diff --git a/aufgabe5.2/slurm/cgroup.conf b/aufgabe5.2/slurm/cgroup.conf new file mode 100644 index 0000000..a5bdbe7 --- /dev/null +++ b/aufgabe5.2/slurm/cgroup.conf @@ -0,0 +1,10 @@ +### +# Slurm cgroup support configuration file +### +CgroupAutomount=yes +CgroupReleaseAgentDir="/etc/slurm/cgroup" +CgroupMountpoint=/dev/cgroup +ConstrainCores=yes +ConstrainDevices=yes +AllowedDevicesFile=/etc/slurm/cgroup_allowed_devices_file.conf +# diff --git a/aufgabe5.2/slurm/cgroup_allowed_devices_file.conf b/aufgabe5.2/slurm/cgroup_allowed_devices_file.conf new file mode 100644 index 0000000..de85847 --- /dev/null +++ b/aufgabe5.2/slurm/cgroup_allowed_devices_file.conf @@ -0,0 +1,2 @@ +/dev/nvidiactl +/dev/nvidia0 diff --git a/aufgabe5.2/slurm/gres.conf b/aufgabe5.2/slurm/gres.conf new file mode 100644 index 0000000..65fea09 --- /dev/null +++ b/aufgabe5.2/slurm/gres.conf @@ -0,0 +1 @@ +Name=gpu File=/dev/nvidia0 diff --git a/aufgabe5.2/slurm/slurm.conf b/aufgabe5.2/slurm/slurm.conf new file mode 100644 index 0000000..4c94650 --- /dev/null +++ b/aufgabe5.2/slurm/slurm.conf @@ -0,0 +1,103 @@ +# +# Example slurm.conf file. Please run configurator.html +# (in doc/html) to build a configuration file customized +# for your environment. +# +# +# slurm.conf file generated by configurator.html. +# +# See the slurm.conf man page for more information. +# +ClusterName=zotac +ControlMachine=zotac0 +#ControlAddr= +#BackupController= +#BackupAddr= +# +SlurmUser=slurm +#SlurmdUser=root +SlurmctldPort=6817 +SlurmdPort=6818 +AuthType=auth/munge +#JobCredentialPrivateKey= +#JobCredentialPublicCertificate= +StateSaveLocation=/tmp +SlurmdSpoolDir=/tmp/slurmd +SwitchType=switch/none +MpiDefault=none +SlurmctldPidFile=/var/run/slurmctld.pid +SlurmdPidFile=/var/run/slurmd.pid +ProctrackType=proctrack/cgroup +#PluginDir= +#CacheGroups=0 +#FirstJobId= +ReturnToService=0 +#MaxJobCount= +#PlugStackConfig= +#PropagatePrioProcess= +#PropagateResourceLimits= +#PropagateResourceLimitsExcept= +#Prolog= +#Epilog= +#SrunProlog= +#SrunEpilog= +#TaskProlog= +#TaskEpilog= +TaskPlugin=task/affinity +TaskPluginParam=sched +#TrackWCKey=no +#TreeWidth=50 +#TmpFS= +UsePAM=1 +# +# TIMERS +SlurmctldTimeout=300 +SlurmdTimeout=300 +InactiveLimit=0 +MinJobAge=300 +KillWait=30 +Waittime=0 +# +# SCHEDULING +SchedulerType=sched/backfill +#SchedulerAuth= +#SchedulerPort= +#SchedulerRootFilter= +SelectType=select/cons_res +SelectTypeParameters=CR_Core +FastSchedule=1 +#PriorityType=priority/multifactor +#PriorityDecayHalfLife=14-0 +#PriorityUsageResetPeriod=14-0 +#PriorityWeightFairshare=100000 +#PriorityWeightAge=1000 +#PriorityWeightPartition=10000 +#PriorityWeightJobSize=1000 +#PriorityMaxAge=1-0 +# +# LOGGING +SlurmctldDebug=3 +#SlurmctldLogFile= +SlurmdDebug=3 +#SlurmdLogFile= +JobCompType=jobcomp/filetxt +JobCompLoc=/var/log/slurm/job_completions +# +# ACCOUNTING +#JobAcctGatherFrequency=30 +# +#AccountingStorageType=accounting_storage/slurmdbd +#AccountingStorageLoc=/var/log/slurm/accounting +#AccountingStorageHost= +#AccountingStoragePass= +#AccountingStorageUser= +# +# COMPUTE NODES +GresTypes=gpu +NodeName=zotac1 Procs=1 State=UNKNOWN Sockets=1 CoresPerSocket=2 ThreadsPerCore=1 +NodeName=zotac[2-4] Procs=1 State=UNKNOWN Sockets=1 CoresPerSocket=2 ThreadsPerCore=1 Gres=gpu:1 + +PartitionName=benchmark Nodes=zotac[1-4] AllowGroups=tutoren,wheel MaxTime=INFINITE State=UP PreemptMode=SUSPEND Shared=EXCLUSIVE Priority=3 +PartitionName=express Nodes=zotac[1-4] Default=YES MaxTime=1:0:0 State=UP Priority=2 +PartitionName=small Nodes=zotac[1-4] MaxTime=2:0:0 State=UP Priority=1 MaxNodes=1 +PartitionName=long Nodes=zotac[1-4] MaxTime=48:0:0 State=UP Priority=0