Merge pull request #1295 from stackhpc/2024.1-cleanup-multinodes

CI: Clean up periodic multinode instances on CI hosting cloud

.github/workflows/stackhpc-ci-cleanup.yml

@@ -76,6 +76,26 @@ jobs:
           OS_APPLICATION_CREDENTIAL_ID: ${{ secrets.OS_APPLICATION_CREDENTIAL_ID }}
           OS_APPLICATION_CREDENTIAL_SECRET: ${{ secrets.OS_APPLICATION_CREDENTIAL_SECRET }}
 
+      - name: Clean up GH actions multinode instances over 12 hours old
+        run: |
+          result=0
+          changes_before=$(date -Imin -d -12hours)
+          for status in ACTIVE BUILD ERROR SHUTOFF; do
+              for instance in $(openstack server list --tags gh-actions-multinode --os-compute-api-version 2.66 --format value --column ID --changes-before $changes_before --status $status); do
+                  echo "Cleaning up $status instance $instance"
+                  openstack server show $instance
+                  if ! openstack server delete $instance; then
+                      echo "Failed to delete $status instance $instance"
+                      result=1
+                  fi
+              done
+          done
+          exit $result
+        env:
+          OS_CLOUD: openstack
+          OS_APPLICATION_CREDENTIAL_ID: ${{ secrets.OS_APPLICATION_CREDENTIAL_ID }}
+          OS_APPLICATION_CREDENTIAL_SECRET: ${{ secrets.OS_APPLICATION_CREDENTIAL_SECRET }}
+
       - name: Send message to Slack via Workflow Builder
         uses: slackapi/[email protected]
         with:

.github/workflows/stackhpc-multinode.yml

@@ -43,7 +43,7 @@ name: Multinode
           - never
           - success
       break_duration:
-        description: How long to break execution for (minutes)
+        description: How long to break execution for (minutes) (note that instances are cleaned up after 12h)
         type: number
         default: 60
       ssh_key: