-
Notifications
You must be signed in to change notification settings - Fork 4
/
rules.yml
199 lines (199 loc) · 7.43 KB
/
rules.yml
1
2
3
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
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
groups:
- name: ackal
rules:
- alert: cloud_logging_logs
expr: min_over_time(gcp_cloud_logging_logs{project=~"ackal-[0-9]{6}"}[15m]) > 39
for: 6h
labels:
severity: page
annotations:
summary: "Ackal Project ({{ $labels.project}}) has {{ $value }} logs"
- name: gcp_exporter
rules:
- alert: gcp_artifact_registry_repositories
# `15m` matches the prometheus.yml scrape_interval
expr: min_over_time(gcp_artifact_registry_registries{}[15m]) > 0
for: 6h
labels:
severity: page
annotations:
summary: "GCP Artifact Registry repositories ({{ $value }}) exist (project: {{ $labels.project }})"
- alert: gcp_cloud_endpoints_services
# `15m` matches the prometheus.yml scrape_interval
expr: min_over_time(gcp_cloud_endpoints_services{}[15m]) > 0
for: 6h
labels:
severity: page
annotations:
summary: "GCP Cloud Endpoints services ({{ $value }}) deployed (project: {{ $labels.project }})"
- alert: gcp_cloud_functions_running
# `15m` matches the prometheus.yml scrape_interval
expr: min_over_time(gcp_cloud_functions_functions{}[15m]) > 0
for: 6h
labels:
severity: page
annotations:
summary: "GCP Cloud Functions ({{ $value }}) running (project: {{ $labels.project }})"
- alert: gcp_cloud_run_jobs_running
# `15m` matches the prometheus.yml scrape_interval
expr: min_over_time(gcp_cloud_run_jobs{}[15m]) > 0
for: 6h
labels:
severity: page
annotations:
summary: "GCP Cloud Run jobs ({{ $value }}) running (project: {{ $labels.project }})"
- alert: gcp_cloud_run_services_running
# `15m` matches the prometheus.yml scrape_interval
expr: min_over_time(gcp_cloud_run_services{}[15m]) > 0
for: 6h
labels:
severity: page
annotations:
summary: "GCP Cloud Run services ({{ $value }}) running (project: {{ $labels.project }})"
- alert: gcp_cloud_monitoring_alert_policies_running
expr: min_over_time(gcp_cloud_monitoring_alert_policies{}[15m]) > 0
for: 6h
labels:
severity: page
annotations:
summary: "GCP Cloud Monitoring Alert Policies ({{ $value }}) running (project: {{ $labels.project }})"
- alert: gcp_cloud_monitoring_uptime_checks_running
expr: min_over_time(gcp_cloud_monitoring_uptime_checks{}[15m]) > 0
for: 6h
labels:
severity: page
annotations:
summary: "GCP Cloud Monitoring Uptime Checks ({{ $value }}) running (project: {{ $labels.project }})"
- alert: gcp_cloud_scheduler_jobs_running
# `15m` matches the prometheus.yml scrape_interval
expr: min_over_time(gcp_cloud_scheduler_jobs{}[15m]) > 0
for: 6h
labels:
severity: page
annotations:
summary: "GCP Cloud Scheduler jobs ({{ $value }}) running (project: {{ $labels.project }})"
- alert: gcp_compute_engine_instances_running
expr: min_over_time(gcp_compute_engine_instances{}[15m]) > 0
for: 6h
labels:
severity: page
annotations:
summary: "GCP Compute Engine Instances ({{ $value }}) running (project: {{ $labels.project }})"
- alert: gcp_compute_engine_forwarding_rules_running
expr: min_over_time(gcp_compute_engine_forwardingrules{}[15m]) > 0
for: 6h
labels:
severity: page
annotations:
summary: "GCP Compute Engine ForwardingRules ({{ $value }}) running (project: {{ $labels.project }})"
- alert: gcp_kubernetes_clusters_running
# `15m` matches the prometheus.yml scrape_interval
expr: min_over_time(gcp_kubernetes_engine_cluster_up{}[15m]) > 0
for: 6h
labels:
severity: page
annotations:
summary: "GCP Kubernetes Engine clusters ({{ $value }}) running (project: {{ $labels.project }})"
- alert: gcp_storage_buckets
expr: min_over_time(gcp_storage_buckets{}[15m]) > 0
for: 6h
labels:
severity: warning
annotations:
summary: "GCP Storage buckets ({{ $value }}) exist (project: {{ $labels.project }})"
- name: gcp_status
rules:
- alert: gcp_status_services
# `15m` matches the prometheus.yml scrape_interval
expr: gcp_status_services{} != 100
for: 15m
labels:
severity: warning
annotations:
summary: GCP Status Services ({{ $labels.region }}) availability discrepancy ({{ $value }}!=100)
- alert: gcp_status_up
# `15m` matches the prometheus.yml scrape_interval
expr: min_over_time(gcp_status_up{region="Americas"}[15m]) != 1.0
for: 15m
labels:
severity: warning
annotations:
summary: GCP Status Service {{ $labels.service }} down
- name: fly_exporter
rules:
- alert: fly_exporter_apps_running
expr: min_over_time(fly_exporter_apps{}[15m]) > 0
for: 6h
labels:
severity: page
annotations:
summary: fly.io {{ $value }} apps deployed
- name: linode_exporter
rules:
- alert: linode_instance_up
expr: min_over_time(linode_instance_up{}[15m])>0
for: 3h
labels:
severity: page
annotations:
summary: Linode {{ $value }} Instances exist
- alert: linode_kubernetes_up
expr: min_over_time(linode_kubernetes_up{}[15m])>0
for: 3h
labels:
severity: page
annotations:
summary: Linode {{ $value }} Kubernetes clusters exist
- alert: linode_nodebalancer_up
expr: min_over_time(linode_nodebalancer_up{}[15m])>0
for: 3h
labels:
severity: page
annotations:
summary: Linode {{ $value }} NodeBalancers exist
- alert: linode_volume_up
expr: min_over_time(linode_volume_up{}[15m])>0
for: 3h
labels:
severity: page
annotations:
summary: Linode {{ $value }} Volumes exist
- name: vultr_exporter
rules:
- alert: vultr_block_storage_up
expr: min_over_time(vultr_block_storage_up{}[15m]) > 0
for: 3h
labels:
severity: page
annotations:
summary: Vultr {{ $value }} Block Storage volumes exist
- alert: vultr_kubernetes_cluster_up
expr: min_over_time(vultr_kubernetes_cluster_up{}[15m]) > 0
for: 3h
labels:
severity: page
annotations:
summary: Vultr {{ $value }} Kubernetes Engine cluster running
- alert: vultr_load_balancer_up
expr: min_over_time(vultr_load_balancer_up{}[15m]) > 0
for: 3h
labels:
severity: page
annotations:
summary: Vultr {{ $value }} Load Balancers running
- alert: vultr_reserved_ips_up
expr: min_over_time(vultr_reserved_ips_up{}[15m]) > 0
for: 3h
labels:
severity: page
annotations:
summary: Vultr {{ $value }} Reserved IPs exist
- name: azure_exporter
rules:
- alert: azure_container_apps_running
expr: min_over_time(azure_container_apps_total{}[15m]) > 0
for: 6h
labels:
severity: page
annotations:
summary: "Azure Container Apps ({{ $value }}) running (resource group: {{ $labels.resourcegroup }})"