‘shosts’ shows each Compute node’s information (processors, RAM memory etc.) on Andromeda.
To view the free compute nodes’ information on Andromeda, type:
[johnchris@l001 simple_stata]$ shosts -f
- A/I/O/T means Allocated/Idle/Other/Total
- Memory is in GB
- The default Partition has a ‘*’
NODELIST PARTITION CPUS(A/I/O/T) ALLOCMEM CPU_LOAD FREE_MEM AVAIL_FEATURES GRES GRES_USED
c001 shared* 48/0/0/48 144GB 44.69 128GB (null) (null) gpu:0
c002 shared* 48/0/0/48 185GB 48.08 99GB (null) (null) gpu:0
c003 shared* 48/0/0/48 23GB 48.03 156GB (null) (null) gpu:0
c004 shared* 44/4/0/48 15GB 48.03 160GB (null) (null) gpu:0
c005 shared* 48/0/0/48 97GB 12.02 162GB (null) (null) gpu:0
c006 shared* 48/0/0/48 97GB 12.02 160GB (null) (null) gpu:0
c007 shared* 48/0/0/48 97GB 12.02 160GB (null) (null) gpu:0
c008 shared* 48/0/0/48 97GB 12.01 160GB (null) (null) gpu:0
c009 shared* 48/0/0/48 97GB 12.05 160GB (null) (null) gpu:0
c010 shared* 48/0/0/48 185GB 48.09 106GB (null) (null) gpu:0
c011 shared* 48/0/0/48 185GB 48.09 62GB (null) (null) gpu:0
c012 shared* 48/0/0/48 185GB 48.09 128GB (null) (null) gpu:0
c013 shared* 40/8/0/48 120GB 54.50 162GB (null) (null) gpu:0
c014 shared* 48/0/0/48 185GB 48.08 132GB (null) (null) gpu:0
c015 shared* 47/1/0/48 116GB 15.18 133GB (null) (null) gpu:0
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.
c226 exclusive 0/0/64/64/64 90B 227GB 64c (null) gpu:0
g001 gpuv100 13/35/0/48 185GB 3GB (null) gpu:v100:4
g002 gpuv100 16/48/0/48 76GB 3GB (null) gpu:v100:4(IDX:0-3)
g004 gpua100 16/48/0/64 76GB 2GB (null) gpu:v100:4(IDX:0-3)
g005 gpua100 16/48/0/64 76GB 2GB (null) gpu:v100:4(IDX:0-3)
g006 gpua100 16/48/0/64 76GB 2GB (null) gpu:v100:4(IDX:0-3)
g008 gpua100 10/54/0/64 72GB 3GB (null) gpu:v100:4(IDX:0-3)
g011 gpua100 20/44/0/64 180GB 1GB (null) gpu:a100:4(IDX:0-3)
g012 gpua100 16/48/0/64 116GB 1GB (null) gpu:a100:4(IDX:0-3)
PARTITION NODELIST NODES(A/I/O/T) CPUS(A/I/O/T)
exclusive c[028-092,133-226] 137/2/20/159 7728/180/9136
gpua100 g[004-007,010-012] 7/0/0/7 106/342/0/448
gpuv100 g[001-002] 2/0/0/2 61/36/0/96
shared* c[001-027,093-132] 58/7/2/67 2926/802/12/3856| NODELIST | CPU nodes: c001 to c226, GPU node: g001 to g012 |
|---|---|
| PARTITION | Name of partitions: shared, exclusive, gpu100, gpuv100 |
| STATE | Possible states include: allocated, completing, down, drained, draining, fail, failing, future, idle |
| MEMORY | 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; TFor example: 40/24/0/64 |
| AVAIL_FEATURES REASON | None |