[slurm-users] Example 16 of CPU Management User and Administrator Guide does not work.

2019-11-20 Thread Uemoto, Tomoki
Hi, All I checked 'Example 16' of CPU Management User and Administrator Guide. However, the following message was output. task/cgroup: task[1] not enough Core objects (4 < 6), disabling affinity task/cgroup: task[3] not enough Core objects (4 < 6), disabling affinity task/cgroup: task[4] no

[slurm-users] node suspending not longer working in slurm-19.05.4

2019-11-20 Thread Bernd Melchers
Hi all, after upgrading from 19.05.3 to 19.05.4 none of the nodes are going into powerdown after becoming idle for four hours. The SuspendProgram is not longer involved by slurm. Any suggestions? slurm.conf: ... # Power Mangement SuspendTime=14400 SuspendTimeout=900 SuspendRate=3 ResumeRate=40 Su

Re: [slurm-users] Example 16 of CPU Management User and Administrator Guide does not work.

2019-11-20 Thread Mark Hahn
task/cgroup: task[1] not enough Core objects (4 < 6), disabling affinity What does this message mean? ... | [root@ohpc137pbsop-sms ~]# grep ^NodeName /etc/slurm/slurm.conf | NodeName=ohpc137pbsop-c001 Sockets=2 CoresPerSocket=4 ThreadsPerCore=1 Procs=8 State=UNKNOWN could you try CoresPerSocke

Re: [slurm-users] Example 16 of CPU Management User and Administrator Guide does not work.

2019-11-20 Thread Uemoto, Tomoki
Thank you. I now have a deeper understanding of this topic. Looks like there is no problem without 'cpu_bind -v' mode. [test@ohpc137pbsop-sms ~]$ srun --nodes=1-1 --ntasks=6 --cpu-bind=cores cat /proc/self/status | grep Cpus_allowed_list Cpus_allowed_list: 0-1,12,24-25,36 Cpus