self-healing-sig/use-cases/heat-mistral-aodh/lb_server.yaml

heat_template_version: rocky
description: A load-balancer server
parameters:
  image:
    type: string
    description: Image used for servers
  key_name:
    type: string
    description: SSH key to connect to the servers
  flavor:
    type: string
    description: flavor used by the servers
  security_group:
    type: string
    description: security_group used by the web servers
  pool_id:
    type: string
    description: Pool to contact
  user_data:
    type: string
    description: Server user_data
  metadata:
    type: json
  network:
    type: string
    description: Network used by the server
  subnet:
    type: string
    description: Subnet used by the server
  external_network:
    type: string
    description: UUID or Name of a Neutron external network
  root_stack_id:
    type: string
    default: ""

conditions:
  is_standalone: {equals: [{get_param: root_stack_id}, ""]}

resources:
  config:
    type: OS::Heat::SoftwareConfig
    properties:
      group: script
      inputs:
      - name: host
      - name: version
      outputs:
      - name: result
      config:
        get_file: nginx-script.sh

  deployment:
    type: OS::Heat::SoftwareDeployment
    properties:
      config:
        get_resource: config
      server:
        get_resource: server
      input_values:
        host: { get_attr: [server, first_address] }
        version: "v1.0.0"

  server:
    type: OS::Nova::Server
    properties:
      flavor: {get_param: flavor}
      security_groups: [{get_param: security_group} ]
      image: {get_param: image}
      key_name: {get_param: key_name}
      metadata: {get_param: metadata}
      user_data: {get_param: user_data}
      user_data_format: SOFTWARE_CONFIG
      networks:
        - {network: {get_param: network} }

  member:
    #type: OS::Neutron::LBaaS::PoolMember
    type: OS::Octavia::PoolMember
    properties:
      pool: {get_param: pool_id}
      address: {get_attr: [server, first_address]}
      protocol_port: 80
      subnet: {get_param: subnet}

  server_floating_ip_assoc:
    type: OS::Neutron::FloatingIPAssociation
    properties:
      floatingip_id: {get_resource: floating_ip}
      port_id: {get_attr: [server, addresses, {get_param: network}, 0, port]}

  floating_ip:
    type: OS::Neutron::FloatingIP
    properties:
      floating_network: {get_param: external_network}

  alarm_queue:
    type: OS::Zaqar::Queue

  stop_event_alarm:
    type: OS::Aodh::EventAlarm
    properties:
      event_type: compute.instance.update
      query:
        - field: traits.instance_id
          value: {get_resource: server}
          op: eq
        - field: traits.state
          value: stopped
          op: eq
      alarm_queues:
       - {get_resource: alarm_queue}

  error_event_alarm:
    type: OS::Aodh::EventAlarm
    properties:
      event_type: compute.instance.update
      query:
        - field: traits.instance_id
          value: {get_resource: server}
          op: eq
        - field: traits.state
          value: error
          op: eq
      alarm_queues:
       - {get_resource: alarm_queue}

  deleted_event_alarm:
    type: OS::Aodh::EventAlarm
    properties:
      event_type: compute.instance.delete.*
      query:
        - field: traits.instance_id
          value: {get_resource: server}
          op: eq
      alarm_queues:
       - {get_resource: alarm_queue}

  # The Aodh event alarm does not take effect immediately; it may take up to
  # 60s (by default) for the event_alarm_cache_ttl to expire and the tenant's
  # alarm data to be loaded. This resource ensures the stack is not completed
  # until the alarm is active. See https://bugs.launchpad.net/aodh/+bug/1651273
  alarm_cache_wait:
    type: OS::Heat::TestResource
    properties:
      action_wait_secs:
        create: 60
        update: 60
      value:
        list_join:
          - ''
          - - {get_attr: [stop_event_alarm, show]}
            - {get_attr: [error_event_alarm, show]}
            - {get_attr: [deleted_event_alarm, show]}

  alarm_subscription:
    type: OS::Zaqar::MistralTrigger
    properties:
      queue_name: {get_resource: alarm_queue}
      workflow_id: {get_resource: autoheal}
      input:
        stack_id: {get_param: "OS::stack_id"}
        root_stack_id:
          if:
            - is_standalone
            - {get_param: "OS::stack_id"}
            - {get_param: "root_stack_id"}

  autoheal:
    type: OS::Mistral::Workflow
    properties:
      description: >
        Mark a server as unhealthy and commence a stack update to replace it.        
      input:
        stack_id:
        root_stack_id:
      type: direct
      tasks:
        - name: resources_mark_unhealthy
          action:
            list_join:
              - ' '
              - - heat.resources_mark_unhealthy
                - stack_id=<% $.stack_id %>
                - resource_name=<% env().notification.body.reason_data.event.traits.where($[0] = 'instance_id').select($[2]).first() %>
                - mark_unhealthy=true
                - resource_status_reason='Marked by alarm'
          on_success:
            - stacks_update
        - name: stacks_update
          action: heat.stacks_update stack_id=<% $.root_stack_id %> existing=true

outputs:
  server_ip:
    description: IP Address of the load-balanced server.
    value: { get_attr: [server, first_address] }
  lb_member:
    description: LB member details.
    value: { get_attr: [member, show] }