Quick note from reading your blog entry.
Last night, I played with the Cloudflare Speedtest a little. It downloads
25MB and a 50MB (or 100MB, can’t remember) as well on a “speedier” network
after it does the 10MB file.
I was getting 1.2Gbs down and 760Mbs up, 4ms of LUL, and seeing those
larger file sizes. I was trying to screenshot and noticed I had those extra
file sizes I had to scroll down for. I ended up getting distracted and not
taking the shot to send. But, it will do a longer/bigger test under right
conditions.
Network here at the house is AT Fiber, 5Gbs up/down - limited to 3.6Gbs
down from Ubiquity UDM SE router/firewall with all IPS/Geo-blocking turned
on. 4.7Gbs non-blocking up. I am building a pfSense box to eliminate the
bottleneck. Couldn’t be happier, good job AS7018.
The machine I was testing from was Win10 wired 10Gbs and gets ~2.2Gbs
up/down for fast.com/speedtest.net. I haven’t take time to test internally
or try and tune that system, or might be CAT5e cabling issue… is fast
enough for me for that system.
Jay
On Wed, Jan 11, 2023 at 12:07 AM Dave Taht via Bloat <
bl...@lists.bufferbloat.net> wrote:
> Dear Luis:
>
> You hit 17 seconds of delay on your test.
>
> I got you beat, today, on my LTE connection, I cracked 182 seconds.
>
> I'd like to thank Verizon for making it possible for me to spew 4000
> words on my kvetches about the current speedtest regimes of speedtest,
> cloudflare, and so on, by making my network connection so lousy today
> that I sat in front of emacs to rant - and y'all for helping tone
> down, a little, this blog entry:
>
> https://blog.cerowrt.org/post/speedtests/
>
> On Tue, Jan 10, 2023 at 9:25 AM Luis A. Cornejo via Rpm
> wrote:
> >
> > Here is my VZ HSI
> >
> >
> > No SQMm on
> >
> > On Sat, Jan 7, 2023 at 6:38 PM Dick Roy via Bloat <
> bl...@lists.bufferbloat.net> wrote:
> >>
> >>
> >>
> >>
> >>
> >> -Original Message-
> >> From: rjmcmahon [mailto:rjmcma...@rjmcmahon.com]
> >> Sent: Friday, January 6, 2023 3:45 PM
> >> To: dick...@alum.mit.edu
> >> Cc: 'MORTON JR., AL'; 'IETF IPPM WG'; 'libreqos'; 'Cake List'; 'Rpm';
> 'bloat'
> >> Subject: Re: [Starlink] [Rpm] [LibreQoS] the grinch meets
> cloudflare'schristmas present
> >>
> >>
> >>
> >> yeah, I'd prefer not to output CLT sample groups at all but the
> >>
> >> histograms aren't really human readable and users constantly ask for
> >>
> >> them. I thought about providing a distance from the gaussian as output
> >>
> >> too but so far few would understand it and nobody I found would act upon
> >>
> >> it.
> >>
> >> [RR] Understandable until such metrics are “actionable”, and that’s “up
> to us to find/define/figure out” it seems to me. Metrics that are not
> actionable are write-only memory and good for little but historical recordJ
> >>
> >> The tool produces the full histograms so no information is really
> >>
> >> missing except for maybe better time series analysis.
> >>
> >> [RR] Isn’t that in fact what we are trying to extract from the e2e
> stats we collect? i.e., infer the time evolution of the system from its
> I/O behavior? As you point out, it’s really hard to do without probes in
> the guts of the system, nd yes, synchronization is important J
> >>
> >>
> >>
> >> The open source flows python code also released with iperf 2 does use
> >>
> >> the komogorov-smirnov distances & distance matrices to cluster when the
> >>
> >> number of histograms are just too much. We've analyzed 1M runs to fault
> >>
> >> isolate the "unexpected interruptions" or "bugs" and without statistical
> >>
> >> support it is just not doable. This does require instrumentation of the
> >>
> >> full path with mapping to a common clock domain (e.g. GPS) and not just
> >>
> >> e2e stats. I find an e2e complaint by an end user about "poor speed" as
> >>
> >> useful as telling a pharmacist I have a fever. Not much diagnostically
> >>
> >> is going on. Take an aspirin.
> >>
> >> [RR] That’s AWESOME!! I love that analogy!
> >>
> >>
> >>
> >> RR
> >>
> >>
> >>
> >> https://en.wikipedia.org/wiki/Kolmogorov%E2%80%93Smirnov_test
> >>
> >> https://sourceforge.net/p/iperf2/code/ci/master/tree/flows/flows.py
> >>
> >>
> >>
> >> Bob
> >>
> >> > See below …
> >>
> >> >
> >>
> >> > -Original Message-
> >>
> >> > From: Starlink [mailto:starlink-boun...@lists.bufferbloat.net] On
> >>
> >> > Behalf Of rjmcmahon via Starlink
> >>
> >> > Sent: Friday, January 6, 2023 12:39 PM
> >>
> >> > To: MORTON JR., AL
> >>
> >> > Cc: Dave Taht via Starlink; IETF IPPM WG; libreqos; Cake List; Rpm;
> >>
> >> > bloat
> >>
> >> > Subject: Re: [Starlink] [Rpm] [LibreQoS] the grinch meets
> >>
> >> > cloudflare'schristmas present
> >>
> >> >
> >>
> >> > Some thoughts are not to use UDP for testing here. Also, these speed
> >>
> >> >
> >>
> >> > tests have little to no information for network engineers about what's
> >>
> >> >
> >>
> >> >
> >>
> >> > going on. Iperf 2 may better assist network engineers but then I'm
> >>
> >>