Starlink has bufferbloat. Bad.
 help / color / mirror / Atom feed
From: Brandon Butterworth <brandon@rd.bbc.co.uk>
To: Sebastian Moeller <moeller0@gmx.de>
Cc: Ulrich Speidel <u.speidel@auckland.ac.nz>,
	Ulrich Speidel via Starlink <starlink@lists.bufferbloat.net>
Subject: Re: [Starlink] Starlink "beam spread"
Date: Wed, 31 Aug 2022 10:25:41 +0100	[thread overview]
Message-ID: <20220831092541.GA9165@sunf10.rd.bbc.co.uk> (raw)
In-Reply-To: <23E930C0-23A5-4ACC-BAB7-D057CD2D8572@gmx.de>

On Wed Aug 31, 2022 at 09:49:50AM +0200, Sebastian Moeller via Starlink wrote:
> +1: I agree with that assessment. What could work (pie-in-the-sky) is if
> the base station control the CDN nodes, they could try to slot requests
> and try to see whether concurrent transfers of the same content could
> not be synchronized and the unicast silently converted into multicast
> between base station and dishy.

Access to a good enough aggregation point is hard

With DSL aggregation, via PPP/L2TP to a few central gateways flattening
any cdn/multicast down to unicast for a large part of the network, limited
how far into the network we could embed our CDN.

Mobile has similar aggregation issues hence eMBMS, we did some work
in 3GPP to extend that to provide a single shared service between
operators so only one set of spectrum was used. It still didn't
create enough capacity vs the demand to make it to deployment yet.

With Starlink capacity being multiplexed per Dishy and uplink
and downlink capacity equal on each satellite there doesn't appear
to be any sharing gain to be had there warranting a CDN in space.

We explored the same situation with the Avanti geo stationary
satellite the last time satellite internet was popular.

Options for Starlink growth are probably not disimilar to 5G - more
MIMO and spectral efficiency. If that gives a satellite more capacity
to Dishys than to ground stations a CDN could be included to make use
of it, probably a single shared CDN (though carrier CDNs didn't go
well in DSL days and as with mobile edge compute the opportunity to
charge for it may limit take up).

I'm assuming there is no scope for shared capacity to all Dishys
permitting something similar to eMBMS, is that true?
 
Do satellite to satellite links change the balance to make a CDN more
likely with the opportunity to upload from less busy regions, or through
cache to cache traffic (content is often geo limited so satellites could
hold some content pools above a certain geo areas allowing cdn storage
re use)?

> But I have no intuition whether that kind of synchronicity is realistic
> for everyting but a few events like a soccer world cup final, a cricket
> test match

I suspect that may be the case. Such GEO limited content complicates matters.

We made our CDN available as a VM which some operators have deployed on
their own hardware (a sort of carrier CDN light) so in theory it could sit
on a Starlink satellite but how many CDNs could they support, just Netflix?

brandon

  reply	other threads:[~2022-08-31  9:25 UTC|newest]

Thread overview: 69+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <mailman.3.1661875202.32670.starlink@lists.bufferbloat.net>
2022-08-30 16:53 ` David P. Reed
2022-08-30 17:32   ` Doc Searls
2022-08-30 20:09     ` Mike Puchol
2022-08-30 20:35       ` Daniel AJ Sokolov
2022-08-30 20:40         ` Mike Puchol
2022-08-30 21:09       ` David Lang
2022-08-30 21:01   ` David Lang
2022-08-30 22:07     ` Brandon Butterworth
2022-08-30 22:21       ` David Lang
2022-08-30 22:37         ` Brandon Butterworth
2022-08-30 23:07           ` David Lang
2022-08-30 23:45             ` Brandon Butterworth
2022-08-30 23:28           ` David P. Reed
2022-08-31  0:12             ` David Lang
2022-08-31  0:31               ` Dave Taht
2022-08-31  0:32               ` David P. Reed
2022-08-31 10:29                 ` Dave Collier-Brown
2022-08-31 18:51                   ` David Lang
2022-08-31 19:04             ` Dave Taht
2022-08-30 22:50       ` Ulrich Speidel
2022-08-30 23:13         ` David Lang
2022-08-31  0:46         ` tom
2022-08-31  0:58           ` Dave Taht
2022-08-31  7:36             ` Mike Puchol
2022-08-31  6:26         ` Sebastian Moeller
2022-08-31  7:25           ` Ulrich Speidel
2022-08-31  7:31             ` Hayden Simon
2022-08-31  7:33             ` David Lang
2022-08-31  9:59               ` Mike Puchol
2022-08-31 10:06                 ` David Lang
2022-08-31 10:12                   ` Mike Puchol
2022-08-31 17:52                 ` Dick Roy
2022-08-31 13:41               ` Ulrich Speidel
2022-08-31 14:30                 ` Mike Puchol
2022-08-31 21:44                   ` Ulrich Speidel
2022-09-01  7:58                 ` Sebastian Moeller
2022-09-01 11:38                   ` Ulrich Speidel
2022-09-01 19:54                     ` Michael Richardson
2022-09-01 21:08                       ` tom
2022-09-02  7:52                         ` Sebastian Moeller
2022-09-02 12:29                           ` tom
2022-08-31  7:49             ` Sebastian Moeller
2022-08-31  9:25               ` Brandon Butterworth [this message]
2022-08-31  9:34                 ` David Lang
2022-09-01  9:12                   ` Brandon Butterworth
2022-08-31 14:52   ` Dave Taht
2022-08-31 15:22     ` [Starlink] starlink upload behavior Dave Taht
2022-09-01 19:24       ` Luis A. Cornejo
2022-09-01 19:50         ` Dave Taht
2022-08-31  8:15 [Starlink] Starlink "beam spread" David Fernández
2022-08-31 14:51 David Fernández
2022-08-31 18:09 ` Michael Richardson
2022-08-31 21:46 ` Ulrich Speidel
2022-08-31 23:44   ` Lin Han
2022-09-01 19:26   ` Dave Taht
     [not found] <mailman.800.1661972667.1281.starlink@lists.bufferbloat.net>
2022-08-31 19:51 ` David P. Reed
2022-08-31 20:28   ` David Lang
2022-08-31 21:17     ` David P. Reed
2022-08-31 21:33       ` David Lang
2022-09-01  7:05         ` Mike Puchol
2022-09-01 11:43           ` Ulrich Speidel
2022-09-01  8:09       ` David Lang
2022-09-01 15:19 David Fernández
2022-09-01 16:33 ` Darrell Budic
2022-09-02  9:32   ` David Fernández
2022-09-01 19:56 ` Michael Richardson
2022-09-02 12:27   ` Sebastian Moeller
2022-09-02 18:34     ` Michael Richardson
2022-09-02 20:11       ` Sebastian Moeller

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

  List information: https://lists.bufferbloat.net/postorius/lists/starlink.lists.bufferbloat.net/

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20220831092541.GA9165@sunf10.rd.bbc.co.uk \
    --to=brandon@rd.bbc.co.uk \
    --cc=moeller0@gmx.de \
    --cc=starlink@lists.bufferbloat.net \
    --cc=u.speidel@auckland.ac.nz \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox