Defined Type: monitoring::host
- Defined in:
- modules/monitoring/manifests/host.pp
Overview
Define monitoring::host
Exports the resource that monitors hosts in icinga
4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 |
# File 'modules/monitoring/manifests/host.pp', line 4
define monitoring::host (
$ip_address = $facts['ipaddress'],
$os = $facts['operatingsystem'],
$host_fqdn = undef,
$group = undef,
$ensure = present,
$critical = false,
$parents = undef,
$contact_group = lookup('contactgroups', {'default_value' => 'admins'}),
$mgmt_contact_group = 'admins',
$notifications_enabled = '1',
Hash[String, String] $mgmt_parents = lookup('monitoring::mgmt_parents', {'default_value' => {}}), # lint:ignore:wmf_styleguide
String $cluster = lookup('cluster'),
String $hostgroup_default = lookup('nagios_group', {'default_value' => "${cluster}_${::site}"}), # lint:ignore:wmf_styleguide
){
$nagios_address = $host_fqdn ? {
undef => $ip_address,
default => $host_fqdn,
}
# Determine the hostgroup:
# If defined in the declaration of resource, we use it;
# If not, adopt the standard format
$hostgroup = $group ? {
/.+/ => $group,
default => $hostgroup_default,
}
$real_contact_groups = $critical ? {
true => "${contact_group},sms,admins",
default => $contact_group,
}
# Define the nagios host instance
# The following if guard is there to ensure we only try to set per host
# attributes in the case the host exports it's configuration. Since this
# definition is also used for non-exported resources as well, this if guard
# is required
if $title == $::hostname {
$image = $os ? {
'Ubuntu' => 'ubuntu',
'Debian' => 'debian',
'Junos' => 'juniper',
default => 'linux40'
}
$icon_image = "vendors/${image}.png"
$vrml_image = "vendors/${image}.png"
$statusmap_image = "vendors/${image}.gd2"
# Allow overriding the parents of a device. This makes the exposed API
# more consistent, even though it's doubtful we will ever use this
# functionality in the case of an exported host
if $parents {
$real_parents = $parents
} elsif ($facts['is_virtual'] == false) and $facts['lldp_parent'] {
# Only set the (automatic) parent for physical hosts. We want to
# still alert for each individual VM when the hosts die, as:
# a) just a host DOWN alert for the VM node is too inconspicuous,
# b) it's usually the case that VMs can be relocated to other nodes
$real_parents = $facts['lldp_parent']
} else {
$real_parents = undef
}
# We have a BMC, and the BMC is configured and it has an IP address
# We always monitor the BMC so never skip notifications
if $facts['has_ipmi'] and $facts['ipmi_lan'] and 'ipaddress' in $facts['ipmi_lan'] {
$mgmt_host = {
"${title}.mgmt" => {
ensure => $ensure,
host_name => "${title}.mgmt",
parents => $mgmt_parents[$::site],
address => $facts['ipmi_lan']['ipaddress'],
hostgroups => 'mgmt',
check_command => 'check_ping!500,20%!2000,100%',
check_period => '24x7',
max_check_attempts => 2,
contact_groups => "${mgmt_contact_group},admins",
notification_interval => 0,
notification_period => '24x7',
notification_options => 'd,u,r,f',
icon_image => undef,
vrml_image => undef,
statusmap_image => undef,
}
}
} else {
$mgmt_host = undef
}
# Populate a network related hostgroup for directly connected to switches
# hosts
if $facts['lldp_parent'] and $facts['lldp_parent'] =~ /asw|csw/ {
$hostgroups = "${hostgroup},${facts['lldp_parent']}"
} else {
$hostgroups = $hostgroup
}
} else {
$icon_image = undef
$vrml_image = undef
$statusmap_image = undef
$real_parents = $parents
$mgmt_host = undef
$hostgroups = $hostgroup
}
$host = {
"${title}" => {
ensure => $ensure,
host_name => $title,
parents => $real_parents,
address => $nagios_address,
hostgroups => $hostgroups,
check_command => 'check_ping!500,20%!2000,100%',
check_period => '24x7',
max_check_attempts => 2,
notifications_enabled => $notifications_enabled,
contact_groups => $real_contact_groups,
notification_interval => 0,
notification_period => '24x7',
notification_options => 'd,u,r,f',
icon_image => $icon_image,
vrml_image => $vrml_image,
statusmap_image => $statusmap_image,
},
}
# This is a hack. We detect if we are running on the scope of an icinga
# host and avoid exporting the resource if yes
if defined(Class['icinga']) {
$rtype = 'nagios_host'
} else {
$rtype = 'monitoring::exported_nagios_host'
}
create_resources($rtype, $host)
if !empty($mgmt_host) {
create_resources($rtype, $mgmt_host)
# We always monitor the BMC so never skip notifications
monitoring::service { "dns_${title}.mgmt":
description => 'DNS',
host => "${title}.mgmt",
check_command => "check_fqdn!${title}.mgmt.${::site}.wmnet",
notifications_enabled => '1',
group => 'mgmt',
check_interval => 60,
retry_interval => 60,
notes_url => 'https://wikitech.wikimedia.org/wiki/Dc-operations/Hardware_Troubleshooting_Runbook',
}
monitoring::service { "ssh_${title}.mgmt":
description => 'SSH',
host => "${title}.mgmt",
check_command => 'check_ssh',
notifications_enabled => '1',
group => 'mgmt',
check_interval => 60,
retry_interval => 60,
notes_url => 'https://wikitech.wikimedia.org/wiki/Dc-operations/Hardware_Troubleshooting_Runbook',
}
}
}
|