From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mailout3.rbg.tum.de (mailout3.rbg.tum.de [131.159.0.8]) (using TLSv1.2 with cipher ADH-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by lists.bufferbloat.net (Postfix) with ESMTPS id F11303B2A4 for ; Thu, 14 Jul 2022 09:33:34 -0400 (EDT) Received: from mailrelay1.rbg.tum.de (mailrelay1.in.tum.de [131.159.254.14]) by mailout3.rbg.tum.de (Postfix) with ESMTPS id 593EC101235; Thu, 14 Jul 2022 15:33:33 +0200 (CEST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=in.tum.de; s=20220209; t=1657805613; bh=SnBJ66RfaCWTUBfcHUjphqaoY9G/hjCIPehWmkU0muE=; h=Date:From:To:Cc:In-Reply-To:References:Subject:From; b=NBJ3Qphjg0SBrtuXZvYo2Cbmr1hJhFCwxDKP3OwPYnWvcBokl+0hDnt4v8E0OAO0I yb3vFX/0PDzPovncvGMO2Qn2HQOwApH8SUcUyIscwWkHqsVCVhfTlKCzJoNBn0QLyZ qliQb5vazvgRb1Qlf7Rc94Ml5yZNOH8Kwap5SUQX29jrKwTWFl1fRfWWCU9s5R22jy cMRhFuEWWyeAIHIjTEOmbxIvWTmw1oYAiV9D1tw5gAqdVAbV+sZIPLCqyhzYAcAoCE BnMqPtB51UTuFcJai9c/8shxuIrNdUEoUzP5I3UpvvNNpdUGJ2j4REfFGrCcTNj6vo xzlHGtu63ZO5w== Received: by mailrelay1.rbg.tum.de (Postfix, from userid 112) id 56331DD2; Thu, 14 Jul 2022 15:33:33 +0200 (CEST) Received: from mailrelay1.rbg.tum.de (localhost [127.0.0.1]) by mailrelay1.rbg.tum.de (Postfix) with ESMTP id 27906DD0; Thu, 14 Jul 2022 15:33:33 +0200 (CEST) Received: from mail.in.tum.de (vmrbg426.in.tum.de [131.159.0.73]) by mailrelay1.rbg.tum.de (Postfix) with ESMTPS id 2598ADCD; Thu, 14 Jul 2022 15:33:33 +0200 (CEST) Received: by mail.in.tum.de (Postfix, from userid 112) id 209C14A04E7; Thu, 14 Jul 2022 15:33:33 +0200 (CEST) Received: (Authenticated sender: mohan) by mail.in.tum.de (Postfix) with ESMTPSA id 949204A02BF; Thu, 14 Jul 2022 15:33:32 +0200 (CEST) (Extended-Queue-bit xtech_ge@fff.in.tum.de) Date: Thu, 14 Jul 2022 15:33:27 +0200 From: Nitinder Mohan To: Jared Mauch Cc: Mike Puchol , Dave Taht via Starlink Message-ID: In-Reply-To: References: <20220713173602.0582c9b3@spidey.rellim.com> <92n4s129-6r15-7q75-7293-qpo73q298srn@ynat.uz> <841ca6dc-d6d3-46ab-87c0-d6bcaa31533b@Spark> <42D3F3C5-C1B3-48EA-8C45-2540ACD787E4@gmx.de> <0C0F0D5F-7CF6-412A-AD1A-392323ADB2FB@gmx.de> <858AB3A2-EDE0-4035-A4FE-EC2313CC3197@puck.nether.net> MIME-Version: 1.0 Content-Type: multipart/alternative; boundary="62d01b2c_167c79cf_2a3f" Subject: Re: [Starlink] starlink at sea 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: Thu, 14 Jul 2022 13:33:35 -0000 --62d01b2c_167c79cf_2a3f Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Content-Disposition: inline Hi Jared, Turns out that SpaceX has deprecated the API calls to get satelliteID and= cellID over gRPC so that information is no longer available. See=C2=A0ht= tps://github.com/danopstech/starlink/issues/27 Too bad since those would have been quite useful to understand performanc= e trends. Thanks and Regards Nitinder Mohan Technical University Munich (TUM) https://www.nitindermohan.com/ =46rom:=C2=A0Nitinder Mohan Reply:=C2=A0Nitinder Mohan Date:=C2=A014. July 2022 at 15:05:42 To:=C2=A0Jared Mauch Cc:=C2=A0Dave Taht via Starlink , Mike = Puchol Subject:=C2=A0 Re: =5BStarlink=5D starlink at sea =20 Hi Jared, Thanks much for the pointer. This seems promising=21 We have a stationary dish available locally so we can try pulling informa= tion at our end.=C2=A0 Thanks and Regards Nitinder Mohan Technical University Munich (TUM) https://www.nitindermohan.com/ =46rom:=C2=A0Jared Mauch Reply:=C2=A0Jared Mauch Date:=C2=A014. July 2022 at 14:57:25 To:=C2=A0Nitinder Mohan Cc:=C2=A0Mike Puchol , Dave Taht via Starlink Subject:=C2=A0 Re: =5BStarlink=5D starlink at sea =20 I haven=E2=80=99t poked hard, but it does seem you can get it: =20 currentCellId current=5Fcell=5Fid =20 Seem to be in the GRPC proto dump from the dish. =20 https://github.com/sparky8512/starlink-grpc-tools/blob/main/extract=5Fpro= toset.py =20 This should pull it out, if you want from my (stationary) dish I bet I ca= n run something to pull/dump the info. =20 - jared =20 > On Jul 14, 2022, at 8:49 AM, Nitinder Mohan via Starlink wrote: =20 > =20 > Hi Mike, =20 > =20 > Do you happen to have a tool that can extract the current uplink channe= l of Starlink and (more importantly) which staellite it is connected to a= t any given time=3F I wanted to track the handovers in Starlink and try t= o find its impact on network performance but cannot seem to get those val= ues. =20 > =20 > Thanks and Regards =20 > =20 > Nitinder Mohan =20 > Technical University Munich (TUM) =20 > https://www.nitindermohan.com/ =20 > =20 > =46rom: Sebastian Moeller via Starlink =20 > Reply: Sebastian Moeller =20 > Date: 14. July 2022 at 14:35:16 =20 > To: Mike Puchol =20 > Cc: Dave Taht via Starlink =20 > Subject: Re: =5BStarlink=5D starlink at sea =20 > =20 >> Hi Mike. =20 >> =20 >> Thanks a lot. This is intersting. =20 >> =20 >> > On Jul 14, 2022, at 14:02, Mike Puchol wrote: =20 >> > =20 >> > The uplink is an O=46DM signal with 128 subcarriers, looking at the = signal in the time domain reveals a frame length corresponding to 14% (fr= om memory, 1,1 us frame vs 6.7 us pause). I have two terminals 1 meter ap= art and they can each achieve 30 Mbps at the same time over the same upli= nk channel. I would expect the satellite to assign a particular set of sl= ots to a terminal. =20 >> =20 >> So assuming the 30 Mbps being gross rate and not measured goodput: =20 >> =20 >> 30Mbps -> 30 / (1.1/(6.7+1.1)) =3D 212.73 Mb/s while actively sending,= and =20 >> 1000000=C2=B5s/s / (6.7+1.1)=C2=B5s =3D 128205.128205 slots/sec =20 >> (30 / (1.1/(6.7+1.1))) * 1000=5E2 / (1000000 / (6.7+1.1)) =3D 1659.27 = bits/slot 1659.27/8 =3D 207.41 Bytes/slot =20 >> =20 >> with 128 subcarriers that would be approximately an average =20 >> =20 >> 1659.27/128 =3D 12.96 or =7E 13 bit/subcarrier =20 >> =20 >> if all carriers are loaded equally (which is unlikely, I expect some r= e-arrangement ot bits between subcarriers to account for different levels= of noise and what not). =20 >> =20 >> =20 >> > If there are any O=46DM blind analysis experts in the room, shout=21= =20 >> =20 >> Please do=21 =20 >> Regards =20 >> Sebastian =20 >> =20 >> > =20 >> > Best, =20 >> > =20 >> > Mike =20 >> > On Jul 14, 2022, 13:33 +0200, Sebastian Moeller ,= wrote: =20 >> >> Hi Mike, =20 >> >> =20 >> >>> On Jul 14, 2022, at 13:15, Mike Puchol via Starlink wrote: =20 >> >>> =20 >> >>> On the multiple terminals, I have verified that the duty cycle of = a consumer terminal is 14%, thus, you could have 7 terminals on a single = uplink channel with some guard time. =20 >> >> =20 >> >> Could you elaborate how that works.how the terminals will be interl= eaved in that situation=3F =20 >> >> =20 >> >> Regards =20 >> >> Sebastian =20 >> >> =20 >> >> =20 >> >>> I have seen 30 Mbps up, so you=E2=80=99d be able to push 210 Mbps = in uplink, or a spectral efficiency of about 3.4 bps/Hz. =20 >> >> =20 >> =20 >> =5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F= =5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F =20 >> Starlink mailing list =20 >> Starlink=40lists.bufferbloat.net =20 >> https://lists.bufferbloat.net/listinfo/starlink =20 > =5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F= =5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F =20 > Starlink mailing list =20 > Starlink=40lists.bufferbloat.net =20 > https://lists.bufferbloat.net/listinfo/starlink =20 --62d01b2c_167c79cf_2a3f Content-Type: text/html; charset="utf-8" Content-Transfer-Encoding: quoted-printable Content-Disposition: inline
Hi Jared,

Turns out that SpaceX has deprecated= the API calls to get satelliteID and cellID over gRPC so that informatio= n is no longer available. See https://github.com/danopstech/starlink= /issues/27

Too bad since those would have been quite useful to und= erstand performance trends.

Thanks and Regards
Nitinder Mohan
Technical University Munich (TUM)

=46rom: Nitinder Mohan <mohan=40in.tum.de>
Reply: Nitinder Mohan <m= ohan=40in.tum.de>
Date: 14= . July 2022 at 15:05:42
To: Jared Mauch <ja= red=40puck.nether.net>
Cc: Dave Taht via Starlink <starlink=40lists.bufferbloat.net>, Mike Puchol <mike=40starlink.sx>
Subject:  Re: =5BStarlink=5D starlink at sea

Hi Jared,

Thanks much for the pointer. This seems promising=21
<= br>
We have a stationary dish available locally so we can try pulling in= formation at our end. 

Thanks and Regards
Nitinder Mohan
Technical University Munich (TUM)

=46rom: Jared Mauch <jared=40puck.nether.net>
Reply: Jared Mauch <jared=40puck.nether.net>
Date: 14. July 2022 at 14:57:25
To: Nitinder Mohan <mohan=40in.tum.de>
Cc: Mike Puchol <= ;mike=40starlink.sx>, Dave Taht vi= a Starlink <starlink=40lists.bufferbloat.net>
Subject:  Re: =5BStarlink=5D starlink at sea

=
I haven=E2=80=99t poked hard, but it does seem you can ge= t it:

currentCellId current=5Fcell=5Fid

Seem to be in the GRPC proto dump from the dish.

https://github.com/sparky8512/starlink-grpc-tools/blob/main/extract=5F= protoset.py

This should pull it out, if you want from my (stationary) dish I bet = I can run something to pull/dump the info.

- jared

> On Jul 14, 2022, at 8:49 AM, Nitinder Mohan via Starlink <sta= rlink=40lists.bufferbloat.net> wrote:
> =20
> Hi Mike,
> =20
> Do you happen to have a tool that can extract the current uplink= channel of Starlink and (more importantly) which staellite it is connect= ed to at any given time=3F I wanted to track the handovers in Starlink an= d try to find its impact on network performance but cannot seem to get th= ose values. =20
> =20
> Thanks and Regards
> =20
> Nitinder Mohan
> Technical University Munich (TUM)
> https://www.nitindermohan.com/
> =20
> =46rom: Sebastian Moeller via Starlink <starlink=40lists.buff= erbloat.net>
> Reply: Sebastian Moeller <moeller0=40gmx.de>
> Date: 14. July 2022 at 14:35:16
> To: Mike Puchol <mike=40starlink.sx>
> Cc: Dave Taht via Starlink <starlink=40lists.bufferbloat.net&= gt;
> Subject: Re: =5BStarlink=5D starlink at sea =20
> =20
>> Hi Mike.
>> =20
>> Thanks a lot. This is intersting.
>> =20
>> > On Jul 14, 2022, at 14:02, Mike Puchol <mike=40starl= ink.sx> wrote:
>> > =20
>> > The uplink is an O=46DM signal with 128 subcarriers, lo= oking at the signal in the time domain reveals a frame length correspondi= ng to 14% (from memory, 1,1 us frame vs 6.7 us pause). I have two termina= ls 1 meter apart and they can each achieve 30 Mbps at the same time over = the same uplink channel. I would expect the satellite to assign a particu= lar set of slots to a terminal.
>> =20
>> So assuming the 30 Mbps being gross rate and not measured go= odput:
>> =20
>> 30Mbps -> 30 / (1.1/(6.7+1.1)) =3D 212.73 Mb/s while acti= vely sending, and =20
>> 1000000=C2=B5s/s / (6.7+1.1)=C2=B5s =3D 128205.128205 slots/= sec
>> (30 / (1.1/(6.7+1.1))) * 1000=5E2 / (1000000 / (6.7+1.1)) =3D= 1659.27 bits/slot 1659.27/8 =3D 207.41 Bytes/slot
>> =20
>> with 128 subcarriers that would be approximately an average = =20
>> =20
>> 1659.27/128 =3D 12.96 or =7E 13 bit/subcarrier =20
>> =20
>> if all carriers are loaded equally (which is unlikely, I exp= ect some re-arrangement ot bits between subcarriers to account for differ= ent levels of noise and what not).
>> =20
>> =20
>> > If there are any O=46DM blind analysis experts in the r= oom, shout=21
>> =20
>> Please do=21
>> Regards
>> Sebastian
>> =20
>> > =20
>> > Best,
>> > =20
>> > Mike
>> > On Jul 14, 2022, 13:33 +0200, Sebastian Moeller <moe= ller0=40gmx.de>, wrote:
>> >> Hi Mike,
>> >> =20
>> >>> On Jul 14, 2022, at 13:15, Mike Puchol via Star= link <starlink=40lists.bufferbloat.net> wrote:
>> >>> =20
>> >>> On the multiple terminals, I have verified that= the duty cycle of a consumer terminal is 14%, thus, you could have 7 ter= minals on a single uplink channel with some guard time.
>> >> =20
>> >> Could you elaborate how that works.how the terminal= s will be interleaved in that situation=3F
>> >> =20
>> >> Regards
>> >> Sebastian
>> >> =20
>> >> =20
>> >>> I have seen 30 Mbps up, so you=E2=80=99d be abl= e to push 210 Mbps in uplink, or a spectral efficiency of about 3.4 bps/H= z.
>> >> =20
>> =20
>> =5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F= =5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F= =5F=5F
>> Starlink mailing list
>> Starlink=40lists.bufferbloat.net
>> https://lists.bufferbloat.net/listinfo/starlink
> =5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F= =5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=5F=
> Starlink mailing list
> Starlink=40lists.bufferbloat.net
> https://lists.bufferbloat.net/listinfo/starlink

--62d01b2c_167c79cf_2a3f--