Skill: Job scheduling and resource management

Understanding of job schedulers and resource management to allocate compute resources effectively. This includes writing job submission scripts, understanding queue policies, optimising resource requests, and supporting fair and efficient use of shared HPC infrastructure.

Related skills

• Cluster management
• Parallel computing and usage of HPC systems

Tools

• Cgroups
• HTCondor
• Load Sharing Facility (LSF)
• Oracle Grid Engine
• Portable Batch System (PBS)
• Simple Linux Utility for Resource Management (SLURM)

Methodologies

• Job scheduling
• Load balancing