Starlink has bufferbloat. Bad.
 help / color / mirror / Atom feed
From: Omer Shapira <omer.shapira@gmail.com>
To: "Dave Täht" <davet@teklibre.net>,
	"Michael Richardson" <mcr@sandelman.ca>
Cc: starlink@lists.bufferbloat.net
Subject: Re: [Starlink] Hello List
Date: Sat, 19 Mar 2022 14:42:16 -0700	[thread overview]
Message-ID: <F6F79EB1-406A-4DEF-A467-37A4C0F4B669@gmail.com> (raw)
In-Reply-To: <20220302200531.GB6564@mail.taht.net>

[-- Attachment #1: Type: text/plain, Size: 2246 bytes --]



> On Mar 2, 2022, at 12:05 PM, Dave Täht <davet@teklibre.net> wrote:
> 
> 
> On Wed, Mar 02, 2022 at 02:55:26PM -0500, Michael Richardson wrote:
>> 
>> <tom@evslin.com <mailto:tom@evslin.com>> wrote:
>>> need to prosper in the hybrid digital world. As all of you know, QoS is much
>>> more than up and downlink speed and tough-to-quantify jitter is a huge part
>>> of it. My measurement tool zoomready (at freecheckip.com <http://freecheckip.com/>
>>> <http://freecheckip.com/ <http://freecheckip.com/>>  and  https://github.com/tevslin/zoomready <https://github.com/tevslin/zoomready>) makes
>>> a more or less continuous measurement of jitter but is quite crude; so
>> 
>> I think that Apple/Stuart did a good job inverting the jitter metric, and calling it
>> Rounds/Revolutions per Minute.  I suggest doing the same in your tool.
> 
> Except it's NOT a jitter metric. It is a latency under load metric primarily aime
> at testing in-band (http 2.0 or quic) AQM latency. Most of our other tests
> to date have a tendency to favor FQ measurements. 

Thanks Dave,

FWIW, the RPM metric is outlined in https://datatracker.ietf.org/doc/draft-ietf-ippm-responsiveness/ 

> 
> Certainly jitter can be pulled out of detailed measurements using some
> of the proposed methodologies. See the rpm@lists.bufferbloat.net <mailto:rpm@lists.bufferbloat.net> list
> an archives for more details.
> 
> We have a regular meeting on implementations and new data
> at 10AM PDT tuesdays if anyone would like to join. 
> 
> 
> 
>> 
>> --
>> ]               Never tell me the odds!                 | ipv6 mesh networks [
>> ]   Michael Richardson, Sandelman Software Works        |    IoT architect   [
>> ]     mcr@sandelman.ca  http://www.sandelman.ca/        |   ruby on rails    [
>> 
> 
> 
> 
>> _______________________________________________
>> Starlink mailing list
>> Starlink@lists.bufferbloat.net
>> https://lists.bufferbloat.net/listinfo/starlink
> 
> _______________________________________________
> Starlink mailing list
> Starlink@lists.bufferbloat.net <mailto:Starlink@lists.bufferbloat.net>
> https://lists.bufferbloat.net/listinfo/starlink <https://lists.bufferbloat.net/listinfo/starlink>

[-- Attachment #2: Type: text/html, Size: 18450 bytes --]

      reply	other threads:[~2022-03-19 21:42 UTC|newest]

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-03-02 18:29 tom
2022-03-02 19:55 ` Michael Richardson
2022-03-02 20:05   ` Dave Täht
2022-03-19 21:42     ` Omer Shapira [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=F6F79EB1-406A-4DEF-A467-37A4C0F4B669@gmail.com \
    --to=omer.shapira@gmail.com \
    --cc=davet@teklibre.net \
    --cc=mcr@sandelman.ca \
    --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