OpenMPI: Major Memory Leak Bug
UPDATE: Fri, Jul 24 - 9:00pm - We have completed compiling and redeploying the new version of OpenMPI. All systems are now running OpenMPI v1.8.7.
We have just been notified of a major memory leak with OpenMPI v1.8.6 (the current version on the HPC). This is a likely reason that many nodes have been crashing and disrupting jobs on the HPC this week.
The OpenMPI Team has released a new version, v1.8.7, and we are upgrading our HPC. This will occur on Friday, July 24 around 9AM. After the upgrade, you can check the version of OpenMPI by loading the appropriate module (gnu-openmpi
, pgi-openmpi
, or intel-openmpi
) and then running ompi_info
. If you use OpenMPI for any of your programs, you will need to recompile your code against the new version. Also, be sure to cancel and resubmit any queued jobs in order to ensure that you are using the correct MPI version.
You can read more details about the OpenMPI v1.8.7 release at: http://www.open-mpi.org/community/lists/announce/2015/07/0070.php.
Please let us know if you have any questions or concerns: support@rcc.fsu.edu.