Allow nodes to appear in more than one group/partition (#174)

* fix duplicated nodename

* Nodes may appear in more than one group

---------

Co-authored-by: jianguo-ukaea <[email protected]>

Author: jovial

README.md

@@ -73,7 +73,7 @@ For each group (if used) or partition any nodes in an ansible inventory group `<
 - Nodes may have arbitrary hostnames but these should be lowercase to avoid a mismatch between inventory and actual hostname.
 - Nodes in a group are assumed to be homogenous in terms of processor and memory.
 - An inventory group may be empty or missing, but if it is not then the play must contain at least one node from it (used to set processor information).
-- Nodes may not appear in more than one group.
+
 
 `openhpc_job_maxtime`: Maximum job time limit, default `'60-0'` (60 days). See [slurm.conf](https://slurm.schedmd.com/slurm.conf.html) parameter `MaxTime` for format. The default is 60 days. The value should be quoted to avoid Ansible conversions.
 

molecule/README.md

@@ -22,6 +22,7 @@ test11 | 1            | N                       | As for #5 but then deletes a n
 test12 | 1            | N                       | As for #5 but enabling job completion and testing `sacct -c`
 test13 | 1            | N                       | As for #5 but tests `openhpc_config` variable.
 test14 | 1            | N                       | As for #5 but also tests `extra_nodes` via State=DOWN nodes.
+test15 | 1            | Y                       | As for #5 but also tests `partitions with different name but with the same NodeName`.
 
 
 # Local Installation & Running

molecule/test15/converge.yml

@@ -0,0 +1,27 @@
+---
+- name: Converge
+  hosts: all
+  vars:
+    openhpc_enable:
+      control: "{{ inventory_hostname in groups['testohpc_login'] }}"
+      batch: "{{ inventory_hostname in groups['testohpc_compute'] }}"
+      runtime: true
+    openhpc_slurm_control_host: "{{ groups['testohpc_login'] | first }}"
+    openhpc_slurm_partitions:
+      - name: "compute"
+        partition_params:
+          PreemptMode: requeue
+      - name: beta
+        groups:
+          - name: "compute"
+        partition_params:
+          PreemptMode: 'OFF'
+          Priority: 1000
+          Default: false
+          AllowAccounts: Group_own_thePartition
+    openhpc_cluster_name: testohpc
+    openhpc_slurm_configless: true
+  tasks:
+    - name: "Include ansible-role-openhpc"
+      include_role:
+        name: "{{ lookup('env', 'MOLECULE_PROJECT_DIRECTORY') | basename }}"

molecule/test15/molecule.yml

@@ -0,0 +1,44 @@
+---
+driver:
+  name: podman
+platforms:
+  - name: testohpc-login-0
+    image: ${MOLECULE_IMAGE}
+    pre_build_image: true
+    groups:
+      - testohpc_login
+    command: /sbin/init
+    tmpfs:
+      - /run
+      - /tmp
+    volumes:
+      - /sys/fs/cgroup:/sys/fs/cgroup:ro
+    network: net1
+  - name: testohpc-compute-0
+    image: ${MOLECULE_IMAGE}
+    pre_build_image: true
+    groups:
+      - testohpc_compute
+    command: /sbin/init
+    tmpfs:
+      - /run
+      - /tmp
+    volumes:
+      - /sys/fs/cgroup:/sys/fs/cgroup:ro
+    network: net1
+  - name: testohpc-compute-1
+    image: ${MOLECULE_IMAGE}
+    pre_build_image: true
+    groups:
+      - testohpc_compute
+    command: /sbin/init
+    tmpfs:
+      - /run
+      - /tmp
+    volumes:
+      - /sys/fs/cgroup:/sys/fs/cgroup:ro
+    network: net1
+provisioner:
+  name: ansible
+verifier:
+  name: ansible

molecule/test15/verify.yml

@@ -0,0 +1,16 @@
+---
+
+- name: Check slurm hostlist
+  hosts: testohpc_login
+  vars:
+    expected_sinfo: | # NB compute is default (*)                                             
+      'compute*,up,60-00:00:00,2,idle,testohpc-compute-[0-1]'
+      'beta,up,60-00:00:00,2,idle,testohpc-compute-[0-1]'
+  tasks:
+  - name: Get slurm partition info
+    command: sinfo --noheader --format="%P,%a,%l,%D,%t,%N" # using --format ensures we control whitespace
+    register: sinfo
+  - name:
+    assert:
+      that: "sinfo.stdout.split() == expected_sinfo.split()"
+      fail_msg: "FAILED - got {{ sinfo.stdout.split() }} expected {{ expected_sinfo.split() }}"

templates/slurm.conf.j2

@@ -150,10 +150,10 @@ NodeName={{ node }}
 # OpenHPC default configuration
 PropagateResourceLimitsExcept=MEMLOCK
 Epilog=/etc/slurm/slurm.epilog.clean
+{% set donehosts = [] %}
 {% for part in openhpc_slurm_partitions %}
     {% set nodelist = [] %}
     {% for group in part.get('groups', [part]) %}
-        
         {% set group_name = group.cluster_name|default(openhpc_cluster_name) ~ '_' ~ group.name %}
 # openhpc_slurm_partitions group: {{ group_name }}
         {% set inventory_group_hosts = groups.get(group_name, []) %}
@@ -164,9 +164,11 @@ Epilog=/etc/slurm/slurm.epilog.clean
             {% set ram_mb = (first_host_hv['ansible_memory_mb']['real']['total'] * (group.ram_multiplier | default(openhpc_ram_multiplier))) | int %}
             {% for hostlist in (inventory_group_hosts | hostlist_expression) %}
         {% set gres = ' Gres=%s' % (','.join(group.gres | map(attribute='conf') )) if 'gres' in group else '' %}
-
+            {% if hostlist not in donehosts %}
 NodeName={{ hostlist }} State=UNKNOWN RealMemory={{ group.get('ram_mb', ram_mb) }} Sockets={{first_host_hv['ansible_processor_count']}} CoresPerSocket={{ first_host_hv['ansible_processor_cores'] }} ThreadsPerCore={{ first_host_hv['ansible_processor_threads_per_core'] }}{{ gres }}
+            {% endif %}
                 {% set _ = nodelist.append(hostlist) %}
+                {% set _ = donehosts.append(hostlist) %}
             {% endfor %}{# nodes #}
         {% endif %}{# inventory_group_hosts #}
         {% for extra_node_defn in group.get('extra_nodes', []) %}
@@ -184,5 +186,4 @@ PartitionName={{part.name}} Default={{ part.get('default', 'YES') }} MaxTime={{
 NodeName=nonesuch
 
 {% if openhpc_slurm_configless %}SlurmctldParameters=enable_configless{% endif %}
-
 ReturnToService=2