torque_queues
**This is an old revision of the document!**
Queues Trestles/Razor
These torque scheduler queues are deprecated as the torque scheduler will be replaced by slurm and most razor 12-core nodes will be retired.
Razor general use queues are
| queue | CPU | memory/node | max PBS spec | max PBS time | notes |
|---|---|---|---|---|---|
| debug12core | 2x Intel X5670 2.93 GHz | 24GB | nodes=2:ppn=12 | walltime=0:0:30:00 | dedicated |
| med12core | 2x Intel X5670 2.93 GHz | 24GB | nodes=24:ppn=12 | walltime=3:00:00:00 | node pool shared |
| tiny12core | 2x Intel X5670 2.93 GHz | 24GB | nodes=24:ppn=12 | walltime=0:06:00:00 | node pool shared |
| debug16core | 2x Intel E5-2670 2.6 GHz | 32GB | nodes=2:ppn=16 | walltime=0:0:30:00 | dedicated |
| tiny16core | 2x Intel E5-2670 2.6 GHz | 32GB | nodes=18:ppn=16 | walltime=0:06:00:00 | node pool shared |
| med16core | 2x Intel E5-2670 2.6 GHz | 32GB | nodes=18:ppn=16 | walltime=3:00:00:00 | node pool shared |
| gpu16core | 2x Intel E5-2630V3 2.4 GHz/2xK40c | 64GB | nodes=1:ppn=16 | walltime=3:00:00:00 | gpu jobs only |
| mem512GB64core | 4x AMD 6276 2.3 GHz | 512GB | nodes=2:ppn=64 | walltime=3:00:00:00 | >64GB shared memory only |
| mem768GB32core | 4x Intel E5-4640 2.4 GHz | 768GB | nodes=2:ppn=32 | walltime=3:00:00:00 | >512 GB shared memory only |
| nebula | nebula cloud |
Production queues in quantity for most usage are tiny/med 12core/16core.
Trestles general use queues are (the first three queues are production queues in quantity)
| queue | CPU | memory/node | max PBS spec | max PBS time | notes |
|---|---|---|---|---|---|
| q10m32c | 4x AMD 6136 2.4 GHz | 64GB | nodes=4:ppn=32 | walltime=0:0:10:00 | or "qtraining" dedicated |
| q30m32c | 4x AMD 6136 2.4 GHz | 64GB | nodes=128:ppn=32 | walltime=0:0:30:00 | node pool shared |
| q06h32c | 4x AMD 6136 2.4 GHz | 64GB | nodes=128:ppn=32 | walltime=0:06:00:00 | node pool shared |
| q72h32c | 4x AMD 6136 2.4 GHz | 64GB | nodes=64:ppn=32 | walltime=3:00:00:00 | node pool shared |
| nebula | nebula cloud |
Production queues in quantity for most usage are q06h32c/q72h32c.
“node pool shared” on tiny/med or q30m/q06h/q72h means that the queues allocate jobs from a common pool of identical nodes, with some dedicated for the shorter queues.
For a complete listing of all defined queues and their properties on each cluster please use the qstat -q command.
torque_queues.1580323414.txt.gz · Last modified: 2020/01/29 18:43 by 127.0.0.1
Except where otherwise noted, content on this wiki is licensed under the following license: GNU Free Documentation License 1.3
