From 00c2a2a8175731a89e220c3860451946a8cef786 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thorsten=20M=C3=BCller?= Date: Mon, 26 Apr 2021 17:21:35 +0200 Subject: [PATCH] config --- roles/slurm/files/cgroup.conf | 11 +++ roles/slurm/files/slurm.conf | 162 ++++++++++++++++++++++++++++++++++ 2 files changed, 173 insertions(+) create mode 100644 roles/slurm/files/cgroup.conf create mode 100644 roles/slurm/files/slurm.conf diff --git a/roles/slurm/files/cgroup.conf b/roles/slurm/files/cgroup.conf new file mode 100644 index 0000000..51a8a1f --- /dev/null +++ b/roles/slurm/files/cgroup.conf @@ -0,0 +1,11 @@ +### +# +# Slurm cgroup support configuration file +# +# See man slurm.conf and man cgroup.conf for further +# information on cgroup configuration parameters +#-- +CgroupAutomount=yes + +ConstrainCores=no +ConstrainRAMSpace=no diff --git a/roles/slurm/files/slurm.conf b/roles/slurm/files/slurm.conf new file mode 100644 index 0000000..8a7bd1b --- /dev/null +++ b/roles/slurm/files/slurm.conf @@ -0,0 +1,162 @@ +# +# See the slurm.conf man page for more information. +# +ControlMachine=slurm-ctl +# ControlAddr=127.0.0.1 +#BackupController= +#BackupAddr= +# +AuthType=auth/munge +#CheckpointType=checkpoint/none +CryptoType=crypto/munge +#DisableRootJobs=NO +#EnforcePartLimits=NO +#Epilog= +#EpilogSlurmctld= +#FirstJobId=1 +#MaxJobId=999999 +#GresTypes= +#GroupUpdateForce=0 +#GroupUpdateTime=600 +#JobCheckpointDir=/var/slurm/checkpoint +#JobCredentialPrivateKey= +#JobCredentialPublicCertificate= +#JobFileAppend=0 +#JobRequeue=1 +#JobSubmitPlugins= +#KillOnBadExit=0 +#LaunchType=launch/slurm +#Licenses=foo*4,bar +#MailProg=/bin/true +#MaxJobCount=5000 +#MaxStepCount=40000 +#MaxTasksPerNode=128 +MpiDefault=pmix +#MpiParams=ports=#-# +#PluginDir= +#PlugStackConfig= +#PrivateData=jobs +# ProctrackType=proctrack/cgroup +ProctrackType=proctrack/linuxproc +#Prolog= +#PrologFlags= +#PrologSlurmctld= +#PropagatePrioProcess=0 +#PropagateResourceLimits= +#PropagateResourceLimitsExcept= +#RebootProgram= +ReturnToService=1 +#SallocDefaultCommand= +SlurmctldPidFile=/var/run/slurm/slurmctld.pid +SlurmctldPort=6817 +SlurmdPidFile=/var/run/slurm/slurmd.pid +SlurmdPort=6818 +SlurmdSpoolDir=/var/spool/slurm/d +SlurmUser=root +#SlurmdUser=root +#SrunEpilog= +#SrunProlog= +StateSaveLocation=/var/spool/slurm/ctld +SwitchType=switch/none +#TaskEpilog= +TaskPlugin=task/none +#TaskPluginParam= +#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 +#FastSchedule=1 +#MaxMemPerCPU=0 +#SchedulerTimeSlice=30 +SchedulerType=sched/backfill +SelectType=select/linear +#SelectTypeParameters= +# +# +# JOB PRIORITY +#PriorityFlags= +#PriorityType=priority/basic +#PriorityDecayHalfLife= +#PriorityCalcPeriod= +#PriorityFavorSmall= +#PriorityMaxAge= +#PriorityUsageResetPeriod= +#PriorityWeightAge= +#PriorityWeightFairshare= +#PriorityWeightJobSize= +#PriorityWeightPartition= +#PriorityWeightQOS= +# +# +# LOGGING AND ACCOUNTING +#AccountingStorageEnforce=0 +#AccountingStorageHost= +#AccountingStorageLoc= +#AccountingStoragePass= +#AccountingStoragePort= +AccountingStorageType=accounting_storage/none +#AccountingStorageUser= +AccountingStoreJobComment=YES +ClusterName=cluster +#DebugFlags= +#JobCompHost= +JobCompLoc=/tmp/jobcomp +#JobCompPass= +#JobCompPort= +JobCompType=jobcomp/filetxt +#JobCompUser= +#JobContainerType=job_container/none +JobAcctGatherFrequency=30 +JobAcctGatherType=jobacct_gather/none +SlurmctldDebug=verbose +#SlurmctldLogFile= +SlurmdDebug=verbose +#SlurmdLogFile= +#SlurmSchedLogFile= +#SlurmSchedLogLevel= +# +# +# POWER SAVE SUPPORT FOR IDLE NODES (optional) +#SuspendProgram= +#ResumeProgram= +#SuspendTimeout= +#ResumeTimeout= +#ResumeRate= +#SuspendExcNodes= +#SuspendExcParts= +#SuspendRate= +#SuspendTime= +# +# +# COMPUTE NODES +NodeName=slurm-exec1 CPUs=1 State=UNKNOWN +NodeName=slurm-exec2 CPUs=1 State=UNKNOWN +NodeName=slurm-submit1 CPUs=1 State=UNKNOWN +PartitionName=debug Nodes=slurm-exec1,slurm-exec2 Default=YES MaxTime=INFINITE State=UP