Commit 33ceea4c authored by Kevin Di Lallo's avatar Kevin Di Lallo
Browse files

fixed faulty alert triggers

parent ca679995

config/values/meep-prometheus.yaml

+4 −4
Original line number Diff line number Diff line
@@ -14,7 +14,7 @@ additionalPrometheusRulesMap: 
    - name: Node Alerts

      rules:

      - alert: HostRebooted

        expr: changes(node_boot_time_seconds[10m]) > 0

        expr: changes(node_boot_time_seconds[10m]) > 10

        for: 0m

        labels:

          severity: warning
@@ -96,13 +96,13 @@ additionalPrometheusRulesMap: 
          summary: Kubernetes pod crash looping (instance {{ $labels.instance }})

          description: Pod {{ $labels.pod }} is crash looping\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}

      - alert: KubernetesPodNotHealthy

        expr: min_over_time(sum by (namespace, pod) (kube_pod_status_phase{phase=~"Pending|Unknown|Failed"})[15m:]) > 0

        for: 5m

        expr: sum by (namespace, pod) (sum_over_time(kube_pod_status_phase{phase=~"Pending|Unknown|Failed"}[5m])) >= 10

        for: 0m

        labels:

          severity: critical

        annotations:

          summary: Kubernetes Pod not healthy (instance {{ $labels.instance }})

          description: Pod has been in a non-ready state for more than 5 minutes in the last 15 minutes.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}

          description: Pod has been in a non-ready state for more than 5 minutes.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}



alertmanager:

  enabled: true