Snapshot (r17855) with an i5-8600K (Stock - 3.6GHz):
root@OpenWrt:~# iperf3 -s -D && iperf3 -c 127.0.0.1
Connecting to host 127.0.0.1, port 5201
[ 5] local 127.0.0.1 port 39188 connected to 127.0.0.1 port 5201
[ ID] Interval Transfer Bitrate Retr Cwnd
[ 5] 0.00-1.00 sec 9.20 GBytes 79.0 Gbits/sec 0 1.25 MBytes
[ 5] 1.00-2.00 sec 9.24 GBytes 79.4 Gbits/sec 0 1.25 MBytes
[ 5] 2.00-3.00 sec 9.21 GBytes 79.1 Gbits/sec 0 1.25 MBytes
[ 5] 3.00-4.00 sec 9.22 GBytes 79.2 Gbits/sec 0 1.25 MBytes
[ 5] 4.00-5.00 sec 9.22 GBytes 79.2 Gbits/sec 0 1.25 MBytes
[ 5] 5.00-6.00 sec 9.21 GBytes 79.1 Gbits/sec 0 1.25 MBytes
[ 5] 6.00-7.00 sec 9.20 GBytes 79.0 Gbits/sec 0 1.25 MBytes
[ 5] 7.00-8.00 sec 9.22 GBytes 79.2 Gbits/sec 0 1.25 MBytes
[ 5] 8.00-9.00 sec 9.21 GBytes 79.1 Gbits/sec 0 1.94 MBytes
[ 5] 9.00-10.00 sec 9.23 GBytes 79.3 Gbits/sec 0 1.94 MBytes
- - - - - - - - - - - - - - - - - - - - - - - - -
[ ID] Interval Transfer Bitrate Retr
[ 5] 0.00-10.00 sec 92.1 GBytes 79.2 Gbits/sec 0 sender
[ 5] 0.00-10.00 sec 92.1 GBytes 79.2 Gbits/sec receiver
1 Like
root@router:~# grep name /etc/board.json
"name": "Linksys WRT32X"
root@router:~# iperf3 -s -D && iperf3 -c 127.0.0.1
Connecting to host 127.0.0.1, port 5201
[ 5] local 127.0.0.1 port 50534 connected to 127.0.0.1 port 5201
[ ID] Interval Transfer Bitrate Retr Cwnd
[ 5] 0.00-1.00 sec 1.07 GBytes 9.18 Gbits/sec 0 1023 KBytes
[ 5] 1.00-2.00 sec 1.09 GBytes 9.37 Gbits/sec 0 895 KBytes
[ 5] 2.00-3.00 sec 1.10 GBytes 9.43 Gbits/sec 0 1023 KBytes
[ 5] 3.00-4.00 sec 1.07 GBytes 9.19 Gbits/sec 0 895 KBytes
[ 5] 4.00-5.00 sec 425 MBytes 3.57 Gbits/sec 0 895 KBytes
[ 5] 5.00-6.00 sec 430 MBytes 3.61 Gbits/sec 0 895 KBytes
[ 5] 6.00-7.00 sec 428 MBytes 3.59 Gbits/sec 0 767 KBytes
[ 5] 7.00-8.00 sec 431 MBytes 3.61 Gbits/sec 0 895 KBytes
[ 5] 8.00-9.00 sec 421 MBytes 3.54 Gbits/sec 1 895 KBytes
[ 5] 9.00-10.00 sec 421 MBytes 3.53 Gbits/sec 0 895 KBytes
- - - - - - - - - - - - - - - - - - - - - - - - -
[ ID] Interval Transfer Bitrate Retr
[ 5] 0.00-10.00 sec 6.82 GBytes 5.86 Gbits/sec 1 sender
[ 5] 0.00-10.00 sec 6.82 GBytes 5.86 Gbits/sec receiver
Xiaomi router 4A gigabit edition, 21.02.
root@mir4ag:~# iperf3 -s -D && iperf3 -c 127.0.0.1
Connecting to host 127.0.0.1, port 5201
[ 5] local 127.0.0.1 port 33188 connected to 127.0.0.1 port 5201
[ ID] Interval Transfer Bitrate Retr Cwnd
[ 5] 0.00-1.01 sec 75.0 MBytes 621 Mbits/sec 0 1023 KBytes
[ 5] 1.01-2.00 sec 72.5 MBytes 616 Mbits/sec 0 1023 KBytes
[ 5] 2.00-3.00 sec 75.0 MBytes 627 Mbits/sec 0 1023 KBytes
[ 5] 3.00-4.00 sec 70.0 MBytes 589 Mbits/sec 0 1023 KBytes
[ 5] 4.00-5.01 sec 80.0 MBytes 665 Mbits/sec 0 1023 KBytes
[ 5] 5.01-6.00 sec 80.0 MBytes 677 Mbits/sec 0 1023 KBytes
[ 5] 6.00-7.01 sec 81.2 MBytes 678 Mbits/sec 0 1023 KBytes
[ 5] 7.01-8.01 sec 81.2 MBytes 679 Mbits/sec 0 1023 KBytes
[ 5] 8.01-9.00 sec 81.1 MBytes 687 Mbits/sec 0 1023 KBytes
[ 5] 9.00-10.01 sec 76.2 MBytes 634 Mbits/sec 0 1023 KBytes
- - - - - - - - - - - - - - - - - - - - - - - - -
[ ID] Interval Transfer Bitrate Retr
[ 5] 0.00-10.01 sec 772 MBytes 647 Mbits/sec 0 sender
[ 5] 0.00-10.01 sec 772 MBytes 647 Mbits/sec receiver
iperf Done.
WoW! I could not have hoped for a better response! This is extremely interesting to me.
You are correct and I would like to say that to me it's just an interesting SINGLE data point to compare routers. Yes this would not be a good way to solely judge anything, However in this day and age we are sorely missing a real meaningful numbers based comparison of devices other then the typical "AC1900" "AX1800" marketing wank etc. Also keep in mind folks the way we are running iperf3 is only single thread, keep that in mind when looking at some of the very high numbers like ** AjkayAlan's** results!
Who is going to be the first member of this forum to break 100gbps???
2 Likes
faser
October 26, 2021, 2:07am
#28
Someone planted a trojan in iperf and push for it's distribution
slh
October 26, 2021, 2:18am
#29
The problem just is, this measurement tells more about the CPU performance (single-threaded), than the achievable throughput over the network (what would be interesting for benchmarking a router). Case in point, wrt3200acm vs nbg6817 - very comparable CPU performance, but the wrt3200acm is much faster at routing (without NSS hardware acceleration for ipq806x).
Is it then a good metric for determining the CPU?
5 Likes
powtrix
October 26, 2021, 4:01am
#30
BusyBox v1.33.1 (2021-10-24 09:01:35 UTC) built-in shell (ash)
_______ ________ __
| |.-----.-----.-----.| | | |.----.| |_
| - || _ | -__| || | | || _|| _|
|_______|| __|_____|__|__||________||__| |____|
|__| W I R E L E S S F R E E D O M
-----------------------------------------------------
OpenWrt 21.02.1, r16325-88151b8303
-----------------------------------------------------
root@OpenWrt:~# uname -a
Linux OpenWrt 5.4.154 #0 SMP Sun Oct 24 09:01:35 2021 armv7l GNU/Linux
root@OpenWrt:~# grep name /etc/board.json
"name": "Linksys EA8500 WiFi Router"
root@OpenWrt:~# iperf3 -s -D && iperf3 -c 127.0.0.1
Connecting to host 127.0.0.1, port 5201
[ 5] local 127.0.0.1 port 38830 connected to 127.0.0.1 port 5201
[ ID] Interval Transfer Bitrate Retr Cwnd
[ 5] 0.00-1.00 sec 476 MBytes 3.99 Gbits/sec 0 1.12 MBytes
[ 5] 1.00-2.00 sec 449 MBytes 3.77 Gbits/sec 0 1.12 MBytes
[ 5] 2.00-3.00 sec 465 MBytes 3.90 Gbits/sec 0 1.12 MBytes
[ 5] 3.00-4.00 sec 452 MBytes 3.80 Gbits/sec 0 1.12 MBytes
[ 5] 4.00-5.00 sec 472 MBytes 3.96 Gbits/sec 0 1.12 MBytes
[ 5] 5.00-6.00 sec 455 MBytes 3.82 Gbits/sec 0 1.12 MBytes
[ 5] 6.00-7.00 sec 464 MBytes 3.89 Gbits/sec 0 1.12 MBytes
[ 5] 7.00-8.00 sec 457 MBytes 3.84 Gbits/sec 0 1.12 MBytes
[ 5] 8.00-9.00 sec 462 MBytes 3.88 Gbits/sec 0 1.12 MBytes
[ 5] 9.00-10.00 sec 455 MBytes 3.82 Gbits/sec 0 1.12 MBytes
- - - - - - - - - - - - - - - - - - - - - - - - -
[ ID] Interval Transfer Bitrate Retr
[ 5] 0.00-10.00 sec 4.50 GBytes 3.87 Gbits/sec 0 sender
[ 5] 0.00-10.00 sec 4.49 GBytes 3.86 Gbits/sec receiver
iperf Done.
root@OpenWrt:~# ps | grep iperf | grep -v grep
6446 root 3080 S iperf3 -s -D
root@OpenWrt:~# kill -9 6446
2 Likes
faser
October 26, 2021, 4:44am
#31
This is a crucial reminder to kill the server running as a daemon in the background!
3 Likes
mk24
October 26, 2021, 1:22pm
#32
By default iperf3 uses all CPU cores. There is a -A option which could restrict it to fewer cores.
The test is of course purely CPU. No networking hardware is involved at all, though packets do move realistically through the kernel network stack.
1 Like
faser
October 26, 2021, 2:48pm
#33
Well not sure what you mean with all CPU cores. Yes it would use any CPUs but it is single threaded so only will use a single core at a time.
lupe
October 26, 2021, 3:10pm
#34
Netgear WNDR4300, 21.02.0
root@splat:~# grep name /etc/board.json
"name": "Netgear WNDR4300"
"name": "WAN (amber)",
root@splat:~# cat /etc/banner | grep OpenWrt
OpenWrt 21.02.0, r16279-5cc0535800
root@splat:~# iperf3 -s -D && sleep 1 && iperf3 -c 127.0.0.1
Connecting to host 127.0.0.1, port 5201
[ 5] local 127.0.0.1 port 46784 connected to 127.0.0.1 port 5201
[ ID] Interval Transfer Bitrate Retr Cwnd
[ 5] 0.00-1.02 sec 38.8 MBytes 320 Mbits/sec 0 1.06 MBytes
[ 5] 1.02-2.00 sec 37.5 MBytes 320 Mbits/sec 0 1.06 MBytes
[ 5] 2.00-3.00 sec 37.5 MBytes 314 Mbits/sec 0 1.06 MBytes
[ 5] 3.00-4.02 sec 38.8 MBytes 320 Mbits/sec 0 1.06 MBytes
[ 5] 4.02-5.01 sec 35.0 MBytes 295 Mbits/sec 0 1.06 MBytes
[ 5] 5.01-6.03 sec 38.8 MBytes 321 Mbits/sec 0 1.06 MBytes
[ 5] 6.03-7.01 sec 37.5 MBytes 319 Mbits/sec 0 1.06 MBytes
[ 5] 7.01-8.03 sec 38.8 MBytes 319 Mbits/sec 0 1.06 MBytes
[ 5] 8.03-9.02 sec 37.5 MBytes 319 Mbits/sec 0 1.06 MBytes
[ 5] 9.02-10.01 sec 35.0 MBytes 296 Mbits/sec 0 1.06 MBytes
- - - - - - - - - - - - - - - - - - - - - - - - -
[ ID] Interval Transfer Bitrate Retr
[ 5] 0.00-10.01 sec 375 MBytes 314 Mbits/sec 0 sender
[ 5] 0.00-10.02 sec 375 MBytes 314 Mbits/sec receiver
iperf Done.
lupe
October 26, 2021, 3:13pm
#35
WNDR4300, 18.06.2
root@routergnome:~# grep name /etc/board.json
"name": "NETGEAR WNDR4300"
"name": "WAN (green)",
"name": "WAN (amber)",
"name": "USB",
"name": "WLAN2G",
"name": "WLAN5G",
"ifname": "eth0.1",
"ifname": "eth0.2",
root@routergnome:~# cat /etc/banner | grep OpenWrt
OpenWrt 18.06.2, r7676-cddd7b4c77
root@routergnome:~# iperf3 -s -D && sleep 1 && iperf3 -c 127.0.0.1
Connecting to host 127.0.0.1, port 5201
[ 5] local 127.0.0.1 port 35312 connected to 127.0.0.1 port 5201
[ ID] Interval Transfer Bitrate Retr Cwnd
[ 5] 0.00-1.01 sec 46.5 MBytes 386 Mbits/sec 0 1.06 MBytes
[ 5] 1.01-2.01 sec 46.0 MBytes 387 Mbits/sec 0 1.06 MBytes
[ 5] 2.01-3.01 sec 47.3 MBytes 396 Mbits/sec 0 1.06 MBytes
[ 5] 3.01-4.00 sec 39.0 MBytes 330 Mbits/sec 0 1.06 MBytes
[ 5] 4.00-5.02 sec 39.1 MBytes 323 Mbits/sec 0 1.06 MBytes
[ 5] 5.02-6.00 sec 41.2 MBytes 350 Mbits/sec 0 1.06 MBytes
[ 5] 6.00-7.00 sec 42.0 MBytes 353 Mbits/sec 0 1.06 MBytes
[ 5] 7.00-8.02 sec 42.9 MBytes 354 Mbits/sec 0 1.06 MBytes
[ 5] 8.02-9.00 sec 41.3 MBytes 352 Mbits/sec 0 1.06 MBytes
[ 5] 9.00-10.02 sec 42.3 MBytes 350 Mbits/sec 0 1.06 MBytes
- - - - - - - - - - - - - - - - - - - - - - - - -
[ ID] Interval Transfer Bitrate Retr
[ 5] 0.00-10.02 sec 428 MBytes 358 Mbits/sec 0 sender
[ 5] 0.00-10.06 sec 426 MBytes 355 Mbits/sec receiver
iperf Done.
root@routergnome:~# killall iperf3
kione
October 26, 2021, 8:24pm
#36
Linksys WRT32X - 21rc3
Ressource monitoring while iperf'ing:
PID PPID USER STAT VSZ %VSZ %CPU COMMAND
16822 1 root R 928 0% 46% iperf3 -s -D
16893 13660 root R 928 0% 37% iperf3 -c 127.0.0.1
And here we go:
root@socketmom ~ iperf3 -s -D && iperf3 -c 127.0.0.1
Connecting to host 127.0.0.1, port 5201
[ 5] local 127.0.0.1 port 37092 connected to 127.0.0.1 port 5201
[ ID] Interval Transfer Bitrate Retr Cwnd
[ 5] 0.00-1.00 sec 1.13 GBytes 9.67 Gbits/sec 0 1.25 MBytes
[ 5] 1.00-2.00 sec 520 MBytes 4.36 Gbits/sec 0 1.25 MBytes
[ 5] 2.00-3.00 sec 571 MBytes 4.79 Gbits/sec 0 1.75 MBytes
[ 5] 3.00-4.00 sec 1011 MBytes 8.48 Gbits/sec 0 1.81 MBytes
[ 5] 4.00-5.00 sec 621 MBytes 5.21 Gbits/sec 0 1.94 MBytes
[ 5] 5.00-6.00 sec 484 MBytes 4.06 Gbits/sec 0 1.94 MBytes
[ 5] 6.00-7.00 sec 648 MBytes 5.43 Gbits/sec 0 1.94 MBytes
[ 5] 7.00-8.00 sec 480 MBytes 4.03 Gbits/sec 0 2.00 MBytes
[ 5] 8.00-9.00 sec 692 MBytes 5.80 Gbits/sec 0 2.00 MBytes
[ 5] 9.00-10.00 sec 466 MBytes 3.91 Gbits/sec 0 2.00 MBytes
- - - - - - - - - - - - - - - - - - - - - - - - -
[ ID] Interval Transfer Bitrate Retr
[ 5] 0.00-10.00 sec 6.49 GBytes 5.58 Gbits/sec 0 sender
[ 5] 0.00-10.00 sec 6.49 GBytes 5.57 Gbits/sec receiver
iperf Done.
root@socketmom ~ killall -9 iperf3
(because -D daemonizes)
1 Like
My testing suggests that RAM performance is the limiting factor for this in higher-end systems. A system with DDR4-2600 is going to stomp a DDR3-1333 system irrespective of CPU.
root@GW:~# ubus call system board | grep model && iperf3 -s -D && ipe
rf3 -c 127.0.0.1 && kill $(pidof iperf3)
"model": "Xiaomi Mi Router 3 Pro",
Connecting to host 127.0.0.1, port 5201
[ 5] local 127.0.0.1 port 47540 connected to 127.0.0.1 port 5201
[ ID] Interval Transfer Bitrate Retr Cwnd
[ 5] 0.00-1.01 sec 76.2 MBytes 636 Mbits/sec 0 1.25 MBytes
[ 5] 1.01-2.01 sec 76.2 MBytes 635 Mbits/sec 0 1.25 MBytes
[ 5] 2.01-3.02 sec 78.8 MBytes 658 Mbits/sec 0 1.25 MBytes
[ 5] 3.02-4.01 sec 75.0 MBytes 635 Mbits/sec 0 1.25 MBytes
[ 5] 4.01-5.00 sec 77.5 MBytes 655 Mbits/sec 0 1.25 MBytes
[ 5] 5.00-6.00 sec 76.2 MBytes 637 Mbits/sec 0 1.25 MBytes
[ 5] 6.00-7.01 sec 76.2 MBytes 633 Mbits/sec 0 1.25 MBytes
[ 5] 7.01-8.01 sec 78.8 MBytes 663 Mbits/sec 0 1.25 MBytes
[ 5] 8.01-9.00 sec 81.2 MBytes 687 Mbits/sec 0 1.25 MBytes
[ 5] 9.00-10.01 sec 82.5 MBytes 690 Mbits/sec 0 1.25 MBytes
- - - - - - - - - - - - - - - - - - - - - - - - -
[ ID] Interval Transfer Bitrate Retr
[ 5] 0.00-10.01 sec 779 MBytes 653 Mbits/sec 0 sender
[ 5] 0.00-10.04 sec 779 MBytes 651 Mbits/sec receiver
iperf Done.
tmomas
October 26, 2021, 11:04pm
#39
Looking at the topic title: Who is going to make a database out of this lose collection of data?
1 Like
slh
October 26, 2021, 11:10pm
#40
The bigger problem still is what actual use this data provides, it neither tells you how fast the CPU is, nor what throughput it could deliver over its ethernet ports nor its radios (not even relative to other devices).
6 Likes
nor were equivalent devices equally quiesced.
I had planned on manually creating a very informal and quick little summary by just including the average once it hits 50+ and putting it in the first post to make it easy for lazy people (like myself) to see without needing to read the entire thing. Nothing fancy because I suck at this.
slh, I appreciate your viewpoint and I would agree with you on most of it but I think you might be slightly overthinking this. Nobody here is going to use these numbers to purchasing decisions or at least they should not. It is just an informal and fun thing to do sort of like the router version of a mine is bigger then yours contest LoL.
2 Likes
slh
October 26, 2021, 11:59pm
#43
So what useful information can you derive from those figures?
As far as I'm concerned, these results don't provide any guidance for rating a device against others - none at all (apart from -maybe- bragging rights in a fantasy football league).
2 Likes
