From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-yw1-x112f.google.com (mail-yw1-x112f.google.com [IPv6:2607:f8b0:4864:20::112f]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by lists.bufferbloat.net (Postfix) with ESMTPS id 102443B29D; Thu, 17 Aug 2023 11:29:40 -0400 (EDT) Received: by mail-yw1-x112f.google.com with SMTP id 00721157ae682-586a684e85aso84082857b3.2; Thu, 17 Aug 2023 08:29:40 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20221208; t=1692286179; x=1692890979; h=cc:to:subject:message-id:date:from:in-reply-to:references :mime-version:from:to:cc:subject:date:message-id:reply-to; bh=RC8kTq94o6H3CRRrryPIyM02w5Y9MtBEms/vpjXKEMo=; b=bw0/6ZtsaOSNnJEmnVHgM91lrz/85ONT5RTgXxs9biqg6xdM0VCE/xXixU8pYk/we+ l02v5z7IDWva/7iQB6ux/w2Y8brwJkc/bHlhN2RpkR6uMXN/7n1djFPSe/ZemZJUAdSW jDaObnjOOZIWbPuzLbbEKLmU1se1sYkiCNvtxSXkqfGTZ4nxGAWpRjBiHA+HPYKeikz0 7Fq7TLg95PK50g4Vsy+rsAikJMKdAyEM5xqRIdFO4F/kOO0p+V0JdihtgW7pLkMGHBNo 6l3ooMvIcZ+csm41qGxgn8seGy0yQvPBnqZ0Bz2Mihqr3c1dazb8E28T9HRgp1D5MpAw DLCQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20221208; t=1692286179; x=1692890979; h=cc:to:subject:message-id:date:from:in-reply-to:references :mime-version:x-gm-message-state:from:to:cc:subject:date:message-id :reply-to; bh=RC8kTq94o6H3CRRrryPIyM02w5Y9MtBEms/vpjXKEMo=; b=VE0okpxekTspfFY9lv1H7Y9Kl7wo2tDJzvGj5Yx6ZVw/ScrVb7PXnhtfbf5wIbB074 y54ARfWxG86wfj9LMmDmtljEmJhai2bBpNQ6qozNIiUczkLuWuSJTHBh2+wpUsuTon1p 8P8761x8jOOhFpuW1CiKcT9C048AdAPud3JS5SLiVKzGbwBQmwswY18DnM9nDuLzSIgF 0Gp/+MnuSzjNwN9ugTgs9MzaeGdA3HbvJABYBDPZZ3yp70PaP33rgnLaJelJqxM+gbR9 /pz2Cxp6ohBUF208Denn1uUqDEAKNlOtI4slNLZ2cOVrgixbUDrp7B/5QiMrc/7SP3zY fEuw== X-Gm-Message-State: AOJu0YwuvPUFc/SvqB8Eyk0FXEkjD9QEje6gTuAPDxs3RwmWt5dQpf7i NhMs/h7vIm1Zi1D16LLMtVpiAjtsO9O7rrPnLx8= X-Google-Smtp-Source: AGHT+IEixy+I7qqcFOv5xpcUBSrpH35lyusrXLgd9FLdbp/ysKQXQowXi+FWl9xQQkUJHyp1LFEVJGSZQeBr37Mui20= X-Received: by 2002:a0d:d601:0:b0:57a:6424:d62e with SMTP id y1-20020a0dd601000000b0057a6424d62emr5557179ywd.48.1692286179326; Thu, 17 Aug 2023 08:29:39 -0700 (PDT) MIME-Version: 1.0 References: <6C0AE2724B354B1E87B55C42C159CC27@SRA6> In-Reply-To: <6C0AE2724B354B1E87B55C42C159CC27@SRA6> From: dan Date: Thu, 17 Aug 2023 09:29:28 -0600 Message-ID: To: dickroy@alum.mit.edu Cc: Dave Taht , libreqos , Rpm , Sam Crawford Content-Type: multipart/alternative; boundary="00000000000093bfda06032014b7" Subject: Re: [LibreQoS] [Starlink] NZ latest latency report X-BeenThere: libreqos@lists.bufferbloat.net X-Mailman-Version: 2.1.20 Precedence: list List-Id: Many ISPs need the kinds of quality shaping cake can do List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 17 Aug 2023 15:29:40 -0000 --00000000000093bfda06032014b7 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable I can imagine the end-to-end latency is something they might not want to talk about. I'm saying this in the context of the english speaking world and transit times from AU and NZ to US, CA, UK. Keep in mind that one-way, it's 35ms from Auckland to Los Angeles for those photons in a vacuum, slightly more in a strand of glass. Cross-planet content really needs to be latency insensitive until we get some sort of FTL data streams lol. But if you are stuck with 35ms across the ocean to the nearest english speaking country, it's even more important to have the last mile be as low latency as possible. The 'content' can just be moved nearer, ie hulu and netflix and the like, but realtime coms with American has an extra 35ms and London 65ms one-way cost so you really can't afford to have 50ms to the end user on either side= . On Wed, Jul 5, 2023 at 6:17=E2=80=AFPM Dick Roy via LibreQoS < libreqos@lists.bufferbloat.net> wrote: > I=E2=80=99m not the expert in the room, however I find the report lacking= in one > very important area. All these results on latencies, speed, etc., are > categorized based on users =E2=80=9Cfirst mile access=E2=80=9D technology= , leqding the > reader to believe the sole source of these numbrs is the =E2=80=9Cfirst m= ile=E2=80=9D which > of course it is not. They do not address the as important issues of the > rest of what=E2=80=99s between =E2=80=9Cend-2-end=E2=80=9D. Take a look = at the gaming latency > results, and you see games hosted in America have very high latencies for > users in New Zealand =E2=80=A6 duhhhhhh! This can=E2=80=99t be news. > > > > While not trivial by any means, what could/should be done to make these > data more useful for consumers is to figure out the effect of everything > past the =E2=80=9Cfirst mile/first hop=E2=80=9D and break it out separate= ly. That way, a > (moderately intelligent) user could make a reasonably informed cost-benef= it > analysis on which combination of first mile technology and back-end servi= ce > provider to choose, assuming there were service providers that offered a > choice of =E2=80=9Cfirst-mile=E2=80=99 access, or backhaul providers that= served a variety > of =E2=80=9Cfirst mile=E2=80=9D providers. Guess we=E2=80=99re a few yea= rs away from that J > > > > RR > > > > -----Original Message----- > From: Starlink [mailto:starlink-bounces@lists.bufferbloat.net] On Behalf > Of Dave Taht via Starlink > Sent: Wednesday, July 5, 2023 6:08 AM > To: libreqos; Rpm; Dave Taht via Starlink > Cc: Sam Crawford > Subject: [Starlink] NZ latest latency report > > > > I do wish that it broke it out by provider, and recommended somehow to > > those suffering still, install a better device... VDSL can be made > > vastly more tolerable. Otherwise pretty good, and brings in > > starlink... > > > > > https://comcom.govt.nz/__data/assets/pdf_file/0016/320326/MBNZ-Autumn-Rep= ort-28-June-2023.pdf > > > > To pick on samknows a little bit, I think the test does not run long > > enough, and should be pulling from higher than what appears to be the > > 75th percentile. > > > > > > > > -- > > Podcast: > https://www.linkedin.com/feed/update/urn:li:activity:7058793910227111937/ > > Dave T=C3=A4ht CSO, LibreQos > > _______________________________________________ > > Starlink mailing list > > Starlink@lists.bufferbloat.net > > https://lists.bufferbloat.net/listinfo/starlink > _______________________________________________ > LibreQoS mailing list > LibreQoS@lists.bufferbloat.net > https://lists.bufferbloat.net/listinfo/libreqos > --00000000000093bfda06032014b7 Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable
I can imagine the end-to-end latency is something they mig= ht not want to talk about.=C2=A0 =C2=A0 I'm saying this in the context = of the english speaking world and transit times from AU and NZ to US, CA, U= K.

Keep in mind that one-way, it's 35ms from Auckland to Los Ang= eles for those photons in a vacuum, slightly more in a strand of glass.=C2= =A0=C2=A0

Cross-planet content really needs to be latency insensitiv= e=C2=A0until we get some sort of FTL data streams lol.

But if you ar= e stuck with 35ms across the ocean to the nearest english speaking country,= it's even more important to have the last mile be as low latency as po= ssible.=C2=A0=C2=A0

The 'content' can just be moved nearer, = ie hulu and netflix and the like, but realtime coms with American has an ex= tra 35ms and London 65ms one-way cost so you really can't afford to hav= e 50ms to the end user on either side.

=C2=A0

On Wed, Jul 5, 2023 at = 6:17=E2=80=AFPM Dick Roy via LibreQoS <libreqos@lists.bufferbloat.net> wrote:

I=E2=80=99m not the expert in the = room, however I find the report lacking in one very important area.=C2=A0 All these results on latencies, speed, etc.,= are categorized based on users =E2=80=9Cfirst mile access=E2=80=9D technology, = leqding the reader to believe the sole source of these numbrs is the =E2=80=9Cfirst mile=E2=80= =9D which of course it is not.=C2=A0 They do not address the as important issues of the rest of= what=E2=80=99s between =E2=80=9Cend-2-end=E2=80=9D.=C2=A0 Take a look at the gaming latenc= y results, and you see games hosted in America have very high latencies for users in New Zealand = =E2=80=A6 duhhhhhh!=C2=A0 This can=E2=80=99t be news.=C2=A0

=C2=A0=

While not trivial by any means, wh= at could/should be done to make these data more useful for consumers is to figure out the effect of everything pa= st the =E2=80=9Cfirst mile/first hop=E2=80=9D and break it out separately.=C2= =A0 That way, a (moderately intelligent) user could make a reasonably informed cost-benefit analysis on which combination of first mile technology and back-end service= provider to choose, assuming there were service providers that offered a choice of = =E2=80=9Cfirst-mile=E2=80=99 access, or backhaul providers that served a variety of =E2=80=9Cfirst mile= =E2=80=9D providers.=C2=A0 Guess we=E2=80=99re a few years away from that J

=C2=A0=

RR

=C2=A0=

-----Original Message-----
From: Starlink [mailto:starlink-bounces@lists.bufferbloat.net] On Beha= lf Of Dave Taht via Starlink
Sent: Wednesday, July 5, 2023 6:08 AM
To: libreqos; Rpm; Dave Taht via Starlink
Cc: Sam Crawford
Subject: [Starlink] NZ latest latency report

=C2=A0=

I do wish that it broke it out by = provider, and recommended somehow to

those suffering still, install a b= etter device... VDSL can be made

vastly more tolerable. Otherwise p= retty good, and brings in

starlink...

=C2=A0=

https://comcom.govt.nz/__data/assets/pdf_file/0016/320326/MB= NZ-Autumn-Report-28-June-2023.pdf

=C2=A0=

To pick on samknows a little bit, = I think the test does not run long

enough, and should be pulling from= higher than what appears to be the

75th percentile.

=C2=A0=

=C2=A0=

=C2=A0=

--

Podcast: https://www.linkedin.com/feed/update/urn:li:ac= tivity:7058793910227111937/

Dave T=C3=A4ht CSO, LibreQos

__________________________________= _____________

Starlink mailing list

Starlink@lists.bufferbloat.net=

https://lists.bufferbloat.net/l= istinfo/starlink

_______________________________________________
LibreQoS mailing list
LibreQo= S@lists.bufferbloat.net
https://lists.bufferbloat.net/listinfo/libreqos
--00000000000093bfda06032014b7--