In almost all cases, do not specify a queue - the system will work out where to best place your job according to the resources requested
|Queue name||Job limit per user||Resource limits per job||Resource limit defaults||Purpose|
|route||Routing queue: jobs submitted without specifying a queue are processed here and routed to one of the other queues according to the resources requested.|
|s48||1000||168 hrs walltime, 1 node||1 hr walltime, 2GB memory, 1 core|
Single-node jobs (serial or multithreaded).
|p12||100||168 hrs walltime, 2+ nodes||1 hour walltime, 1 core per node|
This queue will not accept interactive jobs - you can use up to 2 nodes interactively for up to 4 hours via the interactive queue.
|interactive||2||4 hrs walltime, 2 full nodes||1 hr walltime, 1 core, 2GB memory|
High-priority interactive use, especially debugging. Interactive jobs go here by default.
Interactive jobs which do not meet the resource limits for this queue will go to the s48 queue, and consequently may take longer to start.
|cgsb-s||1000||168 hours walltime, 48 GB memory, 12 cores on a single node||12 hrs walltime, 1 core|
Long-running CGSB jobs. (see HPC Stakeholders)
Jobs needing more than 96 hours and submitted by CGSB users will be routed to this queue and scheduled on the CGSB-owned nodes
|sysadm||0||Maintenance reservations by system administrators: normal users do not have access to this queue|