Skip to content

Defect: Deadlock or race-condition running on a cluster #688

Open
@zbeekman

Description

@zbeekman
  • I am reporting a bug others will be able to reproduce and not asking a question or requesting a new feature.

System information including:

  • OpenCoarrays Version: 2.8.0
  • Fortran Compiler: gfortran 8.2.0
  • C compiler used for building lib: gcc 8.2.0
  • Installation method: install.sh was used to build and install MPICH 3.3, then CMake was used
  • All flags & options passed to the installer N/A (normall CMake build)
  • Output of uname -a: Linux n001 3.10.0-957.27.2.el7.x86_64 #1 SMP Tue Jul 9 16:53:14 UTC 2019 x86_64 x86_64 x86_64 GNU/Linux
  • MPI library being used: MPICH 3.3
  • Machine architecture and number of physical cores: Dual socket Broadwell node, 28 cores total, E5-2690 v4
  • Version of CMake: 3.15.4

To help us debug your issue please explain:

What you were trying to do (and why)

Run OC test suite to verify functionality

What happened (include command output, screenshots, logs, etc.)

3 tests timeout after a long time (90 seconds or more):

  • get_array
  • send_array
  • co_heat

What you expected to happen

Run in a reasonable amount of time

Step-by-step reproduction instructions to reproduce the error/bug

Load the following modules on Talapas:

Currently Loaded Modules:
  1) prl   2) bright   3) slurm/18.08   4) cmake/3.15.4   5) racs-eb   6) gcc/8.2.0

Install MPICH 3.3 with install.sh:

 ./install.sh -p mpich -j 16 -I 3.3 -i "${HOME}/.local/mpich-3.3" -c $(which gcc) -C $(which g++) -f $(which gfortran)

Source the file to get stuff on my path:

$ source ~/local-env.sh
$ cat ~/local-env.sh
#!/bin/bash

export MANPATH="${HOME}/.local/share/man${MANPATH+:${MANPATH}}"
export PATH="${HOME}/.local/bin${PATH+:${PATH}}"
export LD_LIBRARY_PATH="${HOME}/.local/lib64:${HOME}/.local/lib:${LD_LIBRARY_PATH+:${LD_LIBRARY_PATH}}"
export LIBRARY_PATH="${HOME}/.local/lib64:${HOME}/.local/lib:${LIBRARY_PATH+:${LIBRARY_PATH}}"
export CPATH="${HOME}/.local/include:${CPATH+:${CPATH}}"

Here is the full output of cmake --system-information:
Talapas.txt

Metadata

Metadata

Assignees

No one assigned

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions