Page History

...

To display a list of fairshare and usage for accounts, use sshare -la. This command will display fairshare information across all account in the SLURM cluster.

[george@umhpcgeorge@login01]$ sshare -la

             Account       User  RawShares  NormShares    RawUsage   NormUsage  EffectvUsage  FairShare    LevelFS                    GrpTRESMins                    TRESRunMins
-------------------- ---------- ---------- ----------- ----------- ----------- ------------- ---------- ---------- ------------------------------ ------------------------------
free                     george          1    0.500000    12805068    0.872021      0.872891   0.250000   0.572809                                cpu=0,mem=0,energy=0,node=0,b+

...

Each core allocated for non-multithreaded jobs will be treated as 2 CPUs and no multiple multithreaded jobs should fall within the same core. All jobs will be billed based on the highest amount of resource type allocated. For examples:

1. A non-multithreaded, 48 cores and 32 GB memory job running in cpu-epyc:
   1. The billing value of each type of resources can be breakdown as follow:
      1. CPU = 96 (2 CPUs per core, 48 cores) * 375 (Billing value per CPU in cpu-epyc) = 36000 RawUsage per minute
      2. Memory = 32 (32 GB memory) * 150 (Billing value per GB memory) = 4800 RawUsage per minute
   2. Therefore, the job will be billed for 36000 RawUsage per minute as 48 cores has the highest RawUsage per minute compared to 32 GB memory.
   A multithreaded, 32 CPUs and 240 GB memory job running in cpu-opteron:
   1. The billing value of each type of resources can be breakdown as follow:CPU = 32 (32 CPUs) * 468.75 (Billing value per CPU in cpu-opteron) = 15000 RawUsage per minute
   2. Memory = 240 (240 GB memory) * 125 (Billing value per GB memory in cpu-opteron) = 30000 RawUsage per minute
   Thus, the job will be billed for 30000 RawUsage per minute as 240 GB memory has the highest RawUsage  per minute compared to 32 CPUs.
2. A non-multithreaded, 2 cores, 64 GB memory and 2 v100s GPUs job running in gpu-v100s:
   1. The billing value can be breakdown as follow:
      1. CPU = 4 (2 CPUs per core, 2 cores) * 1437.5 (Billing value per CPU in gpu-v100s) = 5750 RawUsage  per minute
      2. Memory = 64 (64 GB memory) * 500 (Billing value per GB memory in gpu-v100s) = 32000 RawUsage  per minute
      3. GPU = 2 (2 GPUs) * 46000 (Billing value per GPU in gpu-v100s) = 92000 RawUsage  per minute
   2. Hence, the job will be billed for 92000 RawUsage  per minute as 2 v100s GPUs has the highest RawUsage  per minute among 2 CPUs and 64 GB memory.

...