Миграция с Nagios на Icinga2 в Австралии

define profiles::services::monitoring::docker_apps(
  Hash $app_list,
  Hash $apps_accessible_from,
  Hash $apps_access_list,
  Hash $webhost_defaults,
  Hash $webcheck_defaults,
  Hash $service_overrides,
  Hash $targets,
  Hash $app_checks,
  )
{
#### APPS ####
  $zone = $name
  $app_list.each | String $app_name, Hash $app_data |
  {

    $notify_group = { 'notify_group' => ($webcheck_defaults[$zone]['notify_group'] + pick($app_data['notify_group'], {} )) } # adds notifications for default group (systems) + any group defined in int/pm_docker_apps.eyaml

    $data = merge($webhost_defaults, $apps_accessible_from, $app_data)

    $site_domain = $app_data['site_domain']

    $regexp = pick($app_data['check_regex'], 'html')        # Pick a regex to check

    $check_url = $app_data['check_url'] ? {
      undef   => { 'http_uri' => '/' },
      default => { 'http_uri' => $app_data['check_url'] }
    }

    $check_regex = $regexp ?{
      'absent' => {},
      default  => {'http_expect_body_regex' => $regexp}
    }

    $site_domain.each | String $vhost, Hash $vdata | {        # Split an app by domains if there are two or more
      $vhost_name = {'http_vhost' => $vhost}

      $vars = $data['vars'] + $vhost_name + $check_regex + $check_url

      $web_ipaddress = is_array($vdata['web_ipaddress']) ? {  # Make IP-address an array if it's not, because askizzy has 2 ips and it's an array
        true  => $vdata['web_ipaddress'],
        false => [$vdata['web_ipaddress']],
      }

      $access_from_zones = [$zone] + $apps_access_list[$data['accessible_from']] # Merge default zone (where the app is defined) and extra zones if they exist
      $web_ipaddress.each | String $ip_address | {            # For each IP (if we have multiple)
        $suffix = length($web_ipaddress) ? {                  # If we have more than one - add IP as a suffix to this hostname to avoid duplicating resources
          1       => '',
          default => "_${ip_address}"
        }
        $octets = split($ip_address, '.')
        $ip_tag = "${octets[2]}.${octets[3]}" # Using last octet only causes a collision between nginx-vip 203.15.70.94 and ext. ip 49.255.194.94

        $access_from_zones.each | $zone_prefix |{
          $zone_target = $targets[$zone_prefix]

          $nginx_vip_name = "${zone_prefix}_nginx-vip-${ip_tag}" # If it's a host for ext - prefix becomes 'ext_' (ext_nginx-vip...)
          $nginx_host_vip = {
            $nginx_vip_name => {
              ensure        => present,
              target        => $zone_target,
              address       => $ip_address,
              check_command => 'hostalive',
              groups        => ['nginx_vip',],
            }
          }

          $ssl_vars = $app_checks['ssl']
          $regex_vars = $app_checks['http'] + $vars + $webcheck_defaults[$zone] + $notify_group

          if !defined( Profiles::Services::Monitoring::Host[$nginx_vip_name] ) {
          ensure_resources('profiles::services::monitoring::host', $nginx_host_vip)
          }

          if !defined( Icinga2::Object::Service["${nginx_vip_name}_ssl"] ) {
            icinga2::object::service {"${nginx_vip_name}_ssl":
              ensure         => $data['ensure'],
              assign         => ["host.name == $nginx_vip_name",],
              groups         => ['webchecks',],
              check_command  => 'ssl',
              check_interval => $service_overrides['ssl']['check_interval'],
              target         => $targets['services'],
              apply          => true,
              vars           => $ssl_vars
            }
          }
          if $regexp != 'absent'{
            if !defined(Icinga2::Object::Service["${vhost}${$suffix} regex"]){
              icinga2::object::service {"${vhost}${$suffix} regex":
                ensure          => $data['ensure'],
                assign          => ["match(*_nginx-vip-${ip_tag}, host.name)",],
                groups          => ['webchecks',],
                check_command   => 'http',
                check_interval  => $service_overrides['regex']['check_interval'],
                target          => $targets['services'],
                enable_flapping => true,
                apply           => true,
                vars            => $regex_vars
              }
            }
          }
        }
      }
    }
  }
}

class profiles::services::monitoring::config(
  Array $default_config,
  Array $hostgroups,
  Hash $hosts = {},
  Hash $host_defaults,
  Hash $services,
  Hash $service_defaults,
  Hash $service_overrides,
  Hash $webcheck_defaults,
  Hash $servicegroups,
  String $servicegroup_target,
  Hash $user_defaults,
  Hash $users,
  Hash $oncall,
  Hash $usergroup_defaults,
  Hash $usergroups,
  Hash $notifications,
  Hash $notification_defaults,
  Hash $notification_commands,
  Hash $timeperiods,
  Hash $webhost_defaults,
  Hash $apps_access_list,
  Hash $check_commands,
  Hash $hosts_api = {},
  Hash $targets = {},
  Hash $host_api_defaults = {},
)
{

  # Profiles::Services::Monitoring::Hostgroup <<| |>> # will be enabled when we move to icinga completely
#### APPS ####
  case $location {
    'int', 'ext': {
      $apps_by_zone = {}
    }
    'pm': {
      $int_apps         = hiera('int_docker_apps')
      $int_app_defaults = hiera('int_docker_app_common')

      $st_apps          = hiera('staging_docker_apps')
      $srs_apps         = hiera('pm_docker_apps_srs')
      $pm_apps          = hiera('pm_docker_apps') + $st_apps + $srs_apps
      $pm_app_defaults  = hiera('pm_docker_app_common')

      $apps_by_zone = {
        'int' => $int_apps,
        'pm'  => $pm_apps,
      }

      $app_access_by_zone = {
        'int' => {'accessible_from' => $int_app_defaults['accessible_from']},
        'pm'  => {'accessible_from' => $pm_app_defaults['accessible_from']},
      }
    }

    default: {
      fail('Please ensure the node has $location fact set (int, pm, ext)')
    }
  }

  file { '/etc/icinga2/conf.d/':
    ensure  => directory,
    recurse => true,
    purge   => true,
    owner   => 'icinga',
    group   => 'icinga',
    mode    => '0750',
    notify  => Service['icinga2'],
  }

  $default_config.each | String $file_name |{
    file {"/etc/icinga2/conf.d/${file_name}":
      ensure => present,
      source => "puppet:///modules/profiles/services/monitoring/default_config/${file_name}",
      owner  => 'icinga',
      group  => 'icinga',
      mode    => '0640',
    }
  }

  $app_checks = {
    'ssl' => $services['webchecks']['checks']['ssl']['vars'],
    'http' => $services['webchecks']['checks']['http_regexp']['vars']
  }

  $apps_by_zone.each | String $zone, Hash $app_list | {
    profiles::services::monitoring::docker_apps{$zone:
      app_list             => $app_list,
      apps_accessible_from => $app_access_by_zone[$zone],
      apps_access_list     => $apps_access_list,
      webhost_defaults     => $webhost_defaults,
      webcheck_defaults    => $webcheck_defaults,
      service_overrides    => $service_overrides,
      targets              => $targets,
      app_checks           => $app_checks,
    }
  }

####    HOSTS    ####

  # Profiles::Services::Monitoring::Host <<| |>> # This is for spaceship invasion when it's ready.
  $hosts_has_large_disks = query_nodes('mountpoints.*.size_bytes >= 1099511627776')

  $hosts.each | String $hostgroup, Hash $list_of_hosts_with_settings | {           # Splitting site lists by hostgroups - docker_host/gluster_host/etc
    $list_of_hosts_in_group = $list_of_hosts_with_settings['hosts']
    $hostgroup_settings     = $list_of_hosts_with_settings['settings']
    $merged_hostgroup_settings = deep_merge($host_defaults, $list_of_hosts_with_settings['settings'])
    $list_of_hosts_in_group.each | String $host_name, Hash $host_settings |{  # Splitting grouplists by hosts
      # Is this host in the array $hosts_has_large_disks ? If so set host.vars.has_large_disks
      if ( $hosts_has_large_disks.reduce(false) | $found, $value| { ( $value =~ "^${host_name}" ) or $found } ) {
        $vars_has_large_disks = { 'has_large_disks' => true }
      } else {
        $vars_has_large_disks = {}
      }
      $host_data = deep_merge($merged_hostgroup_settings, $host_settings)
      $hostgroup_settings_vars = pick($hostgroup_settings['vars'], {})
      $host_settings_vars = pick($host_settings['vars'], {})
      $host_notify_group = delete_undef_values($host_defaults['vars']['notify_group'] + $hostgroup_settings_vars['notify_group'] + $host_settings_vars['notify_group'])
      $host_data_vars = delete_undef_values(deep_merge($host_data['vars'] , {'notify_group' => $host_notify_group}, $vars_has_large_disks)) # Merging vars separately

      $hostgroups = delete_undef_values([$hostgroup] + $host_data['groups'])

      profiles::services::monitoring::host{$host_name:
        ensure             => $host_data['ensure'],
        display_name       => $host_data['display_name'],
        address            => $host_data['address'],
        groups             => $hostgroups,
        target             => $host_data['target'],
        check_command      => $host_data['check_command'],
        check_interval     => $host_data['check_interval'],
        max_check_attempts => $host_data['max_check_attempts'],
        vars               => $host_data_vars,
        template           => $host_data['template'],
      }
    }
  }
  if !empty($hosts_api){                                                                # All hosts managed by API
    $hosts_api.each | String $zone, Hash $hosts_api_zone | {                            # Split api hosts by zones
      $hosts_api_zone.each | String $hostgroup, Hash $list_of_hosts_with_settings | {   # Splitting site lists by hostgroups - docker_host/gluster_host/etc
        $list_of_hosts_in_group = $list_of_hosts_with_settings['hosts']
        $hostgroup_settings     = $list_of_hosts_with_settings['settings']
        $merged_hostgroup_settings = deep_merge($host_api_defaults, $list_of_hosts_with_settings['settings'])
        $list_of_hosts_in_group.each | String $host_name, Hash $host_settings |{        # Splitting grouplists by hosts
          # Is this host in the array $hosts_has_large_disks ? If so set host.vars.has_large_disks
          if ( $hosts_has_large_disks.reduce(false) | $found, $value| { ( $value =~ "^${host_name}" ) or $found } ) {
            $vars_has_large_disks = { 'has_large_disks' => true }
          } else {
            $vars_has_large_disks = {}
          }
          $host_data = deep_merge($merged_hostgroup_settings, $host_settings)
          $hostgroup_settings_vars = pick($hostgroup_settings['vars'], {})

          $host_settings_vars = pick($host_settings['vars'], {})
          $host_api_notify_group = delete_undef_values($host_defaults['vars']['notify_group'] + $hostgroup_settings_vars['notify_group'] + $host_settings_vars['notify_group'])
          $host_data_vars = delete_undef_values(deep_merge($host_data['vars'] , {'notify_group' => $host_api_notify_group}, $vars_has_large_disks))
          $hostgroups = delete_undef_values([$hostgroup] + $host_data['groups'])

          if defined(Profiles::Services::Monitoring::Host[$host_name]){
            $hostname = "${host_name}_from_${zone}"
          }
          else
          {
            $hostname = $host_name
          }
          profiles::services::monitoring::host{$hostname:
            ensure             => $host_data['ensure'],
            display_name       => $host_data['display_name'],
            address            => $host_data['address'],
            groups             => $hostgroups,
            target             => "${host_data['target_base']}/${zone}/hosts.conf",
            check_command      => $host_data['check_command'],
            check_interval     => $host_data['check_interval'],
            max_check_attempts => $host_data['max_check_attempts'],
            vars               => $host_data_vars,
            template           => $host_data['template'],
          }
        }
      }
    }
  }

#### END OF HOSTS ####

####   SERVICES   ####

  $services.each | String $service_group, Hash $s_list |{             # Service_group and list of services in that group
    $service_list = $s_list['checks']                                 # List of actual checks, separately from SG settings
    $service_list.each | String $service_name, Hash $data |{

      $merged_defaults = merge($service_defaults, $s_list['settings']) # global service defaults + service group defaults
      $merged_data = merge($merged_defaults, $data)

      $settings_vars = pick($s_list['settings']['vars'], {})
      $this_service_vars = pick($data['vars'], {})
      $all_service_vars = delete_undef_values($service_defaults['vars'] + $settings_vars + $this_service_vars)

      # If we override default check_timeout, but not nrpe_timeout, make nrpe_timeout the same as check_timeout
      if ( $merged_data['check_timeout'] and ! $this_service_vars['nrpe_timeout'] ) {
        # NB: Icinga will convert 1m to 60 automatically!
        $nrpe = { 'nrpe_timeout' => $merged_data['check_timeout'] }
      } else {
        $nrpe = {}
      }

      # By default we use nrpe and all commands are run via nrpe. So vars.nrpe_command = $service_name is a default value
      # If it's server-side Icinga command - we don't need 'nrpe_command'
      # but there is no harm to have that var and the code is shorter

      if $merged_data['check_command'] == 'nrpe'{
        $check_command = $merged_data['vars']['nrpe_command'] ? {
          undef   => { 'nrpe_command' => $service_name },
          default => { 'nrpe_command' => $merged_data['vars']['nrpe_command'] }
        }
      }else{
        $check_command = {}
      }

      # Assembling $vars from Global Default service settings, servicegroup settings, this particular check settings and let's not forget nrpe settings.
      if $all_service_vars['graphite_template'] {
        $graphite_template = {'check_command' => $all_service_vars['graphite_template']}
      }else{
        $graphite_template = {'check_command' => $service_name}
      }
      $service_notify = [] + pick($settings_vars['notify_group'], []) + pick($this_service_vars['notify_group'], []) # pick is required everywhere, otherwise becomes "The value '' cannot be converted to Numeric"

      $service_notify_group = $service_notify ? {
        []      => $service_defaults['vars']['notify_group'],
        default => $service_notify
      } # Assing default group (systems) if no other groups are defined

      $vars = $all_service_vars + $nrpe + $check_command + $graphite_template + {'notify_group' => $service_notify_group}

      # This needs to be merged separately, because merging it as part of MERGED_DATA overwrites arrays instead of merging them, so we lose some "assign" and "ignore" values

      $assign = delete_undef_values($service_defaults['assign'] + $s_list['settings']['assign'] + $data['assign'])
      $ignore = delete_undef_values($service_defaults['ignore'] + $s_list['settings']['ignore'] + $data['ignore'])

      icinga2::object::service {$service_name:
        ensure             => $merged_data['ensure'],
        apply              => $merged_data['apply'],
        enable_flapping    => $merged_data['enable_flapping'],
        assign             => $assign,
        ignore             => $ignore,
        groups             => [$service_group],
        check_command      => $merged_data['check_command'],
        check_interval     => $merged_data['check_interval'],
        check_timeout      => $merged_data['check_timeout'],
        check_period       => $merged_data['check_period'],
        display_name       => $merged_data['display_name'],
        event_command      => $merged_data['event_command'],
        retry_interval     => $merged_data['retry_interval'],
        max_check_attempts => $merged_data['max_check_attempts'],
        target             => $merged_data['target'],
        vars               => $vars,
        template           => $merged_data['template'],
      }
    }
  }
#### END OF SERVICES ####

#### OTHER BORING STUFF ####

  $servicegroups.each | $servicegroup, $description |{
    icinga2::object::servicegroup{ $servicegroup:
      target       => $servicegroup_target,
      display_name => $description
    }
  }

  $hostgroups.each| String $hostgroup |{
    profiles::services::monitoring::hostgroup { $hostgroup:}
  }

  $notifications.each | String $name, Hash $settings |{

    $assign = pick($notification_defaults['assign'], []) + $settings['assign']
    $ignore = pick($notification_defaults['ignore'], []) + $settings['ignore']

    $merged_settings = $settings + $notification_defaults

    icinga2::object::notification{$name:
      target       => $merged_settings['target'],
      apply        => $merged_settings['apply'],
      apply_target => $merged_settings['apply_target'],
      command      => $merged_settings['command'],
      interval     => $merged_settings['interval'],
      states       => $merged_settings['states'],
      types        => $merged_settings['types'],
      assign       => delete_undef_values($assign),
      ignore       => delete_undef_values($ignore),
      user_groups  => $merged_settings['user_groups'],
      period       => $merged_settings['period'],
      vars         => $merged_settings['vars'],
    }
  }

  # Merging notification settings for users with other settings
  $users_oncall = deep_merge($users, $oncall)
  # Magic. Do not touch.
  create_resources('icinga2::object::user', $users_oncall, $user_defaults)
  create_resources('icinga2::object::usergroup', $usergroups, $usergroup_defaults)
  create_resources('icinga2::object::timeperiod',$timeperiods)
  create_resources('icinga2::object::checkcommand', $check_commands)
  create_resources('icinga2::object::notificationcommand', $notification_commands)

  profiles::services::sudoers { 'icinga_runs_ping_l2':
    ensure            => present,
    sudoersd_template => 'profiles/os/redhat/centos7/sudoers/icinga.erb',
  }

}

profiles::services::monitoring::config::services:
  perf_checks:
    settings:
      check_interval: '2m'
      assign:
        - 'host.vars.type == linux'
    checks:
      procs: {}
      load: {}
      memory: {}
      disk:
        check_interval: '5m'
        vars:
          notification_period: '24x7'
      disk_iops:
        vars:
          notifications:
            - 'silent'
      cpu:
        vars:
          notifications:
            - 'silent'
      dns_fqdn:
        check_interval: '15m'
        ignore:
          - 'xenserver in host.groups'
        vars:
          notifications:
            - 'silent'
      iftraffic_nrpe:
        vars:
          notifications:
            - 'silent'
  logging:
    settings:
      assign:
        - 'logserver in host.groups'
    checks:
       rsyslog: {}
      nginx_limit_req_other: {}
      nginx_limit_req_s2s: {}
      nginx_limit_req_s2x: {}
      nginx_limit_req_srs: {}
     logstash: {}
      logstash_api:
        vars:
          notifications:
            - 'silent'