Initial commit

cluster_setup/cloud_cluster_setup.md

+## Generate _ubuntu_ user SSH keys
+
+```
+ssh-keygen -t rsa -N "" -f $HOME/.ssh/id_rsa
+cat $HOME/.ssh/id_rsa.pub >> $HOME/.ssh/authorized_keys
+```
+
+## Install NFS
+
+### Master
+
+```
+sudo apt-get update
+sudo apt-get install nfs-kernel-server
+sudo cat '/home	10.0.0.0/24(rw,sync,no_root_squash,no_subtree_check)' >> /etc/exports
+sudo service nfs-kernel-server start
+```
+
+### Node
+
+```
+sudo apt-get update
+sudo apt-get install nfs-common
+sudo cat '10.0.0.8:/home    /home   nfs auto,noatime,nolock,bg,nfsvers=4,intr,tcp,actimeo=1800 0 0' >> /etc/fstab
+```
+
+
+## Install SLURM
+
+### Master
+
+```
+sudo apt-get install slurm-wlm
+sudo bash -c 'echo CgroupAutomount=yes >> /etc/slurm-llnl/cgroup.conf'
+sudo chown slurm:slurm /etc/slurm-llnl/cgroup.conf
+sudo cp /etc/munge/munge.key $HOME/
+```
+
+### Node
+
+```
+sudo apt-get install slurmd
+sudo bash -c 'echo CgroupAutomount=yes >> /etc/slurm-llnl/cgroup.conf'
+sudo chown slurm:slurm /etc/slurm-llnl/cgroup.conf
+sudo cp /home/ubuntu/munge.key /etc/munge/munge.key
+sudo service munge restart
+```

cluster_setup/slurm.conf

+ControlMachine=master-nfs
+ControlAddr=10.0.0.8
+#
+MpiDefault=none
+ProctrackType=proctrack/cgroup
+ReturnToService=1
+SlurmctldPidFile=/var/run/slurm-llnl/slurmctld.pid
+SlurmdPidFile=/var/run/slurm-llnl/slurmd.pid
+SlurmdSpoolDir=/var/lib/slurm-llnl/slurmd
+SlurmUser=slurm
+StateSaveLocation=/var/lib/slurm-llnl/slurmctld
+SwitchType=switch/none
+TaskPlugin=task/none
+#
+# SCHEDULING
+FastSchedule=1
+SchedulerType=sched/backfill
+SelectType=select/cons_res
+SelectTypeParameters=CR_CPU_Memory
+#
+# LOGGING AND ACCOUNTING
+AccountingStorageType=accounting_storage/filetxt
+AccountingStorageLoc=/var/log/slurm-llnl/accounting
+ClusterName=cluster
+JobAcctGatherType=jobacct_gather/linux
+SlurmctldLogFile=/var/log/slurm-llnl/slurmctld.log
+SlurmdLogFile=/var/log/slurm-llnl/slurmd.log
+AuthType=auth/munge
+
+# MEMORY LIMITS
+DefMemPerCPU=100
+MaxMemPerCPU=500
+MemLimitEnforce=yes
+KillWait=0
+
+# COMPUTE NODES
+NodeName=node-nfs NodeAddr=10.0.0.18 CPUs=2 ThreadsPerCore=1 RealMemory=4096 TmpDisk=19788
+PartitionName=swc Nodes=node-nfs Default=YES MaxTime=2 State=UP