I have a small 2 compute node GPU cluster, where each node as 2 GPUs.

$ sinfo -o "%20N  %10c  %10m  %25f  %30G "
NODELIST              CPUS        MEMORY      AVAIL_FEATURES             GRES                          
o186i[126-127]        128         64000       (null)                     gpu:nvidia_a40:2(S:0-1) 

In my batch script, I request 4 GPUs and let Slurm decide how many nodes to automatically allocate.  I also tell it I want 1 task per node.


$ cat rig_batch.sh
#!/usr/bin/env bash

#SBATCH --ntasks-per-node=1
#SBATCH --nodes=1-9
#SBATCH --gpus=4
#SBATCH --error=/home/corujor/slurm-error.log
#SBATCH --output=/home/corujor/slurm-output.log

bash -c 'echo $(hostname):SLURM_JOBID=${SLURM_JOBID}:SLURM_PROCID=${SLURM_PROCID}:CUDA_VISIBLE_DEVICES=${CUDA_VISIBLE_DEVICES}'


I submit my batch script on slurm-22.05.2.

$ sbatch rig_batch.sh
Submitted batch job 7


I get the expected results.  That is, since each compute node has 2 GPUs and I requested 4 GPUs, Slurm allocated 2 nodes, and 1 task per node.


$ cat slurm-output.log
o186i126:SLURM_JOBID=7:SLURM_PROCID=0:CUDA_VISIBLE_DEVICES=0,1
o186i127:SLURM_JOBID=7:SLURM_PROCID=1:CUDA_VISIBLE_DEVICES=0,1


However, when I try to submit the same batch script on slurm-22.05.7, it fails.

$ sbatch rig_batch.sh
sbatch: error: Batch job submission failed: Requested node configuration is not available


Here is my configuration.


$ scontrol show config
Configuration data as of 2023-01-12T21:38:55
AccountingStorageBackupHost = (null)
AccountingStorageEnforce = none
AccountingStorageHost   = localhost
AccountingStorageExternalHost = (null)
AccountingStorageParameters = (null)
AccountingStoragePort   = 6819
AccountingStorageTRES   = cpu,mem,energy,node,billing,fs/disk,vmem,pages
AccountingStorageType   = accounting_storage/slurmdbd
AccountingStorageUser   = N/A
AccountingStoreFlags    = (null)
AcctGatherEnergyType    = acct_gather_energy/none
AcctGatherFilesystemType = acct_gather_filesystem/none
AcctGatherInterconnectType = acct_gather_interconnect/none
AcctGatherNodeFreq      = 0 sec
AcctGatherProfileType   = acct_gather_profile/none
AllowSpecResourcesUsage = No
AuthAltTypes            = (null)
AuthAltParameters       = (null)
AuthInfo                = (null)
AuthType                = auth/munge
BatchStartTimeout       = 10 sec
BcastExclude            = /lib,/usr/lib,/lib64,/usr/lib64
BcastParameters         = (null)
BOOT_TIME               = 2023-01-12T17:17:11
BurstBufferType         = (null)
CliFilterPlugins        = (null)
ClusterName             = grenoble_test
CommunicationParameters = (null)
CompleteWait            = 0 sec
CoreSpecPlugin          = core_spec/none
CpuFreqDef              = Unknown
CpuFreqGovernors        = OnDemand,Performance,UserSpace
CredType                = cred/munge
DebugFlags              = Gres
DefMemPerNode           = UNLIMITED
DependencyParameters    = (null)
DisableRootJobs         = Yes
EioTimeout              = 60
EnforcePartLimits       = ANY
Epilog                  = (null)
EpilogMsgTime           = 2000 usec
EpilogSlurmctld         = (null)
ExtSensorsType          = ext_sensors/none
ExtSensorsFreq          = 0 sec
FederationParameters    = (null)
FirstJobId              = 1
GetEnvTimeout           = 2 sec
GresTypes               = gpu
GpuFreqDef              = high,memory=high
GroupUpdateForce        = 1
GroupUpdateTime         = 600 sec
HASH_VAL                = Match
HealthCheckInterval     = 0 sec
HealthCheckNodeState    = ANY
HealthCheckProgram      = (null)
InactiveLimit           = 0 sec
InteractiveStepOptions  = --interactive --preserve-env --pty $SHELL
JobAcctGatherFrequency  = 30
JobAcctGatherType       = jobacct_gather/none
JobAcctGatherParams     = (null)
JobCompHost             = localhost
JobCompLoc              = /var/log/slurm_jobcomp.log
JobCompPort             = 0
JobCompType             = jobcomp/none
JobCompUser             = root
JobContainerType        = job_container/none
JobCredentialPrivateKey = /apps/slurm/etc/.slurm.key
JobCredentialPublicCertificate = /apps/slurm/etc/slurm.cert
JobDefaults             = (null)
JobFileAppend           = 0
JobRequeue              = 1
JobSubmitPlugins        = (null)
KillOnBadExit           = 0
KillWait                = 30 sec
LaunchParameters        = use_interactive_step
LaunchType              = launch/slurm
Licenses                = (null)
LogTimeFormat           = iso8601_ms
MailDomain              = (null)
MailProg                = /bin/mail
MaxArraySize            = 1001
MaxDBDMsgs              = 20008
MaxJobCount             = 10000
MaxJobId                = 67043328
MaxMemPerNode           = UNLIMITED
MaxNodeCount            = 2
MaxStepCount            = 40000
MaxTasksPerNode         = 512
MCSPlugin               = mcs/none
MCSParameters           = (null)
MessageTimeout          = 10 sec
MinJobAge               = 300 sec
MpiDefault              = pmix
MpiParams               = (null)
NEXT_JOB_ID             = 274
NodeFeaturesPlugins     = (null)
OverTimeLimit           = 0 min
PluginDir               = /apps/slurm-22-05-7-1/lib/slurm
PlugStackConfig         = (null)
PowerParameters         = (null)
PowerPlugin             =
PreemptMode             = OFF
PreemptType             = preempt/none
PreemptExemptTime       = 00:00:00
PrEpParameters          = (null)
PrEpPlugins             = prep/script
PriorityParameters      = (null)
PrioritySiteFactorParameters = (null)
PrioritySiteFactorPlugin = (null)
PriorityType            = priority/basic
PrivateData             = none
ProctrackType           = proctrack/linuxproc
Prolog                  = (null)
PrologEpilogTimeout     = 65534
PrologSlurmctld         = (null)
PrologFlags             = (null)
PropagatePrioProcess    = 0
PropagateResourceLimits = ALL
PropagateResourceLimitsExcept = (null)
RebootProgram           = (null)
ReconfigFlags           = (null)
RequeueExit             = (null)
RequeueExitHold         = (null)
ResumeFailProgram       = (null)
ResumeProgram           = (null)
ResumeRate              = 300 nodes/min
ResumeTimeout           = 60 sec
ResvEpilog              = (null)
ResvOverRun             = 0 min
ResvProlog              = (null)
ReturnToService         = 1
RoutePlugin             = route/default
SchedulerParameters     = (null)
SchedulerTimeSlice      = 30 sec
SchedulerType           = sched/backfill
ScronParameters         = (null)
SelectType              = select/cons_tres
SelectTypeParameters    = CR_CPU
SlurmUser               = slurm(1182)
SlurmctldAddr           = (null)
SlurmctldDebug          = debug
SlurmctldHost[0]        = o186i208
SlurmctldLogFile        = /var/log/slurmctld.log
SlurmctldPort           = 6817
SlurmctldSyslogDebug    = (null)
SlurmctldPrimaryOffProg = (null)
SlurmctldPrimaryOnProg  = (null)
SlurmctldTimeout        = 120 sec
SlurmctldParameters     = (null)
SlurmdDebug             = info
SlurmdLogFile           = /var/log/slurmd.log
SlurmdParameters        = (null)
SlurmdPidFile           = /var/run/slurmd.pid
SlurmdPort              = 6818
SlurmdSpoolDir          = /var/spool/slurmd
SlurmdSyslogDebug       = (null)
SlurmdTimeout           = 300 sec
SlurmdUser              = root(0)
SlurmSchedLogFile       = (null)
SlurmSchedLogLevel      = 0
SlurmctldPidFile        = /var/slurm/run/slurmctld.pid
SlurmctldPlugstack      = (null)
SLURM_CONF              = /apps/slurm-22-05-7-1/etc/slurm.conf
SLURM_VERSION           = 22.05.7
SrunEpilog              = (null)
SrunPortRange           = 0-0
SrunProlog              = (null)
StateSaveLocation       = /var/spool/slurmctld
SuspendExcNodes         = (null)
SuspendExcParts         = (null)
SuspendProgram          = (null)
SuspendRate             = 60 nodes/min
SuspendTime             = INFINITE
SuspendTimeout          = 30 sec
SwitchParameters        = (null)
SwitchType              = switch/none
TaskEpilog              = (null)
TaskPlugin              = task/affinity
TaskPluginParam         = (null type)
TaskProlog              = (null)
TCPTimeout              = 2 sec
TmpFS                   = /tmp
TopologyParam           = (null)
TopologyPlugin          = topology/none
TrackWCKey              = No
TreeWidth               = 50
UsePam                  = No
UnkillableStepProgram   = (null)
UnkillableStepTimeout   = 60 sec
VSizeFactor             = 0 percent
WaitTime                = 0 sec
X11Parameters           = (null)
 

MPI Plugins Configuration:

PMIxCliTmpDirBase       = (null)
PMIxCollFence           = (null)
PMIxDebug               = 0
PMIxDirectConn          = yes
PMIxDirectConnEarly     = no
PMIxDirectConnUCX       = no
PMIxDirectSameArch      = no
PMIxEnv                 = (null)
PMIxFenceBarrier        = no
PMIxNetDevicesUCX       = (null)
PMIxTimeout             = 300
PMIxTlsUCX              = (null)

Slurmctld(primary) at o186i208 is UP



The only difference when I run this with slurm-22.05.2, is that I have to make this change or Slurm will complain.  Other than that, the same configuration is used for both slurm-22.05.2 and slurm.05.7.  In both cases, I am running on the same cluster using the same compute nodes, just pointing to different versions of Slurm.

#MpiDefault=pmix
MpiDefault=none