Job-submission queues and charges

Calculating charges | Checking and managing charges

Most of the Cheyenne batch queues are for exclusive use, and jobs are charged for all 36 cores on each node that is used. Jobs in the shared use "share" queue are charged only for the cores that are used.

The "regular" queue, which has a 12-hour wall-clock limit, meets most users' needs for running batch jobs.

See this page for information on running Geyser and Caldera jobs.

Queue name Priority order Wall clock (hours) Description
premium 1 12 Jobs are charged at 150% of the regular rate.
regular 2 12 Most production batch jobs run in this queue; also accepts interactive jobs.
economy 3 12 Production batch jobs charged at 70% of the regular rate.
share NA 6 Interactive and serial batch use for debugging and other tasks on a single, shared, 128-GB node. An individual job can use up to 18 cores. A user can run multiple jobs in the share queue concurrently if the total number of cores they require is no more than 18. Additional jobs that the user submits remain in the queue to run later.

Using MPT in share queue jobs requires additional commands in your batch script. See this page for details.

Some additional queues on the system are for dedicated purposes and accessible only to authorized users.


Calculating charges

Exclusive nodes

Charges for use of Cheyenne are calculated in terms of core-hours. Jobs run in Cheyenne queues other than "share" are charged for exclusive use of the nodes by this formula:

wall-clock hours × nodes used × cores per node

Number of nodes used

Your batch script indicates how many Cheyenne nodes your job will use. In this example, you have selected 2 nodes, each of which has 36 cores. Your job will be charged for the use of 72 cores.

#PBS -l select=2:ncpus=36:mpiprocs=36

Shared nodes

Charges for jobs that you run on a shared node are calculated by this formula.

core-seconds/3600

Checking and managing charges

Cheyenne users can check computing and storage charges through the CISL Systems Accounting Manager (SAM).

If you have concerns about using your allocation most efficiently, contact CISL for guidance. Sometimes jobs can be configured to make better use of the processors, and you may be able to save by using a less expensive queue.

We can refund core-hours if system failures cause jobs to fail and the failed jobs are reported promptly. To request a refund, send job details to cislhelp@ucar.edu. Include the date of the failure, Job ID, project code, and what system problem you suspect caused the job to fail. Technical limitations prevent us from verifying refund eligibility for jobs more than seven days old.