*2 login nodes: syrah[144,256]

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 Syrah Job Limits

Hardware

There are 316 compute nodes. All compute nodes have dual socket 8-core Intel Xeon E5-2670 (2.6 GHz) for 16 cores/node & 64 GB memory/node. The nodes are connected via InfiniBand QDR (QLogic)

Scheduling

Jobs are scheduled per node. There are 2 node scheduling pools:

• pdebug—8 nodes (128 cores)
• pbatch—308 nodes (4928 cores), only batch use permitted.

   Syrah limits:
                              Max nodes/job   Max runtime
   -------------------------------------------------------
   pdebug                         4(*)       60 minutes
   pbatch                         128          16 hours
   -------------------------------------------------------

   Please limit standby jobs to 12 hours maximum.

(*) Please limit the use of pdebug to 4 nodes on a PER USER basis, not a PER JOB basis, to allow other users access.  Using more than the posted limit PER USER can result in job removal without notice. Please be a good neighbor, and be considerate of others utilizing the pdebug partition. Pdebug is scheduled using fairshare.  Also, do not use debug to run batch jobs.  Specifically, do not chain jobs to run one after the other during evenings and weekends.  Individuals who misuse the debug queue in this or any similar manner will be denied access to running jobs in the debug queue.

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