1. Home
  2. Sonic Cluster
  3. Queuing System & Scheduler

Queuing System & Scheduler

Job Scheduler(SLURM):

Slurm (Simple Linux Utility for Resource Management) is an open-source job scheduler that allocates compute resources on clusters for queued researcher defined jobs. Slurm has been deployed at various national and international computing centers, and by approximately 60% of the TOP500 supercomputers in the world.

You can learn more about SLURM and its commands from the official Slurm website.

Queuing System:

When a job is submitted, it is placed in a queue. There are different queues available for different purposes. The user must select any one of the queues from the ones listed below which is appropriate for his/her computation need.

Slurm partitions are essentially different queues that point to collections of nodes. On Sonic  there is one partition:

  • long:¬†this partition has 14 compute nodes that have been set aside for running the longer jobs. This partition has no time limits.
Queue nameNo. of NodesNode listDefault walltime
(day-hrs:min)
Total No. of CPUs (threads)
long14sonic[1-14]no limit(inf)1344
NOTE: devel is the default partition
Sonic cluster doesn't have a "devel" partition and all nodes are in single partition "long"

Useful commands

Slurm CommandDescriptionSyntex
sbatchSubmit a batch serial or parallel job using slurm submit scriptsbatch slurm_submit_script.sub
srunRun a script or application interactivelysrun --pty -p test -t 10 --mem 1000 /bin/bash [script or app]
scancelKill a job by job id numberscancel 999999
squeueView status of your jobssqueue -u OR squeue -l
sinfoView the cluster nodes, partitions and node status informationsinfo OR sinfo -lNe
sacctCheck current job by id numbersacct -j 999999

Usage Guidelines

  • Users are supposed to submit jobs only through the scheduler.
  • Users are not supposed to run any job on the master node.
  • Users are not allowed to run a job by direct login to any compute node.
Was this article helpful to you? Yes No