Use base-64 encoded munge key

README.md

@@ -42,7 +42,7 @@ each list element:
 
 `openhpc_slurm_configless`: Optional, default false. If true then slurm's ["configless" mode](https://slurm.schedmd.com/configless_slurm.html) is used.
 
-`openhpc_munge_key`: Optional. Define a munge key to use. If not provided then one is generated but the `openhpc_slurm_control_host` must be in the play.
+`openhpc_munge_key_b64`: Optional. A base-64 encoded munge key. If not provided then the one generated on package install is used, but the `openhpc_slurm_control_host` must be in the play.
 
 `openhpc_login_only_nodes`: Optional. If using "configless" mode specify the name of an ansible group containing nodes which are login-only nodes (i.e. not also control nodes), if required. These nodes will run `slurmd` to contact the control node for config.
 

defaults/main.yml

@@ -131,7 +131,7 @@ ohpc_default_extra_repos:
 # Concatenate all repo definitions here
 ohpc_repos: "{{ ohpc_openhpc_repos[ansible_distribution_major_version] + ohpc_default_extra_repos[ansible_distribution_major_version] + openhpc_extra_repos }}"
 
-openhpc_munge_key:
+openhpc_munge_key_b64:
 openhpc_login_only_nodes: ''
 openhpc_module_system_install: true
 

tasks/runtime.yml

@@ -18,31 +18,17 @@
     state: directory
   when: inventory_hostname == openhpc_slurm_control_host
 
-- name: Generate a Munge key on control host
-  # NB this is usually a no-op as the package install actually generates a (node-unique) one, so won't usually trigger handler
-  command: "dd if=/dev/urandom of=/etc/munge/munge.key bs=1 count=1024"
-  args:
-    creates: "/etc/munge/munge.key"
-  when: inventory_hostname == openhpc_slurm_control_host
-
 - name: Retrieve Munge key from control host
+  # package install generates a node-unique one
   slurp:
     src: "/etc/munge/munge.key"
   register: openhpc_control_munge_key
   delegate_to: "{{ openhpc_slurm_control_host }}"
   when: openhpc_slurm_control_host in ansible_play_hosts
 
-- name: Fix permissions on /etc to pass Munge startup checks
-  # Rocky-9-GenericCloud-Base-9.4-20240523.0.x86_64.qcow2 makes /etc g=rwx rather than g=rx (where group=root)
-  # which fails munged startup checks
-  file:
-    path: /etc
-    state: directory
-    mode: g-w
-
 - name: Write Munge key
   copy:
-    content: "{{ openhpc_munge_key or (openhpc_control_munge_key.content | b64decode) }}"
+    content: "{{ (openhpc_munge_key_b64 or openhpc_control_munge_key.content) | b64decode }}"
     dest: "/etc/munge/munge.key"
     owner: munge
     group: munge

tasks/validate.yml

@@ -32,9 +32,16 @@
   loop: "{{ openhpc_nodegroups }}"
   run_once: true
 
-- name: Fail if configuration is old
+- name: Fail if partition configuration is outdated
   assert:
     that: openhpc_slurm_partitions is not defined
     fail_msg: stackhpc.openhpc parameter openhpc_slurm_partitions has been replaced - see openhpc_nodegroups and openhpc_partitions
   delegate_to: localhost
   run_once: true
+
+- name: Fail if munge key configuration is outdated
+  assert:
+    that: openhpc_munge_key is not defined
+    fail_msg: stackhpc.openhpc parameter openhpc_munge_key has been replaced with openhpc_munge_key_b64
+  delegate_to: localhost
+  run_once: true