openibd.service is failed on a particular node

"openibd.service" status:

[compute-5 ~]$ sudo systemctl status openibd.service

● openibd.service - openibd - configure Mellanox devices

Loaded: loaded (/usr/lib/systemd/system/openibd.service; enabled; vendor preset: disabled)

Active: failed (Result: exit-code) since Mon 2021-02-22 02:42:23 CET; 1min 8s ago

Docs: file:/etc/infiniband/openib.conf

Process: 168237 ExecStart=/etc/init.d/openibd start bootid=%b (code=exited, status=3)

Main PID: 168237 (code=exited, status=3)

Feb 22 02:42:22 compute-5 openibd[168237]: Module ib_ipoib belong to kernel which is not a part of MLNX_OFED, skipping…[FAILED]

Feb 22 02:42:22 compute-5 openibd[168237]: Loading HCA driver and Access Layer:[ OK ]

Feb 22 02:42:22 compute-5 openibd[168237]: Module rdma_cm belong to kernel which is not a part of MLNX_OFED, skipping…[FAILED]

Feb 22 02:42:22 compute-5 openibd[168237]: Module ib_ucm belong to kernel which is not a part of MLNX_OFED, skipping…[FAILED]

Feb 22 02:42:22 compute-5 root[182861]: openibd: ERROR: Module ib_ucm belong to kernel which is not a part of MLNX_OFED, skipping…

Feb 22 02:42:23 compute-5 openibd[168237]: Module rdma_ucm belong to kernel which is not a part of MLNX_OFED, skipping…[FAILED]

Feb 22 02:42:23 compute-5 systemd[1]: openibd.service: main process exited, code=exited, status=3/NOTIMPLEMENTED

Feb 22 02:42:23 compute-5 systemd[1]: Failed to start openibd - configure Mellanox devices.

Feb 22 02:42:23 compute-5 systemd[1]: Unit openibd.service entered failed state.

Feb 22 02:42:23 compute-5 systemd[1]: openibd.service failed.

We have tried to restart the “openibd.service” but it won’t help.

[compute-5 ~]$ sudo systemctl restart openibd.service

Job for openibd.service failed because the control process exited with error code. See “systemctl status openibd.service” and “journalctl -xe” for details.

Hi Prekash,

It seems that you are working with a non-supported kernel.

You can try to re-install the MLNX_OFED driver with “–add-kernel-support” flag.

Regards,

Chen

Hi @Chen Hamami​ ,

Thanks for your update.

Will It impact any VM on the particular node because 4 VM’s are running on the node.

Regards,

Prakash Kumar K