Remove alertmanager alerts (#296)

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

Signed-off-by: ArthurSens <[email protected]>
Co-authored-by: Aleksandar Aleksandrov <[email protected]>

Author: ArthurSens

lib/alert-filter.libsonnet

@@ -68,6 +68,16 @@ local unwatedAlerts = [
   'KubeletDown',  // Re-added to platform-mixin
   'KubeClientErrors',
 
+  // From Alertmanager
+  'AlertmanagerFailedReload',  // Re-added to platform-mixin
+  'AlertmanagerFailedToSendAlerts',  // Re-added to platform-mixin
+  'AlertmanagerMembersInconsistent',
+  'AlertmanagerClusterFailedToSendAlerts',
+  'AlertmanagerConfigInconsistent',
+  'AlertmanagerClusterDown',
+  'AlertmanagerClusterCrashlooping',
+
+
   // From kube-state-metrics
   'KubeStateMetricsWatchErrors',  // Re-added to platform-mixin
   'KubeStateMetricsShardingMismatch',

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

@@ -63,129 +63,7 @@ spec:
     - expr: count without(instance, pod, node) (up == 0)
       record: count:up0
   - name: alertmanager.rules
-    rules:
-    - alert: AlertmanagerFailedReload
-      annotations:
-        description: Configuration has failed to load for {{ $labels.namespace }}/{{ $labels.pod}}.
-        runbook_url: https://github.com/gitpod-io/runbooks/blob/main/runbooks/AlertmanagerFailedReload.md
-        summary: Reloading an Alertmanager configuration has failed.
-      expr: |
-        # Without max_over_time, failed scrapes could create false negatives, see
-        # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
-        max_over_time(alertmanager_config_last_reload_successful{job="alertmanager-main",namespace="monitoring-satellite"}[5m]) == 0
-      for: 10m
-      labels:
-        severity: critical
-    - alert: AlertmanagerMembersInconsistent
-      annotations:
-        description: Alertmanager {{ $labels.namespace }}/{{ $labels.pod}} has only found {{ $value }} members of the {{$labels.job}} cluster.
-        runbook_url: https://github.com/gitpod-io/runbooks/blob/main/runbooks/AlertmanagerMembersInconsistent.md
-        summary: A member of an Alertmanager cluster has not found all other cluster members.
-      expr: |
-        # Without max_over_time, failed scrapes could create false negatives, see
-        # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
-          max_over_time(alertmanager_cluster_members{job="alertmanager-main",namespace="monitoring-satellite"}[5m])
-        < on (cluster) group_left
-          count by (cluster) (max_over_time(alertmanager_cluster_members{job="alertmanager-main",namespace="monitoring-satellite"}[5m]))
-      for: 15m
-      labels:
-        severity: critical
-    - alert: AlertmanagerFailedToSendAlerts
-      annotations:
-        description: Alertmanager {{ $labels.namespace }}/{{ $labels.pod}} failed to send {{ $value | humanizePercentage }} of notifications to {{ $labels.integration }}.
-        runbook_url: https://github.com/gitpod-io/runbooks/blob/main/runbooks/AlertmanagerFailedToSendAlerts.md
-        summary: An Alertmanager instance failed to send notifications.
-      expr: |
-        (
-          rate(alertmanager_notifications_failed_total{job="alertmanager-main",namespace="monitoring-satellite"}[5m])
-        /
-          rate(alertmanager_notifications_total{job="alertmanager-main",namespace="monitoring-satellite"}[5m])
-        )
-        > 0.01
-      for: 5m
-      labels:
-        severity: warning
-    - alert: AlertmanagerClusterFailedToSendAlerts
-      annotations:
-        description: The minimum notification failure rate to {{ $labels.integration }} sent from any instance in the {{$labels.job}} cluster is {{ $value | humanizePercentage }}.
-        runbook_url: https://github.com/gitpod-io/runbooks/blob/main/runbooks/AlertmanagerClusterFailedToSendAlerts.md
-        summary: All Alertmanager instances in a cluster failed to send notifications to a critical integration.
-      expr: |
-        min by (cluster, integration) (
-          rate(alertmanager_notifications_failed_total{job="alertmanager-main",namespace="monitoring-satellite", integration=~`slack|pagerduty`}[5m])
-        /
-          rate(alertmanager_notifications_total{job="alertmanager-main",namespace="monitoring-satellite", integration=~`slack|pagerduty`}[5m])
-        )
-        > 0.01
-      for: 5m
-      labels:
-        severity: critical
-    - alert: AlertmanagerClusterFailedToSendAlerts
-      annotations:
-        description: The minimum notification failure rate to {{ $labels.integration }} sent from any instance in the {{$labels.job}} cluster is {{ $value | humanizePercentage }}.
-        runbook_url: https://github.com/gitpod-io/runbooks/blob/main/runbooks/AlertmanagerClusterFailedToSendAlerts.md
-        summary: All Alertmanager instances in a cluster failed to send notifications to a non-critical integration.
-      expr: |
-        min by (cluster, integration) (
-          rate(alertmanager_notifications_failed_total{job="alertmanager-main",namespace="monitoring-satellite", integration!~`slack|pagerduty`}[5m])
-        /
-          rate(alertmanager_notifications_total{job="alertmanager-main",namespace="monitoring-satellite", integration!~`slack|pagerduty`}[5m])
-        )
-        > 0.01
-      for: 5m
-      labels:
-        severity: warning
-    - alert: AlertmanagerConfigInconsistent
-      annotations:
-        description: Alertmanager instances within the {{$labels.job}} cluster have different configurations.
-        runbook_url: https://github.com/gitpod-io/runbooks/blob/main/runbooks/AlertmanagerConfigInconsistent.md
-        summary: Alertmanager instances within the same cluster have different configurations.
-      expr: |
-        count by (cluster) (
-          count_values by (cluster) ("config_hash", alertmanager_config_hash{job="alertmanager-main",namespace="monitoring-satellite"})
-        )
-        != 1
-      for: 20m
-      labels:
-        severity: critical
-    - alert: AlertmanagerClusterDown
-      annotations:
-        description: '{{ $value | humanizePercentage }} of Alertmanager instances within the {{$labels.job}} cluster have been up for less than half of the last 5m.'
-        runbook_url: https://github.com/gitpod-io/runbooks/blob/main/runbooks/AlertmanagerClusterDown.md
-        summary: Half or more of the Alertmanager instances within the same cluster are down.
-      expr: |
-        (
-          count by (cluster) (
-            avg_over_time(up{job="alertmanager-main",namespace="monitoring-satellite"}[5m]) < 0.5
-          )
-        /
-          count by (cluster) (
-            up{job="alertmanager-main",namespace="monitoring-satellite"}
-          )
-        )
-        >= 0.5
-      for: 5m
-      labels:
-        severity: critical
-    - alert: AlertmanagerClusterCrashlooping
-      annotations:
-        description: '{{ $value | humanizePercentage }} of Alertmanager instances within the {{$labels.job}} cluster have restarted at least 5 times in the last 10m.'
-        runbook_url: https://github.com/gitpod-io/runbooks/blob/main/runbooks/AlertmanagerClusterCrashlooping.md
-        summary: Half or more of the Alertmanager instances within the same cluster are crashlooping.
-      expr: |
-        (
-          count by (cluster) (
-            changes(process_start_time_seconds{job="alertmanager-main",namespace="monitoring-satellite"}[10m]) > 4
-          )
-        /
-          count by (cluster) (
-            up{job="alertmanager-main",namespace="monitoring-satellite"}
-          )
-        )
-        >= 0.5
-      for: 5m
-      labels:
-        severity: critical
+    rules: []
   - name: kube-state-metrics
     rules: []
   - name: kubernetes-apps