portfolio/enterprise-infra-simulator/scenarios/scaling_event.yml

---
- name: Enterprise Scaling Event Scenario
  hosts: all
  become: yes
  gather_facts: yes
  vars:
    scaling_threshold: 80
    cooldown_period: 300
    max_scale_up: 5
    min_instances: 2

  pre_tasks:
    - name: Log scenario start
      lineinfile:
        path: "/var/log/scaling_scenario.log"
        line: "{{ ansible_date_time.iso8601 }} - Starting scaling event scenario"
        create: yes

    - name: Check current load
      command: uptime
      register: system_load
      changed_when: false

    - name: Parse load average
      set_fact:
        load_1min: "{{ system_load.stdout.split(',')[0].split()[-1] | float }}"
        load_5min: "{{ system_load.stdout.split(',')[1] | float }}"
        load_15min: "{{ system_load.stdout.split(',')[2] | float }}"

  tasks:
    - name: Evaluate scaling conditions
      set_fact:
        scale_up_needed: "{{ load_5min > scaling_threshold }}"
        scale_down_needed: "{{ load_5min < (scaling_threshold * 0.3) }}"

    - name: Scale up web servers
      include_role:
        name: scale_up
        tasks_from: web_servers
      vars:
        scale_count: "{{ [max_scale_up, (load_5min / 10) | int] | min }}"
      when: scale_up_needed and "'webservers' in group_names"

    - name: Scale up database servers
      include_role:
        name: scale_up
        tasks_from: database_servers
      vars:
        scale_count: "{{ [2, (load_5min / 20) | int] | min }}"
      when: scale_up_needed and "'databases' in group_names"

    - name: Update load balancer configuration
      include_role:
        name: load_balancer
        tasks_from: update_backends
      when: scale_up_needed

    - name: Scale down web servers
      include_role:
        name: scale_down
        tasks_from: web_servers
      vars:
        scale_count: "{{ [(inventory_hostname | regex_findall('[0-9]+') | first | int) - min_instances, 1] | max }}"
      when: scale_down_needed and "'webservers' in group_names" and (inventory_hostname | regex_findall('[0-9]+') | first | int) > min_instances

    - name: Wait for cooldown period
      pause:
        seconds: "{{ cooldown_period }}"
      when: scale_up_needed or scale_down_needed

    - name: Verify scaling results
      uri:
        url: http://localhost/health
        method: GET
        status_code: 200
      register: health_check
      until: health_check.status == 200
      retries: 5
      delay: 10
      when: "'webservers' in group_names"

    - name: Update monitoring thresholds
      include_role:
        name: monitoring
        tasks_from: update_alerts
      vars:
        new_threshold: "{{ scaling_threshold + 10 }}"

    - name: Send scaling notification
      mail:
        to: "{{ scaling_notification_email | default('infra-team@company.com') }}"
        subject: "Infrastructure Scaling Event - {{ inventory_hostname }}"
        body: |
          Scaling event completed on {{ inventory_hostname }}

          Load averages: {{ load_1min }}, {{ load_5min }}, {{ load_15min }}
          Action taken: {{ 'Scale Up' if scale_up_needed else 'Scale Down' if scale_down_needed else 'No Action' }}
          Health check: {{ 'PASSED' if health_check.status == 200 else 'FAILED' }}

          See /var/log/scaling_scenario.log for details
      when: scaling_notification_email is defined
      ignore_errors: yes

  post_tasks:
    - name: Generate scaling scenario report
      template:
        src: templates/scaling_scenario_report.j2
        dest: "/var/log/scaling_scenario_report_{{ ansible_date_time.iso8601 }}.log"
      vars:
        scenario_outcome: "{{ 'SUCCESS' if health_check.status == 200 else 'WARNING' }}"
        load_metrics: "{{ load_1min }}, {{ load_5min }}, {{ load_15min }}"

    - name: Log scenario completion
      lineinfile:
        path: "/var/log/scaling_scenario.log"
        line: "{{ ansible_date_time.iso8601 }} - Scaling event scenario completed"