Merge pull request #161 from stackhpc/feat/update-slurmconf

Non-functional changes to slurm.conf

Author: sjpb

.github/workflows/ci.yml

@@ -25,8 +25,7 @@ jobs:
       matrix:
         image:
           - 'centos:7'
-          - 'rockylinux:8.6'
-          - 'rockylinux:8.7'
+          - 'rockylinux:8.8'
         scenario:
           - test1
           - test1b

files/slurm.conf.ohpc

@@ -0,0 +1,160 @@
+#
+# 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=cluster
+SlurmctldHost=linux0
+#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
+#Prolog=
+#PrologFlags=
+#PrologSlurmctld=
+#PropagatePrioProcess=0
+#PropagateResourceLimits=
+#PropagateResourceLimitsExcept=
+#RebootProgram=
+SlurmctldPidFile=/var/run/slurmctld.pid
+SlurmctldPort=6817
+SlurmdPidFile=/var/run/slurmd.pid
+SlurmdPort=6818
+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=
+#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
+# OpenHPC default configuration
+TaskPlugin=task/affinity
+PropagateResourceLimitsExcept=MEMLOCK
+JobCompType=jobcomp/filetxt
+Epilog=/etc/slurm/slurm.epilog.clean
+NodeName=c[1-4] Sockets=2 CoresPerSocket=8 ThreadsPerCore=2 State=UNKNOWN
+PartitionName=normal Nodes=c[1-4] Default=YES MaxTime=24:00:00 State=UP Oversubscribe=EXCLUSIVE
+SlurmctldParameters=enable_configless
+ReturnToService=1

molecule/README.md

@@ -29,10 +29,11 @@ test14 | 1            | N                       | As for #5 but also tests `extr
 Local installation on a RockyLinux 8.x machine looks like:
 
     sudo dnf install -y podman
+    sudo dnf install podman-plugins # required for DNS
     sudo yum install -y git
     git clone [email protected]:stackhpc/ansible-role-openhpc.git
     cd ansible-role-openhpc/
-    python3.8 -m venv venv
+    python3.9 -m venv venv
     . venv/bin/activate
     pip install -U pip
     pip install -r molecule/requirements.txt
@@ -44,8 +45,6 @@ Then to run tests, e.g.::
     MOLECULE_IMAGE=centos:7 molecule test --all # NB some won't work as require OpenHPC v2.x (-> CentOS 8.x) features - see `.github/workflows/ci.yml`
     MOLECULE_IMAGE=rockylinux:8.6 molecule test --all
 
-**NB:** If the host network has an MTU smaller than 1500 (the docker default), check `molecule.yml` for the relevant test contains `DOCKER_MTU`, then prepend `DOCKER_MTU=<mtu>` to your command. If you have already run molecule you will need to destroy the instances and run `docker network prune` before retrying.
-
 During development you may want to:
 
 - See some debugging information by prepending:

molecule/requirements.txt

@@ -1,4 +1,5 @@
 pip
 setuptools
-molecule[podman,lint,ansible]
+molecule[lint,ansible]
+molecule-plugins[podman]
 ansible>=2.9.0

molecule/test12/molecule.yml

@@ -14,10 +14,6 @@ platforms:
     volumes:
       - /sys/fs/cgroup:/sys/fs/cgroup:ro
     network: net1
-    docker_networks:
-      - name: net1
-        driver_options:
-          com.docker.network.driver.mtu: ${DOCKER_MTU:-1500} # 1500 is docker default
   - name: testohpc-compute-0
     image: ${MOLECULE_IMAGE}
     pre_build_image: true

molecule/test14/molecule.yml

@@ -14,10 +14,6 @@ platforms:
     volumes:
       - /sys/fs/cgroup:/sys/fs/cgroup:ro
     network: net1
-    docker_networks:
-      - name: net1
-        driver_options:
-          com.docker.network.driver.mtu: ${DOCKER_MTU:-1500} # 1500 is docker default
   - name: testohpc-compute-0
     image: ${MOLECULE_IMAGE}
     pre_build_image: true
@@ -30,10 +26,6 @@ platforms:
     volumes:
       - /sys/fs/cgroup:/sys/fs/cgroup:ro
     network: net1
-    docker_networks:
-      - name: net1
-        driver_options:
-          com.docker.network.driver.mtu: ${DOCKER_MTU:-1500} # 1500 is docker default
   - name: testohpc-compute-1
     image: ${MOLECULE_IMAGE}
     pre_build_image: true
@@ -46,10 +38,6 @@ platforms:
     volumes:
       - /sys/fs/cgroup:/sys/fs/cgroup:ro
     network: net1
-    docker_networks:
-      - name: net1
-        driver_options:
-          com.docker.network.driver.mtu: ${DOCKER_MTU:-1500} # 1500 is docker default
 provisioner:
   name: ansible
 verifier:

molecule/test5/molecule.yml

@@ -14,10 +14,6 @@ platforms:
     volumes:
       - /sys/fs/cgroup:/sys/fs/cgroup:ro
     network: net1
-    docker_networks:
-      - name: net1
-        driver_options:
-          com.docker.network.driver.mtu: ${DOCKER_MTU:-1500} # 1500 is docker default
   - name: testohpc-compute-0
     image: ${MOLECULE_IMAGE}
     pre_build_image: true
@@ -30,10 +26,6 @@ platforms:
     volumes:
       - /sys/fs/cgroup:/sys/fs/cgroup:ro
     network: net1
-    docker_networks:
-      - name: net1
-        driver_options:
-          com.docker.network.driver.mtu: ${DOCKER_MTU:-1500} # 1500 is docker default
   - name: testohpc-compute-1
     image: ${MOLECULE_IMAGE}
     pre_build_image: true
@@ -46,10 +38,6 @@ platforms:
     volumes:
       - /sys/fs/cgroup:/sys/fs/cgroup:ro
     network: net1
-    docker_networks:
-      - name: net1
-        driver_options:
-          com.docker.network.driver.mtu: ${DOCKER_MTU:-1500} # 1500 is docker default
 provisioner:
   name: ansible
 verifier:

molecule/test6/molecule.yml

@@ -14,10 +14,6 @@ platforms:
     volumes:
       - /sys/fs/cgroup:/sys/fs/cgroup:ro
     network: net1
-    docker_networks:
-      - name: net1
-        driver_options:
-          com.docker.network.driver.mtu: ${DOCKER_MTU:-1500} # 1500 is docker default
 provisioner:
   name: ansible
   inventory: