Commits · f381488d1c2036199347750745bbe8cead1f1df8 · hpc-team / HPCasCode

Jun 22, 2018
- Update smb.conf - Remove min_clien_protocol=SMB2 · 1bb4492e
  Trung Nguyen authored 6 years ago
  
  Former-commit-id: 1d598771
  1bb4492e
- Edit smg.conf to remove default workgroup set to Monash · bec8c630
  Trung Nguyen authored 6 years ago
  
  Former-commit-id: b2636288
  bec8c630
- Add smb_conf role · fb4e5d9f
  Trung Nguyen authored 6 years ago
  
  Former-commit-id: 5f327898
  fb4e5d9f
Jun 07, 2018
- Updated create-dev-uvm.sh · 84155f94
  Jafar Lie authored 6 years ago
  
  Former-commit-id: 4623bc76
  84155f94
- systemd unit file to fix uvm · 753a2605
  Jafar Lie authored 6 years ago
  
  Former-commit-id: b82fd0f8
  753a2605
Jun 06, 2018
- rmmod various nvidia components before attempting an install: · 48355612
  Chris Hines authored 6 years ago
  
  Former-commit-id: 0bf2b86e
  48355612
Jun 05, 2018
- don't use the output of nvidia-smi directly, pass it through a map defined in vars · 782ce123
  Chris Hines authored 6 years ago
  
  Former-commit-id: a834e7ec
  782ce123
- nvidia-probe.py should exit 1 if there is an error · 7fa0e492
  Chris Hines authored 6 years ago
  
  Former-commit-id: a45849c9
  7fa0e492
May 21, 2018
- Clear pending yum transaction before installing extra pkgs · 1c4698cf
  Trung Nguyen authored 6 years ago
  
  Former-commit-id: 25583100
  1c4698cf
May 18, 2018
- Fixed repos paths · b3b45176
  Trung Nguyen authored 6 years ago
  
  Former-commit-id: 538f8bba
  b3b45176
May 17, 2018
- Restore nvidia installation · c630343f
  Gin Tan (Monash University) authored 6 years ago
  
  Former-commit-id: 684c0470
  c630343f
May 15, 2018
- Update roce_mode.service · f5a3c808
  Gin Tan authored 6 years ago
  
  Former-commit-id: c6661587
  f5a3c808
- full path to cma_roce_mode · 62f84205
  Chris Hines authored 6 years ago
  
  Former-commit-id: 713b331d
  62f84205
May 14, 2018
- create a systemd service file to force the roce mode on mellanox files to RoCE v1 on boot · 5ad8e5ea
  Chris Hines authored 6 years ago
  
  Former-commit-id: 658b7de2
  5ad8e5ea
May 11, 2018
- Revert "Merge branch 'update' into 'master'" · 3757e031
  Chris Hines authored 6 years ago
  
  This reverts merge request !167 Former-commit-id: 23b2f03e
  3757e031
Apr 25, 2018
- Typo · 164133aa
  Gin Tan (Monash University) authored 6 years ago
  
  Former-commit-id: f788b928
  164133aa
Apr 24, 2018
- Added missing rpm for nvidia drivr install · 903a4cb2
  Gin Tan (Monash University) authored 6 years ago
  
  Former-commit-id: 02e2a3f3
  903a4cb2
Apr 23, 2018
- new role to clean out /var/crash before and upgrade · a202f08c
  Chris Hines authored 6 years ago
  
  Former-commit-id: cc901a79
  a202f08c
Apr 13, 2018
- Adding driver installation with yum · e6d32e55
  Gin Tan (Monash University) authored 6 years ago
  
  Former-commit-id: 5cc65913
  e6d32e55
- Use yum to install nvidia driver · ca9128c4
  Gin Tan (Monash University) authored 6 years ago
  
  Former-commit-id: b8afca88
  ca9128c4
Mar 29, 2018
- update the mellanox driver, also update the reboot procedure · 4aba2730
  Chris Hines authored 6 years ago
  
  Former-commit-id: d518678c
  4aba2730
- changes to the config_repos role so hopefully we can upgrade cleanly without... · a6440ac4
  Chris Hines authored 6 years ago
  
  changes to the config_repos role so hopefully we can upgrade cleanly without reinserting the base repos Former-commit-id: 2c9accd0
  a6440ac4
Mar 19, 2018
- remove the faulty cleanup_x role · e59f9c2b
  Chris Hines authored 7 years ago
  
  Former-commit-id: fa156ea5
  e59f9c2b
Mar 16, 2018
- updated slurm epilog for X clean up · 69b607b4
  Jafar Lie authored 7 years ago
  
  Former-commit-id: 1cd81921
  69b607b4
Mar 15, 2018

M3 has decided to change where we store some parts of slurm, in particular... · b27a7fab

Chris Hines authored 7 years ago

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


Former-commit-id: e6eb57fb

b27a7fab

Mar 14, 2018
- Adding option to disable KMEM in cgroup · 37e5b2fc
  Gin Tan (Monash University) authored 7 years ago
  
  Former-commit-id: aac097c0
  37e5b2fc
- update the unit file for slurmdbd to respect the directory we want the pid to go to · 11d527a5
  Chris Hines authored 7 years ago
  
  Former-commit-id: ce047d0c
  11d527a5
Mar 13, 2018
- allow use of a ldap readonly server for failover (but don't mandate it) · 6108584f
  Chris Hines authored 7 years ago
  
  Former-commit-id: 59d9297a
  6108584f
Mar 07, 2018
- set the killmode so restarting slurmd doesn't cause the users jobs to be killed · 69423b9f
  Chris Hines authored 7 years ago
  
  Former-commit-id: e467abe0
  69423b9f
Jan 22, 2018
- Modifying the NHC check_fs_used $DF_FLAGS variable in sysconfig. · b0ca3069
  Gin Tan (Monash University) authored 7 years ago
  
  Refer to https://github.com/mej/nhc Former-commit-id: 87dd7d06
  b0ca3069
- Remove -a to make the check_fs_used work · 4d28d050
  Gin Tan (Monash University) authored 7 years ago
  
  Former-commit-id: fd0db365
  4d28d050
Jan 10, 2018

Make slurmctld and slurmdbd explicitily disabled on startup (rather than just... · 3626a83d

Chris Hines authored 7 years ago

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

Former-commit-id: adb46795

3626a83d

Jan 09, 2018
- Do not enabled slurmctld and slurmdbd in systemd · b1150a2a
  Gin Tan (Monash University) authored 7 years ago
  
  Former-commit-id: b5466172
  b1150a2a
Jan 03, 2018
- fix an error detecting the ppolicy and enable the auxposixgroup schema · 4c695a8e
  Chris Hines authored 7 years ago
  
  Former-commit-id: 7519d863
  4c695a8e
Dec 06, 2017
- template · 34fa0bf0
  Jafar Lie authored 7 years ago
  
  Former-commit-id: 2a302213
  34fa0bf0
- commit · 37956581
  Jafar Lie authored 7 years ago
  
  Former-commit-id: 7a126398
  37956581
Dec 05, 2017

Updating slurmdbd logrotate service file · 3469c77d
Gin Tan authored 7 years ago
```
Former-commit-id: 07342fe0
```
3469c77d

Modified the iptables.j2 file to: · cf3a78f5

Simon Michnowicz authored 7 years ago

- 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


Former-commit-id: 93dc59ba

cf3a78f5

Nov 27, 2017
- clean up X script and cron install · b2dbbd6a
  Jafar Lie authored 7 years ago
  
  Former-commit-id: aa5a5dec
  b2dbbd6a
- Fixed xorg.conf.j2 template · 95a00d45
  Jafar Lie authored 7 years ago
  
  Former-commit-id: eab73154
  95a00d45