Comment 0 for bug 1583432

Revision history for this message
Benjamin Sperisen (lasindi) wrote :

To reproduce, install the mpi4py package from Ubuntu. Enter

$ python

and then run:

>>> from mpi4py import MPI

An error message like the following is printed, and python exits:
******************************************************************************************

[compy:04228] mca: base: component_find: unable to open /usr/lib/openmpi/lib/openmpi/mca_shmem_posix: /usr/lib/openmpi/lib/openmpi/mca_shmem_posix.so: undefined symbol: opal_shmem_base_framework (ignored)
[compy:04228] mca: base: component_find: unable to open /usr/lib/openmpi/lib/openmpi/mca_shmem_mmap: /usr/lib/openmpi/lib/openmpi/mca_shmem_mmap.so: undefined symbol: opal_show_help (ignored)
[compy:04228] mca: base: component_find: unable to open /usr/lib/openmpi/lib/openmpi/mca_shmem_sysv: /usr/lib/openmpi/lib/openmpi/mca_shmem_sysv.so: undefined symbol: opal_show_help (ignored)
--------------------------------------------------------------------------
It looks like opal_init failed for some reason; your parallel process is
likely to abort. There are many reasons that a parallel process can
fail during opal_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):

  opal_shmem_base_select failed
  --> Returned value -1 instead of OPAL_SUCCESS
--------------------------------------------------------------------------
--------------------------------------------------------------------------
It looks like orte_init failed for some reason; your parallel process is
likely to abort. There are many reasons that a parallel process can
fail during orte_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):

  opal_init failed
  --> Returned value Error (-1) instead of ORTE_SUCCESS
--------------------------------------------------------------------------
--------------------------------------------------------------------------
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):

  ompi_mpi_init: ompi_rte_init failed
  --> Returned "Error" (-1) instead of "Success" (0)
--------------------------------------------------------------------------
*** An error occurred in MPI_Init_thread
*** on a NULL communicator
*** MPI_ERRORS_ARE_FATAL (processes in this communicator will now abort,
*** and potentially your MPI job)
[compy:4228] Local abort before MPI_INIT completed successfully; not able to aggregate error messages, and not able to guarantee that all other processes were killed!
******************************************************************************************

It appears to have something to do with how the mpi4py package was built. The following is a work-around which involves removing the Ubuntu package. First, remove it:

$ sudo apt-get remove mpi4py

Then install the Open MPI headers (the next step involves building mpi4py) and pip:

$ sudo apt-get install libopenmpi-dev python-pip

Finally install mpi4py:

$ sudo pip install mpi4py

If you try the python command above, it should now work fine.