Srijan, The logs suggest you explicitly request the btl/sm component, and this typically occurs via a openmpi-mca-params.conf (that contains a line such as btl = sm,openib,self), or the OMPI_MCA_btl environment variable
Cheers, Gilles On Mon, Jul 13, 2020 at 1:50 AM Srijan Chatterjee via users < users@lists.open-mpi.org> wrote: > Dear Open MPI users, > I am using the following system > CentOS release 6.6 > Rocks 6.2 > I have been trying to install openmpi-3.1.3. > After installing it, in the example folder if want to test run I got the > following error > > I run command mpirun -np 1 hello_c > > [user@chimera examples]$ mpirun -np 1 hello_c > libibverbs: Warning: no userspace device-specific driver found for > /sys/class/infiniband_verbs/uverbs0 > libibverbs: Warning: no userspace device-specific driver found for > /sys/class/infiniband_verbs/uverbs0 > -------------------------------------------------------------------------- > As of version 3.0.0, the "sm" BTL is no longer available in Open MPI. > > Efficient, high-speed same-node shared memory communication support in > Open MPI is available in the "vader" BTL. To use the vader BTL, you > can re-run your job with: > > mpirun --mca btl vader,self,... your_mpi_application > -------------------------------------------------------------------------- > -------------------------------------------------------------------------- > A requested component was not found, or was unable to be opened. This > means that this component is either not installed or is unable to be > used on your system (e.g., sometimes this means that shared libraries > that the component requires are unable to be found/loaded). Note that > Open MPI stopped checking at the first component that it did not find. > > Host: chimera.pnc.res.in > Framework: btl > Component: sm > -------------------------------------------------------------------------- > -------------------------------------------------------------------------- > It looks like MPI_INIT failed for some reason; your parallel process is > likely to abort. There are many reasons that a parallel process can > fail during MPI_INIT; some of which are due to configuration or environment > problems. This failure appears to be an internal failure; here's some > additional information (which may only be relevant to an Open MPI > developer): > > mca_bml_base_open() failed > --> Returned "Not found" (-13) instead of "Success" (0) > -------------------------------------------------------------------------- > [chimera:04271] *** An error occurred in MPI_Init > [chimera:04271] *** reported by process [1310326785,0] > [chimera:04271] *** on a NULL communicator > [chimera:04271] *** Unknown error > [chimera:04271] *** MPI_ERRORS_ARE_FATAL (processes in this communicator > will now abort, > [chimera:04271] *** and potentially your MPI job) > > > > I am quite new to it, so please inform me if you need additional > information about the system. > Any advice is welcomed. > > Srijan > > > > > > > -- > SRIJAN CHATTERJEE >
