master
conf 156 lines 4.93 KB
Raw
1 # Health alerts for Fortinet FortiGate SNMP-monitored devices
2
3 # Hardware sensor alarm
4 template: fortigate_hw_sensor_alarm
5 on: snmp.device_prof_fgHwSensorEntAlarmStatus
6 class: Errors
7 type: System
8 component: Hardware
9 lookup: average -1m unaligned percentage of ok
10 units: %
11 every: 10s
12 warn: $this < 100
13 delay: down 5m multiplier 1.5 max 1h
14 summary: FortiGate sensor ${label:sensor_name} alarm
15 info: Hardware sensor ${label:sensor_name} on FortiGate device has triggered an alarm
16 to: sysadmin
17
18 # HA node sync status
19 template: fortigate_ha_node_out_of_sync
20 on: snmp.device_prof_fgHaStatsSyncStatus
21 class: Errors
22 type: System
23 component: HA
24 lookup: average -1m unaligned percentage of in_sync
25 units: %
26 every: 10s
27 warn: $this < 100
28 delay: down 2m multiplier 1.5 max 1h
29 summary: FortiGate HA node ${label:ha_node_hostname} sync
30 info: FortiGate HA cluster member ${label:ha_node_hostname} (${label:ha_node_serial}) is out of sync
31 to: sysadmin
32
33 # HA node CPU usage
34 template: fortigate_ha_node_cpu_high
35 on: snmp.device_prof_fgHaStatsCpuUsage
36 class: Utilization
37 type: System
38 component: HA
39 lookup: average -5m unaligned
40 units: %
41 every: 1m
42 warn: $this > 75
43 crit: $this > 90
44 delay: down 5m multiplier 1.5 max 1h
45 summary: FortiGate HA node ${label:ha_node_hostname} CPU
46 info: CPU utilization on FortiGate HA cluster member ${label:ha_node_hostname} is high
47 to: sysadmin
48
49 # HA node memory usage
50 template: fortigate_ha_node_memory_high
51 on: snmp.device_prof_fgHaStatsMemUsage
52 class: Utilization
53 type: System
54 component: HA
55 lookup: average -5m unaligned
56 units: %
57 every: 1m
58 warn: $this > 80
59 crit: $this > 95
60 delay: down 5m multiplier 1.5 max 1h
61 summary: FortiGate HA node ${label:ha_node_hostname} memory
62 info: Memory utilization on FortiGate HA cluster member ${label:ha_node_hostname} is high
63 to: sysadmin
64
65 # SD-WAN link dead
66 template: fortigate_sdwan_link_dead
67 on: snmp.device_prof_fgVWLHealthCheckLinkState
68 class: Errors
69 type: System
70 component: Network
71 lookup: average -1m unaligned percentage of alive
72 units: %
73 every: 10s
74 crit: $this < 100
75 delay: down 1m multiplier 1.5 max 1h
76 summary: FortiGate SD-WAN ${label:sdwan_healthcheck} link down
77 info: SD-WAN health-check ${label:sdwan_healthcheck} on interface ${label:sdwan_interface} reports link is dead
78 to: sysadmin
79
80 # SD-WAN link high latency
81 template: fortigate_sdwan_link_latency_high
82 on: snmp.device_prof_fgVWLHealthCheckLinkLatency
83 class: Latency
84 type: System
85 component: Network
86 lookup: average -5m unaligned
87 units: ms
88 every: 1m
89 warn: $this > 300
90 crit: $this > 500
91 delay: down 5m multiplier 1.5 max 1h
92 summary: FortiGate SD-WAN ${label:sdwan_healthcheck} latency
93 info: SD-WAN health-check ${label:sdwan_healthcheck} on interface ${label:sdwan_interface} has high latency
94 to: sysadmin
95
96 # SD-WAN link packet loss
97 template: fortigate_sdwan_link_packet_loss
98 on: snmp.device_prof_fgVWLHealthCheckLinkPacketLoss
99 class: Errors
100 type: System
101 component: Network
102 lookup: average -5m unaligned
103 units: %
104 every: 1m
105 warn: $this > 1
106 crit: $this > 5
107 delay: down 5m multiplier 1.5 max 1h
108 summary: FortiGate SD-WAN ${label:sdwan_healthcheck} packet loss
109 info: SD-WAN health-check ${label:sdwan_healthcheck} on interface ${label:sdwan_interface} has high packet loss
110 to: sysadmin
111
112 # IPS critical severity events
113 template: fortigate_ips_critical_events
114 on: snmp.device_prof_fgIpsSeverity
115 class: Errors
116 type: System
117 component: Intrusion Prevention
118 lookup: average -5m unaligned of critical
119 units: {event}/s
120 every: 1m
121 warn: $this > 0
122 crit: $this > 10
123 delay: down 5m multiplier 1.5 max 1h
124 summary: FortiGate IPS critical events (VDOM ${label:vdom_name})
125 info: Critical severity intrusions detected on FortiGate VDOM ${label:vdom_name}
126 to: sysadmin
127
128 # Link monitor dead
129 template: fortigate_link_monitor_dead
130 on: snmp.device_prof_fgLinkMonitorState
131 class: Errors
132 type: System
133 component: Network
134 lookup: average -1m unaligned percentage of alive
135 units: %
136 every: 10s
137 crit: $this < 100
138 delay: down 1m multiplier 1.5 max 1h
139 summary: FortiGate link monitor ${label:link_monitor} down
140 info: Link monitor ${label:link_monitor} reports gateway probe is dead
141 to: sysadmin
142
143 # Wireless AP offline
144 template: fortigate_wireless_ap_offline
145 on: snmp.device_prof_fgWcWtpSessionConnectionState
146 class: Errors
147 type: System
148 component: Wireless
149 lookup: average -1m unaligned percentage of onLine
150 units: %
151 every: 10s
152 warn: $this < 100
153 delay: down 5m multiplier 1.5 max 1h
154 summary: FortiGate wireless AP ${label:wtp_id} connection
155 info: Wireless access point ${label:wtp_id} (model ${label:wtp_model}) is not online
156 to: sysadmin