This is an old revision of the document!
Similar to Matlab, MRtrix will, by default, spawn as many threads as it sees cores on the compute node where it's running. This will cause problems and significantly slow down the whole node. To prevent this, multi-threading should be disabled or carefully set to match the number of slots/cores assigned to your job.
The /etc/mrtrix.conf configuration file is set on chead and on each node to disable multi-threading by default, by assigning the NumberOfThreads parameter to 0.
In your script when you call MRtrix, include -nthreads $NSLOTS
. This will set up multi-threading for the number of slots/cores your job has.