# Prometheus Alerting Rules

apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
  name: shared-services-alerts
  namespace: monitoring
  labels:
    app: prometheus
spec:
  groups:
    - name: kubernetes.rules
      interval: 30s
      rules:
        - alert: PodCrashLooping
          expr: rate(kube_pod_container_status_restarts_total[15m]) > 0
          for: 5m
          labels:
            severity: warning
          annotations:
            summary: "Pod {{ $labels.namespace }}/{{ $labels.pod }} is crash looping"
            description: "Pod {{ $labels.namespace }}/{{ $labels.pod }} has restarted {{ $value }} times in the last 15 minutes"

        - alert: PodNotReady
          expr: sum by (namespace, pod) (kube_pod_status_phase{phase!~"Running|Succeeded"}) > 0
          for: 10m
          labels:
            severity: warning
          annotations:
            summary: "Pod {{ $labels.namespace }}/{{ $labels.pod }} is not ready"
            description: "Pod {{ $labels.namespace }}/{{ $labels.pod }} has been in a non-ready state for more than 10 minutes"

        - alert: HighMemoryUsage
          expr: (sum by (namespace, pod) (container_memory_usage_bytes) / sum by (namespace, pod) (kube_pod_container_resource_limits_memory_bytes)) > 0.9
          for: 5m
          labels:
            severity: warning
          annotations:
            summary: "Pod {{ $labels.namespace }}/{{ $labels.pod }} memory usage is high"
            description: "Pod {{ $labels.namespace }}/{{ $labels.pod }} is using {{ $value | humanizePercentage }} of its memory limit"

        - alert: HighCPUUsage
          expr: (sum by (namespace, pod) (rate(container_cpu_usage_seconds_total[5m])) / sum by (namespace, pod) (kube_pod_container_resource_limits_cpu)) > 0.9
          for: 5m
          labels:
            severity: warning
          annotations:
            summary: "Pod {{ $labels.namespace }}/{{ $labels.pod }} CPU usage is high"
            description: "Pod {{ $labels.namespace }}/{{ $labels.pod }} is using {{ $value | humanizePercentage }} of its CPU limit"

    - name: application.rules
      interval: 30s
      rules:
        - alert: HighErrorRate
          expr: rate(http_requests_total{status=~"5.."}[5m]) > 0.1
          for: 5m
          labels:
            severity: critical
          annotations:
            summary: "High error rate detected"
            description: "Error rate is {{ $value }} errors per second"

        - alert: HighLatency
          expr: histogram_quantile(0.95, rate(http_request_duration_seconds_bucket[5m])) > 1
          for: 10m
          labels:
            severity: warning
          annotations:
            summary: "High latency detected"
            description: "95th percentile latency is {{ $value }} seconds"

        - alert: ServiceDown
          expr: up{job=~".+"} == 0
          for: 1m
          labels:
            severity: critical
          annotations:
            summary: "Service {{ $labels.job }} is down"
            description: "Service {{ $labels.job }} has been down for more than 1 minute"

    - name: infrastructure.rules
      interval: 30s
      rules:
        - alert: NodeNotReady
          expr: kube_node_status_condition{condition="Ready",status="true"} == 0
          for: 5m
          labels:
            severity: critical
          annotations:
            summary: "Node {{ $labels.node }} is not ready"
            description: "Node {{ $labels.node }} has been in a not-ready state for more than 5 minutes"

        - alert: DiskSpaceLow
          expr: (node_filesystem_avail_bytes / node_filesystem_size_bytes) < 0.1
          for: 5m
          labels:
            severity: warning
          annotations:
            summary: "Disk space low on {{ $labels.instance }}"
            description: "Disk {{ $labels.device }} on {{ $labels.instance }} has only {{ $value | humanizePercentage }} space available"