This pages summarizes known problems and troubleshoot information that help running experiments a a MHz rate.
1. Open MPI failed to TCP connect
We observe that when running using more than a few nodes (> 20) and that nodes assigned to your job are from mixed pools (cmp, mon, or eb nodes mixed in), jobs may fail with the following message:
-------------------------------------------------------------------------- WARNING: Open MPI failed to TCP connect to a peer MPI process. This should not happen. Your Open MPI job may now hang or fail. Local host: drp-srcf-eb010 PID: 130465 Message: connect() to 172.21.164.90:1055 failed Error: Operation now in progress (115) -------------------------------------------------------------------------- |
---|
This happens because we have multiple interfaces (tcp, ib, etc.) assigned to a node, however some might not have all enabled and that results in no connection when a node is missing that selected interface.
Solution
1. Restrict to 172.21.164 subnet
export OMPI_MCA_btl_tcp_if_include=172.21.164.90/1072 |
---|
2. Exclude 172.21.152 subnet
export OMPI_MCA_btl_tcp_if_exclude=eno1 |
---|
2. Node configurations
To achieve a MHz rate, the heavy-lifting core SMD0 (MPI rank 0) needs to be assigned on an individual node exclusively. This will allow the entire node to read smalldata in parallel at the full bandwidth.