A publication of the Office of Advanced Simulation & Computing, NNSA Defense Programs
NA-ASC-500-07—Issue 4
September 2007
Return to this issue’s stories
Moab Rollout at Sandia
The Moab workload manager from Cluster Resources, Inc., was adopted by ASC as a Tri-Lab standard job scheduler last August. The job scheduler manages user’s compute jobs, allocates resources, and gathers accounting data. Users would have a common set of job management tools, systems administrators would be able to share expertise, and management would gain a common set of reporting metrics. The initial goal of the Tri-Lab Workload Management Board was to ensure a uniform job scheduling environment across all new ASC platforms. However, with a site-wide license in place, all three labs are moving rapidly to deploy the Moab scheduler on existing systems too.
In August 2007, Sandia completed the rollout of Moab on Red Storm, Red RoSE, Black RoSE, and all of Sandia’s HPC capacity clusters, well ahead of schedule. Moab provides new capabilities for Red Storm, including the ability to request specific memory configurations for compute jobs, and the ability to effectively use backfill algorithms to run smaller, shorter jobs when nodes are available. These new capabilities have greatly improved the system management in support of the peak workload associated with the end of the fiscal year.
Tri-Labs Workload Management Board met at Sandia in July. During that meeting, the team agreed on near-term goals for FY08 based on having Moab running on the ASC platforms, including common usage reporting across ASC platforms, common management configurations, and a shared Web site on the classified network that will host Moab documentation.
DOE Privacy Disclaimer | Sandia Privacy Disclaimer
Last Modified September 27, 2007
Developed and maintained by Sandia National Laboratories for NA.114