[trailer]

Hello,


I am using OpenFOAM v2012 on Ubuntu 20.04.


When I run simulations in parallel, I get the following statement:

Invalid MIT-MAGIC-COOKIE-1 key

What is this? Is it influencing anything on the simulation? How can I correct this?


Best Regards!

[trailer]

Changed the driver from NVIDIA to X.ORg and it disappeared...

[trailer]

Has anyone else experienced this and was able to solve it with nvidia drivers?

[olesen]

Could try with

  export QT_X11_NO_MITSHM=1

and see if that help at all.

[trailer]

Hello Mr. Olesen,


Thanks for the input, but that did not remove the "Invalid MIT-MAGIC-COOKIE-1 key" statement.

The results do not appear to be affected by that, but it is very annoying!

[s1291]

Try:

# remove openmpi-bin
sudo apt remove openmpi-bin

# install mpich
sudo apt install mpich

[trailer]

Originally Posted by s1291

Try:

# remove openmpi-bin
sudo apt remove openmpi-bin

# install mpich
sudo apt install mpich

Not good. Just by executing those commands I get whenever I load OpenFOAM

gcc: error: unrecognized command line option ‘--showme:link’

And when I run something in parallel:

[[INVALID],INVALID] ORTE_ERROR_LOG: A system-required executable either could not be found or was not executable by this user in file ess_singleton_module.c at line 572
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):

  orte_ess_init failed
  --> Returned value A system-required executable either could not be found or was not executable by this user (-126) instead of ORTE_SUCCESS

[s1291]

Please check these posts:

• https://askubuntu.com/questions/8105...owmelink-error
  
• gcc: error: unrecognized command line option '--showme:link'
  

Otherwise, revert to the previous state:

# Remove mpich
sudo apt remove mpich

# Install openmpi-bin
sudo apt install openmpi-bin libopenmpi-dev

[alexey.v.medvedev]

Originally Posted by trailer

Invalid MIT-MAGIC-COOKIE-1 key

What is this? Is it influencing anything on the simulation? How can I correct this?

The issue is caused by the `libhwloc` library, which is used by `OpenRTE` (the OpenMPI component) to explore the hardware topology of the node during the launch of parallel processes. When `hwloc_topology_load()` is called, `libhwloc` iterates over all of its available components, which are implemented as plug-ins. One of these components, `gl`, is responsible for gathering information about the system's graphics devices and uses X11 calls like `XOpenDisplay()`, which can generate the error message "Invalid MIT-MAGIC-COOKIE-1 key" if it fails to connect to the X11 server.

In many cases, this gl component is not needed on HPC clusters and can be safely disabled by setting the `HWLOC_COMPONENTS` environment variable to exclude it:

`export HWLOC_COMPONENTS="-gl"`