Hello. I apologize for my English. Apparently there is a bug when
working with the LAG interface. (bonding)
root@server:~# cat /proc/net/bonding/bond0
Ethernet Channel Bonding Driver: v3.7.1 (April 27, 2011)
Bonding Mode: load balancing (xor)
Transmit Hash Policy: layer2 (0)
MII Status: up
MII Polling Interval (ms): 100
Up Delay (ms): 200
Down Delay (ms): 200
Slave Interface: enp1s0f1
MII Status: up
Speed: 10000 Mbps
Duplex: full
Link Failure Count: 0
Permanent HW addr: 00:1b:21:bc:6e:7d
Slave queue ID: 0
Slave Interface: enp1s0f0
MII Status: up
Speed: 10000 Mbps
Duplex: full
Link Failure Count: 0
Permanent HW addr: 00:1b:21:bc:6e:7c
Slave queue ID: 0
Linux distribution and version: Ubuntu 18.04 LTS and Arch Linux
(2019-11-01)
Linux kernel and version: Linux server 4.15.0-72-generic #81-Ubuntu SMP
and Linux Arch 4.19.88-1-lts
InfiniBand hardware and firmware version: 10-Gigabit SFI/SFP+ Network
Connection (Ethernet Server Adapter X520-2)
https://ark.intel.com/content/www/us/en/ark/products/39776/intel-ethernet-converged-network-adapter-x520-da2.html
Configuring Soft-RoCE.
Reproduce the bug:
root@server:~# rxe_cfg add bond0
Name Link Driver Speed NMTU IPv4_addr RDEV RMTU
bond0 yes bonding 9000 192.168.90.1 rxe0 (?)
eno1 yes e1000e 1500 192.168.5.208
enp1s0f0 yes ixgbe 9000
enp1s0f1 yes ixgbe 9000
virbr0 no bridge 1500 192.168.122.1
root@server:~# rxe_cfg status
IB device 'rxe0' wasn't found
Name Link Driver Speed NMTU IPv4_addr RDEV RMTU
bond0 yes bonding 9000 192.168.90.1 rxe0 (?)
eno1 yes e1000e 1500 192.168.5.208
enp1s0f0 yes ixgbe 9000
enp1s0f1 yes ixgbe 9000
virbr0 no bridge 1500 192.168.122.1
virbr0-nic no tun 1500
root@server:~# ibv_devices
device node GUID
------ ----------------
root@server:~# ibv_devinfo
No IB devices found
root@server:~# ibstat rxe0
ibpanic: [1715] main: 'rxe0' IB device can't be found: Success
Also have problems with:
[root@test ~]# rdma link add rxe0 type rxe netdev bond1
error: Invalid argument
[root@test ~]# rdma link add rxe0 type rxe netdev enp0s3
error: Invalid argument
Tnx.
