* [Bloat] Fwd: Interop runner with satellite links [not found] <2572762.KRHqeOQrTU@7b74a564-70da-4baa-82f8-b74434554dd0> @ 2021-09-30 19:32 ` Dave Taht 2021-10-01 7:49 ` Erik Auerswald 0 siblings, 1 reply; 3+ messages in thread From: Dave Taht @ 2021-09-30 19:32 UTC (permalink / raw) To: bloat, basti.endres of interest to the bufferbloat lost. Nice work sebastian! ---------- Forwarded message --------- From: Sebastian Endres <basti.endres@fau.de> Date: Wed, Sep 29, 2021 at 12:58 PM Subject: Interop runner with satellite links To: <etosat@ietf.org>, <quic@ietf.org> Cc: <joerg.deutschmann@fau.de> Dear all, for my master's thesis we ran measurements of all publicly available QUIC implementations over an emulated satellite link. The results are available online: https://interop.sedrubal.de/ A click on the results also shows time-offset plots, but are not available for every combination. In general, the performance of QUIC over high latency (e.g., geostationary satellites) is rather poor, especially if there is packet loss. Would it make sense to add such tests with challenging link characteristics to the official QUIC interop runner? Best regards, Sebastian -- Fixing Starlink's Latencies: https://www.youtube.com/watch?v=c9gLo6Xrwgw Dave Täht CEO, TekLibre, LLC ^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [Bloat] Fwd: Interop runner with satellite links 2021-09-30 19:32 ` [Bloat] Fwd: Interop runner with satellite links Dave Taht @ 2021-10-01 7:49 ` Erik Auerswald 2021-10-06 9:09 ` Joerg Deutschmann 0 siblings, 1 reply; 3+ messages in thread From: Erik Auerswald @ 2021-10-01 7:49 UTC (permalink / raw) To: bloat; +Cc: basti.endres Hi, On Thu, Sep 30, 2021 at 12:32:01PM -0700, Dave Taht wrote: > of interest to the bufferbloat lost. Nice work sebastian! > > ---------- Forwarded message --------- > From: Sebastian Endres <basti.endres@fau.de> > Date: Wed, Sep 29, 2021 at 12:58 PM > Subject: Interop runner with satellite links > [...] > for my master's thesis we ran measurements of all publicly available > QUIC implementations over an emulated satellite link. The results are > available online: https://interop.sedrubal.de/ The web site gives an emulated RTT of 600ms. When I worked on satellite based IP connectivity for cargo ships ten years ago, I saw minimum (unloaded) RTTs of about 1.1s (1100ms) for both LEO (Iridium back then) and GEO based systems. Thus 600ms RTT seems quite optimistic to me, at least from the point of view of a user of satellite systems. Thanks, Erik -- It's impossible to learn very much by simply sitting in a lecture, or even by simply doing problems that are assigned. -- Richard P. Feynman ^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [Bloat] Fwd: Interop runner with satellite links 2021-10-01 7:49 ` Erik Auerswald @ 2021-10-06 9:09 ` Joerg Deutschmann 0 siblings, 0 replies; 3+ messages in thread From: Joerg Deutschmann @ 2021-10-06 9:09 UTC (permalink / raw) To: bloat Dear Erik, we have four different European geostationary satellite providers for fixed wireless access, and we usually see RTTs between 600ms and 700ms (unloaded, bufferbloat not tested yet), so it seems that the situation has improved. Some not in-depth measurements: https://www.ietf.org/proceedings/104/slides/slides-104-maprg-satellite-internet-performance-measurements-jorg-deutschmann-01.pdf Best regards, Joerg ^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2021-10-06 9:09 UTC | newest] Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed) -- links below jump to the message on this page -- [not found] <2572762.KRHqeOQrTU@7b74a564-70da-4baa-82f8-b74434554dd0> 2021-09-30 19:32 ` [Bloat] Fwd: Interop runner with satellite links Dave Taht 2021-10-01 7:49 ` Erik Auerswald 2021-10-06 9:09 ` Joerg Deutschmann
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox