[root@rocks7 ~]# slurmd -C
NodeName=rocks7 slurmd: Considering each NUMA node as a socket
CPUs=32 Boards=1 SocketsPerBoard=4 CoresPerSocket=8 ThreadsPerCore=1
RealMemory=64261
UpTime=15-21:30:53
[root@rocks7 ~]# scontrol show node rocks7
NodeName=rocks7 Arch=x86_64 CoresPerSocket=1
CPUAlloc=0 CP
On Sunday, 29 April 2018 2:34:09 AM AEST Mahmood Naderan wrote:
> [root@rocks7 ~]# sinfo --list-reasons
> REASON USER TIMESTAMP NODELIST
> Low socket*core*thre root 2018-04-19T16:46:39 rocks7
slurmd thinks that "rocks7" doesn't have enough hardware resources to m
[root@rocks7 ~]# sinfo --list-reasons
REASON USER TIMESTAMP NODELIST
Low socket*core*thre root 2018-04-19T16:46:39 rocks7
Regards,
Mahmood
On Sat, Apr 28, 2018 at 6:01 PM, Chris Samuel wrote:
> On Saturday, 28 April 2018 7:58:08 PM AEST Mahmood Naderan wrote
On Saturday, 28 April 2018 7:58:08 PM AEST Mahmood Naderan wrote:
> I see that the state of the frontend is Drained. Is that the default
> state?
Probably not. What does "sinfo --list-reasons" say?
--
Chris Samuel : http://www.csamuel.org/ : Melbourne, VIC
Hi again
I see that the state of the frontend is Drained. Is that the default
state? The following line
PartitionName=OTHERS AllowAccounts=em1 Nodes=compute-0-[2-3],rocks7
Should include all core numbers of all nodes. The computes are set to
idle, but the frontend is drained.
Regards,
Mahmood
