Merge branch 'main' into add-mimir-continoustest-alerts

giantswarm · Nov 5, 2024 · d6b4ace · d6b4ace
2 parents c375c42 + 44be18c
commit d6b4ace
Show file tree

Hide file tree

Showing 79 changed files with 1,070 additions and 785 deletions.
diff --git a/.circleci/config.yml b/.circleci/config.yml
@@ -1,88 +1,92 @@
 version: 2.1
 orbs:
-  architect: giantswarm/architect@5.8.0
+  architect: giantswarm/architect@5.11.1
 
 workflows:
   package-and-push-chart-on-tag:
     jobs:
-      - architect/push-to-app-catalog:
-          context: "architect"
-          executor: app-build-suite
-          name: app-catalog
-          app_catalog: "control-plane-catalog"
-          app_catalog_test: "control-plane-test-catalog"
-          chart: "prometheus-rules"
+    - architect/push-to-app-catalog:
+        context: architect
+        executor: app-build-suite
+        name: app-catalog
+        app_catalog: control-plane-catalog
+        app_catalog_test: control-plane-test-catalog
+        chart: prometheus-rules
           # Trigger job on git tag.
-          filters:
-            tags:
-              only: /^v.*/
+        filters:
+          tags:
+            only: /^v.*/
 
-      - architect/push-to-app-collection:
-          context: "architect"
-          name: aws-app-collection
-          app_name: "prometheus-rules"
-          app_namespace: "monitoring"
-          app_collection_repo: "aws-app-collection"
-          requires:
-            - app-catalog
-          filters:
-            branches:
-              ignore: /.*/
-            tags:
-              only: /^v.*/
+          branches:
+            ignore:
+            - main
+            - master
+    - architect/push-to-app-collection:
+        context: architect
+        name: aws-app-collection
+        app_name: prometheus-rules
+        app_namespace: monitoring
+        app_collection_repo: aws-app-collection
+        requires:
+        - app-catalog
+        filters:
+          branches:
+            ignore: /.*/
+          tags:
+            only: /^v.*/
 
-      - architect/push-to-app-collection:
-          context: architect
-          name: push-to-capa-app-collection
-          app_name: "prometheus-rules"
-          app_namespace: "monitoring"
-          app_collection_repo: "capa-app-collection"
-          requires:
-            - app-catalog
-          filters:
-            branches:
-              ignore: /.*/
-            tags:
-              only: /^v.*/
+    - architect/push-to-app-collection:
+        context: architect
+        name: push-to-capa-app-collection
+        app_name: prometheus-rules
+        app_namespace: monitoring
+        app_collection_repo: capa-app-collection
+        requires:
+        - app-catalog
+        filters:
+          branches:
+            ignore: /.*/
+          tags:
+            only: /^v.*/
 
-      - architect/push-to-app-collection:
-          context: architect
-          name: push-to-capz-app-collection
-          app_name: "prometheus-rules"
-          app_namespace: "monitoring"
-          app_collection_repo: "capz-app-collection"
-          requires:
-            - app-catalog
-          filters:
-            branches:
-              ignore: /.*/
-            tags:
-              only: /^v.*/
+    - architect/push-to-app-collection:
+        context: architect
+        name: push-to-capz-app-collection
+        app_name: prometheus-rules
+        app_namespace: monitoring
+        app_collection_repo: capz-app-collection
+        requires:
+        - app-catalog
+        filters:
+          branches:
+            ignore: /.*/
+          tags:
+            only: /^v.*/
 
-      - architect/push-to-app-collection:
-          context: architect
-          name: push-to-cloud-director-app-collection
-          app_name: "prometheus-rules"
-          app_namespace: "monitoring"
-          app_collection_repo: "cloud-director-app-collection"
-          requires:
-            - app-catalog
-          filters:
-            branches:
-              ignore: /.*/
-            tags:
-              only: /^v.*/
+    - architect/push-to-app-collection:
+        context: architect
+        name: push-to-cloud-director-app-collection
+        app_name: prometheus-rules
+        app_namespace: monitoring
+        app_collection_repo: cloud-director-app-collection
+        requires:
+        - app-catalog
+        filters:
+          branches:
+            ignore: /.*/
+          tags:
+            only: /^v.*/
 
-      - architect/push-to-app-collection:
-          context: "architect"
-          name: vsphere-app-collection
-          app_name: "prometheus-rules"
-          app_namespace: "monitoring"
-          app_collection_repo: "vsphere-app-collection"
-          requires:
-            - app-catalog
-          filters:
-            branches:
-              ignore: /.*/
-            tags:
-              only: /^v.*/
+    - architect/push-to-app-collection:
+        context: architect
+        name: vsphere-app-collection
+        app_name: prometheus-rules
+        app_namespace: monitoring
+        app_collection_repo: vsphere-app-collection
+        requires:
+        - app-catalog
+        filters:
+          branches:
+            ignore: /.*/
+          tags:
+            only: /^v.*/
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -7,14 +7,129 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [4.23.0] - 2024-10-30
+
+### Changed
+
+- Rename all `prometheus-agent` related inhibitions to `monitoring-agent` inhibitions.
+- Move `Inhibition` from a suffix to a prefix for the prometheus-agent inhibitions to match with the other inhibition alerts:
+- `PrometheusAgentFailingInhibition`       => `InhibitionPrometheusAgentFailing`
+- `PrometheusAgentShardsMissingInhibition` => `InhibitionPrometheusAgentShardsMissing`
+
+### Fixed
+
+- Fixes the statefulset.rules name as it is currently replacing the deployment.rules alerts.
+
+## [4.22.0] - 2024-10-29
+
+### Changed
+
+- Change `KubeletVolumeSpaceTooLow` to only page when there are 500MB or less of space left, letting the node-problem-detector handle the rest.
+
+## [4.21.1] - 2024-10-25
+
+### Fixed
+
+- Updated `aggregation:giantswarm:cluster_release_version` expression to support CAPI clusters
+
+## [4.21.0] - 2024-10-25
+
+### Changed
+
+- Set the `InhibitionControlPlaneUnhealthy` to be valid for all CAPI clusters, not just MCs.
+
+## [4.20.0] - 2024-10-22
+
+### Added
+
+- Added InhibitionClusterWithoutWorkerNodes for CAPA
+
+### Changed
+
+- Modify `KyvernoWebhookHasNoAvailableReplicas` to check specifically for Kyverno resource webhook.
+- Inhibit prometheas-agent alerts when a cluster has no worker nodes (AWS vintage only for now)
+
+## [4.19.0] - 2024-10-15
+
+### Added
+
+- Alert `StatefulsetNotSatisfiedAtlas`
+
+### Changed
+
+- Update alloy-app to 0.6.1. This includes:
+  - an upgrade to upstream version 1.4.2
+  - a ciliumnetworkpolicy fix for clustering.
+
+## [4.18.0] - 2024-10-08
+
+### Added
+
+- Alerting rule for Loki missing logs at ingestion
+
+## [4.17.0] - 2024-10-03
+
+### Removed
+
+- Remove legacy in-house slo framework.
+
+## [4.16.1] - 2024-09-26
+
+### Fixed
+
+- fix `LokiFailedCompaction` to take latest successfull compaction across multiple compactor/backend pods
+
+## [4.16.0] - 2024-09-26
+
+### Added
+
+- Add `LokiFailedCompaction` alert to know when Loki did not manage to run a successfull compaction in the last 2 hours.
+
+### Removed
+
+- Remove CRsync alerting rules.
+
+### Changed
+
+- Migrate BigMac alerts to Shield
+- Upgrade Alloy to 0.5.2 which brings no value to this repo.
+
+### Fixed
+
+- Dashboard links in alertmanager and mimir rules
+- Fix cert-manager down alert.
+- Remove deprecated app labels for `external-dns` and `ingress-nginx` alerts.
+- Remove deprecated app labels for `kube-state-metrics` alerts.
+- Fix falco events alerts node label to hostname as node does not exist.
+- Fix `MimirHPAReachedMaxReplicas` description to render the horizontalpodautoscaler label.
+
+## [4.15.2] - 2024-09-17
+
+### Fixed
+
+- Update `MimirHPAReachedMaxReplicas` opsrecipe link
+- Fix aggregation rule of the `slo:current_burn_rate:ratio` slo.
+
+## [4.15.1] - 2024-09-16
+
+### Removed
+
+- Remove aggregation of slo:period_error_budget_remaining:ratio` as this value can be easily computed and creates a lot of time series in Grafana Cloud
+
+## [4.15.0] - 2024-09-16
+
 ### Added
 
+- Add aggregations for slo metrics to export them to grafana cloud
 - Add `MimirHPAReachedMaxReplicas` alert, to detect when Mimir's HPAs have reached maximum capacity.
 - Add `MimirContinuousTestFailingOnWrites` and `MimirContinuousTestFailingOnReads` alerts.
 
 ### Changed
 
 - Added dashboards to several mimir alerts
+- Change `IRSAACMCertificateExpiringInLessThan60Days` to
+  `IRSAACMCertificateExpiringInLessThan45Days`. The ACM certificate is renewed
+  60 days before expiration and the alert can fire prematurely.
 
 ## [4.14.0] - 2024-09-05
 
@@ -1364,7 +1479,7 @@ Fix `PromtailRequestsErrors` alerts as promtail retries after some backoff so ac
 
 - Deprecate `role=master` in favor of `role=control-plane`.
 - Rename alerts containing `Master` with `ControlPlane`
-- Added "cancel_if_prometheus_agent_down" for phoenix alerts ManagementClusterCriticalPodMetricMissing, ManagementClusterDeploymentMissingAWS, WorkloadClusterNonCriticalDeploymentNotSatisfiedKaas
+- Added `cancel_if_prometheus_agent_down` for phoenix alerts ManagementClusterCriticalPodMetricMissing, ManagementClusterDeploymentMissingAWS, WorkloadClusterNonCriticalDeploymentNotSatisfiedKaas
 
 ## [2.94.0] - 2023-04-26
 
@@ -3075,7 +3190,20 @@ Fix `PromtailRequestsErrors` alerts as promtail retries after some backoff so ac
 
 - Add existing rules from https://github.com/giantswarm/prometheus-meta-operator/pull/637/commits/bc6a26759eb955de92b41ed5eb33fa37980660f2
 
-[Unreleased]: https://github.com/giantswarm/prometheus-rules/compare/v4.14.0...HEAD
+[Unreleased]: https://github.com/giantswarm/prometheus-rules/compare/v4.23.0...HEAD
+[4.23.0]: https://github.com/giantswarm/prometheus-rules/compare/v4.22.0...v4.23.0
+[4.22.0]: https://github.com/giantswarm/prometheus-rules/compare/v4.21.1...v4.22.0
+[4.21.1]: https://github.com/giantswarm/prometheus-rules/compare/v4.21.0...v4.21.1
+[4.21.0]: https://github.com/giantswarm/prometheus-rules/compare/v4.20.0...v4.21.0
+[4.20.0]: https://github.com/giantswarm/prometheus-rules/compare/v4.19.0...v4.20.0
+[4.19.0]: https://github.com/giantswarm/prometheus-rules/compare/v4.18.0...v4.19.0
+[4.18.0]: https://github.com/giantswarm/prometheus-rules/compare/v4.17.0...v4.18.0
+[4.17.0]: https://github.com/giantswarm/prometheus-rules/compare/v4.16.1...v4.17.0
+[4.16.1]: https://github.com/giantswarm/prometheus-rules/compare/v4.16.0...v4.16.1
+[4.16.0]: https://github.com/giantswarm/prometheus-rules/compare/v4.15.2...v4.16.0
+[4.15.2]: https://github.com/giantswarm/prometheus-rules/compare/v4.15.1...v4.15.2
+[4.15.1]: https://github.com/giantswarm/prometheus-rules/compare/v4.15.0...v4.15.1
+[4.15.0]: https://github.com/giantswarm/prometheus-rules/compare/v4.14.0...v4.15.0
 [4.14.0]: https://github.com/giantswarm/prometheus-rules/compare/v4.13.3...v4.14.0
 [4.13.3]: https://github.com/giantswarm/prometheus-rules/compare/v4.13.2...v4.13.3
 [4.13.2]: https://github.com/giantswarm/prometheus-rules/compare/v4.13.1...v4.13.2

diff --git a/CODEOWNERS b/CODEOWNERS
@@ -1,8 +1,8 @@
 * @giantswarm/team-atlas
-/helm/prometheus-rules/templates/kaas/bigmac/ @giantswarm/team-bigmac
 /helm/prometheus-rules/templates/kaas/phoenix/ @giantswarm/team-phoenix
 /helm/prometheus-rules/templates/kaas/rocket/ @giantswarm/team-rocket
-/helm/prometheus-rules/templates/kaas/turtles/ @giantswarm/team-turtles
+/helm/prometheus-rules/templates/kaas/turtles/ @giantswarm/team-tenet
+/helm/prometheus-rules/templates/kaas/tenet/ @giantswarm/team-tenet
 /helm/prometheus-rules/templates/platform/atlas/ @giantswarm/team-atlas
 /helm/prometheus-rules/templates/platform/cabbage/ @giantswarm/team-cabbage
 /helm/prometheus-rules/templates/platform/honeybadger/ @giantswarm/team-honeybadger

diff --git a/Makefile.custom.mk b/Makefile.custom.mk
@@ -38,3 +38,12 @@ pint: install-tools template-chart ## Run pint
 pint-all: install-tools template-chart ## Run pint with extra checks
 	GENERATE_ONLY=true bash test/hack/bin/verify-rules.sh
 	./test/hack/bin/run-pint.sh test/conf/pint/pint-all.hcl ${PINT_TEAM_FILTER}
+
+##@ Mixins
+update-mimir-mixin: install-tools ##        Update Mimir mixins
+	./mimir/update.sh
+
+update-loki-mixin: install-tools ##        Update Loki mixins
+	./loki/update.sh
+
+update-mixin: update-mimir-mixin update-loki-mixin ##        Update all mixins
diff --git a/helm/prometheus-rules/Chart.yaml b/helm/prometheus-rules/Chart.yaml
@@ -5,7 +5,7 @@ home: https://github.com/giantswarm/prometheus-rules
 icon: https://s.giantswarm.io/app-icons/1/png/default-app-light.png
 name: prometheus-rules
 appVersion: '0.1.0'
-version: '4.14.0'
+version: '4.23.0'
 annotations:
   application.giantswarm.io/team: "atlas"
   config.giantswarm.io/version: 1.x.x
diff --git a/helm/prometheus-rules/templates/alloy-rules.yaml b/helm/prometheus-rules/templates/alloy-rules.yaml
@@ -27,5 +27,5 @@ spec:
   namespace: monitoring
   # used by renovate
   # repo: giantswarm/alloy
-  version: 0.5.1
+  version: 0.6.1
 {{- end -}}