mirror of
https://github.com/librenms/librenms.git
synced 2024-10-07 16:52:45 +00:00
* Add service alert rules https://community.librenms.org/t/configuring-alerting-via-nagios-plugins/1389/5?u=florianbeer * Fix escaping * Update alert_rules.json
114 lines
3.7 KiB
JSON
114 lines
3.7 KiB
JSON
[
|
|
{
|
|
"rule": "%macros.device_down = \"1\"",
|
|
"name": "Devices up/down",
|
|
"default": true
|
|
},
|
|
{
|
|
"rule": "%devices.uptime < \"300\" && %macros.device = \"1\"",
|
|
"name": "Device rebooted",
|
|
"extra": "{\"count\": 1}",
|
|
"default": true
|
|
},
|
|
{
|
|
"rule": "%bgpPeers.bgpPeerState != \"established\" && %macros.device_up = \"1\"",
|
|
"name": "BGP Session down",
|
|
"extra": "{\"count\": 1}",
|
|
"default": true
|
|
},
|
|
{
|
|
"rule": "%bgpPeers.bgpPeerFsmEstablishedTime < \"300\" && %bgpPeers.bgpPeerState = \"established\" && %macros.device_up = \"1\"",
|
|
"name": "BGP Session established",
|
|
"extra": "{\"count\": 1}",
|
|
"default": true
|
|
},
|
|
{
|
|
"rule": "%macros.port_down = \"1\"",
|
|
"name": "Port status up/down",
|
|
"extra": "{\"count\": 1}",
|
|
"default": true
|
|
},
|
|
{
|
|
"rule": "%macros.port_usage_perc >= \"80\" && %macros.port_up = \"1\" && %macros.port = \"1\"",
|
|
"name": "Port utilisation over threshold",
|
|
"default": true
|
|
},
|
|
{
|
|
"rule": "%sensors.sensor_current > %sensors.sensor_limit && %sensors.sensor_alert = \"1\" && %macros.device_up = \"1\"",
|
|
"name": "Sensor over limit",
|
|
"default": true
|
|
},
|
|
{
|
|
"rule": "%sensors.sensor_current < %sensors.sensor_limit_low && %sensors.sensor_alert = \"1\" && %macros.device_up = \"1\"",
|
|
"name": "Sensor under limit",
|
|
"default": true
|
|
},
|
|
{
|
|
"rule": "%services.service_status != \"0\" && %macros.device_up = \"1\"",
|
|
"name": "Service up/down",
|
|
"default": true
|
|
},
|
|
{
|
|
"rule": "%wireless_sensors.sensor_current >= %wireless_sensors.sensor_limit && %wireless_sensors.sensor_alert = \"1\" && %macros.device_up = \"1\"",
|
|
"name": "Wireless Sensor over limit",
|
|
"default": true
|
|
},
|
|
{
|
|
"rule": "%wireless_sensors.sensor_current <= %wireless_sensors.sensor_limit_low && %wireless_sensors.sensor_alert = \"1\" && %macros.device_up = \"1\"",
|
|
"name": "Wireless Sensor under limit",
|
|
"default": true
|
|
},
|
|
{
|
|
"rule": "%macros.bill_quota_over_quota >= \"75\"",
|
|
"name": "Quota bills over 75% used"
|
|
},
|
|
{
|
|
"rule": "%macros.bill_cdr_over_quota >= \"75\"",
|
|
"name": "CDR bills over 75% used"
|
|
},
|
|
{
|
|
"rule": "%ipsec_tunnels.tunnel_status != \"active\" && %macros.device_up = \"1\"",
|
|
"name": "IPSec tunnels down"
|
|
},
|
|
{
|
|
"rule": "%pollers.time_taken >= \"250\"",
|
|
"name": "Poller is taking too long"
|
|
},
|
|
{
|
|
"rule": "%macros.device_up = \"1\" && %devices.os = \"asa\" && %ciscoASA.data > \"5000\"",
|
|
"name": "Cisco ASA connections over 5000"
|
|
},
|
|
{
|
|
"rule": "%processors.processor_usage > \"85\" && %macros.device_up = \"1\"",
|
|
"name": "Processor usage over 85%"
|
|
},
|
|
{
|
|
"rule": "%sensors.sensor_descr = \"Primary Unit.*\" && %sensors.sensor_current = \"10\" && %sensors.sensor_prev = \"9\"",
|
|
"name": "Cisco ASA Primary unit changed to standby"
|
|
},
|
|
{
|
|
"rule": "%ports.ifOperStatus = \"down\" && %ports.ifOperStatus_prev = \"up\" && %macros.device_up = \"1\"",
|
|
"name": "Port status change from up to down"
|
|
},
|
|
{
|
|
"rule": "%ports.ifOutErrors_rate >= \"100\" || %ports.ifInErrors_rate >= \"100\"",
|
|
"name": "Interface Errors Rate greater than 100"
|
|
},
|
|
{
|
|
"rule": "%eventlog.type = \"discovery\" && %eventlog.message ~ \"@autodiscovered@\" && %eventlog.datetime >= %macros.past_60m",
|
|
"name": "Device discovered within the last 60 minutes"
|
|
},
|
|
{
|
|
"rule": "%wireless_sensors.sensor_class = 'clients' && %wireless_sensors.sensor_current >= %wireless_sensors.sensor_limit && %wireless_sensors.sensor_alert = \"1\" && %macros.device_up = \"1\"",
|
|
"name": "Too many wireless clients"
|
|
},
|
|
{
|
|
"rule": "Service warning",
|
|
"name": "%services.service_status = \"1\""
|
|
},
|
|
{
|
|
"rule": "Service critical",
|
|
"name": "%services.service_status = \"2\""
|
|
}
|
|
]
|