Job scheduler
The queueing system on a traditional HPC cluster that decides when a submitted job runs. Eugo has no queue: you launch a cluster and dispatch work to it.
On a shared on-premises cluster a scheduler is unavoidable. Many users contend for one fixed pool of nodes, so jobs wait in a queue and a batch script describes what to run. Requesting compute per run removes the contention that made the queue necessary, which is why nothing in these courses involves writing a submission script. Eugo's scheduler places tasks onto nodes within a cluster you already have, which is a different job entirely.
FundamentalsDistributed compute
Related terms
- Scheduler: The component on the head node that decides which compute node runs each task, honoring the resources that task requested.
- HPC as a service (HPCaaS): High-performance computing consumed on demand rather than owned: request compute for one run, stop paying when it ends. No hardware, no scheduler to run.
- Cluster: A set of machines, one head node and one or more compute nodes, launched together to run distributed work.
- Head node: The machine in a cluster that coordinates work: it schedules tasks onto compute nodes and tracks their results.