Livermore Computing (LC) provides a large variety of High Performance Computing (HPC) clusters. Slurm is the batch scheduler and resource manager that schedules almost all LC clusters. Some LC clusters have been or are being transitioned to the Flux workload manager, including all El Capitan systems.

Almost all LC compute platforms have policies around job limits and queue usage. In addition to viewing this information on the web, users can run the joblimits command on an LC cluster.

Batch Schedulers and Workload Managers

LC has deployed, supported, and/or developed several tools to help in the scheduling of jobs and management of HPC workloads over its history.

Moab (deprecated)

In 2006, the NNSA Tri-Labs selected the Moab Workload Manager to be the standard batch system on clusters across all three labs it was used for over ten years. We have since switched to using Slurm and Flux as our current schedulers.

Slurm on TOSS 4

All of the LC clusters except the CORAL2 systems run Slurm as their scheduler and workload manager. Flux is also available and may be run as a guest workload manager by users inside of their Slurm allocation.

Flux and TOSS 4

The CORAL2 systems (Sierra, Tuolumne, rzAdams) and early access systems are using the Flux as their scheduler and workload manager.

The Batch System Primer provides an introduction to the concepts and terms used for running jobs on LC’s HPC clusters. From there, the links on the left provide the user guides to running jobs using Slurm and Flux.