Examples

[app]
sandbox-app-01 ansible_host=10.0.1.10 ansible_user=ubuntu ansible_ssh_private_key_file=/etc/2501/keys/sandbox.pem

---
- name: Fill up /var with large dummy files
  hosts: app
  become: true
  tasks:
    - name: Create a large log directory with old rotated logs
      file:
        path: /var/log/myapp
        state: directory

    - name: Generate 6GB of fake rotated logs
      shell: |
        for i in $(seq 1 60); do
          dd if=/dev/urandom of=/var/log/myapp/app.log.$i bs=1M count=100 2>/dev/null
        done
      args:
        creates: /var/log/myapp/app.log.60

    - name: Verify partition is above 90%
      shell: df /var | awk 'NR==2 {print $5}' | tr -d '%'
      register: usage
      failed_when: usage.stdout | int < 90

---
- name: Verify at least 5GB is free on /var
  hosts: app
  become: true
  tasks:
    - name: Get free space on /var in GB
      shell: df /var --output=avail -BG | tail -1 | tr -d 'G '
      register: free_gb

    - name: Assert at least 5GB free
      assert:
        that: free_gb.stdout | int >= 5
        fail_msg: "Only {{ free_gb.stdout }}GB free on /var, expected at least 5GB"

---
- name: Remove dummy log files
  hosts: app
  become: true
  tasks:
    - name: Delete generated log files
      file:
        path: /var/log/myapp
        state: absent
      ignore_errors: true

[web]
sandbox-web-01 ansible_host=10.0.1.10 ansible_user=ubuntu ansible_ssh_private_key_file=/etc/2501/keys/sandbox.pem

---
- name: Introduce broken nginx configuration
  hosts: web
  become: true
  tasks:
    - name: Ensure nginx is installed
      apt:
        name: nginx
        state: present
        update_cache: true

    - name: Write config with syntax error (missing semicolon)
      copy:
        dest: /etc/nginx/sites-available/default
        content: |
          server {
            listen 80
            root /var/www/html;
            index index.html;
          }

    - name: Attempt to reload nginx (will fail: intentional)
      systemd:
        name: nginx
        state: restarted
      ignore_errors: true

---
- name: Verify nginx is healthy
  hosts: web
  become: true
  tasks:
    - name: Config syntax is valid
      command: nginx -t

    - name: Service is active
      command: systemctl is-active nginx

    - name: Port 80 is responding
      uri:
        url: http://localhost:80
        status_code: [200, 301, 302]

---
- name: Reset nginx to clean state
  hosts: web
  become: true
  tasks:
    - name: Stop nginx
      systemd:
        name: nginx
        state: stopped
        enabled: false
      ignore_errors: true

    - name: Remove broken config
      file:
        path: /etc/nginx/sites-available/default
        state: absent
      ignore_errors: true

[k8s]
sandbox-k8s-01 ansible_host=10.0.1.30 ansible_user=ubuntu ansible_ssh_private_key_file=/etc/2501/keys/sandbox.pem

---
- name: Deploy a crashlooping workload
  hosts: k8s
  tasks:
    - name: Create production namespace
      command: kubectl create namespace production
      ignore_errors: true

    - name: Deploy api-server with a bad env var (wrong DB_HOST)
      shell: |
        kubectl apply -f - <<EOF
        apiVersion: apps/v1
        kind: Deployment
        metadata:
          name: api-server
          namespace: production
        spec:
          replicas: 1
          selector:
            matchLabels:
              app: api-server
          template:
            metadata:
              labels:
                app: api-server
            spec:
              containers:
              - name: api-server
                image: busybox
                command: ["sh", "-c"]
                args:
                  - |
                    if [ -z "$DB_HOST" ] || [ "$DB_HOST" = "CHANGEME" ]; then
                      echo "ERROR: DB_HOST is not configured" >&2
                      exit 1
                    fi
                    echo "Connected to $DB_HOST"
                    sleep infinity
                env:
                - name: DB_HOST
                  value: "CHANGEME"
        EOF

    - name: Wait for pod to enter CrashLoopBackOff
      shell: |
        for i in $(seq 1 30); do
          STATUS=$(kubectl get pods -n production -l app=api-server -o jsonpath='{.items[0].status.containerStatuses[0].state.waiting.reason}' 2>/dev/null)
          if [ "$STATUS" = "CrashLoopBackOff" ]; then exit 0; fi
          sleep 5
        done
        exit 1

---
- name: Verify api-server pod is running
  hosts: k8s
  tasks:
    - name: Wait for pod to be ready
      shell: kubectl wait --for=condition=ready pod -l app=api-server -n production --timeout=120s

    - name: Confirm pod is not in an error state
      shell: |
        STATUS=$(kubectl get pods -n production -l app=api-server -o jsonpath='{.items[0].status.phase}')
        [ "$STATUS" = "Running" ]

---
- name: Remove the test deployment
  hosts: k8s
  tasks:
    - name: Delete api-server deployment
      command: kubectl delete deployment api-server -n production
      ignore_errors: true

    - name: Delete production namespace
      command: kubectl delete namespace production
      ignore_errors: true