WiFi 7 routers with high VPN server speed

X

xiaofan

High Supremacy Member
HWZ Insider
Joined
Sep 16, 2018
Messages
30,842
Reaction score
8,570
xiaofan said:
If you look at the theoretical test, low power Intel CPU beats MediaTek Filogic 880 and Filogic 830 comfortably.
https://github.com/cyyself/wg-bench

Asus TUF-AX4200 / MT7986AVOpenWRT Snapshot / 6.1.78936 Mbits/sec
Raspberry Pi 4 / BCM2711*OpenWRT 23.05.2 / 5.15.1371.02 Gbits/sec
Intel Atom C3558Debian bookworm / 6.1.0-131.26 Gbits/sec
Banana Pi BPI-R4 / MT7988AOpenWRT Snapshot / 6.1.771.27 Gbits/sec
Intel Celeron(R) J4125Linux pve / 6.2.162.12 Gbits/sec
Intel Celeron N5105*Debian bookworm / 6.1.382.46 Gbits/sec
Intel N100Debian bookworm / 6.1.763.97 Gbits/sec
Intel N100Debian bookworm / 6.6.134.65 Gbits/sec
Click to expand...

Results from an LxC container (Intel N100, two virtaul core, 1GB RAM, 1GB Swap, Proxmox PVE 8.2.7).

Bash: 
root@ubuntu2204ct12:~/wg-bench# ./setup-netns.sh 

root@ubuntu2204ct12:~/wg-bench# ./benchmark.sh 
Connecting to host 169.254.200.2, port 5201
[  5] local 169.254.200.1 port 40328 connected to 169.254.200.2 port 5201
[ ID] Interval           Transfer     Bitrate         Retr  Cwnd
[  5]   0.00-1.00   sec   410 MBytes  3.44 Gbits/sec    0   2.82 MBytes       
[  5]   1.00-2.00   sec   404 MBytes  3.39 Gbits/sec    0   2.82 MBytes       
[  5]   2.00-3.00   sec   406 MBytes  3.41 Gbits/sec    0   2.82 MBytes       
[  5]   3.00-4.00   sec   410 MBytes  3.44 Gbits/sec    0   2.98 MBytes       
[  5]   4.00-5.00   sec   405 MBytes  3.40 Gbits/sec    0   2.98 MBytes       
[  5]   5.00-6.00   sec   412 MBytes  3.46 Gbits/sec    0   2.98 MBytes       
[  5]   6.00-7.00   sec   402 MBytes  3.37 Gbits/sec    0   2.98 MBytes       
[  5]   7.00-8.00   sec   408 MBytes  3.42 Gbits/sec    0   2.98 MBytes       
[  5]   8.00-9.00   sec   408 MBytes  3.42 Gbits/sec    0   2.98 MBytes       
[  5]   9.00-10.00  sec   402 MBytes  3.38 Gbits/sec    0   2.98 MBytes       
- - - - - - - - - - - - - - - - - - - - - - - - -
[ ID] Interval           Transfer     Bitrate         Retr
[  5]   0.00-10.00  sec  3.97 GBytes  3.41 Gbits/sec    0             sender
[  5]   0.00-10.04  sec  3.97 GBytes  3.40 Gbits/sec                  receiver

iperf Done.

root@ubuntu2204ct12:~/wg-bench# ./benchmark.sh -R
Connecting to host 169.254.200.2, port 5201
Reverse mode, remote host 169.254.200.2 is sending
[  5] local 169.254.200.1 port 60648 connected to 169.254.200.2 port 5201
[ ID] Interval           Transfer     Bitrate
[  5]   0.00-1.00   sec   300 MBytes  2.52 Gbits/sec                  
[  5]   1.00-2.00   sec   294 MBytes  2.47 Gbits/sec                  
[  5]   2.00-3.00   sec   293 MBytes  2.46 Gbits/sec                  
[  5]   3.00-4.00   sec   292 MBytes  2.45 Gbits/sec                  
[  5]   4.00-5.00   sec   294 MBytes  2.46 Gbits/sec                  
[  5]   5.00-6.00   sec   293 MBytes  2.46 Gbits/sec                  
[  5]   6.00-7.00   sec   291 MBytes  2.44 Gbits/sec                  
[  5]   7.00-8.00   sec   291 MBytes  2.44 Gbits/sec                  
[  5]   8.00-9.00   sec   293 MBytes  2.46 Gbits/sec                  
[  5]   9.00-10.00  sec   292 MBytes  2.45 Gbits/sec                  
- - - - - - - - - - - - - - - - - - - - - - - - -
[ ID] Interval           Transfer     Bitrate         Retr
[  5]   0.00-10.04  sec  2.87 GBytes  2.45 Gbits/sec    0             sender
[  5]   0.00-10.00  sec  2.86 GBytes  2.46 Gbits/sec                  receiver

iperf Done.
root@ubuntu2204ct12:~/wg-bench# ./clean-up.sh    

root@ubuntu2204ct12:~/wg-bench# lsb_release -a
No LSB modules are available.
Distributor ID: Ubuntu
Description:    Ubuntu 22.04.5 LTS
Release:        22.04
Codename:       jammy
 
Last edited:
X

xiaofan

High Supremacy Member
HWZ Insider
Joined
Sep 16, 2018
Messages
30,842
Reaction score
8,570
OpenWRT virtual router, Intel N100 mini PC running Proxmox PVE 8.2.7. I assign 4GB RAM and two virtual CPU core to the OpenWRT virtual machine.

OpenWRT WAN: 192.168.50.138
OpenWRT LAN: 192.168.48.1
OpenWRT LAN client, LxC contatiner: 192.168.48.111
Laptop with 2.5Gbe USB Ethernet adapter (192.168.50.157) as iperf3 client

When the Laptop Wireguard client is not ON, then we can not ping the iperf3 server. OOkla Speedtest will be able to saturate the 2.5Gbe connection (using Singtel 5Gbps Fibre Internet service here in Singapore).

Bash: 
PS C:\work\speedtest\iperf-3.16-win64> ping 192.168.48.111

Pinging 192.168.48.111 with 32 bytes of data:
Request timed out.
Request timed out.
Request timed out.
Request timed out.

Ping statistics for 192.168.48.111:
    Packets: Sent = 4, Received = 0, Lost = 4 (100% loss),

PS C:\work\speedtest\ookla-speedtest-1.2.0-win64> .\speedtest.exe -s 13623

   Speedtest by Ookla

      Server: Singtel - Singapore (id: 13623)
         ISP: Singtel Fibre
Idle Latency:     2.39 ms   (jitter: 0.26ms, low: 1.81ms, high: 2.62ms)
    Download:  2346.39 Mbps (data used: 1.2 GB)
                 14.99 ms   (jitter: 39.34ms, low: 1.77ms, high: 224.86ms)
      Upload:  2327.54 Mbps (data used: 1.1 GB)
                 12.26 ms   (jitter: 0.96ms, low: 1.47ms, high: 13.35ms)
 Packet Loss:     0.0%
  Result URL: https://www.speedtest.net/result/c/af6132a2-4a88-4e21-b81a-75c17323d890

When the Laptop Wireguard client is ON, then we can ping the iperf3 server from the laptop. OOkla SpeedTest results will be reduced but not much.

From iperf3 results (NAT involved), we can say the virtual OpenWRT Wireguard VPN server performance is about 1.99Gbps download and 2.09Gbps upload.

From OOkla SpeedTest results (no NAT involved), we can say the OpenWRT Wireguard VPN server performance is 1.999Gbps download and 2.226Gbps.

Bash: 
PS C:\work\speedtest\iperf-3.16-win64> ping 192.168.48.111

Pinging 192.168.48.111 with 32 bytes of data:
Reply from 192.168.48.111: bytes=32 time=2ms TTL=63
Reply from 192.168.48.111: bytes=32 time=5ms TTL=63
Reply from 192.168.48.111: bytes=32 time=5ms TTL=63
Reply from 192.168.48.111: bytes=32 time=3ms TTL=63

Ping statistics for 192.168.48.111:
    Packets: Sent = 4, Received = 4, Lost = 0 (0% loss),
Approximate round trip times in milli-seconds:
    Minimum = 2ms, Maximum = 5ms, Average = 3ms

PS C:\work\speedtest\iperf-3.16-win64> .\iperf3.exe -c  192.168.48.111 -R
Connecting to host 192.168.48.111, port 5201
Reverse mode, remote host 192.168.48.111 is sending
[  5] local 10.0.8.2 port 3073 connected to 192.168.48.111 port 5201
[ ID] Interval           Transfer     Bitrate
[  5]   0.00-1.01   sec   238 MBytes  1.98 Gbits/sec
[  5]   1.01-2.01   sec   239 MBytes  2.01 Gbits/sec
[  5]   2.01-3.01   sec   242 MBytes  2.03 Gbits/sec
[  5]   3.01-4.01   sec   246 MBytes  2.05 Gbits/sec
[  5]   4.01-5.01   sec   238 MBytes  2.00 Gbits/sec
[  5]   5.01-6.01   sec   237 MBytes  1.99 Gbits/sec
[  5]   6.01-7.01   sec   244 MBytes  2.05 Gbits/sec
[  5]   7.01-8.01   sec   236 MBytes  1.98 Gbits/sec
[  5]   8.01-9.01   sec   223 MBytes  1.87 Gbits/sec
[  5]   9.01-10.01  sec   237 MBytes  1.99 Gbits/sec
- - - - - - - - - - - - - - - - - - - - - - - - -
[ ID] Interval           Transfer     Bitrate         Retr
[  5]   0.00-10.01  sec  2.33 GBytes  2.00 Gbits/sec    0             sender
[  5]   0.00-10.01  sec  2.32 GBytes  1.99 Gbits/sec                  receiver

iperf Done.
PS C:\work\speedtest\iperf-3.16-win64> .\iperf3.exe -c  192.168.48.111
Connecting to host 192.168.48.111, port 5201
[  5] local 10.0.8.2 port 3173 connected to 192.168.48.111 port 5201
[ ID] Interval           Transfer     Bitrate
[  5]   0.00-1.01   sec   236 MBytes  1.95 Gbits/sec
[  5]   1.01-2.01   sec   247 MBytes  2.08 Gbits/sec
[  5]   2.01-3.01   sec   248 MBytes  2.07 Gbits/sec
[  5]   3.01-4.01   sec   240 MBytes  2.02 Gbits/sec
[  5]   4.01-5.00   sec   239 MBytes  2.02 Gbits/sec
[  5]   5.00-6.00   sec   262 MBytes  2.20 Gbits/sec
[  5]   6.00-7.01   sec   256 MBytes  2.12 Gbits/sec
[  5]   7.01-8.00   sec   251 MBytes  2.12 Gbits/sec
[  5]   8.00-9.00   sec   251 MBytes  2.12 Gbits/sec
[  5]   9.00-10.02  sec   263 MBytes  2.18 Gbits/sec
- - - - - - - - - - - - - - - - - - - - - - - - -
[ ID] Interval           Transfer     Bitrate
[  5]   0.00-10.02  sec  2.43 GBytes  2.09 Gbits/sec                  sender
[  5]   0.00-10.02  sec  2.43 GBytes  2.08 Gbits/sec                  receiver

iperf Done.

PS C:\work\speedtest\ookla-speedtest-1.2.0-win64> .\speedtest.exe -s 13623

   Speedtest by Ookla

      Server: Singtel - Singapore (id: 13623)
         ISP: Singtel Fibre
Idle Latency:     3.50 ms   (jitter: 2.35ms, low: 2.86ms, high: 11.08ms)
    Download:  1999.41 Mbps (data used: 1.2 GB)
                 11.02 ms   (jitter: 8.59ms, low: 3.78ms, high: 244.23ms)
      Upload:  2226.21 Mbps (data used: 2.8 GB)
                 13.59 ms   (jitter: 1.43ms, low: 2.62ms, high: 30.32ms)
 Packet Loss:     1.3%
  Result URL: https://www.speedtest.net/result/c/8ca986b9-878e-4c70-87cf-180fe7636c93
 
J

Jun Jun

Senior Member
Joined
Jun 21, 2016
Messages
1,191
Reaction score
142
Bcm 4916 vs filogic 880 vs qualcomm 1200 pro which is the better chip? Whats their difference?
 
X

xiaofan

High Supremacy Member
HWZ Insider
Joined
Sep 16, 2018
Messages
30,842
Reaction score
8,570
Jun Jun said:
Bcm 4916 vs filogic 880 vs qualcomm 1200 pro which is the better chip? Whats their difference?
Click to expand...

In terms of raw CPU power:
Qualcomm IPQ9570/9574 > MediaTek MT7988A (CPU in the Filogic 880 chipset) > Broadcom BCM4916

Differences: ARM core used, Clock Speed difference, NPU function, etc.
 
J

Jun Jun

Senior Member
Joined
Jun 21, 2016
Messages
1,191
Reaction score
142
xiaofan said:
In terms of raw CPU power:
Qualcomm IPQ9570/9574 > MediaTek MT7988A (CPU in the Filogic 880 chipset) > Broadcom BCM4916

Differences: ARM core used, Clock Speed difference, NPU function, etc.
Click to expand...
Tplink mentioned their be900 using bcm4916A2
 
J

Jun Jun

Senior Member
Joined
Jun 21, 2016
Messages
1,191
Reaction score
142
xiaofan said:
In terms of raw CPU power:
Qualcomm IPQ9570/9574 > MediaTek MT7988A (CPU in the Filogic 880 chipset) > Broadcom BCM4916

Differences: ARM core used, Clock Speed difference, NPU function, etc.
Click to expand...
They say be900 is stronger than be800 which is using 9570 and be805 filogic 880
 
J

Jun Jun

Senior Member
Joined
Jun 21, 2016
Messages
1,191
Reaction score
142
If range and speed and support/stability wise does not prove any improvement then no point
 
J

Jun Jun

Senior Member
Joined
Jun 21, 2016
Messages
1,191
Reaction score
142
Now changed to be800 different symptom. Smart devices keep dropping. They also finding it weird. So will test again with be900.
 
J

Jun Jun

Senior Member
Joined
Jun 21, 2016
Messages
1,191
Reaction score
142
I am also doing testing with them. Hopefully be900 is finally the answer.
 
X

xiaofan

High Supremacy Member
HWZ Insider
Joined
Sep 16, 2018
Messages
30,842
Reaction score
8,570
Jun Jun said:
I am also doing testing with them. Hopefully be900 is finally the answer.
Click to expand...

TP-Link Archer BE900 is not worth buying in general, unless the price is not much higher than Archer BE800.

The following review is from Dongknows.
https://dongknows.com/tp-link-archer-be900-be24000-wi-fi-7-router-review/

Archer BE800 review from Dongknows.
https://dongknows.com/tp-link-archer-be800-be19000-wi-fi-7-router-review/

Both reviews were written two years ago, not so sure if the updated FW make the Archer BE900 a bit better or not.

Dongknows did not review Archer BE805 though, just a quick check from him.
https://dongknows.com/tp-link-archer-be805-be19000-wi-fi-7-router-review/

In Singapore, due to the lower cost of Archer BE805, it has the best value. In terms of value:
Archer BE805 >> Archer BE800 > Archer BE900.
 
J

Jun Jun

Senior Member
Joined
Jun 21, 2016
Messages
1,191
Reaction score
142
xiaofan said:
TP-Link Archer BE900 is not worth buying in general, unless the price is not much higher than Archer BE800.

The following review is from Dongknows.
https://dongknows.com/tp-link-archer-be900-be24000-wi-fi-7-router-review/

Archer BE800 review from Dongknows.
https://dongknows.com/tp-link-archer-be800-be19000-wi-fi-7-router-review/

Both reviews were written two years ago, not so sure if the updated FW make the Archer BE900 a bit better or not.

Dongknows did not review Archer BE805 though, just a quick check from him.
https://dongknows.com/tp-link-archer-be805-be19000-wi-fi-7-router-review/

In Singapore, due to the lower cost of Archer BE805, it has the best value. In terms of value:
Archer BE805 >> Archer BE800 > Archer BE900.
Click to expand...
If tplink can let me choose be900 is it better in terms of coverage and performance ？
 
J

Jun Jun

Senior Member
Joined
Jun 21, 2016
Messages
1,191
Reaction score
142
And comparison to their deco, which is their best product as of now in terms of specs?
 
X

xiaofan

High Supremacy Member
HWZ Insider
Joined
Sep 16, 2018
Messages
30,842
Reaction score
8,570
Jun Jun said:
And comparison to their deco, which is their best product as of now in terms of specs?
Click to expand...

Jun Jun said:
I m only looking at their best product.
Click to expand...

Probably Deco BE95 for the consumer wireless router, but by right it is not available in Singapore due to the use of 6GHz-2.
https://www.tp-link.com/sg/home-networking/deco/deco-be95/

The real good product from TP-Link is the Omada series if you want their best product.
https://www.omadanetworks.com/sg/business-networking/all-omada/
 
kashix

kashix

Arch-Supremacy Member
HWZ Insider
Joined
Dec 27, 2007
Messages
11,582
Reaction score
2,482
J

Jun Jun

Senior Member
Joined
Jun 21, 2016
Messages
1,191
Reaction score
142
Cant find information on be95 cpu. But does it sacrifice any speed or range if i am using wired back haul? Read something bad abt the 2nd 6ghz for the backhaul.
xiaofan said:
Probably Deco BE95 for the consumer wireless router, but by right it is not available in Singapore due to the use of 6GHz-2.
https://www.tp-link.com/sg/home-networking/deco/deco-be95/

The real good product from TP-Link is the Omada series if you want their best product.
https://www.omadanetworks.com/sg/business-networking/all-omada/
Click to expand...
 
You must log in or register to reply here.
Important Forum Advisory Note
This forum is moderated by volunteer moderators who will react only to members' feedback on posts. Moderators are not employees or representatives of HWZ. Forum members and moderators are responsible for their own posts.

Please refer to our Community Guidelines and Standards, Terms of Service and Member T&Cs for more information.
Top