From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail.taht.net (mail.taht.net [176.58.107.8]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by lists.bufferbloat.net (Postfix) with ESMTPS id E29FD3B29D for ; Tue, 1 Jun 2021 17:02:13 -0400 (EDT) Received: from smtpclient.apple (unknown [206.214.236.71]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.taht.net (Postfix) with ESMTPSA id 3A90A22C13; Tue, 1 Jun 2021 21:02:12 +0000 (UTC) From: Dave Taht Message-Id: <959B062F-FED3-4B07-8552-814D2EB8D396@teklibre.net> Content-Type: multipart/alternative; boundary="Apple-Mail=_E62B1243-40B1-4450-8617-211EDC4BCFB4" Mime-Version: 1.0 (Mac OS X Mail 14.0 \(3654.80.0.2.43\)) Date: Tue, 1 Jun 2021 14:02:09 -0700 In-Reply-To: <64576217-0531-45F5-B8C6-74702A62A7F6@gmail.com> Cc: dickroy@alum.mit.edu, Scott Staton To: starlink@lists.bufferbloat.net References: <637E0107-95CA-46DE-8D52-DC7750EFAC37@teklibre.net> <7372ADF5-67E6-407D-8522-B2FE6EE115CD@teklibre.net> <64576217-0531-45F5-B8C6-74702A62A7F6@gmail.com> X-Mailer: Apple Mail (2.3654.80.0.2.43) Subject: Re: [Starlink] starlink videoconference today at 1PM PDT X-BeenThere: starlink@lists.bufferbloat.net X-Mailman-Version: 2.1.20 Precedence: list List-Id: "Starlink has bufferbloat. Bad." List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 01 Jun 2021 21:02:14 -0000 --Apple-Mail=_E62B1243-40B1-4450-8617-211EDC4BCFB4 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset=utf-8 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.=20 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...=20 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 = wrote: >=20 > I'll be there, if nothing else, to lurk! Thanks for the invite. >=20 > Rich >=20 >> On Jun 1, 2021, at 3:26 PM, Dave Taht > wrote: >>=20 >> 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. >>=20 >>> On Jun 1, 2021, at 8:59 AM, Dave Taht > wrote: >>>=20 >>> Sorry for the late notice, as this is a regularly scheduled = bufferbloat =E2=80=9Cworking latency=E2=80=9D meeting. Today=E2=80=99s = focus is on starlink.=20 >>>=20 >>> 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. >>>=20 >>> We=E2=80=99ve been using the following galene.org = based videoconferencing server for our meetings >>>=20 >>> https://tun.taht.net:8443/group/bufferbloat = >>>=20 >>> Use any login you like, with no password, chrome is best >>>=20 >>> TODAY=E2=80=99S AGENDA >>>=20 >>> 5 minutes Dave Taht Overview of where we are >>>=20 >>> 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 >>>=20 >>>=20 >>=20 >> _______________________________________________ >> Starlink mailing list >> Starlink@lists.bufferbloat.net = >> https://lists.bufferbloat.net/listinfo/starlink >=20 --Apple-Mail=_E62B1243-40B1-4450-8617-211EDC4BCFB4 Content-Transfer-Encoding: quoted-printable Content-Type: text/html; charset=utf-8 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@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@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@teklibre.net> wrote:

Sorry = for the late notice, as this is a regularly scheduled bufferbloat = =E2=80=9Cworking latency=E2=80=9D meeting. Today=E2=80=99s 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=E2=80=99ve been using = the following galene.org = based videoconferencing server for our meetings

https://tun.taht.net:8443/group/bufferbloat

Use any login you like, = with no password, chrome is best

TODAY=E2=80=99S 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@lists.bufferbloat.net
https://lists.bufferbloat.net/listinfo/starlink


= --Apple-Mail=_E62B1243-40B1-4450-8617-211EDC4BCFB4--