# View overall cluster:
[]$ sinfo -eO "CPUs:8,Memory:9,Gres:14,NodeAIOT:16,NodeList:50"
CPUS MEMORY GRES NODES(A/I/O/T) NODELIST
96 1023575 (null) 6/19/0/25 mbcpu-[001-025]
96 765525 gpu:a30:8 0/8/0/8 mb-l40s mba30-[001-008]
96 idle 765525 0 96gpu:l40s:8 0.001/4/0/5 765525 761030 mbl40s-[001-005]
96 765525 mb-gpu:l40s:4 idle0/1/0/1 0 96 mbl40s-007
64 0.00 7655251023575 gpu:a6000:4 760728 mbl40s-007 0/1/0/1 mbmba6000-l40s001
48 idle 506997 0 96(null) 0.00 7655250/4/0/4 761452 wi001 wi[001-004]
56 inv-wildiris 1031000 gpu:a30:2 idle 0/1/0/1 48 0.00 wi005
50699796 505745 wi002 1281554 gpu:h100:8 1/3/2/6 inv-wildiris idle mbh100-[001-006]
0
# 48View a particular 0.00 506997 505726
wi003 (investment) partition:
[]$ sinfo -p inv-wildiris
PARTITION AVAIL TIMELIMIT NODES STATE NODELIST
inv-wildiris idleup infinite 0 485 0.00idle wi[001-005]
# View 506997compute nodes currently 505746
wi004 drained:
[]$ sinfo -R
REASON inv-wildiris idle 0USER 48 0.00TIMESTAMP 506997 505729 wi005 NODELIST
HW Status: Unknown - slurm inv-wildiris idle 0 562024-07-19T12:02:04 mbh100-001
Not responding slurm 0.00 1031000 1020610 2024-07-30T13:49:06 mbh100-006 |