Multiprocessing could not start all subprocesses specified by `num_processes` on ARC server

[i-am-sijia]

Describe the issue Not able to run multiprocessing on ARC server when setting num_processes > 21, even though there are 64 cores on the server. The partitioned data files were generated for all the num_processes, but the mp_household runner was only able to start for up to 20 subprocesses. The same multiprocessing setting runs fine on WSP server, all number of num_processes are started and run fine.

I noticed the ARC server has 4 CPU sockets. All other machines I've worked with have1 CPU socket. Not sure if this is causing the issue here. This needs further testing and investigation, will report back if we find what's causing the issue.

[guyrousseau]

Thanks, Sijia for bringing this up to everyone's attention. I strongly encourage other Consortium members to verify the task manager of your server to identify and determine how many sockets you have, see ARC server example pictured herein.