is now what about half of 
Internet users use. Maybe not the folk that visit your services, but 
Internet users nonetheless. So you're in the process of being 
outnumbered. But that's perhaps of academic interest only, for now, at 
least.

What's a bit more pertinent in some respects is a point that Vint 
brought up, and this is that if you want a new IPv4 address these days, 
you will generally need to buy it from someone who has an allocation. Or 
lease it - which is a little controversial, but not a debate I'm wanting 
to enter here. Let's stay with the buying price tag for a moment.

I came home from APNIC54 last year with the insight that my employer's 
/16 IPv4 allocation was worth around US$3.5 million. Since we've had the 
/16 for ages, I started wondering whether this was even on our asset 
list. I was pretty sure that it ought to be. Turns out it wasn't - when 
every $100 monitor in our place is. So I started asking questions and am 
told that there was a hastily arranged meeting between IT and Finance.

The upshot is that we now have a $3.5m asset on our books that may 
appreciate or depreciate, and people who are responsible for managing 
it. In fact, I dug a bit further and found a total of around NZ$100m 
worth of IPv4 addresses in NZ's public sector, including a /16 held by a 
government department that wasn't part of any AS. NZ's auditor general's 
office told me that they expected public sector agencies to list IPv4 
holdings on their balance sheets.

Why is this important? Because otherwise, there is nothing that stops an 
individual with access to your RIR account from transferring your IPv4 
holdings to whichever party they so desire. If the addresses are not on 
your asset list, then there's nothing that documents that you own the 
value that is inherent in them and thus nothing to sue anyone for. One 
imagines this as the ultimate stunt that a disgruntled sysadmin might 
pull off before they leave your employ.

But let's get back to that newly-found asset that we now have to manage. 
Your next CGNAT now becomes an investment in making that newly-found 
asset a little less tradable. A bit like putting a shiny new building 
right onto the only access way to your back sections you've just been 
told you can actually develop.

Of course, this only applies to folk who sit on larger address blocks - 
for a /24, it won't make much of a difference on the balance sheet.

-- 

****************************************************************
Dr. Ulrich Speidel

School of Computer Science

Room 303S.594 (City Campus)

The University of Auckland
u.speidel@auckland.ac.nz
http://www.cs.auckland.ac.nz/~ulrich/
****************************************************************

Re: [Starlink] APNIC56 last week

[Sebastian Moeller]

Hi Ulrich,


nice tangential discussion. I guess what we might expect is some "Kipp-Punkt"/tipping-point at which acquiring new IPv4 becomes cost prohibitive enough so new deployments go IPv6 only, at which point the existing IPv4 offers might devaluate pretty quickly... Now, if IPv6 would have been made more like IPv4 this would be considerably easier (I am thinking DHPCv6 and Android devices here, and I am only speaking of ease of deployment; I accept there are valid reasons for a SLAAC-only position like Android's). The US$1 million (or better 3.5 Million) question is when this tipping-point will be?
Tangent: German ISPs tend to charge ~5EUR/month extra for static public IPv4 addresses so over a typical 24 month contract period can easily tolerate a cost of 5*24 = 120 EUR for an IPv4 address (that will afterwards still be in the ISP's property). They typically provision either full DualStack (from the incumbent sitting on a large pile of IPv4s) or ds-lite and for a few unfortunate one's CG-NAT-IPv4 only. But even the IPv6 addresses/prefixes are typically dynamically assigned with relative short renewal periods (like 24 hours). 

Regards
	Sebastian


P.S.: My personal gripes with IPv6 are much smaller, I mostly miss stuff like ICMP timestamps in ICMPv6 and the IP timestamp option in IPv6*, or the fact that privacy extensions (as well intended as they are) make it harder for novice users to actually use their IPv6 globally routable addresses to make services available.

*) I think I understand the limitations of both ICMP and IP timestamps compared to the more elaborate alternatives that have been RFC'd as alternatives and that apparently convinced team IPv6 to not carry these things over from IPv4, but boy, no amount of higher temporal precision makes up for the point that many deployed servers today happily respond tp ICMP/IP timestamp requests, ubiquity in itself is a major asset.


> On Sep 23, 2023, at 12:53, Ulrich Speidel via Starlink <starlink@lists.bufferbloat.net> wrote:
> 
> On 23/09/2023 4:22 pm, Noel Butler via Starlink wrote:
>> IPv6 is only 4% of traffic that hits my Mail Servers, it's less than 1% on my Web servers.
>> Just like TCP, it wont be going anywhere, not quietly, and if it were to, likely be long after I'm gone, QUIC seems an interesting project, and I guess only the decades ahead of us will tell of it becomes a raging success.
> 
> Now what that tells me is that you and those that use your mail / web servers are within networks that are either in networks that are old and have legacy IPv4 allocations, or that are new, desparate, and rich. And Geoff, if you asked him, would tell you that this is perfectly fine by him - as long as you're happy with it. In fact, I can recall a presentation of his not too long ago (APNIC54, AINTEC22?) where he said pretty much exactly that he didn't foresee a rapid demise of IPv4.
> 
> But if you look at the Internet as a whole - and Geoff does, in a very ingenious way, I might add - then we notice that the percentage of IPv6 out there has been growing steadily. IPv6 is now what about half of Internet users use. Maybe not the folk that visit your services, but Internet users nonetheless. So you're in the process of being outnumbered. But that's perhaps of academic interest only, for now, at least.
> 
> What's a bit more pertinent in some respects is a point that Vint brought up, and this is that if you want a new IPv4 address these days, you will generally need to buy it from someone who has an allocation. Or lease it - which is a little controversial, but not a debate I'm wanting to enter here. Let's stay with the buying price tag for a moment.
> 
> I came home from APNIC54 last year with the insight that my employer's /16 IPv4 allocation was worth around US$3.5 million. Since we've had the /16 for ages, I started wondering whether this was even on our asset list. I was pretty sure that it ought to be. Turns out it wasn't - when every $100 monitor in our place is. So I started asking questions and am told that there was a hastily arranged meeting between IT and Finance.
> 
> The upshot is that we now have a $3.5m asset on our books that may appreciate or depreciate, and people who are responsible for managing it. In fact, I dug a bit further and found a total of around NZ$100m worth of IPv4 addresses in NZ's public sector, including a /16 held by a government department that wasn't part of any AS. NZ's auditor general's office told me that they expected public sector agencies to list IPv4 holdings on their balance sheets.
> 
> Why is this important? Because otherwise, there is nothing that stops an individual with access to your RIR account from transferring your IPv4 holdings to whichever party they so desire. If the addresses are not on your asset list, then there's nothing that documents that you own the value that is inherent in them and thus nothing to sue anyone for. One imagines this as the ultimate stunt that a disgruntled sysadmin might pull off before they leave your employ.
> 
> But let's get back to that newly-found asset that we now have to manage. Your next CGNAT now becomes an investment in making that newly-found asset a little less tradable. A bit like putting a shiny new building right onto the only access way to your back sections you've just been told you can actually develop.
> 
> Of course, this only applies to folk who sit on larger address blocks - for a /24, it won't make much of a difference on the balance sheet.
> 
> -- 
> 
> ****************************************************************
> Dr. Ulrich Speidel
> 
> School of Computer Science
> 
> Room 303S.594 (City Campus)
> 
> The University of Auckland
> u.speidel@auckland.ac.nz
> http://www.cs.auckland.ac.nz/~ulrich/
> ****************************************************************
> 
> 
> 
> _______________________________________________
> Starlink mailing list
> Starlink@lists.bufferbloat.net
> https://lists.bufferbloat.net/listinfo/starlink

Re: [Starlink] APNIC56 last week

[Hesham ElBakoury]

[-- Attachment #1: Type: text/plain, Size: 2452 bytes --]

In this Geoff blog (
https://blog.apnic.net/2022/05/04/the-transition-to-ipv6-are-we-there-yet/)
figure 1 shows the increasing IPv6 uptake since 2012 and figure 3 shows the
increasing price of IPv4 addresses. Geoff concluded by saying that he does
not know when the IPv6 transition will end.

Hesham

On Fri, Sep 22, 2023, 6:33 PM Noel Butler via Starlink <
starlink@lists.bufferbloat.net> wrote:

> On 20/09/2023 11:13, Dave Taht via Starlink wrote:
>
>
>
> As vs Geoffs presentation on QUIC eating the universe in terms of traffic
> volume, and the world becoming a giant content distribution network, I
> still hold, that the internet is a communications network, and that despite
> content moving ever closer to the edges, more private content, and
> connecting people to people, and vpns to corporations, will remain an
> important use case. Ssh as one example, still holds the underpinnings of
> the network together, and is very low traffic volume, and there is no such
> thing as a "voip caching server". Also, big providers of replicated
> content, such as steam, are experimenting with bittorrent-like techniques
> again. QUIC makes torrent extremely feasible once again.
>
>
> Despite my high level of respect for Geoff, he, and others like him, often
> talk things up to push things their way of thinking, we only need look at
> the FUD they came out with in mid 90's about IPv4's imminent demise giving
> it three to five years before depletion, and here we are 30 years later and
> it is still the most dominant transport protocol by a long long mile
> despite allegedly  running out only a few years ago and not in early 2000's
> as they tried to claim. (Even today there are still reserve stocks on /24's
> for newbies from some regions, and the bigger networks have years of
> stockpiled addresses in reserve).
>
> It's also like the local water board here who last week came out saying a
> whopping 70% of people surveyed said they'd drink recycled water, of course
> it was the local water board that conducted this alleged survey, because
> >90% of the more independent polling shows a totally different story.
>
> "Ohh, everybody's doing it"  "must be safe" "we should do it"  ... nah...
> TCP isn't going anywhere, nor is UDP, not in my lifetime anyway :)
>
> Cheers
>
>
> _______________________________________________
> Starlink mailing list
> Starlink@lists.bufferbloat.net
> https://lists.bufferbloat.net/listinfo/starlink
>

[-- Attachment #2: Type: text/html, Size: 3541 bytes --]

Re: [Starlink] APNIC56 last week

[Ulrich Speidel]

[-- Attachment #1: Type: text/plain, Size: 9246 bytes --]

People who buy IPv4 address blocks can most certainly afford them - the 
big buyers are large ISPs and CSPs that offer IPv4 as a service.

Pressure points that make migration to v6 attractive can vary, and don't 
always meet the eye. Networks that are heavily NATed are inherently more 
complex to manage, and forensics becomes a nightmare.

My personal pressure point: I have an unfortunately not-so-little 
service role here in which I get to deal with a certain subset of 
students who think that outsourcing each and every assessment in their 
degree is the thing to do. It's not-so-little because there aren't so 
few of them, sadly. So we decided some time ago that we'd pull some of 
our core courses into invigilated labs for tests and exams, using 
systems such as CodeRunner for assessment. We also log client IPs at the 
CodeRunner end in order to detect clients not coming from the lab (or 
rather, we do now, after discovering that you need to get the load 
balancer to propagate the actual client IP to see more than one 
meaningless address). And we do find - not a test or exam goes by 
without some folk being observed having questions answered from IP 
addresses outside the lab.

So what does this have to do with IPv4? Well, I never get to catch 
anyone for collusion because of IPv4. One reason for this is that even 
if they did collude (and from what I've seen to date, it wouldn't 
surprise me in the slightest), the lab sits behind a NAT (many computers 
hosting no services), and the CodeRunner instance sits outside. All 
students in the lab are seen coming from the same address. So imagine 
Alice sitting a test for herself and Bob answering questions 1 to 4 for 
both of them, while Bob takes care of 5 to 8. No way we can detect this 
- even packet capture inside the lab won't help up because user IDs are 
hidden behind HTTPS. IPv6 would do away with the problem altogether - 
we'd see Alice's machine answering 1 to 4 for both her and Bob, and 
Bob's machine answering 5 to 8 for both of them.

We also get issues when we see two students who we suspect to be 
"connected" coming in from the same CGNAT IP address in non-lab 
assessments. This could be coincidence, an external helper, or just 
people being flatmates, but IPv4 makes us more myopic here than we need 
to be.

On 23/09/2023 11:28 pm, Sebastian Moeller wrote:
> Hi Ulrich,
>
>
> nice tangential discussion. I guess what we might expect is some 
> "Kipp-Punkt"/tipping-point at which acquiring new IPv4 becomes cost 
> prohibitive enough so new deployments go IPv6 only, at which point the 
> existing IPv4 offers might devaluate pretty quickly... Now, if IPv6 
> would have been made more like IPv4 this would be considerably easier 
> (I am thinking DHPCv6 and Android devices here, and I am only speaking 
> of ease of deployment; I accept there are valid reasons for a 
> SLAAC-only position like Android's). The US$1 million (or better 3.5 
> Million) question is when this tipping-point will be?
> Tangent: German ISPs tend to charge ~5EUR/month extra for static 
> public IPv4 addresses so over a typical 24 month contract period can 
> easily tolerate a cost of 5*24 = 120 EUR for an IPv4 address (that 
> will afterwards still be in the ISP's property). They typically 
> provision either full DualStack (from the incumbent sitting on a large 
> pile of IPv4s) or ds-lite and for a few unfortunate one's CG-NAT-IPv4 
> only. But even the IPv6 addresses/prefixes are typically dynamically 
> assigned with relative short renewal periods (like 24 hours).
>
> Regards
> Sebastian
>
>
> P.S.: My personal gripes with IPv6 are much smaller, I mostly miss 
> stuff like ICMP timestamps in ICMPv6 and the IP timestamp option in 
> IPv6*, or the fact that privacy extensions (as well intended as they 
> are) make it harder for novice users to actually use their IPv6 
> globally routable addresses to make services available.
>
> *) I think I understand the limitations of both ICMP and IP timestamps 
> compared to the more elaborate alternatives that have been RFC'd as 
> alternatives and that apparently convinced team IPv6 to not carry 
> these things over from IPv4, but boy, no amount of higher temporal 
> precision makes up for the point that many deployed servers today 
> happily respond tp ICMP/IP timestamp requests, ubiquity in itself is a 
> major asset.
>
>
> > On Sep 23, 2023, at 12:53, Ulrich Speidel via Starlink 
> <starlink@lists.bufferbloat.net> wrote:
> >
> > On 23/09/2023 4:22 pm, Noel Butler via Starlink wrote:
> >> IPv6 is only 4% of traffic that hits my Mail Servers, it's less 
> than 1% on my Web servers.
> >> Just like TCP, it wont be going anywhere, not quietly, and if it 
> were to, likely be long after I'm gone, QUIC seems an interesting 
> project, and I guess only the decades ahead of us will tell of it 
> becomes a raging success.
> >
> > Now what that tells me is that you and those that use your mail / 
> web servers are within networks that are either in networks that are 
> old and have legacy IPv4 allocations, or that are new, desparate, and 
> rich. And Geoff, if you asked him, would tell you that this is 
> perfectly fine by him - as long as you're happy with it. In fact, I 
> can recall a presentation of his not too long ago (APNIC54, AINTEC22?) 
> where he said pretty much exactly that he didn't foresee a rapid 
> demise of IPv4.
> >
> > But if you look at the Internet as a whole - and Geoff does, in a 
> very ingenious way, I might add - then we notice that the percentage 
> of IPv6 out there has been growing steadily. IPv6 is now what about 
> half of Internet users use. Maybe not the folk that visit your 
> services, but Internet users nonetheless. So you're in the process of 
> being outnumbered. But that's perhaps of academic interest only, for 
> now, at least.
> >
> > What's a bit more pertinent in some respects is a point that Vint 
> brought up, and this is that if you want a new IPv4 address these 
> days, you will generally need to buy it from someone who has an 
> allocation. Or lease it - which is a little controversial, but not a 
> debate I'm wanting to enter here. Let's stay with the buying price tag 
> for a moment.
> >
> > I came home from APNIC54 last year with the insight that my 
> employer's /16 IPv4 allocation was worth around US$3.5 million. Since 
> we've had the /16 for ages, I started wondering whether this was even 
> on our asset list. I was pretty sure that it ought to be. Turns out it 
> wasn't - when every $100 monitor in our place is. So I started asking 
> questions and am told that there was a hastily arranged meeting 
> between IT and Finance.
> >
> > The upshot is that we now have a $3.5m asset on our books that may 
> appreciate or depreciate, and people who are responsible for managing 
> it. In fact, I dug a bit further and found a total of around NZ$100m 
> worth of IPv4 addresses in NZ's public sector, including a /16 held by 
> a government department that wasn't part of any AS. NZ's auditor 
> general's office told me that they expected public sector agencies to 
> list IPv4 holdings on their balance sheets.
> >
> > Why is this important? Because otherwise, there is nothing that 
> stops an individual with access to your RIR account from transferring 
> your IPv4 holdings to whichever party they so desire. If the addresses 
> are not on your asset list, then there's nothing that documents that 
> you own the value that is inherent in them and thus nothing to sue 
> anyone for. One imagines this as the ultimate stunt that a disgruntled 
> sysadmin might pull off before they leave your employ.
> >
> > But let's get back to that newly-found asset that we now have to 
> manage. Your next CGNAT now becomes an investment in making that 
> newly-found asset a little less tradable. A bit like putting a shiny 
> new building right onto the only access way to your back sections 
> you've just been told you can actually develop.
> >
> > Of course, this only applies to folk who sit on larger address 
> blocks - for a /24, it won't make much of a difference on the balance 
> sheet.
> >
> > --
> >
> > ****************************************************************
> > Dr. Ulrich Speidel
> >
> > School of Computer Science
> >
> > Room 303S.594 (City Campus)
> >
> > The University of Auckland
> > u.speidel@auckland.ac.nz
> > http://www.cs.auckland.ac.nz/~ulrich/ 
> <http://www.cs.auckland.ac.nz/~ulrich>
> > ****************************************************************
> >
> >
> >
> > _______________________________________________
> > Starlink mailing list
> > Starlink@lists.bufferbloat.net
> > https://lists.bufferbloat.net/listinfo/starlink 
> <https://lists.bufferbloat.net/listinfo/starlink>

-- 
****************************************************************
Dr. Ulrich Speidel

School of Computer Science

Room 303S.594 (City Campus)

The University of Auckland
u.speidel@auckland.ac.nz  
http://www.cs.auckland.ac.nz/~ulrich/
****************************************************************



[-- Attachment #2: Type: text/html, Size: 11222 bytes --]

Re: [Starlink] APNIC56 last week

[Larry Press]

[-- Attachment #1: Type: text/plain, Size: 10054 bytes --]

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=3479tkagiNo&list=PLrRMhEONgz06oMXQOljB5BoZxZw6cShLN&index=3

In his next Starlink simulation, Mark Hadley assumed four:
https://www.youtube.com/watch?v=QEIUdMiColU&list=PLrRMhEONgz06oMXQOljB5BoZxZw6cShLN&index=2

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, Bard 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 <starlink-bounces@lists.bufferbloat.net> on behalf of David Lang via Starlink <starlink@lists.bufferbloat.net>
Sent: Friday, September 22, 2023 1:41 AM
To: Alexandre Petrescu <alexandre.petrescu@gmail.com>
Cc: starlink@lists.bufferbloat.net <starlink@lists.bufferbloat.net>
Subject: Re: [Starlink] APNIC56 last week

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 they 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


  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.bufferbloat.net>
> Reply-To: Alexandre Petrescu <alexandre.petrescu@gmail.com>
> To: starlink@lists.bufferbloat.net
> Subject: Re: [Starlink] APNIC56 last week
>
>
> Le 21/09/2023 à 21:05, Inemesit Affia via Starlink a écrit :
>> 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 considered
> 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/2022/04/SDA-OCT-Standard-v3.0.pdf__;!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYhXDWmzfQ$ ),
> 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 while
> above some particular continents or areas, but not sure.  It takes 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.  It makes a lot of difference whether there are 2 or
> 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
>> <starlink@lists.bufferbloat.net> wrote:
>>
>>
>>     Le 19/09/2023 à 06:39, Ulrich Speidel via Starlink a écrit :
>>     > 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/program/*/day/6/technical-2/__;Iw!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYjUChNXHQ$
>>
>>
>>     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 kepler
>>     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 advantageous,
>>     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 band
>>     > 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/starlink__;!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYgJ4na9hA$
>>
>>
>> _______________________________________________
>> Starlink mailing list
>> Starlink@lists.bufferbloat.net
>> https://urldefense.com/v3/__https://lists.bufferbloat.net/listinfo/starlink__;!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYgJ4na9hA$
> _______________________________________________
> Starlink mailing list
> Starlink@lists.bufferbloat.net
> https://urldefense.com/v3/__https://lists.bufferbloat.net/listinfo/starlink__;!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYgJ4na9hA$
>

[-- Attachment #2: Type: text/html, Size: 16555 bytes --]

Re: [Starlink] APNIC56 last week

[Dave Taht]

[-- Attachment #1: Type: text/plain, Size: 11299 bytes --]

I long for an update from mark. It was a great simulation. I would
love to see it use the known downlink data we are seeing nowadays, and
to see it calculate best case paths.

As for BARD and chatgpt: Chatgpt said I had died in 2020, "leaving
behind a substantial body of work. Bard has me presiding over
Magareatha.

It would be funnier, I suppose, if my grip on reality was weaker, or I
was less unsure I really was living in a simulation.

On Sat, Sep 23, 2023 at 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=3479tkagiNo&list=PLrRMhEONgz06oMXQOljB5BoZxZw6cShLN&index=3
>
> In his next Starlink simulation, Mark Hadley assumed four:
> https://www.youtube.com/watch?v=QEIUdMiColU&list=PLrRMhEONgz06oMXQOljB5BoZxZw6cShLN&index=2
>
> 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, Bard 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 <starlink-bounces@lists.bufferbloat.net> on behalf of David Lang via Starlink <starlink@lists.bufferbloat.net>
> Sent: Friday, September 22, 2023 1:41 AM
> To: Alexandre Petrescu <alexandre.petrescu@gmail.com>
> Cc: starlink@lists.bufferbloat.net <starlink@lists.bufferbloat.net>
> Subject: Re: [Starlink] APNIC56 last week
>
> 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 they 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
>
>
>   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.bufferbloat.net>
> > Reply-To: Alexandre Petrescu <alexandre.petrescu@gmail.com>
> > To: starlink@lists.bufferbloat.net
> > Subject: Re: [Starlink] APNIC56 last week
> >
> >
> > Le 21/09/2023 à 21:05, Inemesit Affia via Starlink a écrit :
> >> 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 considered
> > 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/2022/04/SDA-OCT-Standard-v3.0.pdf__;!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYhXDWmzfQ$ ),
> > 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 while
> > above some particular continents or areas, but not sure.  It takes 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.  It makes a lot of difference whether there are 2 or
> > 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
> >> <starlink@lists.bufferbloat.net> wrote:
> >>
> >>
> >>     Le 19/09/2023 à 06:39, Ulrich Speidel via Starlink a écrit :
> >>     > 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/program/*/day/6/technical-2/__;Iw!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYjUChNXHQ$
> >>
> >>
> >>     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 kepler
> >>     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 advantageous,
> >>     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 band
> >>     > 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/starlink__;!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYgJ4na9hA$
> >>
> >>
> >> _______________________________________________
> >> Starlink mailing list
> >> Starlink@lists.bufferbloat.net
> >> https://urldefense.com/v3/__https://lists.bufferbloat.net/listinfo/starlink__;!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYgJ4na9hA$
> > _______________________________________________
> > Starlink mailing list
> > Starlink@lists.bufferbloat.net
> > https://urldefense.com/v3/__https://lists.bufferbloat.net/listinfo/starlink__;!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYgJ4na9hA$
> >
> _______________________________________________
> Starlink mailing list
> Starlink@lists.bufferbloat.net
> https://lists.bufferbloat.net/listinfo/starlink



-- 
Oct 30: https://netdevconf.info/0x17/news/the-maestro-and-the-music-bof.html
Dave Täht CSO, LibreQos

[-- Attachment #2: image.png --]
[-- Type: image/png, Size: 84813 bytes --]

Re: [Starlink] APNIC56 last week

[Hesham ElBakoury]

[-- Attachment #1: Type: text/plain, Size: 13916 bytes --]

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
<https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>
1
<https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>.
The laser communication system is about *40% faster* than fiber due to the
speed of light in vacuum
<https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>
1
<https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>.
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
<https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>
1
<https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>.
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
<https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>
1
<https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>.
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
<https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>
1
<https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>
.

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’s announcements.

Is there anything else I can help you with? 😊
Learn more:
1. nextbigfuture.com
<https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>
2. arstechnica.com
<https://arstechnica.com/information-technology/2021/01/spacex-adds-laser-links-to-starlink-satellites-to-serve-earths-polar-areas/>
3. spaceflightnow.com
<https://spaceflightnow.com/2021/09/14/spacex-launches-first-full-batch-of-laser-equipped-starlink-satellites/>—
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=3479tkagiNo&list=PLrRMhEONgz06oMXQOljB5BoZxZw6cShLN&index=3
>
> In his next Starlink simulation, Mark Hadley assumed four:
>
> https://www.youtube.com/watch?v=QEIUdMiColU&list=PLrRMhEONgz06oMXQOljB5BoZxZw6cShLN&index=2
>
> 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, Bard
> 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 <starlink-bounces@lists.bufferbloat.net> on behalf of
> David Lang via Starlink <starlink@lists.bufferbloat.net>
> *Sent:* Friday, September 22, 2023 1:41 AM
> *To:* Alexandre Petrescu <alexandre.petrescu@gmail.com>
> *Cc:* starlink@lists.bufferbloat.net <starlink@lists.bufferbloat.net>
> *Subject:* Re: [Starlink] APNIC56 last week
>
> 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 they
> 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
>
>
>   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.bufferbloat.net>
> > Reply-To: Alexandre Petrescu <alexandre.petrescu@gmail.com>
> > To: starlink@lists.bufferbloat.net
> > Subject: Re: [Starlink] APNIC56 last week
> >
> >
> > Le 21/09/2023 à 21:05, Inemesit Affia via Starlink a écrit :
> >> 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 considered
> > 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/2022/04/SDA-OCT-Standard-v3.0.pdf__;!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYhXDWmzfQ$
> ),
> > 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 while
> > above some particular continents or areas, but not sure.  It takes 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.  It makes a lot of difference whether there are 2 or
> > 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
> >> <starlink@lists.bufferbloat.net> wrote:
> >>
> >>
> >>     Le 19/09/2023 à 06:39, Ulrich Speidel via Starlink a écrit :
> >>     > 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/program/*/day/6/technical-2/__;Iw!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYjUChNXHQ$
> >>
> >>
> >>     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 kepler
> >>     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 advantageous,
> >>     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 band
> >>     > 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/starlink__;!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYgJ4na9hA$
> >>
> >>
> >> _______________________________________________
> >> Starlink mailing list
> >> Starlink@lists.bufferbloat.net
> >>
> https://urldefense.com/v3/__https://lists.bufferbloat.net/listinfo/starlink__;!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYgJ4na9hA$
> > _______________________________________________
> > Starlink mailing list
> > Starlink@lists.bufferbloat.net
> >
> https://urldefense.com/v3/__https://lists.bufferbloat.net/listinfo/starlink__;!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYgJ4na9hA$
> >
> _______________________________________________
> Starlink mailing list
> Starlink@lists.bufferbloat.net
> https://lists.bufferbloat.net/listinfo/starlink
>

[-- Attachment #2: Type: text/html, Size: 21560 bytes --]

Re: [Starlink] APNIC56 last week

[Michael Richardson]

[-- Attachment #1: Type: text/plain, Size: 1332 bytes --]


Noel Butler via Starlink <starlink@lists.bufferbloat.net> wrote:
    > Despite my high level of respect for Geoff, he, and others like him, often
    > talk things up to push things their way of thinking, we only need look at the
    > FUD they came out with in mid 90's about IPv4's imminent demise giving

I think you malign Geoff to no purpose.

Geoff Houston is brilliant in putting up well thought out strawmans
(strawmen? Strawpeople?), often with the goal of cristalizing what exactly we don't like about them.

    > It's also like the local water board here who last week came out saying a
    > whopping 70% of people surveyed said they'd drink recycled water, of course
    > it was the local water board that conducted this alleged survey, because >90%
    > of the more independent polling shows a totally different story.

I've never seen such independent polling.  I've seen water bottle company polls :-)

If you think IPv4 is fine, then Geoff's architecture, with 0.0.0.0/1 being for
eyeballs NAT44, 128.0.0.0/3 for institutions and SDN and class C being
swamp/infrastructure should work just fine.  The question is how to get
there.



--
Michael Richardson <mcr+IETF@sandelman.ca>   . o O ( IPv6 IøT consulting )
           Sandelman Software Works Inc, Ottawa and Worldwide





[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 515 bytes --]

Re: [Starlink] APNIC56 last week

[Noel Butler]

[-- Attachment #1: Type: text/plain, Size: 2086 bytes --]

On 25/09/2023 04:30, Michael Richardson wrote:

>> FUD they came out with in mid 90's about IPv4's imminent demise giving
> 
> I think you malign Geoff to no purpose.
> 
> Geoff Houston is brilliant in putting up well thought out strawmans
> (strawmen? Strawpeople?), often with the goal of cristalizing what 
> exactly we don't like about them.

So, we only use the facts that suite our arguments?

Only way to make informed decisions is to consider all aspects, even the 
ones we cover our eyes with, you know, can't see it so it isn't 
happening type ones :)

>> It's also like the local water board here who last week came out 
>> saying a
>> whopping 70% of people surveyed said they'd drink recycled water, of 
>> course
>> it was the local water board that conducted this alleged survey, 
>> because >90%
>> of the more independent polling shows a totally different story.
> 
> I've never seen such independent polling.  I've seen water bottle 
> company polls :-)

The water board in Queensland Australia did just that, countered by 
media polling, now, and over the past 10 years.

> If you think IPv4 is fine, then Geoff's architecture, with 0.0.0.0/1 
> being for
> eyeballs NAT44, 128.0.0.0/3 for institutions and SDN and class C being
> swamp/infrastructure should work just fine.  The question is how to get
> there.

Please quote my post where I said ipv4 is fine, I don't seem to have it 
in sent mail, and if it was all okie dokie, I wouldn't have been running 
ipv6 myself for past 10½ years ;)

-- 
Regards,
Noel Butler

This Email, including attachments, may contain legally privileged 
information, therefore at all times remains confidential and subject to 
copyright protected under international law. You may not disseminate 
this message without the authors express written authority to do so.   
If you are not the intended recipient, please notify the sender then 
delete all copies of this message including attachments immediately. 
Confidentiality, copyright, and legal privilege are not waived or lost 
by reason of the mistaken delivery of this message.

[-- Attachment #2: Type: text/html, Size: 4098 bytes --]

Re: [Starlink] APNIC56 last week

[Noel Butler]

[-- Attachment #1: Type: text/plain, Size: 2682 bytes --]

On 23/09/2023 20:53, Ulrich Speidel via Starlink wrote:

> Now what that tells me is that you and those that use your mail / web 
> servers are within networks that are either in networks that are old 
> and have legacy IPv4 allocations, or that are new, desparate, and rich.

Mail is mostly Australian since that's where my userbase is, but there 
is considerable international (even when I exclude the spambots, gmail, 
outlook socials etc), as for WWW, and excluding most bots, last time I 
checked webalizer the figures on a couple of my sites were less than 10% 
from Aus and the rest (obviously) international, so its more varied than 
one might think, but it does vary depending on the site being visited, I 
don't run the BBC or CNN, so of course I wont see the diverse ranges 
they will.

> So you're in the process of being outnumbered. But that's perhaps of 
> academic interest only, for now, at least.

Yes, like I previously said, not in my lifetime.

> I came home from APNIC54 last year with the insight that my employer's 
> /16 IPv4 allocation was worth around US$3.5 million. Since we've had 
> the /16 for ages, I started wondering whether this was even on our 
> asset list. I was pretty sure that it ought to be. Turns out it wasn't 
> - when

I've no doubt they aren't on many, but putting a price on an intangible 
asset that varies is not so easy, what it's worth today it wont be in 
six months, yes, with ipv4 that means probably worth more, but a new 
buyer might not want nor need them, so that's another sales stream you 
need to find, and then you're competing against others with the same 
asset, a CGNAT device is physical one they can keep using without 
interrupting services to clients if they so choose, the only intangible 
asset that's worth something is the ongoing good will, you don't get 
that from address space unless you have a fresh faced startup type 
buyer. I'm curious though, your part of a University, so it's not like 
you're going to be able to use that extra 3.5m, I don;t see the Uni 
giving up its resources, a business of course is a different matter.

-- 
Regards,
Noel Butler

This Email, including attachments, may contain legally privileged 
information, therefore at all times remains confidential and subject to 
copyright protected under international law. You may not disseminate 
this message without the authors express written authority to do so.   
If you are not the intended recipient, please notify the sender then 
delete all copies of this message including attachments immediately. 
Confidentiality, copyright, and legal privilege are not waived or lost 
by reason of the mistaken delivery of this message.

[-- Attachment #2: Type: text/html, Size: 4468 bytes --]

Re: [Starlink] APNIC56 last week

[Ulrich Speidel]

[-- Attachment #1: Type: text/plain, Size: 3647 bytes --]

On 25/09/2023 5:40 pm, Noel Butler via Starlink wrote:
> Mail is mostly Australian since that's where my userbase is, but there 
> is considerable international (even when I exclude the spambots, 
> gmail, outlook socials etc), as for WWW, and excluding most bots, last 
> time I checked webalizer the figures on a couple of my sites were less 
> than 10% from Aus and the rest (obviously) international, so its more 
> varied than one might think, but it does vary depending on the site 
> being visited, I don't run the BBC or CNN, so of course I wont see the 
> diverse ranges they will.
IPv6 adoption in Australia (and NZ) is a bit behind the curve, 
internationally.
>> So you're in the process of being outnumbered. But that's perhaps of 
>> academic interest only, for now, at least.
> Yes, like I previously said, not in my lifetime.
I'm not sure how old you are, but I could imagine things going pretty 
quickly from some point onwards.
>> I came home from APNIC54 last year with the insight that my 
>> employer's /16 IPv4 allocation was worth around US$3.5 million. Since 
>> we've had the /16 for ages, I started wondering whether this was even 
>> on our asset list. I was pretty sure that it ought to be. Turns out 
>> it wasn't - when
> I've no doubt they aren't on many, but putting a price on an 
> intangible asset that varies is not so easy, what it's worth today it 
> wont be in six months, yes, with ipv4 that means probably worth more, 
> but a new buyer might not want nor need them, so that's another sales 
> stream you need to find, and then you're competing against others with 
> the same asset, a CGNAT device is physical one they can keep using 
> without interrupting services to clients if they so choose, the only 
> intangible asset that's worth something is the ongoing good will, you 
> don't get that from address space unless you have a fresh faced 
> startup type buyer. I'm curious though, your part of a University, so 
> it's not like you're going to be able to use that extra 3.5m, I don;t 
> see the Uni giving up its resources, a business of course is a 
> different matter.

The point is that an IPv4 allocation is no longer a resource unless you 
have an active need for it. We've sold entire campuses lately, so I 
wouldn't bet on IPv4 holdings... Incidentally, goodwill isn't the only 
intangible asset that's worth something - my father used to work in that 
space for decades and I earned extra pocket money proofreading an M&A 
textbook for practitioners, and I can tell you that the true list was 
long, even 40 years ago...

You only really "need" IPv4 if you operate a network with a lot of 
servers that see inbound traffic from random clients in networks you 
have no control over. So it's in demand primarily from parties that 
predominantly operate servers and are experiencing growth, as well as 
networks that are invested in IPv4 and need more to support their 
growth. But that's a substantial market. I'd expect IPv4 prices to fall 
once the demand for IPv4 subsides, and that's going to be when the 
overwhelming majority of the world runs IPv6. That might be another 5 or 
10 years away - hard to tell. At current growth rates, probably not 20 
though. Not sure what you're projecting as your lifetime ;-)

-- 
****************************************************************
Dr. Ulrich Speidel

School of Computer Science

Room 303S.594 (City Campus)

The University of Auckland
u.speidel@auckland.ac.nz  
http://www.cs.auckland.ac.nz/~ulrich/
****************************************************************



[-- Attachment #2: Type: text/html, Size: 5778 bytes --]

Re: [Starlink] APNIC56 last week

[Hayden Simon]

[-- Attachment #1: Type: text/plain, Size: 4006 bytes --]

I’d love a loan of your crystal ball, please 😊


HAYDEN SIMON
UBER GROUP LIMITED
MANAGING DIRECTOR
E: h@uber.nz
M: 021 0707 014
W: www.uber.nz
53 PORT ROAD | PO BOX 5083 | WHANGAREI | NEW ZEALAND
From: Starlink <starlink-bounces@lists.bufferbloat.net> On Behalf Of Ulrich Speidel via Starlink
Sent: Monday, September 25, 2023 6:00 PM
To: starlink@lists.bufferbloat.net
Subject: Re: [Starlink] APNIC56 last week

On 25/09/2023 5:40 pm, Noel Butler via Starlink wrote:

Mail is mostly Australian since that's where my userbase is, but there is considerable international (even when I exclude the spambots, gmail, outlook socials etc), as for WWW, and excluding most bots, last time I checked webalizer the figures on a couple of my sites were less than 10% from Aus and the rest (obviously) international, so its more varied than one might think, but it does vary depending on the site being visited, I don't run the BBC or CNN, so of course I wont see the diverse ranges they will.
IPv6 adoption in Australia (and NZ) is a bit behind the curve, internationally.


So you're in the process of being outnumbered. But that's perhaps of academic interest only, for now, at least.

Yes, like I previously said, not in my lifetime.
I'm not sure how old you are, but I could imagine things going pretty quickly from some point onwards.


I came home from APNIC54 last year with the insight that my employer's /16 IPv4 allocation was worth around US$3.5 million. Since we've had the /16 for ages, I started wondering whether this was even on our asset list. I was pretty sure that it ought to be. Turns out it wasn't - when

I've no doubt they aren't on many, but putting a price on an intangible asset that varies is not so easy, what it's worth today it wont be in six months, yes, with ipv4 that means probably worth more, but a new buyer might not want nor need them, so that's another sales stream you need to find, and then you're competing against others with the same asset, a CGNAT device is physical one they can keep using without interrupting services to clients if they so choose, the only intangible asset that's worth something is the ongoing good will, you don't get that from address space unless you have a fresh faced startup type buyer. I'm curious though, your part of a University, so it's not like you're going to be able to use that extra 3.5m, I don;t see the Uni giving up its resources, a business of course is a different matter.

The point is that an IPv4 allocation is no longer a resource unless you have an active need for it. We've sold entire campuses lately, so I wouldn't bet on IPv4 holdings... Incidentally, goodwill isn't the only intangible asset that's worth something - my father used to work in that space for decades and I earned extra pocket money proofreading an M&A textbook for practitioners, and I can tell you that the true list was long, even 40 years ago...

You only really "need" IPv4 if you operate a network with a lot of servers that see inbound traffic from random clients in networks you have no control over. So it's in demand primarily from parties that predominantly operate servers and are experiencing growth, as well as networks that are invested in IPv4 and need more to support their growth. But that's a substantial market. I'd expect IPv4 prices to fall once the demand for IPv4 subsides, and that's going to be when the overwhelming majority of the world runs IPv6. That might be another 5 or 10 years away - hard to tell. At current growth rates, probably not 20 though. Not sure what you're projecting as your lifetime ;-)

--

****************************************************************

Dr. Ulrich Speidel



School of Computer Science



Room 303S.594 (City Campus)



The University of Auckland

u.speidel@auckland.ac.nz<mailto:u.speidel@auckland.ac.nz>

http://www.cs.auckland.ac.nz/~ulrich/

****************************************************************







[-- Attachment #2: Type: text/html, Size: 14577 bytes --]

Re: [Starlink] APNIC56 last week

[Noel Butler]

[-- Attachment #1: Type: text/plain, Size: 2423 bytes --]

On 25/09/2023 15:00, Ulrich Speidel via Starlink wrote:

>> 
> IPv6 adoption in Australia (and NZ) is a bit behind the curve, 
> internationally.

A bit? We're dragging our heels :)  Very strange too since Geoff is from 
AU, in fact my home city, fun fact, until I move about 15 years ago we 
apparently lived one street apart.

> 

> I'm not sure how old you are, but I could imagine things going pretty 
> quickly from some point onwards.

Not too distant from retirement, like to think I'd still be kickin on 
for further 25 or so after that

> The point is that an IPv4 allocation is no longer a resource unless you 
> have an active need for it.

Reminds me of a blog post a few years ago I did that showed how many 
well known prominent websites were not reachable by ipv6, I should grab 
that list and recheck them to see how many fail today.

> Incidentally, goodwill isn't the only intangible asset that's worth 
> something - my father used to work in that space for decades and I 
> earned extra pocket money proofreading an M&A textbook for 
> practitioners, and I can tell you that the true list was long, even 40 
> years ago...

Interesting, depends on industry I guess, with hosting, it's just the 
goodwill (userbase), you only own the physical assets that provide the 
services, you cant own a client, nor own their data, same thing for 
(most)  ISP's and RSP's, but I guess in other industries there could be 
other things, and since they don't apply to me I'm ignorant of them.

> You only really "need" IPv4 if you operate a network with a lot of 
> servers that see inbound traffic from random clients in networks you 
> have no control over.

You just named 99.9R% of the services in the world.

> Not sure what you're projecting as your lifetime ;-)

I hope 90 odd, but if I don't retire soon it'll be substantially less 
haha

-- 
Regards,
Noel Butler

This Email, including attachments, may contain legally privileged 
information, therefore at all times remains confidential and subject to 
copyright protected under international law. You may not disseminate 
this message without the authors express written authority to do so.   
If you are not the intended recipient, please notify the sender then 
delete all copies of this message including attachments immediately. 
Confidentiality, copyright, and legal privilege are not waived or lost 
by reason of the mistaken delivery of this message.

[-- Attachment #2: Type: text/html, Size: 4642 bytes --]

Re: [Starlink] APNIC56 last week

[Alexandre Petrescu]

Le 24/09/2023 à 14:00, Hesham ElBakoury a écrit :
> 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 
> <https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>^1 
> <https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>. 
>
>
I think BING (like others) is wrong in this case.  Current fiber has a 
much lower latency than 17 milliseconds.  I'd say in the range of lower 
tens of microseconds or hundreds of nanoseconds. But dont quote me on that.

Apart the AI's inability aspect, it stays interesting if future LEO 
Internet access systems competes to fiber in the right range.

The timestamped technologies should be compared.  Starlink today's 20ms 
should be compared to today's advanced 5G 1ms, and not to 4G 50ms.  
Future LEO Internet access should be compared to future 6G terrestrial 
and future FTTH, because they also evolve.

Alex


> The laser communication system is about *40% faster* than fiber due to 
> the speed of light in vacuum 
> <https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>^1 
> <https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>. 
> 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 
> <https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>^1 
> <https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>. 
> 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 
> <https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>^1 
> <https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>. 
> 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 
> <https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>^1 
> <https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>.
>
> 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’s announcements.
>
> Is there anything else I can help you with? 😊
>
> Learn more:
> 1. nextbigfuture.com 
> <https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>
> 2. arstechnica.com 
> <https://arstechnica.com/information-technology/2021/01/spacex-adds-laser-links-to-starlink-satellites-to-serve-earths-polar-areas/>
> 3. spaceflightnow.com 
> <https://spaceflightnow.com/2021/09/14/spacex-launches-first-full-batch-of-laser-equipped-starlink-satellites/>— 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=3479tkagiNo&list=PLrRMhEONgz06oMXQOljB5BoZxZw6cShLN&index=3
>     <https://www.youtube.com/watch?v=3479tkagiNo&list=PLrRMhEONgz06oMXQOljB5BoZxZw6cShLN&index=3>
>
>     In his next Starlink simulation, Mark Hadley assumed four:
>     https://www.youtube.com/watch?v=QEIUdMiColU&list=PLrRMhEONgz06oMXQOljB5BoZxZw6cShLN&index=2
>     <https://www.youtube.com/watch?v=QEIUdMiColU&list=PLrRMhEONgz06oMXQOljB5BoZxZw6cShLN&index=2>
>
>     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, Bard 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 <starlink-bounces@lists.bufferbloat.net> on
>     behalf of David Lang via Starlink <starlink@lists.bufferbloat.net>
>     *Sent:* Friday, September 22, 2023 1:41 AM
>     *To:* Alexandre Petrescu <alexandre.petrescu@gmail.com>
>     *Cc:* starlink@lists.bufferbloat.net <starlink@lists.bufferbloat.net>
>     *Subject:* Re: [Starlink] APNIC56 last week
>     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 they 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
>
>
>       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.bufferbloat.net>
>     > Reply-To: Alexandre Petrescu <alexandre.petrescu@gmail.com>
>     > To: starlink@lists.bufferbloat.net
>     > Subject: Re: [Starlink] APNIC56 last week
>     >
>     >
>     > Le 21/09/2023 à 21:05, Inemesit Affia via Starlink a écrit :
>     >> 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
>     considered
>     > 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/2022/04/SDA-OCT-Standard-v3.0.pdf__;!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYhXDWmzfQ$
>     ),
>     > 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 while
>     > above some particular continents or areas, but not sure.  It
>     takes 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.  It makes a lot of difference whether there
>     are 2 or
>     > 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
>     >> <starlink@lists.bufferbloat.net> wrote:
>     >>
>     >>
>     >>     Le 19/09/2023 à 06:39, Ulrich Speidel via Starlink a écrit :
>     >>     > 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/program/*/day/6/technical-2/__;Iw!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYjUChNXHQ$
>
>     >>
>     >>
>     >>     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 kepler
>     >>     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
>     advantageous,
>     >>     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 band
>     >>     > 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/starlink__;!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYgJ4na9hA$
>
>     >>
>     >>
>     >> _______________________________________________
>     >> Starlink mailing list
>     >> Starlink@lists.bufferbloat.net
>     >>
>     https://urldefense.com/v3/__https://lists.bufferbloat.net/listinfo/starlink__;!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYgJ4na9hA$
>
>     > _______________________________________________
>     > Starlink mailing list
>     > Starlink@lists.bufferbloat.net
>     >
>     https://urldefense.com/v3/__https://lists.bufferbloat.net/listinfo/starlink__;!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYgJ4na9hA$
>
>     >
>     _______________________________________________
>     Starlink mailing list
>     Starlink@lists.bufferbloat.net
>     https://lists.bufferbloat.net/listinfo/starlink
>

Re: [Starlink] APNIC56 last week

[David Lang]

[-- Attachment #1: Type: text/plain, Size: 16674 bytes --]

On Mon, 25 Sep 2023, Alexandre Petrescu wrote:

> Apart the AI's inability aspect, it stays interesting if future LEO Internet 
> access systems competes to fiber in the right range.

wired (including fiber) is going to beat wireless pretty much anywhere it's 
available. Wireless (and LEO) have the advantage that it's EXPENSIVE to run 
wires, so they start to shine when the use density decreases (and even there, 
there will be areas where 'fiber is bing run down this road anyway, so let's 
offer service to people along the way to earn a few penny's and some good PR)

the quirk where very long range communication can be slightly lower round-trip 
time by first hopping up into space is balanced by the more limited bandwidth 
available through that space connection (you have to get through miles of 
atmosphere, and that's going to limit your throughput compared to millimeters to 
get into the fiber)

> The timestamped technologies should be compared.  Starlink today's 20ms 
> should be compared to today's advanced 5G 1ms, and not to 4G 50ms.  Future 
> LEO Internet access should be compared to future 6G terrestrial and future 
> FTTH, because they also evolve.

True, but when you are looking at limits imposed by known physics, it's a pretty 
safe bet. Yes, it is possible that quantum entanglement will translate into FTL 
communications that can be used to replace everything we know, but that's rather 
unlikely for at least a LONG time.

David Lang

> Alex
>
>
>> The laser communication system is about *40% faster* than fiber due to the 
>> speed of light in vacuum 
>> <https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>^1 
>> <https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>. 
>> 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 
>> <https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>^1 
>> <https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>. 
>> 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 
>> <https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>^1 
>> <https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>. 
>> 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 
>> <https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>^1 
>> <https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>.
>> 
>> 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’s announcements.
>> 
>> Is there anything else I can help you with? 😊
>> 
>> Learn more:
>> 1. nextbigfuture.com 
>> <https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>
>> 2. arstechnica.com 
>> <https://arstechnica.com/information-technology/2021/01/spacex-adds-laser-links-to-starlink-satellites-to-serve-earths-polar-areas/>
>> 3. spaceflightnow.com 
>> <https://spaceflightnow.com/2021/09/14/spacex-launches-first-full-batch-of-laser-equipped-starlink-satellites/>— 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=3479tkagiNo&list=PLrRMhEONgz06oMXQOljB5BoZxZw6cShLN&index=3
>>     <https://www.youtube.com/watch?v=3479tkagiNo&list=PLrRMhEONgz06oMXQOljB5BoZxZw6cShLN&index=3>
>>
>>     In his next Starlink simulation, Mark Hadley assumed four:
>>     https://www.youtube.com/watch?v=QEIUdMiColU&list=PLrRMhEONgz06oMXQOljB5BoZxZw6cShLN&index=2
>>     <https://www.youtube.com/watch?v=QEIUdMiColU&list=PLrRMhEONgz06oMXQOljB5BoZxZw6cShLN&index=2>
>>
>>     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, Bard 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 <starlink-bounces@lists.bufferbloat.net> on
>>     behalf of David Lang via Starlink <starlink@lists.bufferbloat.net>
>>     *Sent:* Friday, September 22, 2023 1:41 AM
>>     *To:* Alexandre Petrescu <alexandre.petrescu@gmail.com>
>>     *Cc:* starlink@lists.bufferbloat.net <starlink@lists.bufferbloat.net>
>>     *Subject:* Re: [Starlink] APNIC56 last week
>>     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 they 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
>> 
>>
>>       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.bufferbloat.net>
>>     > Reply-To: Alexandre Petrescu <alexandre.petrescu@gmail.com>
>>     > To: starlink@lists.bufferbloat.net
>>     > Subject: Re: [Starlink] APNIC56 last week
>>     >
>>     >
>>     > Le 21/09/2023 à 21:05, Inemesit Affia via Starlink a écrit :
>>     >> 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
>>     considered
>>     > 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/2022/04/SDA-OCT-Standard-v3.0.pdf__;!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYhXDWmzfQ$
>>     ),
>>     > 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 while
>>     > above some particular continents or areas, but not sure.  It
>>     takes 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.  It makes a lot of difference whether there
>>     are 2 or
>>     > 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
>>     >> <starlink@lists.bufferbloat.net> wrote:
>>     >>
>>     >>
>>     >>     Le 19/09/2023 à 06:39, Ulrich Speidel via Starlink a écrit :
>>     >>     > 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/program/*/day/6/technical-2/__;Iw!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYjUChNXHQ$
>>
>>     >>
>>     >>
>>     >>     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 kepler
>>     >>     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
>>     advantageous,
>>     >>     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 band
>>     >>     > 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/starlink__;!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYgJ4na9hA$
>>
>>     >>
>>     >>
>>     >> _______________________________________________
>>     >> Starlink mailing list
>>     >> Starlink@lists.bufferbloat.net
>>     >>
>>     https://urldefense.com/v3/__https://lists.bufferbloat.net/listinfo/starlink__;!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYgJ4na9hA$
>>
>>     > _______________________________________________
>>     > Starlink mailing list
>>     > Starlink@lists.bufferbloat.net
>>     >
>>     https://urldefense.com/v3/__https://lists.bufferbloat.net/listinfo/starlink__;!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYgJ4na9hA$
>>
>>     >
>>     _______________________________________________
>>     Starlink mailing list
>>     Starlink@lists.bufferbloat.net
>>     https://lists.bufferbloat.net/listinfo/starlink
>> 
>

Re: [Starlink] APNIC56 last week

[Frantisek Borsik]

[-- Attachment #1: Type: text/plain, Size: 18412 bytes --]

There are horrible latencies observed on wired - including fiber, and FWA
with good QoE solutions beats fiber (without it) anytime.
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.


All the best,

Frank

Frantisek (Frank) Borsik



https://www.linkedin.com/in/frantisekborsik

Signal, Telegram, WhatsApp: +421919416714

iMessage, mobile: +420775230885

Skype: casioa5302ca

frantisek.borsik@gmail.com


On Mon, Sep 25, 2023 at 10:59 AM David Lang via Starlink <
starlink@lists.bufferbloat.net> wrote:

> On Mon, 25 Sep 2023, Alexandre Petrescu wrote:
>
> > Apart the AI's inability aspect, it stays interesting if future LEO
> Internet
> > access systems competes to fiber in the right range.
>
> wired (including fiber) is going to beat wireless pretty much anywhere
> it's
> available. Wireless (and LEO) have the advantage that it's EXPENSIVE to
> run
> wires, so they start to shine when the use density decreases (and even
> there,
> there will be areas where 'fiber is bing run down this road anyway, so
> let's
> offer service to people along the way to earn a few penny's and some good
> PR)
>
> the quirk where very long range communication can be slightly lower
> round-trip
> time by first hopping up into space is balanced by the more limited
> bandwidth
> available through that space connection (you have to get through miles of
> atmosphere, and that's going to limit your throughput compared to
> millimeters to
> get into the fiber)
>
> > The timestamped technologies should be compared.  Starlink today's 20ms
> > should be compared to today's advanced 5G 1ms, and not to 4G 50ms.
> Future
> > LEO Internet access should be compared to future 6G terrestrial and
> future
> > FTTH, because they also evolve.
>
> True, but when you are looking at limits imposed by known physics, it's a
> pretty
> safe bet. Yes, it is possible that quantum entanglement will translate
> into FTL
> communications that can be used to replace everything we know, but that's
> rather
> unlikely for at least a LONG time.
>
> David Lang
>
> > Alex
> >
> >
> >> The laser communication system is about *40% faster* than fiber due to
> the
> >> speed of light in vacuum
> >> <
> https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>^1
>
> >> <
> https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>.
>
> >> 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
> >> <
> https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>^1
>
> >> <
> https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>.
>
> >> 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
> >> <
> https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>^1
>
> >> <
> https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>.
>
> >> 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
> >> <
> https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html>^1
>
> >> <
> https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html
> >.
> >>
> >> 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’s announcements.
> >>
> >> Is there anything else I can help you with? 😊
> >>
> >> Learn more:
> >> 1. nextbigfuture.com
> >> <
> https://www.nextbigfuture.com/2021/09/version-2-starlink-with-lasers-and-gen-2-spacex-starlink-bigger-and-faster.html
> >
> >> 2. arstechnica.com
> >> <
> https://arstechnica.com/information-technology/2021/01/spacex-adds-laser-links-to-starlink-satellites-to-serve-earths-polar-areas/
> >
> >> 3. spaceflightnow.com
> >> <
> https://spaceflightnow.com/2021/09/14/spacex-launches-first-full-batch-of-laser-equipped-starlink-satellites/>— 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=3479tkagiNo&list=PLrRMhEONgz06oMXQOljB5BoZxZw6cShLN&index=3
> >>     <
> https://www.youtube.com/watch?v=3479tkagiNo&list=PLrRMhEONgz06oMXQOljB5BoZxZw6cShLN&index=3
> >
> >>
> >>     In his next Starlink simulation, Mark Hadley assumed four:
> >>
> https://www.youtube.com/watch?v=QEIUdMiColU&list=PLrRMhEONgz06oMXQOljB5BoZxZw6cShLN&index=2
> >>     <
> https://www.youtube.com/watch?v=QEIUdMiColU&list=PLrRMhEONgz06oMXQOljB5BoZxZw6cShLN&index=2
> >
> >>
> >>     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, Bard 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 <starlink-bounces@lists.bufferbloat.net> on
> >>     behalf of David Lang via Starlink <starlink@lists.bufferbloat.net>
> >>     *Sent:* Friday, September 22, 2023 1:41 AM
> >>     *To:* Alexandre Petrescu <alexandre.petrescu@gmail.com>
> >>     *Cc:* starlink@lists.bufferbloat.net <
> starlink@lists.bufferbloat.net>
> >>     *Subject:* Re: [Starlink] APNIC56 last week
> >>     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 they 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
> >>
> >>
> >>       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.bufferbloat.net>
> >>     > Reply-To: Alexandre Petrescu <alexandre.petrescu@gmail.com>
> >>     > To: starlink@lists.bufferbloat.net
> >>     > Subject: Re: [Starlink] APNIC56 last week
> >>     >
> >>     >
> >>     > Le 21/09/2023 à 21:05, Inemesit Affia via Starlink a écrit :
> >>     >> 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
> >>     considered
> >>     > 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/2022/04/SDA-OCT-Standard-v3.0.pdf__;!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYhXDWmzfQ$
> >>     ),
> >>     > 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 while
> >>     > above some particular continents or areas, but not sure.  It
> >>     takes 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.  It makes a lot of difference whether there
> >>     are 2 or
> >>     > 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
> >>     >> <starlink@lists.bufferbloat.net> wrote:
> >>     >>
> >>     >>
> >>     >>     Le 19/09/2023 à 06:39, Ulrich Speidel via Starlink a écrit :
> >>     >>     > 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/program/*/day/6/technical-2/__;Iw!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYjUChNXHQ$
> >>
> >>     >>
> >>     >>
> >>     >>     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 kepler
> >>     >>     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
> >>     advantageous,
> >>     >>     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 band
> >>     >>     > 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/starlink__;!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYgJ4na9hA$
> >>
> >>     >>
> >>     >>
> >>     >> _______________________________________________
> >>     >> Starlink mailing list
> >>     >> Starlink@lists.bufferbloat.net
> >>     >>
> >>
> https://urldefense.com/v3/__https://lists.bufferbloat.net/listinfo/starlink__;!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYgJ4na9hA$
> >>
> >>     > _______________________________________________
> >>     > Starlink mailing list
> >>     > Starlink@lists.bufferbloat.net
> >>     >
> >>
> https://urldefense.com/v3/__https://lists.bufferbloat.net/listinfo/starlink__;!!P7nkOOY!pso4rogBStK7jR7pEg21ACCfJyL_ZCltZip5K7pxmJhmaSKfOY1RgwXzW4EtPOvEhS9XoLRaKS8QbVoEgYgJ4na9hA$
> >>
> >>     >
> >>     _______________________________________________
> >>     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
>

[-- Attachment #2: Type: text/html, Size: 30089 bytes --]

Re: [Starlink] APNIC56 last week

[David Fernández]

Hi David,

Mike said each satellite has 3 ISL, two connecting to the satellites
in front and back in the same orbital plane, then a third one that can
point anywhere (almost):

https://lists.bufferbloat.net/pipermail/starlink/2022-September/001000.html?fbclid=IwAR0TaPTdxVEp5iVWxch91mjnDT7aKVaOXPmyOd93PBING29YBWy9SNbV278

Regards,

David

> Date: Fri, 22 Sep 2023 01:41:16 -0700 (PDT)
> From: David Lang <david@lang.hm>
> To: Alexandre Petrescu <alexandre.petrescu@gmail.com>
> Cc: starlink@lists.bufferbloat.net
> Subject: Re: [Starlink] APNIC56 last week
> Message-ID: <1oor055r-p02p-3o25-9056-p257s819q308@ynat.uz>
> Content-Type: text/plain; charset="utf-8"; Format="flowed"
>
> 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 they
> 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