Merge pull request #36 from grycap/devel

Ser drmaa version and test new slurm versions

README.md

@@ -40,6 +40,46 @@ The variables that can be passed to this role and a brief description about them
 	user: user1
 	# Install DRMAA library
 	drmaa_lib_install: false
+	drmaa_lib_version: 1.0.7
+	# SLURM default configuration options
+	slurm_default_conf_options:
+		AuthType: auth/munge
+		CryptoType: crypto/munge
+		FirstJobId: 1
+		JobRequeue: 0
+		JobSubmitPlugins: all_partitions
+		ProctrackType: proctrack/pgid
+		ReturnToService: 2
+		SlurmctldPidFile: /var/run/slurmctld.pid
+		SlurmctldPort: 6817
+		SlurmdPidFile: /var/run/slurmctld.pid
+		SlurmdPort: 6818
+		SlurmdSpoolDir: /var/spool/slurm
+		SlurmUser: slurm
+		StateSaveLocation: /var/slurm/checkpoint
+		SwitchType: switch/none
+		TaskPlugin: task/none
+		InactiveLimit: 0
+		KillWait: 30
+		MessageTimeout: 30
+		MinJobAge: 300
+		SlurmctldTimeout: 30
+		SlurmdTimeout: 40
+		Waittime: 0
+		FastSchedule: 1
+		SchedulerType: sched/backfill
+		SelectType: select/linear
+		AccountingStorageType: accounting_storage/none
+		ClusterName: cluster
+		JobCompType: jobcomp/none
+		JobAcctGatherFrequency: 30
+		JobAcctGatherType: jobacct_gather/none
+		SlurmctldDebug: debug5
+		SlurmctldLogFile: /var/log/slurm/slurmctld.log
+		SlurmdDebug: debug5
+		SlurmdLogFile: /var/log/slurm/slurmd.log
+	# SLURM user configuration options
+	slurm_conf_options: {}
 
 Example Playbook
 ----------------

defaults/main.yml

@@ -34,3 +34,43 @@ max_number_of_nodes: 3
 slurm_vnode_prefix: wn
 # Install DRMAA library
 drmaa_lib_install: false
+drmaa_lib_version: 1.0.7
+# SLURM default configuration options
+slurm_default_conf_options:
+  AuthType: auth/munge
+  CryptoType: crypto/munge
+  FirstJobId: 1
+  JobRequeue: 0
+  JobSubmitPlugins: all_partitions
+  ProctrackType: proctrack/pgid
+  ReturnToService: 2
+  SlurmctldPidFile: /var/run/slurmctld.pid
+  SlurmctldPort: 6817
+  SlurmdPidFile: /var/run/slurmctld.pid
+  SlurmdPort: 6818
+  SlurmdSpoolDir: /var/spool/slurm
+  SlurmUser: slurm
+  StateSaveLocation: /var/slurm/checkpoint
+  SwitchType: switch/none
+  TaskPlugin: task/none
+  InactiveLimit: 0
+  KillWait: 30
+  MessageTimeout: 30
+  MinJobAge: 300
+  SlurmctldTimeout: 30
+  SlurmdTimeout: 40
+  Waittime: 0
+  FastSchedule: 1
+  SchedulerType: sched/backfill
+  SelectType: select/linear
+  AccountingStorageType: accounting_storage/none
+  ClusterName: cluster
+  JobCompType: jobcomp/none
+  JobAcctGatherFrequency: 30
+  JobAcctGatherType: jobacct_gather/none
+  SlurmctldDebug: debug5
+  SlurmctldLogFile: /var/log/slurm/slurmctld.log
+  SlurmdDebug: debug5
+  SlurmdLogFile: /var/log/slurm/slurmd.log
+# SLURM user configuration options
+slurm_conf_options: {}

tasks/drmaa.yml

@@ -1,10 +1,5 @@
 ---
   # Install DRMAA Library for slurm
-  - set_fact:
-      INSTALL_PATH: /opt
-      ID_FILE: "9"
-      FILENAME: "slurm-drmaa-1.0.7"
-
   - name: Check if lib exists
     stat: path=/usr/local/lib/libdrmaa.so
     register: libstat
@@ -14,10 +9,21 @@
     - name: Install GCC
       package: name=gcc state=present
 
+    - set_fact:
+        INSTALL_PATH: /opt
+        FILENAME: "slurm-drmaa-{{ drmaa_lib_version }}"
+
     - name: Download lib
       get_url:
         url: http://apps.man.poznan.pl/trac/slurm-drmaa/downloads/9
         dest: "{{ INSTALL_PATH }}/{{ FILENAME }}.tgz"
+      when: drmaa_lib_version == "1.0.7"
+
+    - name: Download lib
+      get_url:
+        url: https://github.com/natefoo/slurm-drmaa/releases/download/{{ drmaa_lib_version }}/slurm-drmaa-{{ drmaa_lib_version }}.tar.gz
+        dest: "{{ INSTALL_PATH }}/{{ FILENAME }}.tgz"
+      when: drmaa_lib_version != "1.0.7"
 
     - name: unarchive lib
       unarchive:

tasks/main.yml

@@ -58,6 +58,15 @@
       - /var/slurm/checkpoint
       - /etc/slurm
 
+  - name: Use BLCR as checkpointing type
+    set_fact:
+      slurm_conf_options: "{{ slurm_default_conf_options | combine({'CheckpointType': 'checkpoint/blcr'}) }}"
+    when : '"blcr" in templates'
+
+  - name: Update default options with user options
+    set_fact:
+      slurm_conf_options: "{{ slurm_default_conf_options | combine(slurm_conf_options) }}"
+
   - name: Include "{{slurm_type_of_node}}" SLURM recipe
     include_tasks: "{{slurm_type_of_node}}.yaml"
 

templates/slurm.conf.j2

@@ -3,160 +3,11 @@
 # See the slurm.conf man page for more information.
 #
 ControlMachine={{slurm_server_name}}
-#ControlAddr=
-#BackupController=
-#BackupAddr=
-#
-AuthType=auth/munge
-CacheGroups=0
 
-{% if 'blcr' in templates %}
-CheckpointType=checkpoint/blcr
-{% endif %}
+{% for key, value in slurm_conf_options.items() %}
+{{key}}={{value}}
+{% endfor %}
 
-CryptoType=crypto/munge
-#DisableRootJobs=NO
-#EnforcePartLimits=NO
-#Epilog=/usr/local/slurm/epilog_controller
-#EpilogSlurmctld=/usr/local/slurm/epilog_controller
-FirstJobId=1
-#MaxJobId=999999
-#GresTypes=
-#GroupUpdateForce=0
-#GroupUpdateTime=600
-#JobCheckpointDir=/var/slurm/checkpoint
-#JobCredentialPrivateKey=
-#JobCredentialPublicCertificate=
-#JobFileAppend=0
-JobRequeue=0
-JobSubmitPlugins=all_partitions
-#KillOnBadExit=0
-#Licenses=foo*4,bar
-#MailProg=/bin/mail
-#MaxJobCount=5000
-#MaxStepCount=40000
-#MaxTasksPerNode=128
-#MpiDefault=openmpi
-#MpiParams=ports=12000-12999
-#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/slurmctld.pid
-SlurmdPort=6818
-SlurmdSpoolDir=/var/spool/slurm
-SlurmUser=slurm
-#SlurmdUser=root
-#SrunEpilog=
-#SrunProlog=
-StateSaveLocation=/var/slurm/checkpoint
-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=30
-#ResvOverRun=0
-MinJobAge=300
-#OverTimeLimit=0
-SlurmctldTimeout=30
-SlurmdTimeout=40
-#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/linear
-#SelectTypeParameters=
-#
-#
-# JOB PRIORITY
-#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=
-#JobCompHost=
-#JobCompLoc=
-#JobCompPass=
-#JobCompPort=
-JobCompType=jobcomp/none
-#JobCompUser=
-JobAcctGatherFrequency=30
-JobAcctGatherType=jobacct_gather/none
-SlurmctldDebug=debug5
-SlurmctldLogFile=/var/log/slurm/slurmctld.log
-SlurmdDebug=debug5
-SlurmdLogFile=/var/log/slurm/slurmd.log
-#SlurmSchedLogFile=
-#SlurmSchedLogLevel=
-#
-#
-# POWER SAVE SUPPORT FOR IDLE NODES (optional)
-#SuspendProgram=
-#ResumeProgram=
-#SuspendTimeout=
-#ResumeTimeout=
-#ResumeRate=
-#SuspendExcNodes=
-#SuspendExcParts=
-#SuspendRate=
-#SuspendTime=
 #
 #
 # COMPUTE NODES

tests/test.yml

@@ -9,3 +9,6 @@
       slurm_wn_ips: ["127.0.0.1"]
       slurm_vnode_prefix: vnode-
       max_number_of_nodes: 1
+      drmaa_lib_install: true
+      drmaa_lib_version: 1.1.4
+      slurm_version: 21.08.8