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 RZWhippet

There are two login nodes, and 36 pdebug (interactive) nodes (no batch nodes). Each node is based on Intel Sapphire Rapids processor with 56 cores per socket, 2 sockets per node, and 256 GB DDR5 memory.

There is 1 scheduling pool:

• pdebug—4032 cores (36 nodes)

Pool                Max cores/job       Max runtime
   ---------------------------------------------------
   pdebug               336 (*)          4 hours (*)
   ---------------------------------------------------

Scheduling

RZWhippet jobs are scheduled using FLUX. SLURM is not used on this partition. Jobs are scheduled per core. Some SLURM commands such as sxterm, sinfo, and squeue are available upon loading the module flux_wrappers. Scheduling is not technically enforced so users are expected to monitor their own behavior and keep themselves within the
current limits while following the policies written below:

Users will not compile on the login nodes. During daytime hours a user can have a maximum of 336 processors with a runtime of up to 4 hours in the queue during the day with the following exception:

(*) = An occasional job for debugging that takes 337-560 processors for a maximum of one hour can be run as long as it is the user's only job in the queue.

• Daytime is 0800-2000 Mondays-Fridays not including holidays.
• No production runs allowed, only development and debugging.
• Users will avoid computationally intensive work on the login node.
• We are all family and expect developers to play nice. However if someone's job(s) have taken over the machine:
  • Call them or send them an email.
  • Call Ines Heinz at 3-7900 and she will call them and/or kill the job.
  • Call Ines's backup (Ellen at 2-4691)and she will get the job killed.
• This approach will be revisited later and additional limits will be set if necessary. If someone monopolizes the machine, developers can always shift to other RZ resources.

Documentation

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

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