feat(add-ons): Add observability stack with kube-prometheus-stack, loki and alloy

2026-09-30 01:09:34 +05:30
parent 148890fb86
commit 576243b33e
17 changed files with 624 additions and 0 deletions
@@ -0,0 +1,124 @@
+apiVersion: argoproj.io/v1alpha1
+kind: Application
+metadata:
+  annotations:
+    argocd.argoproj.io/sync-wave: "4"
+  name: loki
+  namespace: argocd
+spec:
+  destination:
+    namespace: monitoring
+    server: https://kubernetes.default.svc
+  project: default
+  sources:
+    - chart: loki
+      helm:
+        values: |
+          deploymentMode: Monolithic
+          loki:
+            auth_enabled: false
+            commonConfig:
+              replication_factor: 1
+            schemaConfig:
+              configs:
+                - from: "2026-09-01"
+                  store: tsdb
+                  object_store: s3
+                  schema: v13
+                  index:
+                    prefix: loki_index_
+                    period: 24h
+            storage:
+              type: s3
+              bucketNames:
+                chunks: loki
+                ruler: loki
+              s3:
+                endpoint: http://garage.garage.svc.cluster.local:3900
+                region: garage
+                accessKeyId: ${LOKI_S3_ACCESS_KEY_ID}
+                secretAccessKey: ${LOKI_S3_SECRET_ACCESS_KEY}
+                s3ForcePathStyle: true
+                insecure: true
+            ingester:
+              chunk_encoding: zstd
+            compactor:
+              retention_enabled: true
+              delete_request_store: s3
+            limits_config:
+              retention_period: 2160h
+          singleBinary:
+            replicas: 1
+            extraEnvFrom:
+              - secretRef:
+                  name: loki-s3
+            persistence:
+              size: 10Gi
+            resources:
+              limits:
+                cpu: "1"
+                memory: 2Gi
+              requests:
+                cpu: 100m
+                memory: 512Mi
+          # Memory limits sit ~20% above memcached's allocation for connection overhead.
+          chunksCache:
+            allocatedMemory: 512
+            resources:
+              limits:
+                cpu: 500m
+                memory: 614Mi
+              requests:
+                cpu: 50m
+                memory: 614Mi
+          resultsCache:
+            allocatedMemory: 128
+            resources:
+              limits:
+                cpu: 500m
+                memory: 154Mi
+              requests:
+                cpu: 50m
+                memory: 154Mi
+          memcachedExporter:
+            resources:
+              limits:
+                cpu: 100m
+                memory: 64Mi
+              requests:
+                cpu: 10m
+                memory: 16Mi
+          # Loki's rules sidecar
+          sidecar:
+            resources:
+              limits:
+                cpu: 100m
+                memory: 256Mi
+              requests:
+                cpu: 10m
+                memory: 64Mi
+          # Grafana and Alloy talk to Loki directly, there is a single tenant.
+          gateway:
+            enabled: false
+          lokiCanary:
+            enabled: false
+          test:
+            enabled: false
+          backend:
+            replicas: 0
+          read:
+            replicas: 0
+          write:
+            replicas: 0
+      repoURL: https://grafana-community.github.io/helm-charts
+      targetRevision: 18.13.7
+    - path: add-ons/loki
+      repoURL: https://gitea.whyredfire.dev/whyredfire/gitops.git
+      targetRevision: main
+  syncPolicy:
+    automated:
+      prune: true
+      selfHeal: true
+    syncOptions:
+      - CreateNamespace=true
+      - ServerSideApply=true