SLURM
Very important to use slurm to schedule jobs on linux machines.
sbatch -w blog-t4gpu-01 -N1 -c2 --mem=5G ./script.sh
squeue
slurm_{job_id}.out
sbatch -N1 -c2 --mem=5G ./s3.sh
sbatch -N1 -c1 --mem=15G ./s3.sh- c: number of cpus
The output can be found in slurm_{job_id}.out file.
https://researchcomputing.princeton.edu/faq/how-to-kill-a-slurm-job
How to kill a Slurm job
The normal method to kill a Slurm job is:
$ scancel <jobid>
You can find your jobid with the following command:
$ squeue -u $USER
If the the job id is 1234567 then to kill the job:
$ scancel 1234567
For more cluster usage tips, see our comprehensive guide on Getting Started with the HPC Clusters at Princeton.
Comments
Post a Comment