Nvidia

See merge request !165

Upgrade

See merge request !164

changes to the config_repos role so hopefully we can upgrade cleanly without reinserting the base repos

M3 has decided to change where we store some parts of slurm, in particular prolo…

See merge request !163

Slurm epilog

See merge request !161

M3 has decided to change where we store some parts of slurm, in particular prolog and epilog will go into /opt/slurm/etc

update the unit file for slurmdbd to respect the directory we want the pid to go to

See merge request !159

Adding option to disable KMEM in cgroup

See merge request !160

allow use of a ldap readonly server for failover (but don't mandate it)

See merge request !158

set the killmode so restarting slurmd doesn't cause the users jobs to be killed

See merge request !157

Remove -a to make the check_fs_used work

See merge request !156

Refer to https://github.com/mej/nhc

Do not enabled slurmctld and slurmdbd in systemd

See merge request !155

Make slurmctld and slurmdbd explicitily disabled on startup (rather than just leaving it to whatever it is currently set to)

fix an error detecting the ppolicy and enable the auxposixgroup schema

See merge request !154

Fix nat server

See merge request !153

Merge branch 'master' of gitlab.erc.monash.edu.au:hpc-team/ansible_cluster_in_a_box into fix_nat_server

Fix nat server to point iptables to use correct public interface name

- template the public interface so NAT Masquerade command goes to right interface
- public inteface name autogenerated by looking at route to 8.8.8.8
- ACCEPT command for private interface modified to use network CIDR. THis is hardcoded to M3 if not defined, so no impact on cluster_in_a_box roles. (Monarch and others will need to pass it as a parameter)
- Not sure if ACCEPT on private interface is used, as compute nodes point to mlx0 interface for routing

Fixed xorg.conf.j2 template

See merge request !150

added gpu role to generate combinations of xorg.conf

See merge request !149