deploy/operator-prometheus-rule.yaml

apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
  name: camel-k-operator
spec:
  groups:
    - name: camel-k-operator
      rules:
        - alert: CamelKReconciliationDuration
          expr: |
            (
            1 - sum(rate(camel_k_reconciliation_duration_seconds_bucket{le="0.5"}[5m])) by (job)
            /
            sum(rate(camel_k_reconciliation_duration_seconds_count[5m])) by (job)
            )
            * 100
            > 10
          for: 1m
          labels:
            severity: warning
          annotations:
            message: |
              {{ printf "%0.0f" $value }}% of the reconciliation requests
              for {{ $labels.job }} have their duration above 0.5s.
        - alert: CamelKReconciliationFailure
          expr: |
            sum(rate(camel_k_reconciliation_duration_seconds_count{result="Errored"}[5m])) by (job)
            /
            sum(rate(camel_k_reconciliation_duration_seconds_count[5m])) by (job)
            * 100
            > 1
          for: 10m
          labels:
            severity: warning
          annotations:
            message: |
              {{ printf "%0.0f" $value }}% of the reconciliation requests
              for {{ $labels.job }} have failed.
        - alert: CamelKSuccessBuildDuration2m
          expr: |
            (
            1 - sum(rate(camel_k_build_duration_seconds_bucket{le="120",result="Succeeded"}[5m])) by (job)
            /
            sum(rate(camel_k_build_duration_seconds_count{result="Succeeded"}[5m])) by (job)
            )
            * 100
            > 10
          for: 1m
          labels:
            severity: warning
          annotations:
            message: |
              {{ printf "%0.0f" $value }}% of the successful builds
              for {{ $labels.job }} have their duration above 2m.
        - alert: CamelKSuccessBuildDuration5m
          expr: |
            (
            1 - sum(rate(camel_k_build_duration_seconds_bucket{le="300",result="Succeeded"}[5m])) by (job)
            /
            sum(rate(camel_k_build_duration_seconds_count{result="Succeeded"}[5m])) by (job)
            )
            * 100
            > 1
          for: 1m
          labels:
            severity: critical
          annotations:
            message: |
              {{ printf "%0.0f" $value }}% of the successful builds
              for {{ $labels.job }} have their duration above 5m.
        - alert: CamelKBuildFailure
          expr: |
            sum(rate(camel_k_build_duration_seconds_count{result="Failed"}[5m])) by (job)
            /
            sum(rate(camel_k_build_duration_seconds_count[5m])) by (job)
            * 100
            > 1
          for: 10m
          labels:
            severity: warning
          annotations:
            message: |
              {{ printf "%0.0f" $value }}% of the builds for {{ $labels.job }} have failed.
        - alert: CamelKBuildError
          expr: |
            sum(rate(camel_k_build_duration_seconds_count{result="Error"}[5m])) by (job)
            /
            sum(rate(camel_k_build_duration_seconds_count[5m])) by (job)
            * 100
            > 1
          for: 10m
          labels:
            severity: critical
          annotations:
            message: |
              {{ printf "%0.0f" $value }}% of the builds for {{ $labels.job }} have errored.
        - alert: CamelKBuildQueueDuration1m
          expr: |
            (
            1 - sum(rate(camel_k_build_queue_duration_seconds_bucket{le="60"}[5m])) by (job)
            /
            sum(rate(camel_k_build_queue_duration_seconds_count[5m])) by (job)
            )
            * 100
            > 1
          for: 1m
          labels:
            severity: warning
          annotations:
            message: |
              {{ printf "%0.0f" $value }}% of the builds for {{ $labels.job }}
              have been queued for more than 1m.
        - alert: CamelKBuildQueueDuration5m
          expr: |
            (
            1 - sum(rate(camel_k_build_queue_duration_seconds_bucket{le="300"}[5m])) by (job)
            /
            sum(rate(camel_k_build_queue_duration_seconds_count[5m])) by (job)
            )
            * 100
            > 1
          for: 1m
          labels:
            severity: critical
          annotations:
            message: |
              {{ printf "%0.0f" $value }}% of the builds for {{ $labels.job }}
              have been queued for more than 5m.