Starlink has bufferbloat. Bad.
 help / color / mirror / Atom feed
From: Nathan Owens <nathan@nathan.io>
To: zoobab@gmail.com
Cc: Andrew Crane <fairalbion@gmail.com>,
	 Dave Taht via Starlink <starlink@lists.bufferbloat.net>
Subject: Re: [Starlink] Full Time Boaters: Reliable Remote Work with Two Starlinks
Date: Sun, 26 Mar 2023 16:26:24 -0700	[thread overview]
Message-ID: <CALjsLJtwZ+pA8HN72nHzAPZkLDKaZqujaQaU83HSMYNWLLfOWQ@mail.gmail.com> (raw)
In-Reply-To: <CANjd3nd=dKbiA39-b-hq8MjxettQUYD1TGfG7F-phR2d+qYTQw@mail.gmail.com>

[-- Attachment #1: Type: text/plain, Size: 1888 bytes --]

> With 2 links you might have more bandwidth, mptcp first saturate one link
before using the second one.

It balances evenly, even with UDP traffic based on my testing.

I recently tried OpenMPTCPRouter on 2x Starlink dishes, and even with the
6.1 dev kernel and upstream MPTCP had some really wonky issues, presumably
caused by the loss and/or latency fluctuations. I'd love it if someone
could sort this out...

On Sun, Mar 26, 2023 at 12:28 PM Benjamin Henrion via Starlink <
starlink@lists.bufferbloat.net> wrote:

> Le dim. 26 mars 2023 à 20:07, Andrew Crane via Starlink <
> starlink@lists.bufferbloat.net> a écrit :
>
>> An acquaintance of mine had dinner with this couple recently and
>> recommended this post. Thought it might be of interest here. I believe the
>> brand of router they use (Peplink) has a 'Mitigate Bufferbloat' option, but
>> the author does not mention that in the post.
>>
>> https://svrenaissance.com/reliable-remote-work-with-starlink/
>>
>
> Openmptcprouter took a lot of inspiration from our 2017 work to port mptcp
> to openwrt.
>
> Mptcp has a mode to duplicate packets over both links, with the slowest
> one being discarted.
>
> Biggest problem for videoconferencing is to encapsulate udp in TCP.
>
> But i have seen multipath UDP, but never tested any solution.
>
> With 2 links you might have more bandwidth, mptcp first saturate one link
> before using the second one.
>
> If anyone is interested, i can provide help to make a setup.
>
> Best,
>
>
>
>> --
>> Andrew
>> _______________________________________________
>> 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: 3666 bytes --]

      reply	other threads:[~2023-03-26 23:26 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-03-26 18:07 Andrew Crane
2023-03-26 19:27 ` Benjamin Henrion
2023-03-26 23:26   ` Nathan Owens [this message]

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=CALjsLJtwZ+pA8HN72nHzAPZkLDKaZqujaQaU83HSMYNWLLfOWQ@mail.gmail.com \
    --to=nathan@nathan.io \
    --cc=fairalbion@gmail.com \
    --cc=starlink@lists.bufferbloat.net \
    --cc=zoobab@gmail.com \
    /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