Administrivia
From UF HPC Wiki
Contents |
Description
Basically this is a page for the administrators of the cluster to put links to things that they need in order to maintain the cluster
Links
- Shutdown Activities
- Common Commands
- Scripts
- System configurations
- System mirror - Create a system mirror using mdadm (software raid)
- Torque - Adding/removing nodes
- TorqueHowto - General instructions for building and configuration of Torque
- TorqueHPC - Specific details regarding Torque at the UF HPC Center
- TargetingNodes - How to target nodes with batch jobs in Torque
- Moab - Link to how to create reservations
- Lustre - Debugging Lustre
- IB HCA Firmware - Check firmware information on IB cards
- Nagios - Patches made to Nagios
- Shutdown - Changes made during shutdown
- HPCifyingNodes - What we do to a stock distribution
- Power Connections
- Image Maintenance - How we maintain our images
- Adding New Nodes - How to add nodes to our cluster
Software Configuration
Virtualization
File Systems
- Root Mirror - How to mirror a root filesystem
Debugging
- Mcelog
- DIMM Replacement
- Mysql
- IBIS - tcl shell for IB MADS
Currently Installed Hardware Info
- Asus K8N-DRE Motherboard
- Tyan Thunder s4881 Motherboard
- Tyan Thunder s2892 Motherboard
- Tyan S3992 (Tiger K8SSA, Barcelona Node)
- Xyratek 4900F Storage
- Falcon III RAID storage chassis (Raid Inc.)
- Sentry Smart CDU
Systems
Troubleshooting
- DIMM Replacement - Notes on replacing troublesome memory on the cluster
- Software RAID - Notes on recovering a software RAID
- Ipmi - IPMI Instructions
Procedures
- Account Creation - Notes on creating an account
