‘shosts’ shows each Compute node’s information (processors, RAM memory etc.) on Andromeda.
To view the free compute nodes’ information on Andromeda, type:
[johnchris@andromeda]$ shosts -f
- A/I/O/T means Allocated/Idle/Other/Total
- Memory is in GB
- The default Partition has a ‘*’
NODELIST CPUS(A/I/O/T) CPU_LOAD FREE_MEM TOTAL_MEM GRES_USED STATE
c001 44/0/4/48 52.08 21GB 187GB N/A allocated+drain+rese
c002 0/0/48/48 8.23 10GB 187GB N/A idle+drain+reserved
c003 0/0/48/48 8.01 173GB 187GB N/A idle+drain
c004 0/0/48/48 8.07 173GB 187GB N/A idle+drain
c005 44/0/4/48 52.21 1GB 187GB N/A allocated+drain+rese
c006 0/0/48/48 8.12 173GB 187GB N/A idle+drain
c007 0/0/48/48 8.02 173GB 187GB N/A idle+drain
c008 0/0/48/48 8.13 173GB 187GB N/A idle+drain
c009 44/0/4/48 52.13 3GB 187GB N/A allocated+drain+rese
c010 0/48/0/48 8.02 145GB 187GB N/A idle+reserved
c011 0/0/48/48 8.21 173GB 187GB N/A idle+drain
c012 0/0/48/48 8.03 173GB 187GB N/A idle+drain
c013 0/0/48/48 8.13 173GB 187GB N/A idle+drain
c014 44/4/0/48 52.10 110GB 187GB N/A allocated+reserved
c015 44/4/0/48 52.05 108GB 187GB N/A allocated+reserved
c016 0/0/48/48 8.03 173GB 187GB N/A idle+drain
c017 0/48/0/48 8.19 171GB 187GB N/A idle+reserved
c019 44/0/4/48 52.11 5GB 187GB N/A allocated+drain+rese
We recommend that users use the -f option to check compute node information before submitting jobs to the cluster. This option lists free memory and available processors for each compute node on Andromeda, providing a useful reference for users.
g013 0/64/0/64 8.07 474GB 250GB gpu:a100:0(IDX:N/A) idle
g014 0/64/0/64 8.03 471GB 250GB gpu:a100:0(IDX:N/A) idle
g015 0/64/0/64 8.05 471GB 250GB gpu:a100:0(IDX:N/A) idle
g016 0/64/0/64 8.04 471GB 250GB gpu:a100:0(IDX:N/A) idle
g017 0/64/0/64 8.05 472GB 250GB gpu:a100:0(IDX:N/A) idle
g018 0/64/0/64 8.07 471GB 250GB gpu:a100:0(IDX:N/A) idle
g019 0/64/0/64 8.04 308GB 250GB gpu:a100:0(IDX:N/A) idle
gb001 0/64/0/64 8.01 1896GB 2014GB gpu:h200:0(IDX:N/A) idle
PARTITION NODELIST NODES(A/I/O/T) CPUS(A/I/O/T)
interactive c[001-092],g[001-009] 55/6/40/101 2119/809/2032/4960
short* c[001-226],cb[001-020],g[001-019],gb001 195/21/50/266 9013/4475/2672/16160
medium c[001-221],cb[001-020],g[001-019],gb001 192/19/50/261 9000/4168/2672/15840
long c[001-221],cb[001-020],g[001-019],gb001 192/19/50/261 9000/4168/2672/15840
| NODELIST | CPU nodes: c001 to c226, GPU node: g001 to g019, gb001 |
|---|---|
| PARTITION | Name of partitions: short, medium, long, interactive |
| STATE | Possible states include: allocated, completing, down, drained, draining, fail, failing, future, idle |
| TOTAL_M | Total RAM memory for the Compute node: 250GB, 185GB and 495GB |
| FREE_MEM | Free RAM memory available on the compute node |
| CPUS(A/I/O/T) | A: Allocated; I: Idle; O; T For example: 40/24/0/64 |
| AVAIL_FEATURES REASON | None |
| CPU_LOAD | Total CPU usage |