Merge branch 'main' into feat/nodegroups-v1

Author: sjpb

.github/workflows/release-image.yml

@@ -0,0 +1,37 @@
+name: Release images
+on:
+  workflow_dispatch:
+  release:
+    types:
+      - published # should work for both pre-releases and releases
+env:
+  IMAGE_PATH: environments/.stackhpc/tofu/cluster_image.auto.tfvars.json
+jobs:
+  ci-image-release:
+    name: ci-image-release
+    runs-on: ubuntu-22.04
+    concurrency: ${{ github.workflow }}-${{ github.ref }}
+    strategy:
+      fail-fast: false
+      matrix:
+        build:
+          - RL8
+          - RL9
+    steps:
+      - uses: actions/checkout@v2
+
+      - name: Write s3cmd configuration
+        run: echo "${{ secrets.ARCUS_S3_CFG }}" > ~/.s3cfg
+
+      - name: Install s3cmd
+        run: |
+          sudo apt-get update
+          sudo apt-get --yes install s3cmd
+      
+      - name: Retrieve image name
+        run: |
+          TARGET_IMAGE=$(jq --arg version "${{ matrix.build }}" -r '.cluster_image[$version]' "${{ env.IMAGE_PATH }}")
+          echo "TARGET_IMAGE=${TARGET_IMAGE}" >> "$GITHUB_ENV"
+      
+      - name: Copy image from pre-release to release bucket
+        run: s3cmd cp s3://openhpc-images-prerelease/${{ env.TARGET_IMAGE }} s3://openhpc-images

.github/workflows/stackhpc.yml

@@ -230,6 +230,16 @@ jobs:
         env:
           DEMO_USER_PASSWORD: ${{ secrets.TEST_USER_PASSWORD }}
 
+      - name: Delete possible volume snapshot from slurm upgrade
+        run: |
+          . venv/bin/activate
+          . environments/.stackhpc/activate  
+          if [ -n "$SNAPSHOT" ]
+          then
+              echo Deleting $SNAPSHOT
+              openstack volume snapshot delete $SNAPSHOT
+          fi
+
       - name: Delete infrastructure
         run: |
           . venv/bin/activate

environments/.stackhpc/tofu/cluster_image.auto.tfvars.json

@@ -1,6 +1,6 @@
 {
     "cluster_image": {
-        "RL8": "openhpc-RL8-250506-1259-abb6394b",
-        "RL9": "openhpc-RL9-250506-1259-abb6394b"
+        "RL8": "openhpc-RL8-250514-1502-5a923b2c",
+        "RL9": "openhpc-RL9-250514-1502-5a923b2c"
     }
 }

environments/common/inventory/group_vars/all/openhpc.yml

@@ -70,3 +70,13 @@ ohpc_openhpc_repos:
 ohpc_default_extra_repos:
   "9": []
   "8": []
+
+# configure slurm database pre-upgrade backups:
+openhpc_slurm_accounting_storage_service: mysql
+openhpc_slurm_accounting_storage_backup_cmd: >-
+  openstack volume snapshot create
+  --volume {{ openhpc_cluster_name }}-state
+  --force
+  {{ openhpc_cluster_name }}-state-{{ ansible_date_time.iso8601_basic_short }}
+openhpc_slurm_accounting_storage_backup_host: localhost
+openhpc_slurm_accounting_storage_backup_become: false

environments/common/inventory/group_vars/all/systemd.yml

@@ -1,9 +1,11 @@
 _systemd_requiresmount_statedir: |
+  {% if appliances_state_dir is defined %}
   [Unit]
   RequiresMountsFor={{ appliances_state_dir | default('') }}
+  {% endif %}
 
-_systemd_dropins_statedir:
-  # mysql not included as role handles state dir correctly
+systemd_dropins:
+  # NB: mysql does not need _systemd_requiresmount_statedir as role handles state dir correctly
   opensearch:
     group: opensearch
     content: "{{ _systemd_requiresmount_statedir }}"
@@ -19,5 +21,3 @@ _systemd_dropins_statedir:
   prometheus:
     group: prometheus
     content: "{{ _systemd_requiresmount_statedir }}"
-
-systemd_dropins: "{{ _systemd_dropins_statedir if appliances_state_dir is defined else {} }}"

environments/common/inventory/group_vars/all/timestamps.yml

@@ -63,10 +63,10 @@ appliances_pulp_repos:
   openhpc_updates:
     '8':
       path: OpenHPC/2/updates/EL_8
-      timestamp: 20241218T154614
+      timestamp: 20250512T003315
     '9':
       path: OpenHPC/3/updates/EL_9
-      timestamp: 20241218T154614
+      timestamp: 20250510T003301
   grafana:
     '8':
       path: grafana/oss/rpm

requirements.yml

@@ -4,7 +4,7 @@ roles:
     version: v25.3.2
     name: stackhpc.nfs
   - src: https://github.com/stackhpc/ansible-role-openhpc.git
-    version: feat/nodegroups # TODO: bump to release
+    version: 5ceb9e1 # on feat/nodegroups-v2 TODO: bump to release
     name: stackhpc.openhpc
   - src: https://github.com/stackhpc/ansible-node-exporter.git
     version: stackhpc