The new Juno cluster is now available to the test users only. Please, create a request if you want to participate. The system is currently composed of 216 CPUs. The system is running the latest CentOS 7.3 Linux operating system on x01-x10 nodes and the Centos 6.9 Linux operating system on u14 node. The login node name is juno. It's a CentOS 7.3 host. The all cluster nodes have access to Isilon solisi File system. The CentOS 7.3 nodes have access to GPFS storage cluster named luna.
The Juno cluster uses LSF (Load Sharing Facility) 10.1 SP6 from IBM to schedule jobs. The default LSF queue, ‘sol_new’, includes all Juno compute nodes.
LSF 10.1 makes use of Linux control groups (cgroups) to limit the CPU cores and memory that a job can use. The goal is to isolate the jobs from each other and prevent them from consuming all the resources on a machine. All LSF job processes are controlled by the Linux cgroup system. If the job processes on a host use more memory than it requested, the job will be terminated by the Linux cgroup memory sub-system.
Memory is consumable resource in GB per slot (-n). All jobs should specify Walltime (-W), otherwise the default Walltime 6 hours will be used. LSF will terminate the job if it exceeds the Walltime. The maximum Walltime for sol_new queue is 744 hours.
The default operating system for Juno jobs is CentOS 6.9. User can request that job will run on the specific type of operating systems or any operating system.
To submit the job to default (CentOS 6.9) operating system:
bsub -n 1 -W 2 -R "rusage[mem=4]" |
To submit the job to CentOS 7.3 operating system:
bsub -n 1 -W 2 -R "rusage[mem=4]" -app anyOS -R"select[type==CentOS7]" |
To submit the job to any operating system:
bsub -n 1 -W 2 -R "rusage[mem=4]" -app anyOS |