Remove prometheus-operator alerts (#299)

Signed-off-by: ArthurSens <[email protected]>

Signed-off-by: ArthurSens <[email protected]>

Author: ArthurSens

lib/alert-filter.libsonnet

@@ -67,6 +67,16 @@ local unwatedAlerts = [
   'KubeletServerCertificateRenewalErrors',
   'KubeletDown',  // Re-added to platform-mixin
   'KubeClientErrors',
+
+  // From prometheus-operator
+  'PrometheusOperatorListErrors',  // Re-added to platform-mixin
+  'PrometheusOperatorWatchErrors',  // Re-added to platform-mixin
+  'PrometheusOperatorReconcileErrors',  // Re-added to platform-mixin
+  'PrometheusOperatorNodeLookupErrors',
+  'PrometheusOperatorNotReady',
+  'ConfigReloaderSidecarErrors',  // Re-added to platform-mixin
+  'PrometheusOperatorRejectedResources',
+  'PrometheusOperatorSyncFailed',
 ];
 
 {

monitoring-satellite/manifests/kube-prometheus-rules/rules.yaml

@@ -1448,91 +1448,9 @@ spec:
       labels:
         severity: critical
   - name: prometheus-operator
-    rules:
-    - alert: PrometheusOperatorListErrors
-      annotations:
-        description: Errors while performing List operations in controller {{$labels.controller}} in {{$labels.namespace}} namespace.
-        runbook_url: https://github.com/gitpod-io/runbooks/blob/main/runbooks/PrometheusOperatorListErrors.md
-        summary: Errors while performing list operations in controller.
-      expr: |
-        (sum by (controller,namespace) (rate(prometheus_operator_list_operations_failed_total{job="prometheus-operator",namespace="monitoring-satellite"}[10m])) / sum by (controller,namespace) (rate(prometheus_operator_list_operations_total{job="prometheus-operator",namespace="monitoring-satellite"}[10m]))) > 0.4
-      for: 15m
-      labels:
-        severity: warning
-    - alert: PrometheusOperatorWatchErrors
-      annotations:
-        description: Errors while performing watch operations in controller {{$labels.controller}} in {{$labels.namespace}} namespace.
-        runbook_url: https://github.com/gitpod-io/runbooks/blob/main/runbooks/PrometheusOperatorWatchErrors.md
-        summary: Errors while performing watch operations in controller.
-      expr: |
-        (sum by (controller,namespace) (rate(prometheus_operator_watch_operations_failed_total{job="prometheus-operator",namespace="monitoring-satellite"}[5m])) / sum by (controller,namespace) (rate(prometheus_operator_watch_operations_total{job="prometheus-operator",namespace="monitoring-satellite"}[5m]))) > 0.4
-      for: 15m
-      labels:
-        severity: warning
-    - alert: PrometheusOperatorSyncFailed
-      annotations:
-        description: Controller {{ $labels.controller }} in {{ $labels.namespace }} namespace fails to reconcile {{ $value }} objects.
-        runbook_url: https://github.com/gitpod-io/runbooks/blob/main/runbooks/PrometheusOperatorSyncFailed.md
-        summary: Last controller reconciliation failed
-      expr: |
-        min_over_time(prometheus_operator_syncs{status="failed",job="prometheus-operator",namespace="monitoring-satellite"}[5m]) > 0
-      for: 10m
-      labels:
-        severity: warning
-    - alert: PrometheusOperatorReconcileErrors
-      annotations:
-        description: '{{ $value | humanizePercentage }} of reconciling operations failed for {{ $labels.controller }} controller in {{ $labels.namespace }} namespace.'
-        runbook_url: https://github.com/gitpod-io/runbooks/blob/main/runbooks/PrometheusOperatorReconcileErrors.md
-        summary: Errors while reconciling controller.
-      expr: |
-        (sum by (controller,namespace) (rate(prometheus_operator_reconcile_errors_total{job="prometheus-operator",namespace="monitoring-satellite"}[5m]))) / (sum by (controller,namespace) (rate(prometheus_operator_reconcile_operations_total{job="prometheus-operator",namespace="monitoring-satellite"}[5m]))) > 0.1
-      for: 10m
-      labels:
-        severity: warning
-    - alert: PrometheusOperatorNodeLookupErrors
-      annotations:
-        description: Errors while reconciling Prometheus in {{ $labels.namespace }} Namespace.
-        runbook_url: https://github.com/gitpod-io/runbooks/blob/main/runbooks/PrometheusOperatorNodeLookupErrors.md
-        summary: Errors while reconciling Prometheus.
-      expr: |
-        rate(prometheus_operator_node_address_lookup_errors_total{job="prometheus-operator",namespace="monitoring-satellite"}[5m]) > 0.1
-      for: 10m
-      labels:
-        severity: warning
-    - alert: PrometheusOperatorNotReady
-      annotations:
-        description: Prometheus operator in {{ $labels.namespace }} namespace isn't ready to reconcile {{ $labels.controller }} resources.
-        runbook_url: https://github.com/gitpod-io/runbooks/blob/main/runbooks/PrometheusOperatorNotReady.md
-        summary: Prometheus operator not ready
-      expr: |
-        min by (controller,namespace) (max_over_time(prometheus_operator_ready{job="prometheus-operator",namespace="monitoring-satellite"}[5m]) == 0)
-      for: 5m
-      labels:
-        severity: warning
-    - alert: PrometheusOperatorRejectedResources
-      annotations:
-        description: Prometheus operator in {{ $labels.namespace }} namespace rejected {{ printf "%0.0f" $value }} {{ $labels.controller }}/{{ $labels.resource }} resources.
-        runbook_url: https://github.com/gitpod-io/runbooks/blob/main/runbooks/PrometheusOperatorRejectedResources.md
-        summary: Resources rejected by Prometheus operator
-      expr: |
-        min_over_time(prometheus_operator_managed_resources{state="rejected",job="prometheus-operator",namespace="monitoring-satellite"}[5m]) > 0
-      for: 5m
-      labels:
-        severity: warning
+    rules: []
   - name: config-reloaders
-    rules:
-    - alert: ConfigReloaderSidecarErrors
-      annotations:
-        description: |-
-          Errors encountered while the {{$labels.pod}} config-reloader sidecar attempts to sync config in {{$labels.namespace}} namespace.
-          As a result, configuration for service running in {{$labels.pod}} may be stale and cannot be updated anymore.
-        runbook_url: https://github.com/gitpod-io/runbooks/blob/main/runbooks/ConfigReloaderSidecarErrors.md
-        summary: config-reloader sidecar has not had a successful reload for 10m
-      expr: |
-        max_over_time(reloader_last_reload_successful{namespace=~".+"}[5m]) == 0
-      for: 10m
-      labels:
-        severity: warning
+    rules: []
   - name: cert-manager
     rules: []
   - name: certificates