Merge branch 'master' into fix/state_save_locn

Author: sjpb

.github/workflows/ci.yml

@@ -43,6 +43,7 @@ jobs:
           - test12
           - test13
           - test14
+          - test15
 
         exclude:
           - image: 'centos:7'
@@ -65,6 +66,8 @@ jobs:
             scenario: test13
           - image: 'centos:7'
             scenario: test14
+          - image: 'centos:7'
+            scenario: test15
 
     steps:
       - name: Check out the codebase.

README.md

@@ -41,7 +41,7 @@ package in the image.
 
 ### slurm.conf
 
-`openhpc_slurm_partitions`: list of one or more slurm partitions.  Each partition may contain the following values:
+`openhpc_slurm_partitions`: Optional. List of one or more slurm partitions, default `[]`.  Each partition may contain the following values:
 * `groups`: If there are multiple node groups that make up the partition, a list of group objects can be defined here.
   Otherwise, `groups` can be omitted and the following attributes can be defined in the partition object:
   * `name`: The name of the nodes within this group.
@@ -57,9 +57,8 @@ package in the image.
 For each group (if used) or partition any nodes in an ansible inventory group `<cluster_name>_<group_name>` will be added to the group/partition. Note that:
 - 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, but if it is not then the play must contain at least one node from it (used to set processor information).
+- 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.
-- A group/partition definition which does not have either a corresponding inventory group or a `extra_nodes` will raise an error.
 
 `openhpc_job_maxtime`: A maximum time job limit in hours, minutes and seconds.  The default is `24:00:00`.
 

molecule/README.md

@@ -21,7 +21,8 @@ test10 | 1            | N                       | As for #5 but then tries to ad
 test11 | 1            | N                       | As for #5 but then deletes a node (actually changes the partition due to molecule/ansible limitations)
 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            |                         | As for #5 but also tests `extra_nodes` via State=DOWN nodes.
+test14 | 1            | N                       | As for #5 but also tests `extra_nodes` via State=DOWN nodes.
+test15 | 1            | N                       | No compute nodes.
 
 # Local Installation & Running
 
@@ -51,8 +52,9 @@ Then to run tests, e.g.::
 
     cd ansible-role-openhpc/
     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=centos:8.2.2004 molecule test --all
-    MOLECULE_IMAGE=centos:8.3.2011 molecule test --all
+    MOLECULE_IMAGE=rockylinux:8.5 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:
 

molecule/test15/converge.yml

@@ -0,0 +1,18 @@
+---
+- name: Converge
+  hosts: all
+  tasks:
+    - name: "Include ansible-role-openhpc"
+      include_role:
+        name: "{{ lookup('env', 'MOLECULE_PROJECT_DIRECTORY') | basename }}"
+      vars:
+        openhpc_enable:
+          control: "{{ inventory_hostname in groups['testohpc_control'] }}"
+          batch: false
+          runtime: true
+        openhpc_slurm_control_host: "{{ groups['testohpc_control'] | first }}"
+        openhpc_slurm_partitions:
+          - name: n/a
+        openhpc_cluster_name: testohpc
+        openhpc_slurm_configless: true
+

molecule/test15/molecule.yml

@@ -0,0 +1,26 @@
+---
+name: single partition, group is partition
+driver:
+  name: docker
+platforms:
+  - name: testohpc-control
+    image: ${MOLECULE_IMAGE}
+    pre_build_image: true
+    groups:
+      - testohpc_control
+    command: /sbin/init
+    tmpfs:
+      - /run
+      - /tmp
+    volumes:
+      - /sys/fs/cgroup:/sys/fs/cgroup:ro
+    networks:
+      - name: net1
+    docker_networks:
+      - name: net1
+        driver_options:
+          com.docker.network.driver.mtu: ${DOCKER_MTU:-1500} # 1500 is docker default
+provisioner:
+  name: ansible
+verifier:
+  name: ansible

molecule/test15/verify.yml

@@ -0,0 +1,12 @@
+---
+
+- name: Check slurm hostlist
+  hosts: testohpc_control
+  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:                        # PARTITION AVAIL  TIMELIMIT  NODES  STATE NODELIST
+      that: "sinfo.stdout_lines == ['n/a*,up,60-00:00:00,0,n/a,']"
+      fail_msg: "FAILED - actual value: {{ sinfo.stdout_lines }}"

tasks/runtime.yml

@@ -1,12 +1,13 @@
 ---
-- name: Fail if openhpc_slurm_control_host or openhpc_cluster_name or openhpc_slurm_partitions are undefined
-  fail:
-    msg: "Undefined openhpc_slurm_control_host or openhpc_cluster_name or openhpc_slurm_partitions, or latter is empty."
-  when:
-    openhpc_slurm_control_host == none or
-    openhpc_cluster_name == none or
-    openhpc_slurm_partitions | length == 0
-
+- name: Check openhpc_slurm_control_host, openhpc_cluster_name or openhpc_slurm_partitions exist
+  assert:
+    that:
+      - openhpc_slurm_control_host is defined
+      - openhpc_cluster_name is defined
+      - openhpc_cluster_name != ''
+      - openhpc_slurm_partitions is defined
+    fail_msg: "Undefined openhpc_slurm_control_host, openhpc_cluster_name or openhpc_slurm_partitions."
+  
 - name: Fail if configless mode selected when not on Centos 8
   fail:
     msg: "openhpc_slurm_configless = True requires Centos8 / OpenHPC v2"