[Starlink] starlink videoconference today at 1PM PDT

[Dave Taht]

thx everyone for coming. I apologize for the chaos. It was the first day of funding for this project...

It was a great and exciting all up test of beta routing code over a beta ISP over an alpha videoconferencing codebase, over lousy wifi, from the side of a mountain, ov and so great to see you all.

The biggest failure was galene started throwing off errors mid-way through which need to be fixed. 

On top of that "all up" test!!!! we were also testing the wifi VI queue, and AF42 dscp passthrough various isps. starlink seems to preserve at least some dscps end to end. Packet captures were taken at various endpoints that should be worth dissecting.

I do fear that large scale use of the VI queue may fail in some locations - including mine - as it is a significantly undertested wifi option.  But sch_cake itself performed brilliantly... 

                  Bulk  Best Effort        Video        Voice
  thresh        625Kbit       10Mbit        5Mbit     2500Kbit
  target         29.1ms          5ms          5ms       7.27ms
  interval        124ms        100ms        100ms        102ms
  pk_delay          0us        2.3ms       4.65ms       1.72ms
  av_delay          0us        243us        414us        128us
  sp_delay          0us         12us         11us          9us
  backlog            0b           0b           0b           0b
  pkts                0        49469       656531          392
  bytes               0     13661709    323367991        49808
  way_inds            0         1011        13752            0
  way_miss            0         3601         1523           12
  way_cols            0            0            0            0
  drops               0           40            6            0
  marks               0            1            0            0
  ack_drop            0          173            0            0
  sp_flows            0            2            0            0
  bk_flows            0            1            0            0
  un_flows            0            0            0            0
  max_len             0         1514         1392          590
  quantum           300          305          300          300


> On Jun 1, 2021, at 12:28 PM, Rich Brown <richb.hanover at gmail.com> wrote:
> 
> I'll be there, if nothing else, to lurk! Thanks for the invite.
> 
> Rich
> 
>> On Jun 1, 2021, at 3:26 PM, Dave Taht <davet at teklibre.net <mailto:davet at teklibre.net>> wrote:
>> 
>> I note for those attending today that donovan and I are behind a starlink terminal and despite our best efforts, it does tend to glitch occasionally. we would appreciate it if a few people here would drop in early so we can test some things.
>> 
>>> On Jun 1, 2021, at 8:59 AM, Dave Taht <davet at teklibre.net <mailto:davet at teklibre.net>> wrote:
>>> 
>>> Sorry for the late notice, as this is a regularly scheduled bufferbloat “working latency” meeting. Today’s focus is on starlink. 
>>> 
>>> We have a very full agenda today, but all are invited here to attend to see the latest results from our work and to help us discuss next steps.
>>> 
>>> We’ve been using the following galene.org <http://galene.org/> based videoconferencing server for our meetings
>>> 
>>> https://tun.taht.net:8443/group/bufferbloat <https://tun.taht.net:8443/group/bufferbloat>
>>> 
>>> Use any login you like, with no password, chrome is best
>>> 
>>> TODAY’S AGENDA
>>> 
>>> 5 minutes Dave Taht Overview of where we are
>>> 
>>> 10 minutes introductions to various volunteers with dishy terminals
>>> 10 minutes discussing future plans this week
>>> 10 minutes ESR irtt updates
>>> 20 minutes open discussion
>>> 
>>> 
>> 
>> _______________________________________________
>> Starlink mailing list
>> Starlink at lists.bufferbloat.net <mailto:Starlink at lists.bufferbloat.net>
>> https://lists.bufferbloat.net/listinfo/starlink
> 

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.bufferbloat.net/pipermail/starlink/attachments/20210601/8b4cc869/attachment.html>