SLURM 是否支持同时在一个节点上运行多个作业？

Question

Our computer cluster runs slurm version 15.08.13 and mpich version is 3.2.1 . My question is, could Slurm support multiple jobs running on one node at the same time? Our computer cluster has 16 cores cpu per node. We want to run two jobs at the same time on one node, each job uses 8 cores.

We have found that if a job uses all of the cpu cores for one node, the state of node becomes "allocated". If a job uses only part of the cpu cores for one node, the state of node becomes "mixed", but subsequent jobs can only be queued and the state of job is "pending".

Our order for submitting an job is as follows:

 srun -N1 -n8 testProgram

So, does Slurm support running multiple jobs on one node at the same time? Thanks.

Answer 1

Yes, provided it was configured with SelectType=select/cons_res , which does not seem to be the case on your system. You can check with show config | grep Select show config | grep Select . See more information here

Answer 2

Yes, you need to set SelectType=select/cons_res or SelectType=select/cons_tes and SelectTypeParameters=CR_CPU_Memory The difference between cons_res and cons_tes is that cons_tres adds GPUs support.