Job Limits

Each LC platform is a shared resource. Users are expected to adhere to the following usage policies to ensure that the resources can be effectively and productively used by everyone. You can view the policies on a system itself by running:

news job.lim.MACHINENAME

Web Version of Tron Job Limits

Tron is an ASC visualization and data analysis resource for users of the Sierra Tri-Lab computer. When not in use for data visualization or analsyis in support of a current ATCC cycle, the system will run compute work.  Tron mounts the same file systems as Sierra.

There will be Visualization Dedicated Access Times (DAT) on short notice when needed.  When possible, 1 hour of advance notice will be provided users.

Tron jobs are scheduled through SLURM and jobs are scheduled per node. Tron has two scheduling pools;

• pvis—60 nodes (math)
• pbatch—84 nodes (math)

Scheduling

Pvis nodes are targeted for Sierra visualization and data analysis.

Pbatch nodes are for postprocessing and other compute work.

Pools               Max nodes/job       Max runtime
---------------------------------------------------
pvis                     24              unlimited
pbatch                   24              24 hours
---------------------------------------------------

NOTE: Jobs in pvis WILL be killed if  they do not meet this criteria;

      1. run in a valid visualization bank provided to current ATCC users on Sierra

      OR

      2. run in standby

While there are currently no time limits for pvis, there may be limits established per user account or per bank. If needed, more restrictive limits will be established.

Hardware

• Intel Cascade Lake 2.9GHz cores
• Mellanox EDR Interconnect
• 32 cores/node
• 384GB memory/node

Documentation

• Linux Clusters Tutorial Part One | Linux Clusters Part Two
• Slurm Tutorial (formerly Slurm and Moab)

Contact

Please call or send email to the LC Hotline if you have questions. LC Hotline | phone: (925) 422-4531 | email: lc-hotline@llnl.gov