fix dashboard links in alertmanager and mimir rules

CHANGELOG.md

@@ -11,6 +11,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 - Upgrade Alloy to 0.5.2 which brings no value to this repo.
 
+### Fixed
+
+- Dashboard links in alertmanager and mimir rules
+
 ## [4.15.2] - 2024-09-17
 
 ### Fixed

helm/prometheus-rules/templates/platform/atlas/alerting-rules/alertmanager.rules.yml

@@ -12,6 +12,7 @@ spec:
     rules:
     - alert: AlertmanagerNotifyNotificationsFailing
       annotations:
+        dashboard: alertmanager-overview/alertmanager-overview
         description: '{{`AlertManager {{ $labels.integration }} notifications are failing.`}}'
         opsrecipe: alert-manager-notifications-failing/
       # Interval = 20m because currently AlertManager config set `group_interval=15m` that means that if a notification fails, it will be retried after 15m
@@ -21,21 +22,20 @@ spec:
       for: 45m
       labels:
         area: platform
-        dashboard: alertmanager-overview/alertmanager-overview
         severity: page
         team: atlas
         topic: monitoring
         cancel_if_outside_working_hours: "true"
     - alert: AlertmanagerPageNotificationsFailing
       annotations:
+        dashboard: alertmanager-overview/alertmanager-overview
         description: '{{`AlertManager {{ $labels.integration }} notifications are failing.`}}'
         opsrecipe: alert-manager-notifications-failing/
       # Here, we decide to notify after 2 successive failures (opsgenie notification), so we need to wait 2*15m = 30m before notifying.
       expr: rate(alertmanager_notifications_failed_total{integration="opsgenie", cluster_type="management_cluster"}[20m]) > 0
       for: 30m
       labels:
         area: platform
-        dashboard: alertmanager-overview/alertmanager-overview
         severity: notify
         team: atlas
         topic: monitoring

helm/prometheus-rules/templates/platform/atlas/alerting-rules/mimir.rules.yml

@@ -29,6 +29,7 @@ spec:
     # This alert will not page for the prometheus-buddy.
     - alert: MimirRestartingTooOften
       annotations:
+        dashboard: ffcd83628d7d4b5a03d1cafd159e6c9c/mimir-overview
         description: '{{`Mimir containers are restarting too often.`}}'
         opsrecipe: mimir/
       expr: |
@@ -41,12 +42,12 @@ spec:
         # This label is used to ensure the alert go through even for non-stable installations
         all_pipelines: "true"
         cancel_if_outside_working_hours: "true"
-        dashboard: ffcd83628d7d4b5a03d1cafd159e6c9c/mimir-overview
         severity: page
         team: atlas
         topic: observability
     - alert: MimirComponentDown
       annotations:
+        dashboard: ffcd83628d7d4b5a03d1cafd159e6c9c/mimir-overview
         description: '{{`Mimir component : {{ $labels.service }} is down.`}}'
         opsrecipe: mimir/
       expr: count(up{job=~"mimir/.*", container!="prometheus"} == 0) by (cluster_id, installation, provider, pipeline, service) > 0
@@ -57,7 +58,6 @@ spec:
         cancel_if_cluster_status_deleting: "true"
         cancel_if_cluster_status_updating: "true"
         cancel_if_outside_working_hours: "true"
-        dashboard: ffcd83628d7d4b5a03d1cafd159e6c9c/mimir-overview
         severity: page
         team: atlas
         topic: observability
@@ -78,6 +78,7 @@ spec:
         topic: observability
     - alert: MimirRulerEventsFailed
       annotations:
+        dashboard: 631e15d5d85afb2ca8e35d62984eeaa0/mimir-ruler
         description: 'Mimir ruler is failing to process PrometheusRules.'
         opsrecipe: mimir/
       expr: rate(mimir_rules_events_failed_total{cluster_type="management_cluster", namespace="mimir"}[5m]) > 0
@@ -88,7 +89,6 @@ spec:
         cancel_if_cluster_status_deleting: "true"
         cancel_if_cluster_status_updating: "true"
         cancel_if_outside_working_hours: "true"
-        dashboard: 631e15d5d85afb2ca8e35d62984eeaa0/mimir-ruler
         severity: page
         team: atlas
         topic: observability
@@ -168,6 +168,7 @@ spec:
         topic: observability
     - alert: MimirCompactorFailedCompaction
       annotations:
+        dashboard: 09a5c49e9cdb2f2b24c6d184574a07fd/mimir-compactor-resources
         description: 'Mimir compactor has been failing its compactions for 2 hours.'
         opsrecipe: mimir/
       # Query is based on the following upstream mixin alerting rule : https://github.com/grafana/mimir/blob/main/operations/mimir-mixin-compiled/alerts.yaml#L858
@@ -178,7 +179,6 @@ spec:
         cancel_if_cluster_status_deleting: "true"
         cancel_if_cluster_status_updating: "true"
         cancel_if_outside_working_hours: "true"
-        dashboard: 09a5c49e9cdb2f2b24c6d184574a07fd/mimir-compactor-resources
         severity: page
         team: atlas
         topic: observability

test/tests/providers/capi/capa-mimir/platform/atlas/alerting-rules/mimir.rules.test.yml

@@ -79,11 +79,11 @@ tests:
               cancel_if_cluster_status_updating: "true"
               cancel_if_outside_working_hours: "true"
               cluster_id: gauss
-              dashboard: ffcd83628d7d4b5a03d1cafd159e6c9c/mimir-overview
               installation: gauss
               provider: aws
               pipeline: testing
             exp_annotations:
+              dashboard: ffcd83628d7d4b5a03d1cafd159e6c9c/mimir-overview
               description: "Mimir component : mimir-ingester is down."
               opsrecipe: "mimir/"
   - interval: 1m
@@ -134,13 +134,13 @@ tests:
               cancel_if_cluster_status_updating: "true"
               cluster_id: golem
               cluster_type: management_cluster
-              dashboard: 631e15d5d85afb2ca8e35d62984eeaa0/mimir-ruler
               installation: golem
               namespace: mimir
               severity: page
               team: atlas
               topic: observability
             exp_annotations:
+              dashboard: 631e15d5d85afb2ca8e35d62984eeaa0/mimir-ruler
               description: "Mimir ruler is failing to process PrometheusRules."
               opsrecipe: "mimir/"
       - alertname: MimirRulerEventsFailed
@@ -163,12 +163,12 @@ tests:
               cancel_if_outside_working_hours: "true"
               cluster_type: management_cluster
               container: mimir-ingester
-              dashboard: ffcd83628d7d4b5a03d1cafd159e6c9c/mimir-overview
               namespace: mimir
               severity: page
               team: atlas
               topic: observability
             exp_annotations:
+              dashboard: ffcd83628d7d4b5a03d1cafd159e6c9c/mimir-overview
               description: Mimir containers are restarting too often.
               opsrecipe: "mimir/"
       - alertname: MimirRestartingTooOften
@@ -405,7 +405,6 @@ tests:
               cancel_if_cluster_status_updating: "true"
               cancel_if_outside_working_hours: "true"
               cluster_id: golem
-              dashboard: 09a5c49e9cdb2f2b24c6d184574a07fd/mimir-compactor-resources
               installation: "golem"
               pipeline: "testing"
               provider: "capa"
@@ -414,6 +413,7 @@ tests:
               team: atlas
               topic: observability
             exp_annotations:
+              dashboard: 09a5c49e9cdb2f2b24c6d184574a07fd/mimir-compactor-resources
               description: Mimir compactor has been failing its compactions for 2 hours.
               opsrecipe: "mimir/"
       - alertname: MimirCompactorFailedCompaction

test/tests/providers/global/platform/atlas/alerting-rules/alertmanager.rules.test.yml

@@ -25,12 +25,12 @@ tests:
               area: platform
               cancel_if_outside_working_hours: "true"
               cluster_type: management_cluster
-              dashboard: alertmanager-overview/alertmanager-overview
               integration: slack
               severity: page
               team: atlas
               topic: monitoring
             exp_annotations:
+              dashboard: alertmanager-overview/alertmanager-overview
               description: "AlertManager slack notifications are failing."
               opsrecipe: alert-manager-notifications-failing/
       - alertname:  AlertmanagerNotifyNotificationsFailing
@@ -52,12 +52,12 @@ tests:
           - exp_labels:
               area: platform
               cluster_type: management_cluster
-              dashboard: alertmanager-overview/alertmanager-overview
               integration: opsgenie
               severity: notify
               team: atlas
               topic: monitoring
             exp_annotations:
+              dashboard: alertmanager-overview/alertmanager-overview
               description: "AlertManager opsgenie notifications are failing."
               opsrecipe: alert-manager-notifications-failing/
       - alertname:  AlertmanagerPageNotificationsFailing