Alerts

alert: HighAPILatency
expr: histogram_quantile(0.95,
  rate(http_request_duration_seconds_bucket{service="lead-gen-saas"}[5m]))
  > 2
for: 5m
labels:
  severity: warning
annotations:
  description: 95th percentile latency is {{ $value | printf "%.2f" }}s
  summary: High API latency on {{ $labels.instance }}

alert: HighHTTPErrorRateInsightful
expr: rate(container_fs_read_bytes_total{image=~".*insightful.*"}[5m])
  > 1e+07
for: 5m
labels:
  severity: warning
annotations:
  summary: High I/O on Insightful Booking container

alert: HighHTTPErrorRateLeadGen
expr: rate(http_requests_total{service="lead-gen-saas",status=~"5.."}[5m])
  > 0.1
for: 5m
labels:
  severity: critical
annotations:
  description: 5xx error rate is {{ $value | printf "%.2f" }}/s
  summary: High 5xx error rate on Lead Gen API

alert: ContainerHighMemory
expr: container_memory_usage_bytes
  / container_spec_memory_limit_bytes > 0.9
for: 5m
labels:
  severity: warning
annotations:
  description: 'Memory usage: {{ $value | printf "%.1f" }}%'
  summary: Container {{ $labels.name }} high memory

alert: ContainerRestarting
expr: changes(container_last_seen[5m])
  > 5
for: 1m
labels:
  severity: warning
annotations:
  summary: Container {{ $labels.name }} restarting frequently

alert: ContainerDown
expr: container_spec_image_tag
  == 0
for: 1m
labels:
  severity: critical
annotations:
  summary: 'Container down: {{ $labels.name }}'

alert: ContainerHighCPU
expr: rate(container_cpu_usage_seconds_total[5m])
  * 100 > 90
for: 5m
labels:
  severity: warning
annotations:
  description: 'CPU usage: {{ $value | printf "%.1f" }}%'
  summary: Container {{ $labels.name }} high CPU

alert: PostgresExporterDown
expr: up{job=~"postgres.*"}
  == 0
for: 5m
labels:
  severity: critical
annotations:
  summary: PostgreSQL exporter down for {{ $labels.job }}

alert: PostgresDeadTuples
expr: pg_stat_user_tables_n_dead_tup
  > 10000
for: 1h
labels:
  severity: warning
annotations:
  description: Table {{ $labels.relname }} has {{ $value }} dead tuples
  summary: High dead tuple count on {{ $labels.database }}

alert: PostgresLongRunningQueries
expr: pg_stat_activity_count{datname!~"template.*"}
  > 10
for: 5m
labels:
  severity: warning
annotations:
  summary: Many active queries on {{ $labels.database }}

alert: PostgresTooManyConnections
expr: pg_stat_activity_count
  > 80
for: 5m
labels:
  severity: warning
annotations:
  description: 'Active connections: {{ $value }}'
  summary: PostgreSQL connections high on {{ $labels.database }}

alert: ExporterDown
expr: up == 0
for: 5m
labels:
  severity: warning
annotations:
  description: '{{ $labels.job }} has been down for 5 minutes'
  summary: 'Exporter down: {{ $labels.job }}'

alert: PrometheusTargetMissing
expr: up{job!="prometheus"}
  == 0
for: 10m
labels:
  severity: critical
annotations:
  description: Target {{ $labels.instance }} has been down for 10 minutes
  summary: 'Prometheus target missing: {{ $labels.job }}'

alert: NginxConnectionFailures
expr: rate(nginx_connections_failed[5m])
  > 0.1
for: 5m
labels:
  severity: warning
annotations:
  description: 'Failed connections: {{ $value | printf "%.2f" }}/s'
  summary: Nginx connection failures

alert: NginxHigh4xxErrors
expr: rate(nginx_http_requests_total{status=~"4.."}[5m])
  > 0.5
for: 5m
labels:
  severity: warning
annotations:
  description: '4xx rate: {{ $value | printf "%.2f" }}/s'
  summary: High 4xx error rate on Nginx

alert: NginxHigh5xxErrors
expr: rate(nginx_http_requests_total{status=~"5.."}[5m])
  > 0.05
for: 5m
labels:
  severity: critical
annotations:
  description: '5xx rate: {{ $value | printf "%.2f" }}/s'
  summary: High 5xx error rate on Nginx

alert: RedisHighMemory
expr: redis_memory_used_bytes
  / redis_memory_max_bytes > 0.9
for: 5m
labels:
  severity: warning
annotations:
  description: Memory usage is {{ $value | printf "%.1f" }}%
  summary: Redis memory usage high

alert: RedisManyExpiredKeys
expr: rate(redis_expired_keys_total[5m])
  > 1000
for: 5m
labels:
  severity: info
annotations:
  summary: High rate of expired keys

alert: RedisTooManyConnections
expr: redis_connected_clients
  > 100
for: 5m
labels:
  severity: warning
annotations:
  description: 'Connected clients: {{ $value }}'
  summary: Redis connected clients high

alert: HighCPUUsage
expr: 100
  - (avg(rate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 90
for: 5m
labels:
  severity: warning
annotations:
  description: CPU usage is {{ $value | printf "%.1f" }}%
  summary: High CPU usage on {{ $labels.instance }}

alert: HighLoadAverage
expr: node_load1
  / count(node_cpu_seconds_total{mode="idle"}) > 1.5
for: 10m
labels:
  severity: warning
annotations:
  description: Load average is {{ $value | printf "%.2f" }}
  summary: High load average on {{ $labels.instance }}

alert: HighMemoryUsage
expr: (1
  - (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes)) * 100 > 90
for: 5m
labels:
  severity: warning
annotations:
  description: Memory usage is {{ $value | printf "%.1f" }}%
  summary: High memory usage on {{ $labels.instance }}

alert: LowDiskSpace
expr: (1
  - (node_filesystem_avail_bytes{mountpoint="/"} / node_filesystem_size_bytes{mountpoint="/"}))
  * 100 > 85
for: 10m
labels:
  severity: warning
annotations:
  description: Disk usage is {{ $value | printf "%.1f" }}%
  summary: Low disk space on {{ $labels.instance }}