There are three queues available on Nautilus, computation, analysis and HPSS. The computation queue is the default. The analysis queue must be requested explicitly (-q analysis) and should only be used when performing data analysis activities (R, IDL, VisIt, Matlab, Kepler, VNC, etc.). As Nautilus is considered primarily an analysis resource rather than a computing resource, jobs in the analysis queue are allowed to preempt those in the computation queue. Job preemption is currently implemented by requeuing the preempted jobs for later execution. For information on using the HPSS queue on Nautilus please refer to the these general instructions.
Queues are used by the batch scheduler to aid in the organization of jobs. An individual user may have up to 5 jobs eligible to start at any one time (regardless of how many jobs may be already running), while an account may have a total of 10 jobs eligible to run across all the users charging against that account. Jobs in excess of these limits will not be considered for execution. Note that these limits apply to the number of jobs eligible to run, not the number of jobs running.
Job priority on Nautilus is based on the number of cores and wall clock time requested. Jobs with larger core counts are given the highest priority. While the scheduler is collecting nodes for larger jobs, those with short wall clock limits and small core counts may use those nodes temporarily without delaying the start time of the larger job.
Maximum walltimes for the queues are given in the following table:
| Queue | Max Walltime |
|---|---|
| computation | 06:00:00 |
| analysis | 24:00:00 |
| HPSS | 24:00:00 |
