NICADD HPC cluster Nhpc/Sysadmin Duties

SysAdmin Duties

Long Term/As needed support - Frontend
- CRCD web site/Dashboard monitors (Sergey)
- PIs/Users communications - message of the day, mail lists (Dave)
Long term/As needed support - Backend
- OS Upgrades (Sergey/Dave)
- Proprietary software licenses (Dave/Andrew)
- System Access maintenance
  - SSL certificates (Dave)
  - VPN support (Andrew)
  - Network configuration (Dave)
  - System Security configuration/monitoring (Dave)
- Hardware maintenance (Dave/Andrew)
  - Compute node rebuilds (Dave)
  - Service nodes support - kvm-srv1; hpcutil, gaea-sn1, gaea-sn2, gaea-un1 (Dave)
  - HPE Support Contracts (Andrew)
  - HPE Repair tickets (Dave)
  - Physical system access at Swen Parson for repair/HP tech communication (Dave)
    - Failed Disk replacement (Dave)
Daily system support
- TORQUE/Moab (scheduling) configuration (Dave)
  - Troubleshooting assistance (why isn’t job running or reservation working?) (Dave)
  - Compute node reservations (Dave)
- System automation
  - CLI monitoring scripts, system watchdogs (Dave)
- LDAP (Dave)
  - Create users & groups (Dave)
  - Users and projects quotas
  - Troubleshoot login issues (Dave)
  - LDAP scripting (Dave)
- Syslog (Dave)
- XDMoD (Dave)
- Nagios/Ganglia monitoring (Dave)
- System troubleshooting (Dave)
System Backup
- DoIT central backup (Dave/Andrew)
- Snapshots to NICADD servers (Sergey)