Starlink has bufferbloat. Bad.
 help / color / mirror / Atom feed
* [Starlink] Starlink Performance Study
@ 2023-09-20 15:04 Livingood, Jason
  2023-09-20 15:43 ` Dave Taht
  0 siblings, 1 reply; 2+ messages in thread
From: Livingood, Jason @ 2023-09-20 15:04 UTC (permalink / raw)
  To: starlink

[-- Attachment #1: Type: text/plain, Size: 652 bytes --]

As some of you may recall I recruiting some US-based Starlink users to host RIPE Atlas probes as part of my role as a RIPE Atlas Ambassador. I just got word that NetForecast conducted a performance study that looked at RIPE Atlas data using some of the data from those and other probes. They looked at homes across the US with 5G fixed wireless, LEO satellite, and DOCSIS.

They have posted a first report of this study at https://www.netforecast.com/wp-content/uploads/FixedWireless_LEO_CableComparisonReport_NFR5148-1.pdf. I am looking forward to other researchers looking into the RIPE Atlas data – I know a few are working on this.

Jason


[-- Attachment #2: Type: text/html, Size: 2612 bytes --]

^ permalink raw reply	[flat|nested] 2+ messages in thread

* Re: [Starlink] Starlink Performance Study
  2023-09-20 15:04 [Starlink] Starlink Performance Study Livingood, Jason
@ 2023-09-20 15:43 ` Dave Taht
  0 siblings, 0 replies; 2+ messages in thread
From: Dave Taht @ 2023-09-20 15:43 UTC (permalink / raw)
  To: Livingood, Jason; +Cc: starlink


[-- Attachment #1.1: Type: text/plain, Size: 1550 bytes --]

Attached is a recent cloudflare test of verizon, taken about 1.2 miles from
a rural tower. While the bandwidth was low for reasons unknown, the latency
was... quite tolerable. Perhaps they are figuring this out.

I have no idea how atlas calculates latency or loss. Over what interval? In
the starlink case especially, I look at a typical plot, and I hope that if
more people looked at details like that, they would despair of using
averages ever again.

On Wed, Sep 20, 2023 at 8:05 AM Livingood, Jason via Starlink <
starlink@lists.bufferbloat.net> wrote:

> As some of you may recall I recruiting some US-based Starlink users to
> host RIPE Atlas probes as part of my role as a RIPE Atlas Ambassador. I
> just got word that NetForecast conducted a performance study that looked at
> RIPE Atlas data using some of the data from those and other probes. They
> looked at homes across the US with 5G fixed wireless, LEO satellite, and
> DOCSIS.
>
>
>
> They have posted a first report of this study at
> https://www.netforecast.com/wp-content/uploads/FixedWireless_LEO_CableComparisonReport_NFR5148-1.pdf.
> I am looking forward to other researchers looking into the RIPE Atlas data
> – I know a few are working on this.
>
>
>
> Jason
>
>
> _______________________________________________
> Starlink mailing list
> Starlink@lists.bufferbloat.net
> https://lists.bufferbloat.net/listinfo/starlink
>


-- 
Oct 30: https://netdevconf.info/0x17/news/the-maestro-and-the-music-bof.html
Dave Täht CSO, LibreQos

[-- Attachment #1.2: Type: text/html, Size: 3007 bytes --]

[-- Attachment #2: verizon.png --]
[-- Type: image/png, Size: 86657 bytes --]

^ permalink raw reply	[flat|nested] 2+ messages in thread

end of thread, other threads:[~2023-09-20 15:43 UTC | newest]

Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2023-09-20 15:04 [Starlink] Starlink Performance Study Livingood, Jason
2023-09-20 15:43 ` Dave Taht

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox