Starlink has bufferbloat. Bad.
 help / color / mirror / Atom feed
From: Dave Taht <dave.taht@gmail.com>
To: Sascha Meinrath <sascha@thexlab.org>
Cc: George Burdell <gb@teklibre.net>, starlink@lists.bufferbloat.net
Subject: Re: [Starlink] starlink <-> starlink tests over ivpv6
Date: Wed, 26 May 2021 13:54:00 -0700	[thread overview]
Message-ID: <CAA93jw4mZ+gmadhcpgxep_xDv8F-+X0DO2-HG7yQoN=beWbtLg@mail.gmail.com> (raw)
In-Reply-To: <911b6113-aebe-43f0-e94f-1ed4a132fe99@thexlab.org>

On Wed, May 26, 2021 at 7:11 AM Sascha Meinrath <sascha@thexlab.org> wrote:
>
> Hi everyone,
>
> I'm happy to put my dishy at the disposal of the group, but have been utterly
> crammed for time. That said, if folks want to walk me through what would be most
> helpful (i.e., specific equipment to plug in/access control to grant/etc.),
> happy to get that implemented so that folks can utilize this resource.

The simplest possible arrangement is a linux box directly in front of
the dishy not their supplied router. Nearly any kind will suffice, so
long as it can get an ipv6 address. I have a mild preference for the
current ubuntu, or the openwrt release candidate, but even centos
would suffice. Supplying our ssh keys for further configuration (if
needed) for other tests, like of DoH vs DNS. We prefer raw hardware
rather than a vm, to rule out interactions with vm jitter and
latencies. A raspi-4 is fine. x86_64 preferred.

Possible, but less useful, would be an osx box, configured to run
netserver and irtt, I can supply working binaries of each.

windows is right out.

> Also, my Starlink network is completely separated from my home network (so folks
> can do pretty much whatever would be most useful with it without worry).
> Physically, it's located in central PA, USA.
>
> Let me know,
>
> --Sascha Meinrath
> Director, X-Lab
> Palmer Chair in Telecommunications
> Penn State University
>
> On 5/26/21 9:20 AM, George Burdell wrote:
> > I have setup a doodle poll for co-ordinating times to meet
> >
> > https://doodle.com/poll/qamim95xpb8kwanx?utm_source=poll&utm_medium=link
> >
> > On Tue, May 18, 2021 at 04:40:51PM -0700, Dave Taht wrote:
> >> I think we are at 6? people with dishys now on this list? Most having
> >> got rid of the starlink provided router?
> >>
> >> What I would love to do is a string of bufferbloat related tests
> >> between your networks, much like I've been testing
> >> to the cloud. This would include traceroute or mtr, the rrul, tcp_nup,
> >> tcp_ndown tests with sqm on and off.
> >>
> >> I know george hasn't been publishing via anything other than git via
> >> rsync, but the simple test scripts there
> >> can be modified to do a string of tests dishy to dishy.
> >>
> >> There are also many ways to take a dynamic ipv6 address and put it
> >> into dns. linode's is straightforward if
> >> you'd want to leverage taht.net.
> >>
> >> (for the record "taht" means "star or planet" in estonian)
> >>
> >>
> >> --
> >> Latest Podcast:
> >> https://www.linkedin.com/feed/update/urn:li:activity:6791014284936785920/
> >>
> >> Dave Täht CTO, TekLibre, LLC
> >> _______________________________________________
> >> 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
> >



-- 
Latest Podcast:
https://www.linkedin.com/feed/update/urn:li:activity:6791014284936785920/

Dave Täht CTO, TekLibre, LLC

  reply	other threads:[~2021-05-26 20:54 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-05-18 23:40 Dave Taht
2021-05-19  8:49 ` Annika Wickert
2021-05-21 15:07   ` Dave Taht
2021-05-21 16:14     ` Paul Vixie
2021-05-26 13:14 ` George Burdell
2021-05-26 13:20 ` George Burdell
2021-05-26 14:11   ` Sascha Meinrath
2021-05-26 20:54     ` Dave Taht [this message]
2021-05-26 20:56   ` Sascha Meinrath
2021-05-26 23:30     ` Nick Buraglio
2021-05-27 13:14       ` Sascha Meinrath

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='CAA93jw4mZ+gmadhcpgxep_xDv8F-+X0DO2-HG7yQoN=beWbtLg@mail.gmail.com' \
    --to=dave.taht@gmail.com \
    --cc=gb@teklibre.net \
    --cc=sascha@thexlab.org \
    --cc=starlink@lists.bufferbloat.net \
    /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