Merge branch 'main' into feat/extend-ood

Author: bertiethorpe

.github/bin/get-s3-image.sh

@@ -17,7 +17,7 @@ if [ -n "$image_exists" ]; then
 else
     echo "Image $image_name not found in OpenStack. Getting it from S3."
 
-    wget https://object.arcus.openstack.hpc.cam.ac.uk/swift/v1/AUTH_3a06571936a0424bb40bc5c672c4ccb1/$bucket_name/$image_name --progress=dot:giga
+    wget https://leafcloud.store/swift/v1/AUTH_f39848421b2747148400ad8eeae8d536/$bucket_name/$image_name --progress=dot:giga
 
     echo "Uploading image $image_name to OpenStack..."
     openstack image create --file $image_name --disk-format qcow2 $image_name --progress

.github/workflows/fatimage.yml

@@ -31,7 +31,7 @@ jobs:
             source_image_name: Rocky-8-GenericCloud-Base-8.10-20240528.0.x86_64.raw
             inventory_groups: control,compute,login,update
           - image_name: openhpc-RL9
-            source_image_name: Rocky-9-GenericCloud-Base-9.5-20241118.0.x86_64.raw
+            source_image_name: Rocky-9-GenericCloud-Base-9.6-20250531.0.x86_64.qcow2
             inventory_groups: control,compute,login,update
     env:
       ANSIBLE_FORCE_COLOR: True

.github/workflows/release-image.yml

@@ -21,7 +21,7 @@ jobs:
       - uses: actions/checkout@v2
 
       - name: Write s3cmd configuration
-        run: echo "${{ secrets.ARCUS_S3_CFG }}" > ~/.s3cfg
+        run: echo "${{ secrets.LEAFCLOUD_S3_CFG }}" > ~/.s3cfg
 
       - name: Install s3cmd
         run: |

.github/workflows/s3-image-sync.yml

@@ -1,4 +1,4 @@
-name: Upload CI-tested images to Arcus S3 and sync clouds
+name: Upload CI-tested images to Leafcloud S3 and sync clouds
 on:
   workflow_dispatch:
   push:
@@ -21,7 +21,7 @@ jobs:
 
       - name: Write s3cmd configuration
         run: |
-          echo "${{ secrets['ARCUS_S3_CFG'] }}" > ~/.s3cfg
+          echo "${{ secrets['LEAFCLOUD_S3_CFG'] }}" > ~/.s3cfg
         shell: bash
 
       - name: Install s3cmd
@@ -73,7 +73,7 @@ jobs:
 
       - name: Write s3cmd configuration
         run: |
-          echo "${{ secrets['ARCUS_S3_CFG'] }}" > ~/.s3cfg
+          echo "${{ secrets['LEAFCLOUD_S3_CFG'] }}" > ~/.s3cfg
         shell: bash
 
       - name: Install s3cmd and qemu-utils

.github/workflows/stackhpc.yml

@@ -9,8 +9,7 @@ on:
       - '**'
       - '!dev/**'
       - 'dev/setup-env.sh'
-      - '!docs/**'
-      - '!README.md'
+      - '!**.md'
       - '!.gitignore'
       - '!.github/workflows/'
       - '.github/workflows/stackhpc'
@@ -19,8 +18,7 @@ on:
       - '**'
       - '!dev/**'
       - 'dev/setup-env.sh'
-      - '!docs/**'
-      - '!README.md'
+      - '!**.md'
       - '!.gitignore'
       - '!.github/workflows/'
       - '.github/workflows/stackhpc'

.github/workflows/upload-release-image.yml.sample

@@ -19,7 +19,7 @@ on:
     inputs:
       image_name:
         type: string
-        description: Image name from: (https://object.arcus.openstack.hpc.cam.ac.uk/swift/v1/AUTH_3a06571936a0424bb40bc5c672c4ccb1/{BUCKET_NAME})
+        description: Image name from: (https://leafcloud.store/swift/v1/AUTH_f39848421b2747148400ad8eeae8d536/{BUCKET_NAME})
         required: true
       bucket_name:
         type: choice

README.md

@@ -61,7 +61,7 @@ Run the following from the repository root to activate the venv:
 Use the `cookiecutter` template to create a new environment to hold your configuration:
 
     cd environments
-    cookiecutter skeleton
+    cookiecutter ../cookiecutter
 
 and follow the prompts to complete the environment name and description.
 

ansible/.gitignore

@@ -96,3 +96,5 @@ roles/*
 !roles/nhc/**
 !roles/eessi/
 !roles/eessi/**
+!roles/topology/
+!roles/topology/**

ansible/fatimage.yml

@@ -190,6 +190,11 @@
         tasks_from: install.yml
       when: "'alertmanager' in group_names"
 
+    - name: Download HPL source
+      include_role:
+        name: hpctests
+        tasks_from: source-hpl.yml
+
 - hosts: prometheus
   become: yes
   gather_facts: yes
@@ -262,7 +267,7 @@
         name: grafana-dashboards
 
 - name: Add support for NVIDIA GPU auto detection to Slurm
-  hosts: cuda
+  hosts: slurm_recompile
   become: yes
   tasks:
     - name: Recompile slurm

ansible/roles/alertmanager/README.md

@@ -11,12 +11,9 @@ Note that:
 - No Grafana dashboard for alerts is currently provided.
 
 Alertmanager is enabled by default on the `control` node in the
-[everything](../../../environments/common/layouts/everything) template which
-`cookiecutter` uses for a new environment's `inventory/groups` file.
+`site` environment's `inventory/groups` file.
 
 In general usage may only require:
-- Adding the `control` node into the `alertmanager` group in `environments/site/groups`
-  if upgrading an existing environment.
 - Enabling the Slack integration (see section below).
 - Possibly setting `alertmanager_web_external_url`.