Initial Commit

create_cluster.sh

@@ -0,0 +1,91 @@
+#!/bin/bash
+
+set -ax
+
+project_name="hpc"
+project="--project ${project_name}"
+lxc="lxc ${project}"
+
+lxc_exec="${lxc} exec"
+
+lxc project create ${project_name}
+
+${lxc} profile edit default < lxd_profile.yaml
+
+ppa="ppa:nuccitheboss/experimental-hpc"
+
+mgmt_node="slurm-master"
+
+${lxc} launch ubuntu:jammy ${mgmt_node}
+sleep 5
+${lxc_exec} ${mgmt_node} -- add-apt-repository -y ${ppa}
+${lxc_exec} ${mgmt_node} -- apt -y install slurm-wlm
+${lxc} file push munge.key ${mgmt_node}/etc/munge/
+${lxc_exec} ${mgmt_node} -- systemctl restart munge
+${lxc_exec} ${mgmt_node} -- systemctl enable munge
+
+${lxc} file push slurm.conf ${mgmt_node}/etc/slurm/
+${lxc_exec} ${mgmt_node} -- mkdir /var/spool/slurmctld
+${lxc_exec} ${mgmt_node} -- chown slurm:slurm /var/spool/slurmctld
+${lxc_exec} ${mgmt_node} -- systemctl start slurmctld
+${lxc_exec} ${mgmt_node} -- systemctl enable slurmctld
+${lxc_exec} ${mgmt_node} -- systemctl start slurmd
+${lxc_exec} ${mgmt_node} -- systemctl enable slurmd
+
+nodes=5
+
+for i in `seq 1 ${nodes}`
+do
+  node=slurm-comp0${i}
+
+  ${lxc} launch ubuntu:jammy ${node}
+  sleep 5
+  ${lxc_exec} ${node} -- add-apt-repository -y ${ppa}
+  ${lxc_exec} ${node} -- apt -y install slurmd
+  ${lxc} file push munge.key ${node}/etc/munge/
+  ${lxc_exec} ${node} -- systemctl restart munge
+  ${lxc_exec} ${node} -- systemctl enable munge
+
+  ${lxc} file push slurm.conf ${node}/etc/slurm/
+  ${lxc_exec} ${node} -- systemctl start slurmd
+  ${lxc_exec} ${node} -- systemctl enable slurmd
+done
+
+tmp_hosts=$(mktemp)
+
+cat > ${tmp_hosts} << EOF
+127.0.0.1 localhost
+
+# The following lines are desirable for IPv6 capable hosts
+::1 ip6-localhost ip6-loopback
+fe00::0 ip6-localnet
+ff00::0 ip6-mcastprefix
+ff02::1 ip6-allnodes
+ff02::2 ip6-allrouters
+ff02::3 ip6-allhosts
+
+EOF
+
+addresses=$(${lxc} list --format json | jq -rc '.[] | select(.name | contains("slurm")) | [.name,.state.network.eth0.addresses[].address]')
+
+for line in ${addresses}
+do
+
+  name=$(echo $line | jq -rc .[0])
+  ipv4=$(echo $line | jq -rc .[1])
+
+  echo ${ipv4} ${name} >> ${tmp_hosts}
+
+done
+
+for line in ${addresses}
+do
+
+  name=$(echo $line | jq -rc .[0])
+
+  ${lxc} file push ${tmp_hosts}  ${name}/etc/hosts
+  ${lxc_exec} ${name} -- sudo systemctl restart slurmd
+
+done
+
+${lxc_exec} ${mgmt_node} -- sudo systemctl restart slurmctld

lxd_profile.yaml

@@ -0,0 +1,9 @@
+devices:
+  eth0:
+    name: eth0
+    network: lxdbr0
+    type: nic
+  root:
+    path: /
+    pool: virtual
+    type: disk

slurm.conf

@@ -0,0 +1,148 @@
+# slurm.conf file generated by configurator.html.
+# Put this file on all nodes of your cluster.
+# See the slurm.conf man page for more information.
+#
+ClusterName=cluster
+SlurmctldHost=slurm-master
+#SlurmctldHost=
+#
+#DisableRootJobs=NO
+#EnforcePartLimits=NO
+#Epilog=
+#EpilogSlurmctld=
+#FirstJobId=1
+#MaxJobId=67043328
+#GresTypes=
+#GroupUpdateForce=0
+#GroupUpdateTime=600
+#JobFileAppend=0
+#JobRequeue=1
+#JobSubmitPlugins=lua
+#KillOnBadExit=0
+#LaunchType=launch/slurm
+#Licenses=foo*4,bar
+#MailProg=/bin/mail
+#MaxJobCount=10000
+#MaxStepCount=40000
+#MaxTasksPerNode=512
+MpiDefault=none
+#MpiParams=ports=#-#
+#PluginDir=
+#PlugStackConfig=
+#PrivateData=jobs
+ProctrackType=proctrack/cgroup
+#Prolog=
+#PrologFlags=
+#PrologSlurmctld=
+#PropagatePrioProcess=0
+#PropagateResourceLimits=
+#PropagateResourceLimitsExcept=
+#RebootProgram=
+ReturnToService=1
+SlurmctldPidFile=/var/run/slurmctld.pid
+SlurmctldPort=6817
+SlurmdPidFile=/var/run/slurmd.pid
+SlurmdPort=6818
+SlurmdSpoolDir=/var/spool/slurmd
+SlurmUser=slurm
+#SlurmdUser=root
+#SrunEpilog=
+#SrunProlog=
+StateSaveLocation=/var/spool/slurmctld
+SwitchType=switch/none
+#TaskEpilog=
+TaskPlugin=task/affinity,task/cgroup
+#TaskProlog=
+#TopologyPlugin=topology/tree
+#TmpFS=/tmp
+#TrackWCKey=no
+#TreeWidth=
+#UnkillableStepProgram=
+#UsePAM=0
+#
+#
+# TIMERS
+#BatchStartTimeout=10
+#CompleteWait=0
+#EpilogMsgTime=2000
+#GetEnvTimeout=2
+#HealthCheckInterval=0
+#HealthCheckProgram=
+InactiveLimit=0
+KillWait=30
+#MessageTimeout=10
+#ResvOverRun=0
+MinJobAge=300
+#OverTimeLimit=0
+SlurmctldTimeout=120
+SlurmdTimeout=300
+#UnkillableStepTimeout=60
+#VSizeFactor=0
+Waittime=0
+#
+#
+# SCHEDULING
+#DefMemPerCPU=0
+#MaxMemPerCPU=0
+#SchedulerTimeSlice=30
+SchedulerType=sched/backfill
+SelectType=select/cons_tres
+#
+#
+# JOB PRIORITY
+#PriorityFlags=
+#PriorityType=priority/basic
+#PriorityDecayHalfLife=
+#PriorityCalcPeriod=
+#PriorityFavorSmall=
+#PriorityMaxAge=
+#PriorityUsageResetPeriod=
+#PriorityWeightAge=
+#PriorityWeightFairshare=
+#PriorityWeightJobSize=
+#PriorityWeightPartition=
+#PriorityWeightQOS=
+#
+#
+# LOGGING AND ACCOUNTING
+#AccountingStorageEnforce=0
+#AccountingStorageHost=
+#AccountingStoragePass=
+#AccountingStoragePort=
+#AccountingStorageType=accounting_storage/slurmdbd
+#AccountingStorageUser=
+#AccountingStoreFlags=
+#JobCompHost=
+#JobCompLoc=
+#JobCompParams=
+#JobCompPass=
+#JobCompPort=
+JobCompType=jobcomp/none
+#JobCompUser=
+#JobContainerType=job_container/none
+JobAcctGatherFrequency=30
+JobAcctGatherType=jobacct_gather/none
+SlurmctldDebug=info
+SlurmctldLogFile=/var/log/slurmctld.log
+SlurmdDebug=info
+SlurmdLogFile=/var/log/slurmd.log
+#SlurmSchedLogFile=
+#SlurmSchedLogLevel=
+#DebugFlags=
+#
+#
+# POWER SAVE SUPPORT FOR IDLE NODES (optional)
+#SuspendProgram=
+#ResumeProgram=
+#SuspendTimeout=
+#ResumeTimeout=
+#ResumeRate=
+#SuspendExcNodes=
+#SuspendExcParts=
+#SuspendRate=
+#SuspendTime=
+#
+#
+# COMPUTE NODES
+NodeName=slurm-master,slurm-comp0[1-5] CPUs=1 State=UNKNOWN
+PartitionName=debug Nodes=slurm-comp0[1-5] Default=YES MaxTime=INFINITE State=UP