KnowHow

技術的なメモを中心にまとめます。
検索にて調べることができます。

SLURM: RockyLinux8のslurm.conf

登録日 :2023/07/29 21:55
カテゴリ :SLURM

RockyLinux8で、slurmdbdを含めて設定成功したslurm.confのサンプル

[user01@newhead slurm]$ cat slurm.conf
#
# 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.
# Put this file on all nodes of your cluster.
# See the slurm.conf man page for more information.
#
ClusterName=RockyLinux8
SlurmctldHost=newhead
#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
#
ProctrackType=proctrack/pgid
#
#Prolog=
#PrologFlags=
#PrologSlurmctld=
#PropagatePrioProcess=0
#PropagateResourceLimits=
#PropagateResourceLimitsExcept=
#RebootProgram=
#ReturnToService=1
#
ReturnToService=0
#
SlurmctldPidFile=/var/run/slurmctld.pid
#SlurmctldPort=6817
#
SlurmctldPort=7817
#
SlurmdPidFile=/var/run/slurmd.pid
#SlurmdPort=6818
#
SlurmdPort=7818
#
SlurmdSpoolDir=/var/spool/slurmd
#SlurmUser=slurm
#
SlurmdUser=root
#
#SrunEpilog=
#SrunProlog=
StateSaveLocation=/var/spool/slurmctld
SwitchType=switch/none
#TaskEpilog=
TaskPlugin=task/affinity
#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
SelectTypeParameters=CR_Core
#
#
# 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/none
#
#AccountingStorageUser=
#AccountingStoreFlags=
#
AccountingStorageType=accounting_storage/slurmdbd
AccountingStorageHost=newhead
AccountingStoragePass=/var/run/munge/munge.socket.2
#
#
#JobCompHost=
#JobCompLoc=
#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=linux[1-32] CPUs=1 State=UNKNOWN
NodeName=newhead CPUs=1 Boards=1 SocketsPerBoard=1 CoresPerSocket=1 ThreadsPerCore=1 RealMemory=770 State=UNKNOWN
NodeName=node1 CPUs=1 Boards=1 SocketsPerBoard=1 CoresPerSocket=1 ThreadsPerCore=1 RealMemory=770 State=UNKNOWN
NodeName=node2 CPUs=1 Boards=1 SocketsPerBoard=1 CoresPerSocket=1 ThreadsPerCore=1 RealMemory=770 State=UNKNOWN
#NodeName=FileServer CPUs=1 Boards=1 SocketsPerBoard=1 CoresPerSocket=1 ThreadsPerCore=1 RealMemory=770 State=UNKNOWN
#
# PARTITION
#PartitionName=debug Nodes=ALL Default=YES MaxTime=INFINITE State=UP
PartitionName=debug Nodes=newhead Default=NO MaxTime=05:00 State=UP
PartitionName=cls1 Nodes=node1 Default=YES MaxTime=INFINITE State=UP
PartitionName=cls2 Nodes=node2 Default=NO MaxTime=INFINITE State=UP
PartitionName=cls3 Nodes=node[1-2] Default=NO MaxTime=INFINITE State=UP
[user01@newhead slurm]$