У меня есть главный узел (Ubuntu 18.04) и два вычислительных узла (Ubuntu 18.04)
С подключением проблем нет
Munge хорош, я пытаюсь командовать (sinfo, scontrol show nodes) .. это не проблема
Пытаюсь найти ошибку ...
но нет проблем
Не знаю почему? что случилось?
Вот мой slurm.conf
# Put this file on all nodes of your cluster.
# See the slurm.conf man page for more information.
#
ControlMachine=master
ControlAddr=IP.IP.IP.IP
#BackupController=
#BackupAddr=
#
AuthType=auth/munge
AuthInfo=/var/run/munge/munge.socket.2
#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=1
#KillOnBadExit=0
#LaunchType=launch/slurm
#Licenses=foo*4,bar
#MailProg=/bin/mail
#MaxJobCount=5000
#MaxStepCount=40000
#MaxTasksPerNode=128
MpiDefault=none
#MpiParams=ports=#-#
#PluginDir=
#PlugStackConfig=
#PrivateData=jobs
ProctrackType=proctrack/cgroup
#Prolog=
#PrologFlags=
#PrologSlurmctld=
#PropagatePrioProcess=0
#PropagateResourceLimits=
#PropagateResourceLimitsExcept=
#RebootProgram=
ReturnToService=1
#SallocDefaultCommand=
SlurmctldPidFile=/var/run/slurm-llnl/slurmctld.pid
SlurmctldPort=6817
SlurmdPidFile=/var/run/slurm-llnl/slurmd.pid
SlurmdPort=6818
SlurmdSpoolDir=/var/spool/slurmd
SlurmUser=slurm
#SlurmdUser=root
#SrunEpilog=
#SrunProlog=
StateSaveLocation=/var/spool/slurm-llnl
SwitchType=switch/none
#TaskEpilog=
TaskPlugin=task/cgroup
TaskPluginParam=Sched
#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/cons_res
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=
#AccountingStorageLoc=
#AccountingStoragePass=
#AccountingStoragePort=
#AccountingStorageType=accounting_storage/none
#AccountingStorageUser=
AccountingStoreJobComment=YES
ClusterName=cluster
#DebugFlags=NO_CONF_HASH
#JobCompHost=
#JobCompLoc=
#JobCompPass=
#JobCompPort=
#JobCompType=jobcomp/filetxt #jobcomp/none
#JobCompUser=
#JobContainerType=job_container/none
JobAcctGatherFrequency=30
#JobAcctGatherType=jobacct_gather/linux #jobacct_gather/none
SlurmctldDebug=3
SlurmctldLogFile=/var/log/slurmctld.log
SlurmdDebug=3
SlurmdLogFile=/var/log/slurmd.log
#SlurmSchedLogFile=
#SlurmSchedLogLevel=
#
#
# POWER SAVE SUPPORT FOR IDLE NODES (optional)
#SuspendProgram=
#ResumeProgram=
#SuspendTimeout=
#ResumeTimeout=
#ResumeRate=
#SuspendExcNodes=
#SuspendExcParts=
#SuspendRate=
#SuspendTime=
#
#
# COMPUTE NODES
GresTypes=gpu
NodeName=NODE1 Gres=gpu:pascal:1 NodeAddr=Ip.IP.IP.IP CPUs=32 State=UNKNOWN CoresPerSocket=8 ThreadsPerCore=2 RealMemory=48209
NodeName=NODE2 Gres=gpu:pascal:1 NodeAddr=Ip.IP.IP.IP CPUs=32 State=UNKNOWN CoresPerSocket=16 ThreadsPerCore=2 RealMemory=128845
PartitionName=Test1 Nodes=NODE1 Default=YES MaxTime=INFINITE State=UP
PartitionName=Test2 Nodes=NODE2 Default=YES MaxTime=INFINITE State=UP
я пробую srun -N2 /bin/hostname
это остановка терминала
srun: Requested partition configuration not available now
srun: job 613 queued and waiting for resources
зачем останавливаться ??
пожалуйста помоги....
Редактировать :
я пробую sbatch
команда
Я запускаю slurm с помощью этой команды, но состояние узла находится в ожидании и не выполняется.