[Cake] [Starlink] [Rpm] [LibreQoS] the grinch meets cloudflare'schristmas present
Dick Roy
dickroy at alum.mit.edu
Fri Jan 6 19:31:57 EST 2023
-----Original Message-----
From: rjmcmahon [mailto:rjmcmahon at rjmcmahon.com]
Sent: Friday, January 6, 2023 3:45 PM
To: dickroy at 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
record:-)
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 :-)
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-bounces at 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
>
> biased ;)
>
> Running iperf 2 https://sourceforge.net/projects/iperf2/ with
>
> --trip-times. Though the sampling and central limit theorem averaging
> is
>
> hiding the real distributions (use --histograms to get those)
>
> _[RR] FWIW (IMNBWM __J). If the output/final histograms indicate the
> PDF is NOT Gaussian, then any application of the CLT is
> inappropriate/contra-indicated! The CLT is a "proof under certain
> regularity conditions/assumptions of underlying/constituent PDFs, that
> the resulting PDF (after all the necessary convolutions are performed
> to get to the PDF of the output) will asymptotically approach a
> Gaussian with only a mean and a std. dev. left to specify. _
>
> Below are 4 parallel TCP streams from my home to one of my servers in
>
> the cloud. First where TCP is limited per CCA. Second is source side
>
> write rate limiting. Things to note:
>
> o) connect times for both at 10-15 ms
>
> o) multiple TCP retries on a few rites - one case is 4 with 5 writes.
>
> Source side pacing eliminates retries
>
> o) Fairness with CCA isn't great but quite good with source side write
>
>
> pacing
>
> o) Queue depth with CCA is about 150 Kbytes about 100K byte with
> source
>
> side pacing
>
> o) min write to read is about 80 ms for both
>
> o) max is 220 ms vs 97 ms
>
> o) stdev for CCA write/read is 30 ms vs 3 ms
>
> o) TCP RTT is 20ms w/CCA and 90 ms with ssp - seems odd here as
>
> TCP_QUICACK and TCP_NODELAY are both enabled.
>
> [ CT] final connect times (min/avg/max/stdev) =
>
> 10.326/13.522/14.986/2150.329 ms (tot/err) = 4/0
>
> [rjmcmahon at ryzen3950 iperf2-code]$ iperf -c *** --hide-ips -e
>
> --trip-times -i 1 -P 4 -t 10 -w 4m --tcp-quickack -N
>
> ------------------------------------------------------------
>
> Client connecting to (**hidden**), TCP port 5001 with pid 107678 (4
>
> flows)
>
> Write buffer size: 131072 Byte
>
> TOS set to 0x0 and nodelay (Nagle off)
>
> TCP window size: 7.63 MByte (WARNING: requested 3.81 MByte)
>
> Event based writes (pending queue watermark at 16384 bytes)
>
> ------------------------------------------------------------
>
> [ 1] local *.*.*.85%enp4s0 port 42480 connected with *.*.*.123 port
>
> 5001 (prefetch=16384) (trip-times) (sock=3) (qack)
>
> (icwnd/mss/irtt=14/1448/10534) (ct=10.63 ms) on 2023-01-06 12:17:56
>
> (PST)
>
> [ 4] local *.*.*.85%enp4s0 port 42488 connected with *.*.*.123 port
>
> 5001 (prefetch=16384) (trip-times) (sock=5) (qack)
>
> (icwnd/mss/irtt=14/1448/14023) (ct=14.08 ms) on 2023-01-06 12:17:56
>
> (PST)
>
> [ 3] local *.*.*.85%enp4s0 port 42502 connected with *.*.*.123 port
>
> 5001 (prefetch=16384) (trip-times) (sock=6) (qack)
>
> (icwnd/mss/irtt=14/1448/14642) (ct=14.70 ms) on 2023-01-06 12:17:56
>
> (PST)
>
> [ 2] local *.*.*.85%enp4s0 port 42484 connected with *.*.*.123 port
>
> 5001 (prefetch=16384) (trip-times) (sock=4) (qack)
>
> (icwnd/mss/irtt=14/1448/14728) (ct=14.79 ms) on 2023-01-06 12:17:56
>
> (PST)
>
> [ ID] Interval Transfer Bandwidth Write/Err Rtry
>
> Cwnd/RTT(var) NetPwr
>
> ...
>
> [ 4] 4.00-5.00 sec 1.38 MBytes 11.5 Mbits/sec 11/0 3
>
>
> 29K/21088(1142) us 68.37
>
> [ 2] 4.00-5.00 sec 1.62 MBytes 13.6 Mbits/sec 13/0 2
>
>
> 31K/19284(612) us 88.36
>
> [ 1] 4.00-5.00 sec 896 KBytes 7.34 Mbits/sec 7/0 5
>
> 16K/18996(658) us 48.30
>
> [ 3] 4.00-5.00 sec 1.00 MBytes 8.39 Mbits/sec 8/0 5
>
> 18K/18133(208) us 57.83
>
> [SUM] 4.00-5.00 sec 4.88 MBytes 40.9 Mbits/sec 39/0 15
>
> [ 4] 5.00-6.00 sec 1.25 MBytes 10.5 Mbits/sec 10/0 4
>
>
> 29K/14717(489) us 89.06
>
> [ 1] 5.00-6.00 sec 1.00 MBytes 8.39 Mbits/sec 8/0 4
>
> 16K/15874(408) us 66.06
>
> [ 3] 5.00-6.00 sec 1.12 MBytes 9.44 Mbits/sec 9/0 4
>
> 16K/15826(382) us 74.54
>
> [ 2] 5.00-6.00 sec 1.50 MBytes 12.6 Mbits/sec 12/0 6
>
>
> 9K/14878(557) us 106
>
> [SUM] 5.00-6.00 sec 4.88 MBytes 40.9 Mbits/sec 39/0 18
>
> [ 4] 6.00-7.00 sec 1.75 MBytes 14.7 Mbits/sec 14/0 4
>
>
> 25K/15472(496) us 119
>
> [ 2] 6.00-7.00 sec 1.00 MBytes 8.39 Mbits/sec 8/0 2
>
> 26K/16417(427) us 63.87
>
> [ 1] 6.00-7.00 sec 1.25 MBytes 10.5 Mbits/sec 10/0 5
>
>
> 16K/16268(679) us 80.57
>
> [ 3] 6.00-7.00 sec 1.00 MBytes 8.39 Mbits/sec 8/0 6
>
> 15K/16629(799) us 63.06
>
> [SUM] 6.00-7.00 sec 5.00 MBytes 41.9 Mbits/sec 40/0 17
>
> [ 4] 7.00-8.00 sec 1.75 MBytes 14.7 Mbits/sec 14/0 4
>
>
> 22K/13986(519) us 131
>
> [ 1] 7.00-8.00 sec 1.12 MBytes 9.44 Mbits/sec 9/0 4
>
> 16K/12679(377) us 93.04
>
> [ 3] 7.00-8.00 sec 896 KBytes 7.34 Mbits/sec 7/0 5
>
> 14K/12971(367) us 70.74
>
> [ 2] 7.00-8.00 sec 1.12 MBytes 9.44 Mbits/sec 9/0 6
>
> 15K/14740(779) us 80.03
>
> [SUM] 7.00-8.00 sec 4.88 MBytes 40.9 Mbits/sec 39/0 19
>
> [root at bobcat iperf2-code]# iperf -s -i 1 -e --hide-ips -w 4m
>
> ------------------------------------------------------------
>
> Server listening on TCP port 5001 with pid 233615
>
> Read buffer size: 128 KByte (Dist bin width=16.0 KByte)
>
> TCP window size: 7.63 MByte (WARNING: requested 3.81 MByte)
>
> ------------------------------------------------------------
>
> [ 1] local *.*.*.123%eth0 port 5001 connected with *.*.*.171 port
> 42480
>
> (trip-times) (sock=4) (peer 2.1.9-master) (qack)
>
> (icwnd/mss/irtt=14/1448/11636) on 2023-01-06 12:17:56 (PST)
>
> [ 2] local *.*.*.123%eth0 port 5001 connected with *.*.*.171 port
> 42502
>
> (trip-times) (sock=5) (peer 2.1.9-master) (qack)
>
> (icwnd/mss/irtt=14/1448/11898) on 2023-01-06 12:17:56 (PST)
>
> [ 3] local *.*.*.123%eth0 port 5001 connected with *.*.*.171 port
> 42484
>
> (trip-times) (sock=6) (peer 2.1.9-master) (qack)
>
> (icwnd/mss/irtt=14/1448/11938) on 2023-01-06 12:17:56 (PST)
>
> [ 4] local *.*.*.123%eth0 port 5001 connected with *.*.*.171 port
> 42488
>
> (trip-times) (sock=7) (peer 2.1.9-master) (qack)
>
> (icwnd/mss/irtt=14/1448/11919) on 2023-01-06 12:17:56 (PST)
>
> [ ID] Interval Transfer Bandwidth Burst Latency
>
> avg/min/max/stdev (cnt/size) inP NetPwr Reads=Dist
>
> ...
>
> [ 2] 4.00-5.00 sec 1.06 MBytes 8.86 Mbits/sec
>
> 129.819/90.391/186.075/31.346 ms (9/123080) 154 KByte 8.532803
>
> 467=461:6:0:0:0:0:0:0
>
> [ 3] 4.00-5.00 sec 1.52 MBytes 12.8 Mbits/sec
>
> 103.552/82.653/169.274/28.382 ms (12/132854) 149 KByte 15.40
>
> 646=643:1:2:0:0:0:0:0
>
> [ 4] 4.00-5.00 sec 1.39 MBytes 11.6 Mbits/sec
>
> 107.503/66.843/143.038/24.269 ms (11/132294) 149 KByte 13.54
>
> 619=617:1:1:0:0:0:0:0
>
> [ 1] 4.00-5.00 sec 988 KBytes 8.10 Mbits/sec
>
> 141.389/119.961/178.785/18.812 ms (7/144593) 170 KByte 7.158641
>
> 409=404:5:0:0:0:0:0:0
>
> [SUM] 4.00-5.00 sec 4.93 MBytes 41.4 Mbits/sec
>
> 2141=2125:13:3:0:0:0:0:0
>
> [ 4] 5.00-6.00 sec 1.29 MBytes 10.8 Mbits/sec
>
> 118.943/86.253/176.128/31.248 ms (10/135098) 164 KByte 11.36
>
> 511=506:2:3:0:0:0:0:0
>
> [ 2] 5.00-6.00 sec 1.09 MBytes 9.17 Mbits/sec
>
> 139.821/102.418/218.875/40.422 ms (9/127424) 148 KByte 8.202049
>
> 487=484:2:1:0:0:0:0:0
>
> [ 3] 5.00-6.00 sec 1.51 MBytes 12.6 Mbits/sec
>
> 102.146/77.085/140.893/18.441 ms (13/121520) 151 KByte 15.47
>
> 640=636:1:3:0:0:0:0:0
>
> [ 1] 5.00-6.00 sec 981 KBytes 8.04 Mbits/sec
>
> 161.901/105.582/219.931/36.260 ms (8/125614) 134 KByte 6.206944
>
> 415=413:2:0:0:0:0:0:0
>
> [SUM] 5.00-6.00 sec 4.85 MBytes 40.7 Mbits/sec
>
> 2053=2039:7:7:0:0:0:0:0
>
> [ 4] 6.00-7.00 sec 1.74 MBytes 14.6 Mbits/sec
>
> 88.846/74.297/101.859/7.118 ms (14/130526) 156 KByte 20.57
>
> 711=707:3:1:0:0:0:0:0
>
> [ 1] 6.00-7.00 sec 1.22 MBytes 10.2 Mbits/sec
>
> 120.639/100.257/157.567/21.770 ms (10/127568) 157 KByte 10.57
>
> 494=488:5:1:0:0:0:0:0
>
> [ 2] 6.00-7.00 sec 1015 KBytes 8.32 Mbits/sec
>
> 144.632/124.368/171.349/16.597 ms (8/129958) 143 KByte 7.188321
>
> 408=403:5:0:0:0:0:0:0
>
> [ 3] 6.00-7.00 sec 1.02 MBytes 8.60 Mbits/sec
>
> 143.516/102.322/173.001/24.089 ms (8/134302) 146 KByte 7.486359
>
> 484=480:4:0:0:0:0:0:0
>
> [SUM] 6.00-7.00 sec 4.98 MBytes 41.7 Mbits/sec
>
> 2097=2078:17:2:0:0:0:0:0
>
> [ 4] 7.00-8.00 sec 1.77 MBytes 14.9 Mbits/sec
>
> 85.406/65.797/103.418/12.609 ms (14/132595) 153 KByte 21.74
>
> 692=687:2:3:0:0:0:0:0
>
> [ 2] 7.00-8.00 sec 957 KBytes 7.84 Mbits/sec
>
> 153.936/131.452/191.464/19.361 ms (7/140042) 160 KByte 6.368199
>
> 429=425:4:0:0:0:0:0:0
>
> [ 1] 7.00-8.00 sec 1.13 MBytes 9.44 Mbits/sec
>
> 131.146/109.737/166.774/22.035 ms (9/131124) 146 KByte 8.998528
>
> 520=516:4:0:0:0:0:0:0
>
> [ 3] 7.00-8.00 sec 1.13 MBytes 9.51 Mbits/sec
>
> 126.512/88.404/220.175/42.237 ms (9/132089) 172 KByte 9.396784
>
> 527=524:1:2:0:0:0:0:0
>
> [SUM] 7.00-8.00 sec 4.96 MBytes 41.6 Mbits/sec
>
> 2168=2152:11:5:0:0:0:0:0
>
> With source side rate limiting to 9 mb/s per stream.
>
> [rjmcmahon at ryzen3950 iperf2-code]$ iperf -c *** --hide-ips -e
>
> --trip-times -i 1 -P 4 -t 10 -w 4m --tcp-quickack -N -b 9m
>
> ------------------------------------------------------------
>
> Client connecting to (**hidden**), TCP port 5001 with pid 108884 (4
>
> flows)
>
> Write buffer size: 131072 Byte
>
> TOS set to 0x0 and nodelay (Nagle off)
>
> TCP window size: 7.63 MByte (WARNING: requested 3.81 MByte)
>
> Event based writes (pending queue watermark at 16384 bytes)
>
> ------------------------------------------------------------
>
> [ 1] local *.*.*.85%enp4s0 port 46448 connected with *.*.*.123 port
>
> 5001 (prefetch=16384) (trip-times) (sock=3) (qack)
>
> (icwnd/mss/irtt=14/1448/10666) (ct=10.70 ms) on 2023-01-06 12:27:45
>
> (PST)
>
> [ 3] local *.*.*.85%enp4s0 port 46460 connected with *.*.*.123 port
>
> 5001 (prefetch=16384) (trip-times) (sock=6) (qack)
>
> (icwnd/mss/irtt=14/1448/16499) (ct=16.54 ms) on 2023-01-06 12:27:45
>
> (PST)
>
> [ 2] local *.*.*.85%enp4s0 port 46454 connected with *.*.*.123 port
>
> 5001 (prefetch=16384) (trip-times) (sock=4) (qack)
>
> (icwnd/mss/irtt=14/1448/16580) (ct=16.86 ms) on 2023-01-06 12:27:45
>
> (PST)
>
> [ 4] local *.*.*.85%enp4s0 port 46458 connected with *.*.*.123 port
>
> 5001 (prefetch=16384) (trip-times) (sock=5) (qack)
>
> (icwnd/mss/irtt=14/1448/16802) (ct=16.83 ms) on 2023-01-06 12:27:45
>
> (PST)
>
> [ ID] Interval Transfer Bandwidth Write/Err Rtry
>
> Cwnd/RTT(var) NetPwr
>
> ...
>
> [ 2] 4.00-5.00 sec 1.00 MBytes 8.39 Mbits/sec 8/0 0
>
> 134K/88055(12329) us 11.91
>
> [ 4] 4.00-5.00 sec 1.00 MBytes 8.39 Mbits/sec 8/0 0
>
> 132K/74867(11755) us 14.01
>
> [ 1] 4.00-5.00 sec 1.00 MBytes 8.39 Mbits/sec 8/0 0
>
> 134K/89101(13134) us 11.77
>
> [ 3] 4.00-5.00 sec 1.00 MBytes 8.39 Mbits/sec 8/0 0
>
> 131K/91451(11938) us 11.47
>
> [SUM] 4.00-5.00 sec 4.00 MBytes 33.6 Mbits/sec 32/0 0
>
> [ 2] 5.00-6.00 sec 1.12 MBytes 9.44 Mbits/sec 9/0 0
>
> 134K/85135(14580) us 13.86
>
> [ 4] 5.00-6.00 sec 1.12 MBytes 9.44 Mbits/sec 9/0 0
>
> 132K/85124(15654) us 13.86
>
> [ 1] 5.00-6.00 sec 1.12 MBytes 9.44 Mbits/sec 9/0 0
>
> 134K/91336(11335) us 12.92
>
> [ 3] 5.00-6.00 sec 1.12 MBytes 9.44 Mbits/sec 9/0 0
>
> 131K/89185(13499) us 13.23
>
> [SUM] 5.00-6.00 sec 4.50 MBytes 37.7 Mbits/sec 36/0 0
>
> [ 2] 6.00-7.00 sec 1.12 MBytes 9.44 Mbits/sec 9/0 0
>
> 134K/85687(13489) us 13.77
>
> [ 4] 6.00-7.00 sec 1.12 MBytes 9.44 Mbits/sec 9/0 0
>
> 132K/82803(13001) us 14.25
>
> [ 1] 6.00-7.00 sec 1.12 MBytes 9.44 Mbits/sec 9/0 0
>
> 134K/86869(15186) us 13.58
>
> [ 3] 6.00-7.00 sec 1.12 MBytes 9.44 Mbits/sec 9/0 0
>
> 131K/91447(12515) us 12.90
>
> [SUM] 6.00-7.00 sec 4.50 MBytes 37.7 Mbits/sec 36/0 0
>
> [ 2] 7.00-8.00 sec 1.00 MBytes 8.39 Mbits/sec 8/0 0
>
> 134K/81814(13168) us 12.82
>
> [ 4] 7.00-8.00 sec 1.00 MBytes 8.39 Mbits/sec 8/0 0
>
> 132K/89008(13283) us 11.78
>
> [ 1] 7.00-8.00 sec 1.00 MBytes 8.39 Mbits/sec 8/0 0
>
> 134K/89494(12151) us 11.72
>
> [ 3] 7.00-8.00 sec 1.00 MBytes 8.39 Mbits/sec 8/0 0
>
> 131K/91083(12797) us 11.51
>
> [SUM] 7.00-8.00 sec 4.00 MBytes 33.6 Mbits/sec 32/0 0
>
> [root at bobcat iperf2-code]# iperf -s -i 1 -e --hide-ips -w 4m
>
> ------------------------------------------------------------
>
> Server listening on TCP port 5001 with pid 233981
>
> Read buffer size: 128 KByte (Dist bin width=16.0 KByte)
>
> TCP window size: 7.63 MByte (WARNING: requested 3.81 MByte)
>
> ------------------------------------------------------------
>
> [ 1] local *.*.*.123%eth0 port 5001 connected with *.*.*.171 port
> 46448
>
> (trip-times) (sock=4) (peer 2.1.9-master) (qack)
>
> (icwnd/mss/irtt=14/1448/11987) on 2023-01-06 12:27:45 (PST)
>
> [ 2] local *.*.*.123%eth0 port 5001 connected with *.*.*.171 port
> 46454
>
> (trip-times) (sock=5) (peer 2.1.9-master) (qack)
>
> (icwnd/mss/irtt=14/1448/11132) on 2023-01-06 12:27:45 (PST)
>
> [ 3] local *.*.*.123%eth0 port 5001 connected with *.*.*.171 port
> 46460
>
> (trip-times) (sock=6) (peer 2.1.9-master) (qack)
>
> (icwnd/mss/irtt=14/1448/11097) on 2023-01-06 12:27:45 (PST)
>
> [ 4] local *.*.*.123%eth0 port 5001 connected with *.*.*.171 port
> 46458
>
> (trip-times) (sock=7) (peer 2.1.9-master) (qack)
>
> (icwnd/mss/irtt=14/1448/17823) on 2023-01-06 12:27:45 (PST)
>
> [ ID] Interval Transfer Bandwidth Burst Latency
>
> avg/min/max/stdev (cnt/size) inP NetPwr Reads=Dist
>
> [ 4] 0.00-1.00 sec 1.09 MBytes 9.15 Mbits/sec
>
> 93.383/90.103/95.661/2.232 ms (8/143028) 128 KByte 12.25
>
> 451=451:0:0:0:0:0:0:0
>
> [ 3] 0.00-1.00 sec 1.08 MBytes 9.06 Mbits/sec
>
> 96.834/95.229/102.645/2.442 ms (8/141580) 131 KByte 11.70
>
> 472=472:0:0:0:0:0:0:0
>
> [ 1] 0.00-1.00 sec 1.10 MBytes 9.19 Mbits/sec
>
> 95.183/92.623/97.579/1.431 ms (8/143571) 131 KByte 12.07
>
> 495=495:0:0:0:0:0:0:0
>
> [ 2] 0.00-1.00 sec 1.09 MBytes 9.15 Mbits/sec
>
> 89.317/84.865/94.906/3.674 ms (8/143028) 122 KByte 12.81
>
> 489=489:0:0:0:0:0:0:0
>
> [ ID] Interval Transfer Bandwidth Reads=Dist
>
> [SUM] 0.00-1.00 sec 4.36 MBytes 36.6 Mbits/sec
>
> 1907=1907:0:0:0:0:0:0:0
>
> [ 4] 1.00-2.00 sec 1.07 MBytes 8.95 Mbits/sec
>
> 92.649/89.987/95.036/1.828 ms (9/124314) 96.5 KByte 12.08
>
> 492=492:0:0:0:0:0:0:0
>
> [ 3] 1.00-2.00 sec 1.06 MBytes 8.93 Mbits/sec
>
> 96.305/95.647/96.794/0.432 ms (9/123992) 100 KByte 11.59
>
> 480=480:0:0:0:0:0:0:0
>
> [ 1] 1.00-2.00 sec 1.06 MBytes 8.89 Mbits/sec
>
> 92.578/90.866/94.145/1.371 ms (9/123510) 95.8 KByte 12.01
>
> 513=513:0:0:0:0:0:0:0
>
> [ 2] 1.00-2.00 sec 1.07 MBytes 8.96 Mbits/sec
>
> 90.767/87.984/94.352/1.944 ms (9/124475) 94.7 KByte 12.34
>
> 489=489:0:0:0:0:0:0:0
>
> [SUM] 1.00-2.00 sec 4.26 MBytes 35.7 Mbits/sec
>
> 1974=1974:0:0:0:0:0:0:0
>
> [ 4] 2.00-3.00 sec 1.09 MBytes 9.13 Mbits/sec
>
> 93.977/91.795/96.561/1.693 ms (8/142656) 112 KByte 12.14
>
> 497=497:0:0:0:0:0:0:0
>
> [ 3] 2.00-3.00 sec 1.08 MBytes 9.04 Mbits/sec
>
> 96.544/95.815/97.798/0.693 ms (8/141208) 114 KByte 11.70
>
> 503=503:0:0:0:0:0:0:0
>
> [ 1] 2.00-3.00 sec 1.07 MBytes 9.01 Mbits/sec
>
> 93.970/91.193/96.325/1.796 ms (8/140846) 111 KByte 11.99
>
> 509=509:0:0:0:0:0:0:0
>
> [ 2] 2.00-3.00 sec 1.08 MBytes 9.10 Mbits/sec
>
> 92.843/90.216/96.355/2.040 ms (8/142113) 111 KByte 12.25
>
> 509=509:0:0:0:0:0:0:0
>
> [SUM] 2.00-3.00 sec 4.32 MBytes 36.3 Mbits/sec
>
> 2018=2018:0:0:0:0:0:0:0
>
> [ 4] 3.00-4.00 sec 1.06 MBytes 8.86 Mbits/sec
>
> 93.222/89.063/96.104/2.346 ms (9/123027) 96.1 KByte 11.88
>
> 487=487:0:0:0:0:0:0:0
>
> [ 3] 3.00-4.00 sec 1.07 MBytes 8.97 Mbits/sec
>
> 96.277/95.051/97.230/0.767 ms (9/124636) 101 KByte 11.65
>
> 489=489:0:0:0:0:0:0:0
>
> [ 1] 3.00-4.00 sec 1.08 MBytes 9.02 Mbits/sec
>
> 93.899/88.732/96.972/2.737 ms (9/125280) 98.6 KByte 12.01
>
> 493=493:0:0:0:0:0:0:0
>
> [ 2] 3.00-4.00 sec 1.07 MBytes 8.97 Mbits/sec
>
> 92.490/89.862/95.265/1.796 ms (9/124636) 96.6 KByte 12.13
>
> 493=493:0:0:0:0:0:0:0
>
> [SUM] 3.00-4.00 sec 4.27 MBytes 35.8 Mbits/sec
>
> 1962=1962:0:0:0:0:0:0:0
>
> [ 4] 4.00-5.00 sec 1.07 MBytes 9.00 Mbits/sec
>
> 92.431/81.888/96.221/4.524 ms (9/124958) 96.8 KByte 12.17
>
> 498=498:0:0:0:0:0:0:0
>
> [ 1] 4.00-5.00 sec 1.07 MBytes 8.97 Mbits/sec
>
> 95.018/93.445/96.200/0.957 ms (9/124636) 99.3 KByte 11.81
>
> 490=490:0:0:0:0:0:0:0
>
> [ 2] 4.00-5.00 sec 1.06 MBytes 8.90 Mbits/sec
>
> 93.874/86.485/95.672/2.810 ms (9/123671) 97.3 KByte 11.86
>
> 481=481:0:0:0:0:0:0:0
>
> [ 3] 4.00-5.00 sec 1.08 MBytes 9.09 Mbits/sec
>
> 95.737/93.881/97.197/0.972 ms (9/126245) 101 KByte 11.87
>
> 484=484:0:0:0:0:0:0:0
>
> [SUM] 4.00-5.00 sec 4.29 MBytes 36.0 Mbits/sec
>
> 1953=1953:0:0:0:0:0:0:0
>
> [ 4] 5.00-6.00 sec 1.09 MBytes 9.13 Mbits/sec
>
> 92.908/86.844/95.994/3.012 ms (8/142656) 111 KByte 12.28
>
> 467=467:0:0:0:0:0:0:0
>
> [ 3] 5.00-6.00 sec 1.07 MBytes 8.94 Mbits/sec
>
> 96.593/95.343/97.660/0.876 ms (8/139760) 113 KByte 11.58
>
> 478=478:0:0:0:0:0:0:0
>
> [ 1] 5.00-6.00 sec 1.08 MBytes 9.03 Mbits/sec
>
> 95.021/91.421/97.167/1.893 ms (8/141027) 112 KByte 11.87
>
> 491=491:0:0:0:0:0:0:0
>
> [ 2] 5.00-6.00 sec 1.08 MBytes 9.06 Mbits/sec
>
> 92.162/82.720/97.692/5.060 ms (8/141570) 109 KByte 12.29
>
> 488=488:0:0:0:0:0:0:0
>
> [SUM] 5.00-6.00 sec 4.31 MBytes 36.2 Mbits/sec
>
> 1924=1924:0:0:0:0:0:0:0
>
> [ 4] 6.00-7.00 sec 1.04 MBytes 8.70 Mbits/sec
>
> 92.793/85.343/96.967/3.552 ms (9/120775) 93.9 KByte 11.71
>
> 485=485:0:0:0:0:0:0:0
>
> [ 2] 6.00-7.00 sec 1.05 MBytes 8.79 Mbits/sec
>
> 91.679/84.479/96.760/3.975 ms (9/122062) 93.8 KByte 11.98
>
> 472=472:0:0:0:0:0:0:0
>
> [ 3] 6.00-7.00 sec 1.06 MBytes 8.88 Mbits/sec
>
> 96.982/95.933/98.371/0.680 ms (9/123349) 100 KByte 11.45
>
> 477=477:0:0:0:0:0:0:0
>
> [ 1] 6.00-7.00 sec 1.05 MBytes 8.80 Mbits/sec
>
> 94.342/91.660/96.025/1.660 ms (9/122223) 96.7 KByte 11.66
>
> 494=494:0:0:0:0:0:0:0
>
> [SUM] 6.00-7.00 sec 4.19 MBytes 35.2 Mbits/sec
>
> 1928=1928:0:0:0:0:0:0:0
>
> [ 4] 7.00-8.00 sec 1.10 MBytes 9.25 Mbits/sec
>
> 92.515/88.182/96.351/2.538 ms (8/144466) 112 KByte 12.49
>
> 510=510:0:0:0:0:0:0:0
>
> [ 3] 7.00-8.00 sec 1.09 MBytes 9.13 Mbits/sec
>
> 96.580/95.737/98.977/1.098 ms (8/142656) 115 KByte 11.82
>
> 480=480:0:0:0:0:0:0:0
>
> [ 1] 7.00-8.00 sec 1.10 MBytes 9.21 Mbits/sec
>
> 95.269/91.719/97.514/2.126 ms (8/143923) 115 KByte 12.09
>
> 515=515:0:0:0:0:0:0:0
>
> [ 2] 7.00-8.00 sec 1.11 MBytes 9.29 Mbits/sec
>
> 90.073/84.700/96.176/4.324 ms (8/145190) 110 KByte 12.90
>
> 508=508:0:0:0:0:0:0:0
>
> [SUM] 7.00-8.00 sec 4.40 MBytes 36.9 Mbits/sec
>
> 2013=2013:0:0:0:0:0:0:0
>
> Bob
>
>>> -----Original Message-----
>
>>
>
>>> From: LibreQoS <libreqos-bounces at lists.bufferbloat.net> On Behalf
> Of
>
>> Dave Taht
>
>>
>
>>> via LibreQoS
>
>>
>
>>> Sent: Wednesday, January 4, 2023 12:26 PM
>
>>
>
>>> Subject: [LibreQoS] the grinch meets cloudflare's christmas present
>
>
>>
>
>>>
>
>>
>
>>> Please try the new, the shiny, the really wonderful test here:
>
>>
>
>>>
>
>>
>
https://urldefense.com/v3/__https://speed.cloudflare.com/__;!!BhdT!iZcFJ8WVU
9S
>
>
>> [1]
>
>>
>
>>>
>
>>
>
9zz5t456oxkfObrC5Xb9j5AG8UO3DqD5x4GAJkawZr0iGwEUtF0_09U8mCDnAkrJ9QEMHGbCMKVw
$
>
>
>> [1]
>
>>
>
>>>
>
>>
>
>>> I would really appreciate some independent verification of
>
>>
>
>>> measurements using this tool. In my brief experiments it appears -
>
>> as
>
>>
>
>>> all the commercial tools to date - to dramatically understate the
>
>>
>
>>> bufferbloat, on my LTE, (and my starlink terminal is out being
>
>>
>
>>> hacked^H^H^H^H^H^Hworked on, so I can't measure that)
>
>>
>
>> [acm]
>
>>
>
>> Hi Dave, I made some time to test "cloudflare's christmas present"
>
>> yesterday.
>
>>
>
>> I'm on DOCSIS 3.1 service with 1Gbps Down. The Upstream has a
> "turbo"
>
>> mode with 40-50Mbps for the first ~3 sec, then steady-state about
>
>> 23Mbps.
>
>>
>
>> When I saw the ~620Mbps Downstream measurement, I was ready to
>
>> complain that even the IP-Layer Capacity was grossly underestimated.
>
>
>> In addition, the Latency measurements seem very low (as you
> asserted),
>
>> although the cloud server was "nearby".
>
>>
>
>> However, I found that Ookla and the ISP-provided measurement were
> also
>
>> reporting ~600Mbps! So the cloudflare Downstream capacity (or
>
>> throughput?) measurement was consistent with others. Our UDPST
> server
>
>> was unreachable, otherwise I would have added that measurement, too.
>
>
>>
>
>> The Upstream measurement graph seems to illustrate the "turbo"
>
>> mode, with the dip after attaining 44.5Mbps.
>
>>
>
>> UDPST saturates the uplink and we measure the full 250ms of the
>
>> Upstream buffer. Cloudflare's latency measurements don't even come
>
>> close.
>
>>
>
>> Al
>
>>
>
>>
>
>>
>
>> Links:
>
>> ------
>
>> [1]
>
>>
>
https://urldefense.com/v3/__https:/speed.cloudflare.com/__;!!BhdT!iZcFJ8WVU9
S9zz5t456oxkfObrC5Xb9j5AG8UO3DqD5x4GAJkawZr0iGwEUtF0_09U8mCDnAkrJ9QEMHGbCMKV
w$
>
>
>> _______________________________________________
>
>> Rpm mailing list
>
>> Rpm at lists.bufferbloat.net
>
>> https://lists.bufferbloat.net/listinfo/rpm
>
> _______________________________________________
>
> Starlink mailing list
>
> Starlink at lists.bufferbloat.net
>
> https://lists.bufferbloat.net/listinfo/starlink
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.bufferbloat.net/pipermail/cake/attachments/20230107/6d09c467/attachment.html>
More information about the Cake
mailing list