master
conf 110 lines 4.4 KB
Raw
1 # you can disable an alarm notification by setting the 'to' line to: silent
2
3 # --- Publish Failures ---
4
5 template: am_event_grid_publish_failures
6 on: azure_monitor.event_grid.publish_rate
7 class: Errors
8 type: Messaging
9 component: Event Grid
10 lookup: average -5m unaligned of failed
11 units: events/s
12 every: 1m
13 warn: $this > (($status >= $WARNING) ? (0) : (5))
14 delay: down 5m multiplier 1.5 max 1h
15 summary: Event Grid publish failures on ${label:resource_name}
16 info: Rate of failed event publish operations on Event Grid topic ${label:resource_name} \
17 in ${label:resource_group} (${label:region}). \
18 Failed publishes indicate authentication, authorization, or schema validation errors
19 to: sysadmin
20
21 # --- Delivery Failures ---
22
23 template: am_event_grid_delivery_failures
24 on: azure_monitor.event_grid.delivery
25 class: Errors
26 type: Messaging
27 component: Event Grid
28 lookup: average -5m unaligned of failed
29 units: events/s
30 every: 1m
31 warn: $this > (($status >= $WARNING) ? (0) : (5))
32 crit: $this > (($status == $CRITICAL) ? (5) : (50))
33 delay: down 5m multiplier 1.5 max 1h
34 summary: Event Grid delivery failures on ${label:resource_name}
35 info: Rate of failed event delivery attempts on Event Grid topic ${label:resource_name} \
36 in ${label:resource_group} (${label:region}). \
37 Persistent delivery failures indicate subscriber endpoint issues
38 to: sysadmin
39
40 template: am_event_grid_dropped_events
41 on: azure_monitor.event_grid.delivery
42 class: Errors
43 type: Messaging
44 component: Event Grid
45 lookup: average -5m unaligned of dropped
46 units: events/s
47 every: 1m
48 warn: $this > (($status >= $WARNING) ? (0) : (1))
49 crit: $this > (($status == $CRITICAL) ? (1) : (10))
50 delay: down 5m multiplier 1.5 max 1h
51 summary: Event Grid dropped events on ${label:resource_name}
52 info: Rate of dropped events on Event Grid topic ${label:resource_name} \
53 in ${label:resource_group} (${label:region}). \
54 Dropped events are permanently lost and indicate exhausted retry attempts \
55 without a dead-letter destination configured
56 to: sysadmin
57
58 template: am_event_grid_dead_lettered_events
59 on: azure_monitor.event_grid.delivery
60 class: Errors
61 type: Messaging
62 component: Event Grid
63 lookup: average -5m unaligned of dead_lettered
64 units: events/s
65 every: 1m
66 warn: $this > (($status >= $WARNING) ? (0) : (1))
67 crit: $this > (($status == $CRITICAL) ? (1) : (10))
68 delay: down 5m multiplier 1.5 max 1h
69 summary: Event Grid dead-lettered events on ${label:resource_name}
70 info: Rate of events sent to the dead-letter destination on Event Grid topic ${label:resource_name} \
71 in ${label:resource_group} (${label:region}). \
72 Dead-lettered events failed all delivery retries and require manual investigation
73 to: sysadmin
74
75 # --- Routing ---
76
77 template: am_event_grid_unmatched_events
78 on: azure_monitor.event_grid.routing
79 class: Errors
80 type: Messaging
81 component: Event Grid
82 lookup: average -5m unaligned of unmatched
83 units: events/s
84 every: 1m
85 warn: $this > (($status >= $WARNING) ? (0) : (10))
86 delay: down 5m multiplier 1.5 max 1h
87 summary: Event Grid unmatched events on ${label:resource_name}
88 info: Rate of events that did not match any subscription on Event Grid topic ${label:resource_name} \
89 in ${label:resource_group} (${label:region}). \
90 Unmatched events indicate missing or misconfigured event subscriptions
91 to: sysadmin
92
93 # --- Latency ---
94
95 template: am_event_grid_destination_processing_duration
96 on: azure_monitor.event_grid.destination_processing_duration
97 class: Latency
98 type: Messaging
99 component: Event Grid
100 lookup: average -5m unaligned of average
101 units: milliseconds
102 every: 1m
103 warn: $this != nan AND $this > (($status >= $WARNING) ? (3000) : (5000))
104 crit: $this != nan AND $this > (($status == $CRITICAL) ? (5000) : (10000))
105 delay: down 5m multiplier 1.5 max 1h
106 summary: Event Grid destination processing duration on ${label:resource_name}
107 info: Average time taken by the subscriber endpoint to process events from Event Grid topic ${label:resource_name} \
108 in ${label:resource_group} (${label:region}). \
109 High processing duration indicates slow or overloaded event subscribers
110 to: sysadmin