[ESPResSo] Espresso over infiniband

[Tristan Bereau]

Dear all,

I am trying to run Espresso in parallel between two nodes linked by an
Infiniband connection.
First of all, I have set up everything such that infiniband is
recognized, and I can successfully start jobs.
However, when running Espresso, my job crashes after a while when trying
to write to a blockfile (one of the Espresso blockfile write command)
because of a "broken pipe." I'm a bit puzzled because this does not
necessarily happen at the first call of the function. The job might be
able to write a few blockfiles before crashing. And, the job *only*
crashes because of a "broken pipe."
Note that everything runs very well if I turn off the infiniband
connection and only use ethernet (same job, same script, same nodes, etc.).

Do I have some stability issues with the connection ?

Thanks for your help,


Tristan