Hi Danny,

Yes of course... Here it is.

N

On Tue, Aug 2, 2011 at 6:52 PM, Danny Auble <[email protected]> wrote:

> **
>
> Hey Nicolas, could you send your complete slurm.conf? It would be
> interesting to see the other plugins you are using that may be contributing
> to the problem.
>
>
>
> Danny
>
>
>
> On Tuesday August 02 2011 6:43:17 PM you wrote:
>
> > Hi all,
>
> >
>
> > I'm having issues with slurm 2.2.7 and specifying the nodes cpu
> information.
>
> >
>
> > If I set the number of sockets, core per socket and thread per core like
>
> > this:
>
> >
>
> > > NodeName=node[2-4] RealMemory=23000 Sockets=2 CoresPerSocket=4
>
> > > ThreadsPerCore=2 State=UNKNOWN
>
> > >
>
> > >> and submit a job, slurmctl crashes. The last section of sclurmctl.log
> is:
>
> >
>
> > > [2011-08-02T17:58:50] debug2: initial priority for job 49852 is 98
>
> > > [2011-08-02T17:58:50] debug2: found 3 usable nodes from config
> containing
>
> > > node[2-4]
>
> > > [2011-08-02T17:58:50] debug3: _pick_best_nodes: job 49852 idle_nodes 65
>
> > > share_nodes 76
>
> > > [2011-08-02T17:58:50] debug2: sched: JobId=49852 allocated resources:
>
> > > NodeList=(null)
>
> > > [2011-08-02T17:58:50] _slurm_rpc_submit_batch_job JobId=49852 usec=1540
>
> > > [2011-08-02T17:58:50] debug: sched: Running job scheduler
>
> > > [2011-08-02T17:58:50] debug2: found 3 usable nodes from config
> containing
>
> > > node[2-4]
>
> > > [2011-08-02T17:58:50] debug3: _pick_best_nodes: job 49852 idle_nodes 65
>
> > > share_nodes 76
>
> > > [2011-08-02T17:58:50] fatal: cons_res: sync loop not progressing
>
> > >
>
> >
>
> >
>
> > I've also seen the error "cons_res: cpus computation error".
>
> >
>
> > There might be something wrong with my configuration, but slurm should
> tell
>
> > me so, not crash when a job is submitted...
>
> >
>
> > I'm playing with these options because a user reported that just using
>
> > Procs=16 would not spread his mpi processes accross the allocated nodes.
>
> > I've fixed that by using --nodes=*-* and --ntasks-per-node=*, but the
> crash
>
> > is still relevant I guess...
>
> >
>
> > Could it be a bug?
>
> >
>
> > Thanks
>
> >
>
> > Nicolas
>
# 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.
#
ControlMachine=unicron
#ControlAddr=
#BackupController=
#BackupAddr=
#
AuthType=auth/munge
CacheGroups=1
#CheckpointType=checkpoint/none
CryptoType=crypto/munge
#DisableRootJobs=NO
#EnforcePartLimits=NO
#Epilog=
#PrologSlurmctld=
#FirstJobId=1
#GresTypes=
#GroupUpdateForce=0
#GroupUpdateTime=600
#JobCheckpointDir=/var/slurm/checkpoint
#JobCredentialPrivateKey=
#JobCredentialPublicCertificate=
#JobFileAppend=0
#JobRequeue=1
#JobSubmitPlugins=1
#KillOnBadExit=0
#Licenses=foo*4,bar
#MailProg=/bin/mail
#MaxJobCount=5000
MaxJobCount=100000
#MaxTasksPerNode=128
MpiDefault=none
#MpiParams=ports=#-#
#PluginDir=
#PlugStackConfig=
#PrivateData=jobs
ProctrackType=proctrack/pgid
#Prolog=
#PrologSlurmctld=
#PropagatePrioProcess=0
#PropagateResourceLimits=
#PropagateResourceLimitsExcept=
ReturnToService=2
#SallocDefaultCommand=
SlurmctldPidFile=/var/run/slurmctld.pid
SlurmctldPort=6817
SlurmdPidFile=/var/run/slurmd.pid
SlurmdPort=6818
SlurmdSpoolDir=/var/tmp/slurmd
SlurmUser=slurm
#SrunEpilog=
#SrunProlog=
StateSaveLocation=/var/tmp/slurmctld
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
#SchedulerRootFilter=1
#SchedulerTimeSlice=30
SchedulerType=sched/backfill
SchedulerPort=7321
SelectType=select/cons_res
SelectTypeParameters=CR_CPU
#
#
# JOB PRIORITY
PriorityType=priority/multifactor
#PriorityDecayHalfLife=
#PriorityCalcPeriod=
PriorityFavorSmall=YES
#PriorityMaxAge=
#PriorityUsageResetPeriod=
PriorityWeightAge=100
#PriorityWeightFairshare=
PriorityWeightJobSize=100
#PriorityWeightPartition=
#PriorityWeightQOS=
#
#
# LOGGING AND ACCOUNTING
#AccountingStorageEnforce=0
#AccountingStorageHost=
#AccountingStorageLoc=
#AccountingStoragePass=
#AccountingStoragePort=
AccountingStorageType=accounting_storage/none
#AccountingStorageUser=
ClusterName=unicron
#DebugFlags=
# Disable /etc/slurm.conf checking:
#DebugFlags=NO_CONF_HASH
#JobCompHost=
#JobCompLoc=
#JobCompPass=
#JobCompPort=
JobCompType=jobcomp/none
#JobCompUser=
JobAcctGatherFrequency=30
JobAcctGatherType=jobacct_gather/none
SlurmctldDebug=3
SlurmctldLogFile=/var/log/slurmctld.log
SlurmdDebug=3
SlurmdLogFile=/var/log/slurmd.log
SlurmSchedLogFile=/var/log/slurmsched.log
SlurmSchedLogLevel=3
#
#
# POWER SAVE SUPPORT FOR IDLE NODES (optional)
#SuspendProgram=
#ResumeProgram=
#SuspendTimeout=
#ResumeTimeout=
#ResumeRate=
#SuspendExcNodes=
#SuspendExcParts=
#SuspendRate=
#SuspendTime=
#
#
# COMPUTE NODES
NodeName=node[2-71,101-105] RealMemory=23000    Procs=16    State=UNKNOWN
NodeName=unicron            RealMemory=12000    Procs=8     State=UNKNOWN
NodeName=nodeKVM            RealMemory=494      Procs=1     State=UNKNOWN

PartitionName=test         Nodes=node[67,70-71]             MaxTime=INFINITE    
State=UP
PartitionName=unicron      Nodes=unicron                    MaxTime=INFINITE    
State=UP
PartitionName=wholecluster Nodes=node[2-71,101-105]         MaxTime=INFINITE    
State=UP
PartitionName=normalnodes  Nodes=node[2-71] Default=YES     MaxTime=INFINITE    
State=UP
PartitionName=supernodes   Nodes=node[101-105]              MaxTime=INFINITE    
State=UP
PartitionName=virtual      Nodes=nodeKVM                    MaxTime=INFINITE    
State=UP

Reply via email to