summaryrefslogtreecommitdiff
path: root/roles/monitoring/prometheus/server/defaults/main/rules_prometheus.yml
blob: b568f722917aed312efb185eb5e7f214350dc3ff (plain) (blame)
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
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
---
## https://awesome-prometheus-alerts.grep.to/rules#prometheus-self-monitoring
prometheus_server_rules_prometheus_extra: []
prometheus_server_rules_prometheus:
  - alert: PrometheusJobMissing
    expr: absent(up{job="prometheus"})
    for: 0m
    labels:
      severity: warning
    annotations:
      summary: Prometheus job missing (instance {{ '{{' }} $labels.instance {{ '}}' }})
      description: "A Prometheus job has disappeared\n  VALUE = {{ '{{' }} $value {{ '}}' }}\n  LABELS = {{ '{{' }} $labels {{ '}}' }}"

  - alert: PrometheusJobMissing
    expr: absent(up{job="prometheus"})
    for: 0m
    labels:
      severity: warning
    annotations:
      summary: Prometheus job missing (instance {{ '{{' }} $labels.instance {{ '}}' }})
      description: "A Prometheus job has disappeared\n  VALUE = {{ '{{' }} $value {{ '}}' }}\n  LABELS = {{ '{{' }} $labels {{ '}}' }}"

  - alert: PrometheusTargetMissing
    expr: up == 0
    for: 0m
    labels:
      severity: critical
    annotations:
      summary: Prometheus target missing (instance {{ '{{' }} $labels.instance {{ '}}' }})
      description: "A Prometheus target has disappeared. An exporter might be crashed.\n  VALUE = {{ '{{' }} $value {{ '}}' }}\n  LABELS = {{ '{{' }} $labels {{ '}}' }}"

  - alert: PrometheusAllTargetsMissing
    expr: count by (job) (up) == 0
    for: 0m
    labels:
      severity: critical
    annotations:
      summary: Prometheus all targets missing (instance {{ '{{' }} $labels.instance {{ '}}' }})
      description: "A Prometheus job does not have living target anymore.\n  VALUE = {{ '{{' }} $value {{ '}}' }}\n  LABELS = {{ '{{' }} $labels {{ '}}' }}"

  - alert: PrometheusConfigurationReloadFailure
    expr: prometheus_config_last_reload_successful != 1
    for: 0m
    labels:
      severity: warning
    annotations:
      summary: Prometheus configuration reload failure (instance {{ '{{' }} $labels.instance {{ '}}' }})
      description: "Prometheus configuration reload error\n  VALUE = {{ '{{' }} $value {{ '}}' }}\n  LABELS = {{ '{{' }} $labels {{ '}}' }}"

  - alert: PrometheusTooManyRestarts
    expr: changes(process_start_time_seconds{job=~"prometheus|pushgateway|alertmanager"}[15m]) > 2
    for: 0m
    labels:
      severity: warning
    annotations:
      summary: Prometheus too many restarts (instance {{ '{{' }} $labels.instance {{ '}}' }})
      description: "Prometheus has restarted more than twice in the last 15 minutes. It might be crashlooping.\n  VALUE = {{ '{{' }} $value {{ '}}' }}\n  LABELS = {{ '{{' }} $labels {{ '}}' }}"

  - alert: PrometheusRuleEvaluationFailures
    expr: increase(prometheus_rule_evaluation_failures_total[3m]) > 0
    for: 0m
    labels:
      severity: critical
    annotations:
      summary: Prometheus rule evaluation failures (instance {{ '{{' }} $labels.instance {{ '}}' }})
      description: "Prometheus encountered {{ '{{' }} $value {{ '}}' }} rule evaluation failures, leading to potentially ignored alerts.\n  VALUE = {{ '{{' }} $value {{ '}}' }}\n  LABELS = {{ '{{' }} $labels {{ '}}' }}"

  - alert: PrometheusTemplateTextExpansionFailures
    expr: increase(prometheus_template_text_expansion_failures_total[3m]) > 0
    for: 0m
    labels:
      severity: critical
    annotations:
      summary: Prometheus template text expansion failures (instance {{ '{{' }} $labels.instance {{ '}}' }})
      description: "Prometheus encountered {{ '{{' }} $value {{ '}}' }} template text expansion failures\n  VALUE = {{ '{{' }} $value {{ '}}' }}\n  LABELS = {{ '{{' }} $labels {{ '}}' }}"

  - alert: PrometheusRuleEvaluationSlow
    expr: prometheus_rule_group_last_duration_seconds > prometheus_rule_group_interval_seconds
    for: 5m
    labels:
      severity: warning
    annotations:
      summary: Prometheus rule evaluation slow (instance {{ '{{' }} $labels.instance {{ '}}' }})
      description: "Prometheus rule evaluation took more time than the scheduled interval. It indicates a slower storage backend access or too complex query.\n  VALUE = {{ '{{' }} $value {{ '}}' }}\n  LABELS = {{ '{{' }} $labels {{ '}}' }}"

  - alert: PrometheusNotificationsBacklog
    expr: min_over_time(prometheus_notifications_queue_length[10m]) > 0
    for: 0m
    labels:
      severity: warning
    annotations:
      summary: Prometheus notifications backlog (instance {{ '{{' }} $labels.instance {{ '}}' }})
      description: "The Prometheus notification queue has not been empty for 10 minutes\n  VALUE = {{ '{{' }} $value {{ '}}' }}\n  LABELS = {{ '{{' }} $labels {{ '}}' }}"

  - alert: PrometheusTargetEmpty
    expr: prometheus_sd_discovered_targets == 0
    for: 0m
    labels:
      severity: critical
    annotations:
      summary: Prometheus target empty (instance {{ '{{' }} $labels.instance {{ '}}' }})
      description: "Prometheus has no target in service discovery\n  VALUE = {{ '{{' }} $value {{ '}}' }}\n  LABELS = {{ '{{' }} $labels {{ '}}' }}"

  - alert: PrometheusTargetScrapingSlow
    expr: prometheus_target_interval_length_seconds{quantile="0.9"} > 60
    for: 5m
    labels:
      severity: warning
    annotations:
      summary: Prometheus target scraping slow (instance {{ '{{' }} $labels.instance {{ '}}' }})
      description: "Prometheus is scraping exporters slowly\n  VALUE = {{ '{{' }} $value {{ '}}' }}\n  LABELS = {{ '{{' }} $labels {{ '}}' }}"

  - alert: PrometheusLargeScrape
    expr: increase(prometheus_target_scrapes_exceeded_sample_limit_total[10m]) > 10
    for: 5m
    labels:
      severity: warning
    annotations:
      summary: Prometheus large scrape (instance {{ '{{' }} $labels.instance {{ '}}' }})
      description: "Prometheus has many scrapes that exceed the sample limit\n  VALUE = {{ '{{' }} $value {{ '}}' }}\n  LABELS = {{ '{{' }} $labels {{ '}}' }}"

  - alert: PrometheusTargetScrapeDuplicate
    expr: increase(prometheus_target_scrapes_sample_duplicate_timestamp_total[5m]) > 0
    for: 0m
    labels:
      severity: warning
    annotations:
      summary: Prometheus target scrape duplicate (instance {{ '{{' }} $labels.instance {{ '}}' }})
      description: "Prometheus has many samples rejected due to duplicate timestamps but different values\n  VALUE = {{ '{{' }} $value {{ '}}' }}\n  LABELS = {{ '{{' }} $labels {{ '}}' }}"

  - alert: PrometheusTsdbCheckpointCreationFailures
    expr: increase(prometheus_tsdb_checkpoint_creations_failed_total[1m]) > 0
    for: 0m
    labels:
      severity: critical
    annotations:
      summary: Prometheus TSDB checkpoint creation failures (instance {{ '{{' }} $labels.instance {{ '}}' }})
      description: "Prometheus encountered {{ '{{' }} $value {{ '}}' }} checkpoint creation failures\n  VALUE = {{ '{{' }} $value {{ '}}' }}\n  LABELS = {{ '{{' }} $labels {{ '}}' }}"

  - alert: PrometheusTsdbCheckpointDeletionFailures
    expr: increase(prometheus_tsdb_checkpoint_deletions_failed_total[1m]) > 0
    for: 0m
    labels:
      severity: critical
    annotations:
      summary: Prometheus TSDB checkpoint deletion failures (instance {{ '{{' }} $labels.instance {{ '}}' }})
      description: "Prometheus encountered {{ '{{' }} $value {{ '}}' }} checkpoint deletion failures\n  VALUE = {{ '{{' }} $value {{ '}}' }}\n  LABELS = {{ '{{' }} $labels {{ '}}' }}"

  - alert: PrometheusTsdbCompactionsFailed
    expr: increase(prometheus_tsdb_compactions_failed_total[1m]) > 0
    for: 0m
    labels:
      severity: critical
    annotations:
      summary: Prometheus TSDB compactions failed (instance {{ '{{' }} $labels.instance {{ '}}' }})
      description: "Prometheus encountered {{ '{{' }} $value {{ '}}' }} TSDB compactions failures\n  VALUE = {{ '{{' }} $value {{ '}}' }}\n  LABELS = {{ '{{' }} $labels {{ '}}' }}"

  - alert: PrometheusTsdbHeadTruncationsFailed
    expr: increase(prometheus_tsdb_head_truncations_failed_total[1m]) > 0
    for: 0m
    labels:
      severity: critical
    annotations:
      summary: Prometheus TSDB head truncations failed (instance {{ '{{' }} $labels.instance {{ '}}' }})
      description: "Prometheus encountered {{ '{{' }} $value {{ '}}' }} TSDB head truncation failures\n  VALUE = {{ '{{' }} $value {{ '}}' }}\n  LABELS = {{ '{{' }} $labels {{ '}}' }}"

  - alert: PrometheusTsdbReloadFailures
    expr: increase(prometheus_tsdb_reloads_failures_total[1m]) > 0
    for: 0m
    labels:
      severity: critical
    annotations:
      summary: Prometheus TSDB reload failures (instance {{ '{{' }} $labels.instance {{ '}}' }})
      description: "Prometheus encountered {{ '{{' }} $value {{ '}}' }} TSDB reload failures\n  VALUE = {{ '{{' }} $value {{ '}}' }}\n  LABELS = {{ '{{' }} $labels {{ '}}' }}"

  - alert: PrometheusTsdbWalCorruptions
    expr: increase(prometheus_tsdb_wal_corruptions_total[1m]) > 0
    for: 0m
    labels:
      severity: critical
    annotations:
      summary: Prometheus TSDB WAL corruptions (instance {{ '{{' }} $labels.instance {{ '}}' }})
      description: "Prometheus encountered {{ '{{' }} $value {{ '}}' }} TSDB WAL corruptions\n  VALUE = {{ '{{' }} $value {{ '}}' }}\n  LABELS = {{ '{{' }} $labels {{ '}}' }}"

  - alert: PrometheusTsdbWalTruncationsFailed
    expr: increase(prometheus_tsdb_wal_truncations_failed_total[1m]) > 0
    for: 0m
    labels:
      severity: critical
    annotations:
      summary: Prometheus TSDB WAL truncations failed (instance {{ '{{' }} $labels.instance {{ '}}' }})
      description: "Prometheus encountered {{ '{{' }} $value {{ '}}' }} TSDB WAL truncation failures\n  VALUE = {{ '{{' }} $value {{ '}}' }}\n  LABELS = {{ '{{' }} $labels {{ '}}' }}"


prometheus_server_rules_prometheus_alertmanager:
  - alert: PrometheusAlertmanagerConfigurationReloadFailure
    expr: alertmanager_config_last_reload_successful != 1
    for: 0m
    labels:
      severity: warning
    annotations:
      summary: Prometheus AlertManager configuration reload failure (instance {{ '{{' }} $labels.instance {{ '}}' }})
      description: "AlertManager configuration reload error\n  VALUE = {{ '{{' }} $value {{ '}}' }}\n  LABELS = {{ '{{' }} $labels {{ '}}' }}"

  - alert: PrometheusAlertmanagerConfigNotSynced
    expr: count(count_values("config_hash", alertmanager_config_hash)) > 1
    for: 0m
    labels:
      severity: warning
    annotations:
      summary: Prometheus AlertManager config not synced (instance {{ '{{' }} $labels.instance {{ '}}' }})
      description: "Configurations of AlertManager cluster instances are out of sync\n  VALUE = {{ '{{' }} $value {{ '}}' }}\n  LABELS = {{ '{{' }} $labels {{ '}}' }}"

  - alert: PrometheusAlertmanagerE2eDeadManSwitch
    expr: vector(1)
    for: 0m
    labels:
      severity: informational
      instance: prometheus
      timeout: 1200
    annotations:
      summary: Prometheus AlertManager E2E dead man switch (instance {{ '{{' }} $labels.instance {{ '}}' }})
      description: "Prometheus DeadManSwitch is an always-firing alert. It's used as an end-to-end test of Prometheus through the Alertmanager.\n  VALUE = {{ '{{' }} $value {{ '}}' }}\n  LABELS = {{ '{{' }} $labels {{ '}}' }}"

  - alert: PrometheusNotConnectedToAlertmanager
    expr: prometheus_notifications_alertmanagers_discovered < 1
    for: 0m
    labels:
      severity: critical
    annotations:
      summary: Prometheus not connected to alertmanager (instance {{ '{{' }} $labels.instance {{ '}}' }})
      description: "Prometheus cannot connect the alertmanager\n  VALUE = {{ '{{' }} $value {{ '}}' }}\n  LABELS = {{ '{{' }} $labels {{ '}}' }}"

  - alert: PrometheusAlertmanagerNotificationFailing
    expr: rate(alertmanager_notifications_failed_total[1m]) > 0
    for: 0m
    labels:
      severity: critical
    annotations:
      summary: Prometheus AlertManager notification failing (instance {{ '{{' }} $labels.instance {{ '}}' }})
      description: "Alertmanager is failing sending notifications\n  VALUE = {{ '{{' }} $value {{ '}}' }}\n  LABELS = {{ '{{' }} $labels {{ '}}' }}"