Proxmox VE host's network speed is limited to 100M in a 1G LAN

[rondochen]

Hi everyone,
I have just discovered today that my whole PVE machine's network speed is limited to 100M. In order to find out the root cause, I had checked that the interface of PVE host and switch are both running in 1G speed. Also, the server's loading was low during testing. And the ethnet cable is 1G supported too.
Can I see some advice here? See which part i am missing.
Any advice or suggestion are appreciated~

Below is the iperf3 test result ran in my PVE host, the Iperf3 server 192.168.0.108 is another physical server outside of PVE.

root@pve:~# iperf3 -c 192.168.0.108  -B 192.168.0.253  
Connecting to host 192.168.0.108, port 5201
[  5] local 192.168.0.253 port 44469 connected to 192.168.0.108 port 5201
[ ID] Interval           Transfer     Bitrate         Retr  Cwnd
[  5]   0.00-1.00   sec  12.0 MBytes   101 Mbits/sec    0    156 KBytes    
[  5]   1.00-2.00   sec  11.4 MBytes  95.4 Mbits/sec    0    199 KBytes    
[  5]   2.00-3.00   sec  11.3 MBytes  94.9 Mbits/sec    0    209 KBytes    
[  5]   3.00-4.00   sec  11.3 MBytes  94.9 Mbits/sec    0    209 KBytes    
[  5]   4.00-5.00   sec  11.3 MBytes  94.9 Mbits/sec    0    219 KBytes    
[  5]   5.00-6.00   sec  10.9 MBytes  91.7 Mbits/sec    0    230 KBytes    
[  5]   6.00-7.00   sec  11.4 MBytes  95.9 Mbits/sec    0    230 KBytes    
[  5]   7.00-8.00   sec  10.9 MBytes  91.7 Mbits/sec    0    230 KBytes    
[  5]   8.00-9.00   sec  11.4 MBytes  95.9 Mbits/sec    0    230 KBytes    
[  5]   9.00-10.00  sec  10.9 MBytes  91.7 Mbits/sec    0    230 KBytes    
- - - - - - - - - - - - - - - - - - - - - - - - -
[ ID] Interval           Transfer     Bitrate         Retr
[  5]   0.00-10.00  sec   113 MBytes  94.8 Mbits/sec    0             sender
[  5]   0.00-10.00  sec   112 MBytes  94.2 Mbits/sec                  receiver

iperf Done.

Interface status of PVE host:

root@pve:~# ethtool eno1
Settings for eno1:
        Supported ports: [ TP ]
        Supported link modes:   10baseT/Half 10baseT/Full
                                100baseT/Half 100baseT/Full
                                1000baseT/Full
        Supported pause frame use: Symmetric
        Supports auto-negotiation: Yes
        Supported FEC modes: Not reported
        Advertised link modes:  10baseT/Half 10baseT/Full
                                100baseT/Half 100baseT/Full
                                1000baseT/Full
        Advertised pause frame use: Symmetric
        Advertised auto-negotiation: Yes
        Advertised FEC modes: Not reported
        Speed: 1000Mb/s
        Duplex: Full
        Port: Twisted Pair
        PHYAD: 1
        Transceiver: internal
        Auto-negotiation: on
        MDI-X: on (auto)
        Supports Wake-on: pumbg
        Wake-on: g
        Current message level: 0x00000007 (7)
                               drv probe link
        Link detected: yes

Interface status of Iperf3 server:

[root@gen10 ~]# ethtool enp2s0f0
Settings for enp2s0f0:
        Supported ports: [ TP ]
        Supported link modes:   10baseT/Half 10baseT/Full
                                100baseT/Half 100baseT/Full
                                1000baseT/Half 1000baseT/Full
        Supported pause frame use: No
        Supports auto-negotiation: Yes
        Supported FEC modes: Not reported
        Advertised link modes:  10baseT/Half 10baseT/Full
                                100baseT/Half 100baseT/Full
                                1000baseT/Half 1000baseT/Full
        Advertised pause frame use: Symmetric
        Advertised auto-negotiation: Yes
        Advertised FEC modes: Not reported
        Link partner advertised link modes:  10baseT/Half 10baseT/Full
                                             100baseT/Half 100baseT/Full
                                             1000baseT/Full
        Link partner advertised pause frame use: Symmetric
        Link partner advertised auto-negotiation: Yes
        Link partner advertised FEC modes: Not reported
        Speed: 1000Mb/s
        Duplex: Full
        Port: Twisted Pair
        PHYAD: 1
        Transceiver: internal
        Auto-negotiation: on
        MDI-X: off
        Supports Wake-on: g
        Wake-on: g
        Current message level: 0x000000ff (255)
                               drv probe link timer ifdown ifup rx_err tx_err
        Link detected: yes

PVE host's interface configuration:

root@pve:~# cat /etc/network/interfaces
auto lo
iface lo inet loopback

iface eno1 inet manual

iface eno2 inet manual

auto vmbr0
iface vmbr0 inet static
        address 192.168.0.253/24
        gateway 192.168.0.1
        bridge-ports eno1
        bridge-stp off
        bridge-fd 0

 

[Lorenz.S]

Hi,

you could also try ethtool vmbr0 on both servers. I also found out, that Linux bridges are speed capped by their slowest bridge port. Maybe you have some slow ports in your bridge?

 

[rondochen]

Hi,

you could also try ethtool vmbr0 on both servers. I also found out, that Linux bridges are speed capped by their slowest bridge port. Maybe you have some slow ports in your bridge?

Thanks for the reply. I am also suspecting the ethernet ports in network switch and the ethernet cable.
I will check this out later.

 

[rondochen]

Thanks for the reply. I am also suspecting the ethernet ports in network switch and the ethernet cable.
I will check this out later.

the ethtool vmbr0 result is shown as below:

root@pve:~# ethtool  vmbr0
Settings for vmbr0:
        Link detected: yes

 

[rondochen]

I had finally found out the root cause!
There was a 100M ethernet cable in the wall, which i didn't see!
The bandwidth gose 1G after replacing the wrong cable.

 

[ghostface]

I had a similar issue with the speed (1000Mbit/s were somehow limited to 100Mbit/s) but used PCI passthrough for the NICs. For the, the folling solution worked in the end https://forum.proxmox.com/threads/proxmox-pfsense-vm-extreme-low-throughput.67281/post-526005

 

[jaxjexjox]

ethtool vmbr0 is a good piece of advice, thank you.
I'm fairly confident ip addr was reporting 1000 for some reason (it's fixed now so I can't confirm)


I've just built a spare machine and it's connecting at 10Mbit (yes, 10, not 100 or 1000) on 2 different ethernet cables too, I'll have to have a play and see what on earth is going on, but this has helped diagnose why a backup was taking a very, very long time.

NOTE: 3'rd, thicker cable the charm, fixed.