Ubuntu mpi4py не будет компилироваться

Question

У меня Ubuntu Desktop LTS 16.04.1, и я сделал следующее. Я зашел на https://www.open-mpi.org/software/ompi/v2.0/, скачал openmpi-2.0.1.tar.gz и установил его с помощью следующих команд:

tar -xvf openmpi-2.0.1.tar.gz
cd openmpi-2.0.1
./configure --prefix="/home/$USER/.openmpi"
make
sudo make install
export PATH="$PATH:/home/$USER/.openmpi/bin"
export LD_LIBRARY_PATH="$LD_LIBRARY_PATH:/home/$USER/.openmpi/lib/"
echo export PATH="$PATH:/home/$USER/.openmpi/bin" >> /home/$USER/.bashrc
echo export LD_LIBRARY_PATH="$LD_LIBRARY_PATH:/home/$USER/.openmpi/lib/" >> /home/$USER/.bashrc

После этого я установил mpi4py, используя:

sudo apt-get update
sudo apt-get install python-mpi4py

После этого я создал файл Python (моя версия Python - Python 2.7.12) с именем some.py, имеющим следующие строки

from mpi4py import MPI
comm = MPI.COMM_WORLD
rank = comm.Get_rank()
print "hello world from process ", rank

Когда я пытаюсь запустить его с помощью mpiexec -n 5 python что-то.py, я получаю следующее:

-------------------------------------------------------
Primary job  terminated normally, but 1 process returned
a non-zero exit code.. Per user-direction, the job has been aborted.
-------------------------------------------------------
--------------------------------------------------------------------------
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
--------------------------------------------------------------------------
*** 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)
[vlad-VirtualBox:3551] Local abort before MPI_INIT completed successfully; not able to aggregate error messages, and not able to guarantee that all other processes were killed!
[vlad-VirtualBox:03551] 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)
[vlad-VirtualBox:03551] 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)
[vlad-VirtualBox:03551] 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)
--------------------------------------------------------------------------
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 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)
--------------------------------------------------------------------------
--------------------------------------------------------------------------
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
--------------------------------------------------------------------------
*** 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)
[vlad-VirtualBox:3552] Local abort before MPI_INIT completed successfully; not able to aggregate error messages, and not able to guarantee that all other processes were killed!
[vlad-VirtualBox:03552] 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)
[vlad-VirtualBox:03552] 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)
[vlad-VirtualBox:03552] 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)
--------------------------------------------------------------------------
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 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)
--------------------------------------------------------------------------

Большинство решений говорят об установке openmpi напрямую из исходного кода, что я и сделал, но это, похоже, не решило мою проблему. У кого-нибудь есть похожая проблема?

Answer 1

Я только что решил: я удалил mpi4py, я установил python-pip и установил с помощью sudo mpi4py через pip. Список команд:

sudo apt-get remove python-mpi4py
sudo apt-get update && sudo apt-get -y upgrade
sudo apt-get install python-pip
sudo pip install mpi4py

ПРИМЕЧАНИЕ. Вам придется немного подождать после обновления sudo apt-get && sudo apt-get -y. Этот вопрос можно закрыть сейчас, спасибо.