Hi Guys, I am also thinking of using NFS for ease of management and was wondering what you had to do in order to use NFS storage for slurm? Do you just have the config files on nfs (/etc/slurm) or do you have binaries etc on nfs storage as well? Is there a documented process somewhere that goes over how to do this? Currently I have everything installed on local disk of each compute and master nodes.
Thanks, -J > On Jan 12, 2014, at 4:21 PM, Christopher Samuel <[email protected]> wrote: > > > -----BEGIN PGP SIGNED MESSAGE----- > Hash: SHA1 > >> On 09/01/14 23:37, Franco Broi wrote: >> >> We have the same setup and see the same message so we added the >> flag to ignore it. Must be an NFS thing. > > We use NFS too and don't see this, but we do a "scontrol reconfigure" > after updating slurm.conf to make sure the compute nodes re-read > slurm.conf so everyone is on the same page again. > > All the best, > Chris > - -- > Christopher Samuel Senior Systems Administrator > VLSCI - Victorian Life Sciences Computation Initiative > Email: [email protected] Phone: +61 (0)3 903 55545 > http://www.vlsci.org.au/ http://twitter.com/vlsci > > -----BEGIN PGP SIGNATURE----- > Version: GnuPG v1.4.14 (GNU/Linux) > Comment: Using GnuPG with Thunderbird - http://www.enigmail.net/ > > iEYEARECAAYFAlLTMTsACgkQO2KABBYQAh/FGACeNr9iJNQYPs0r9oFsCNBZzQZg > xB0AnjLp5rkE4skZH8dhufOLZMklUNbH > =bdW3 > -----END PGP SIGNATURE-----
