Lumenpulse/prometheus-rules.yml at main · Steddy0/Lumenpulse · GitHub

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
# prometheus-rules.yml
# Alert rules for LumenPulse backend monitoring
#
# These rules define when alerts should fire based on metric conditions
# Place this file in the root directory and reference it in prometheus.yml

groups:
  - name: lumenpulse_alerts
    interval: 30s
    rules:
      # ===================
      # HTTP Error Alerts
      # ===================

      - alert: HighErrorRate
        expr: |
          (rate(http_errors_total[5m]) / rate(http_requests_total[5m])) > 0.05
        for: 5m
        labels:
          severity: warning
          service: backend
        annotations:
          summary: 'High error rate detected'
          description: '{{ .Labels.instance }} has error rate > 5% (current: {{ $value | humanizePercentage }})'
          runbook: 'https://wiki.example.com/runbooks/high-error-rate'

      - alert: CriticalErrorRate
        expr: |
          (rate(http_errors_total[5m]) / rate(http_requests_total[5m])) > 0.10
        for: 2m
        labels:
          severity: critical
          service: backend
        annotations:
          summary: 'Critical error rate detected'
          description: '{{ .Labels.instance }} has error rate > 10% (current: {{ $value | humanizePercentage }})'
          runbook: 'https://wiki.example.com/runbooks/critical-error-rate'

      # ===================
      # Latency Alerts
      # ===================

      - alert: HighLatencyP95
        expr: |
          histogram_quantile(0.95, rate(http_request_duration_seconds_bucket[5m])) > 1
        for: 5m
        labels:
          severity: warning
          service: backend
        annotations:
          summary: 'High P95 latency detected'
          description: '{{ .Labels.instance }} P95 latency > 1s (current: {{ $value | humanizeDuration }})'
          runbook: 'https://wiki.example.com/runbooks/high-latency'

      - alert: HighLatencyP99
        expr: |
          histogram_quantile(0.99, rate(http_request_duration_seconds_bucket[5m])) > 3
        for: 5m
        labels:
          severity: critical
          service: backend
        annotations:
          summary: 'Critical P99 latency detected'
          description: '{{ .Labels.instance }} P99 latency > 3s (current: {{ $value | humanizeDuration }})'
          runbook: 'https://wiki.example.com/runbooks/critical-latency'

      # ====================
      # Job Queue Alerts
      # ====================

      - alert: QueueBacklogWarning
        expr: job_queue_size > 100
        for: 10m
        labels:
          severity: warning
          service: backend
        annotations:
          summary: 'Job queue backlog warning'
          description: '{{ .Labels.queue_name }} queue has {{ $value }} jobs pending'

      - alert: QueueBacklogCritical
        expr: job_queue_size > 1000
        for: 5m
        labels:
          severity: critical
          service: backend
        annotations:
          summary: 'Critical job queue backlog'
          description: '{{ .Labels.queue_name }} queue has {{ $value }} jobs (critical backlog)'

      - alert: JobFailureRate
        expr: |
          rate(jobs_failed_total[5m]) > 0.1
        for: 5m
        labels:
          severity: warning
          service: backend
        annotations:
          summary: 'High job failure rate'
          description: '{{ .Labels.queue_name }} has > 10% job failures (current: {{ $value | humanize }}/sec)'

      # ====================
      # Ingestion Dataset SLA Alerts
      # ====================

      - alert: IngestionDatasetFreshnessSLABreach
        expr: |
          lumenpulse_ingestion_dataset_freshness_seconds
            > on(dataset) lumenpulse_ingestion_dataset_freshness_target_seconds
        for: 5m
        labels:
          severity: critical
          service: data-processing
        annotations:
          summary: 'Ingestion dataset freshness SLA breach'
          description: '{{ .Labels.dataset }} freshness is {{ $value | humanizeDuration }}, above its configured SLA target'
          runbook: 'apps/data-processing/INGESTION_ALERTING_RUNBOOK.md'

      - alert: IngestionDatasetCompletenessSLABreach
        expr: |
          lumenpulse_ingestion_dataset_completeness_ratio < 0
            or lumenpulse_ingestion_dataset_completeness_ratio
              < on(dataset) lumenpulse_ingestion_dataset_completeness_target_ratio
        for: 5m
        labels:
          severity: critical
          service: data-processing
        annotations:
          summary: 'Ingestion dataset completeness SLA breach'
          description: '{{ .Labels.dataset }} completeness ratio is {{ $value | humanize }}, below its configured SLA target or unknown'
          runbook: 'apps/data-processing/INGESTION_ALERTING_RUNBOOK.md'

      # ====================
      # Request Rate Alerts
      # ====================

      - alert: UnusuallyLowRequestRate
        expr: |
          rate(http_requests_total[5m]) < 0.1
        for: 10m
        labels:
          severity: warning
          service: backend
        annotations:
          summary: 'Unusually low request rate'
          description: '{{ .Labels.instance }} request rate is abnormally low ({{ $value | humanize }}/sec)'

      - alert: NoRequests
        expr: |
          increase(http_requests_total[5m]) == 0
        for: 10m
        labels:
          severity: critical
          service: backend
        annotations:
          summary: 'No requests detected'
          description: '{{ .Labels.instance }} has received no requests in the last 5 minutes'

      # ====================
      # Memory Alerts
      # ====================

      - alert: HighMemoryUsage
        expr: |
          (process_resident_memory_bytes / node_memory_MemTotal_bytes) > 0.8
        for: 5m
        labels:
          severity: warning
          service: backend
        annotations:
          summary: 'High memory usage detected'
          description: '{{ .Labels.instance }} is using > 80% of available memory'

      # ====================
      # Health Checks
      # ====================

      - alert: InstanceDown
        expr: |
          up{job="lumenpulse-backend"} == 0
        for: 1m
        labels:
          severity: critical
          service: backend
        annotations:
          summary: 'Instance is down'
          description: '{{ .Labels.instance }} has been down for more than 1 minute'

      # ====================
      # Recording Rules (Pre-computed metrics)
      # ====================

      # These compute common values once to improve dashboard performance
      - record: 'job:http:requests:rate5m'
        expr: 'rate(http_requests_total[5m])'

      - record: 'job:http:errors:rate5m'
        expr: 'rate(http_errors_total[5m])'

      - record: 'job:http:error_rate:ratio'
        expr: |
          rate(http_errors_total[5m]) / rate(http_requests_total[5m])

      - record: 'job:http:latency:p95'
        expr: |
          histogram_quantile(0.95, rate(http_request_duration_seconds_bucket[5m]))

      - record: 'job:http:latency:p99'
        expr: |
          histogram_quantile(0.99, rate(http_request_duration_seconds_bucket[5m]))