Openmpi

Northword2022年11月1日小于 1 分钟

Openmpi

各种乱七八糟的报错

libi40iw-i40iw_ucreate_qp: failed to create QP, unsupported QP type: 0x4
--------------------------------------------------------------------------
Failed to create a queue pair (QP):

Hostname: compute-0-9
Requested max number of outstanding WRs in the SQ:                1
Requested max number of outstanding WRs in the RQ:                2
Requested max number of SGEs in a WR in the SQ:                   511
Requested max number of SGEs in a WR in the RQ:                   511
Requested max number of data that can be posted inline to the SQ: 0
Error:    File exists

Check requested attributes.
--------------------------------------------------------------------------
--------------------------------------------------------------------------
Open MPI has detected that there are UD-capable Verbs devices on your
system, but none of them were able to be setup properly.  This may
indicate a problem on this system.

You job will continue, but Open MPI will ignore the "ud" oob component
in this run.

Hostname: compute-0-9
--------------------------------------------------------------------------

解决:

Put “oob=tcp” in your default MCA param file

新建 ~/.openmpi/mca-params.conf,写入 oob=tcp 即可。

MCA param file:

  • $HOME/.openmpi/mca-params.conf: This is the user-supplied set of values, which has the highest precedence.
  • $prefix/etc/openmpi-mca-params.conf: This is the system-supplied set of values, which has a lower precedence.

参考: