Add victoria metrics for long term metrics storage

2023-05-03 00:52:24 -04:00 · 2023-05-03 00:52:24 -04:00 · d5c7d7d28d
parent 49ad416dfc
commit d5c7d7d28d
14 changed files with 1467 additions and 253 deletions
--- a/cluster/apps/database/kustomization.yaml
+++ b/cluster/apps/database/kustomization.yaml
@ -6,4 +6,4 @@ resources:
 - ./postgresql
 - ./redis
 - ./minio
- ./mariadb
+#- ./mariadb
--- a/cluster/apps/monitoring/kube-prometheus-stack/helm-release.yaml
+++ b/cluster/apps/monitoring/kube-prometheus-stack/helm-release.yaml
@ -51,6 +51,23 @@ spec:
              - *grafana-host
            secretName: wildcard-main-tls

+      sidecar:
+        datasources:
+          defaultDatasourceEnabled: false
+          isDefaultDatasource: false
+
+      # Add Victoria Metrics as the default datasource
+      additionalDataSources:
+      - name: Victoria
+        uid: victoria-metrics-server
+        type: prometheus
+        jsonData:
+          tlsSkipVerify: true
+        editable: false
+        url: http://victoria-metrics-server.monitoring.svc:8428
+        version: 1
+        isDefault: true
+
    prometheus:
      ingress:
        enabled: true
@ -70,6 +87,22 @@ spec:
      prometheusSpec:
        enableAdminAPI: false

+        retention: 1d
+
+        remoteWrite:
+        - url: http://victoria-metrics-server.monitoring.svc:8428/api/v1/write
+
+        storageSpec:
+          volumeClaimTemplate:
+            spec:
+              storageClassName: hostpath
+              selector:
+                matchLabels:
+                  app.kubernetes.io/name: kube-prometheus-stack-pv
+              resources:
+                requests:
+                  storage: 30Gi
+
    kubeControllerManager:
      enabled: true
      endpoints:
--- a/cluster/apps/monitoring/kube-prometheus-stack/kustomization.yaml
+++ b/cluster/apps/monitoring/kube-prometheus-stack/kustomization.yaml
@ -1,6 +1,7 @@
 apiVersion: kustomize.config.k8s.io/v1beta1
 kind: Kustomization
 resources:
+- ./prom-pv.yaml
 - ./helm-repository.yaml
 - ./helm-release.yaml
 - ./alertmanager-config.yaml
--- a/cluster/apps/monitoring/kube-prometheus-stack/prom-pv.yaml
+++ b/cluster/apps/monitoring/kube-prometheus-stack/prom-pv.yaml
@ -0,0 +1,16 @@
+apiVersion: v1
+kind: PersistentVolume
+metadata:
+  name: prometheus-pv
+  namespace: monitoring
+  labels:
+    app.kubernetes.io/name: kube-prometheus-stack-pv
+spec:
+  storageClassName: hostpath
+  persistentVolumeReclaimPolicy: Retain
+  capacity:
+    storage: 30Gi
+  accessModes:
+    - ReadWriteOnce
+  hostPath:
+    path: "/mnt/MainPool/Kubernetes/prometheus"
--- a/cluster/apps/monitoring/kustomization.yaml
+++ b/cluster/apps/monitoring/kustomization.yaml
@ -5,4 +5,5 @@ resources:
 - ./network_policy.yaml
 - ./kube-prometheus-stack
 - ./zfs-exporter
- ./alertmanager-gotify-bridge
+- ./alertmanager-gotify-bridge
+- ./victoria-metrics
--- a/cluster/apps/monitoring/mimir/helm-release.yaml
+++ b/cluster/apps/monitoring/mimir/helm-release.yaml
@ -1,188 +0,0 @@
-apiVersion: helm.toolkit.fluxcd.io/v2beta1
-kind: HelmRelease
-metadata:
-  name: mimir
-  namespace: monitoring
-spec:
-  interval: 5m
-  chart:
-    spec:
-      chart: mimir-distributed
-      version: 2.8.x
-      sourceRef:
-        kind: HelmRepository
-        name: grafana-charts
-        namespace: flux-system
-
-  values:
-    global:
-      extraEnvFrom:
-      - secretRef:
-        name: mimir-secret
-
-    mimir:
-      structuredConfig:
-        common:
-          storage:
-            backend: s3
-            s3:
-              endpoint: minio.database:9000
-              access_key_id: $${S3_ACCESS_KEY}
-              secret_access_key: $${S3_SECRET_KEY}
-              insecure: true
-              bucket_name: mimir
-
-    compactor:
-      persistentVolume:
-        size: 20Gi
-      resources:
-        limits:
-          memory: 2.1Gi
-        requests:
-          cpu: 1
-          memory: 1.5Gi
-
-    distributor:
-      replicas: 2
-      resources:
-        limits:
-          memory: 5.7Gi
-        requests:
-          cpu: 2
-          memory: 4Gi
-
-    ingester:
-      persistentVolume:
-        size: 50Gi
-      replicas: 3
-      resources:
-        limits:
-          memory: 12Gi
-        requests:
-          cpu: 3.5
-          memory: 8Gi
-      topologySpreadConstraints: {}
-      affinity:
-        podAntiAffinity:
-          requiredDuringSchedulingIgnoredDuringExecution:
-            - labelSelector:
-                matchExpressions:
-                  - key: target # support for enterprise.legacyLabels
-                    operator: In
-                    values:
-                      - ingester
-              topologyKey: 'kubernetes.io/hostname'
-
-            - labelSelector:
-                matchExpressions:
-                  - key: app.kubernetes.io/component
-                    operator: In
-                    values:
-                      - ingester
-              topologyKey: 'kubernetes.io/hostname'
-
-      zoneAwareReplication:
-        topologyKey: 'kubernetes.io/hostname'
-
-    admin-cache:
-      enabled: true
-      replicas: 2
-
-    chunks-cache:
-      enabled: true
-      replicas: 2
-
-    index-cache:
-      enabled: true
-      replicas: 3
-
-    metadata-cache:
-      enabled: true
-
-    results-cache:
-      enabled: true
-      replicas: 2
-
-    minio:
-      enabled: false
-
-    # Deployed by kube-prometheus-stack
-    alertmanager:
-      enabled: false
-
-    overrides_exporter:
-      replicas: 1
-      resources:
-        limits:
-          memory: 128Mi
-        requests:
-          cpu: 100m
-          memory: 128Mi
-
-    querier:
-      replicas: 1
-      resources:
-        limits:
-          memory: 5.6Gi
-        requests:
-          cpu: 2
-          memory: 4Gi
-
-    query_frontend:
-      replicas: 1
-      resources:
-        limits:
-          memory: 2.8Gi
-        requests:
-          cpu: 2
-          memory: 2Gi
-
-    ruler:
-      replicas: 1
-      resources:
-        limits:
-          memory: 2.8Gi
-        requests:
-          cpu: 1
-          memory: 2Gi
-
-    store_gateway:
-      persistentVolume:
-        size: 10Gi
-      replicas: 3
-      resources:
-        limits:
-          memory: 2.1Gi
-        requests:
-          cpu: 1
-          memory: 1.5Gi
-      topologySpreadConstraints: {}
-      affinity:
-        podAntiAffinity:
-          requiredDuringSchedulingIgnoredDuringExecution:
-            - labelSelector:
-                matchExpressions:
-                  - key: target # support for enterprise.legacyLabels
-                    operator: In
-                    values:
-                      - store-gateway
-              topologyKey: 'kubernetes.io/hostname'
-
-            - labelSelector:
-                matchExpressions:
-                  - key: app.kubernetes.io/component
-                    operator: In
-                    values:
-                      - store-gateway
-              topologyKey: 'kubernetes.io/hostname'
-      zoneAwareReplication:
-        topologyKey: 'kubernetes.io/hostname'
-
-    nginx:
-      replicas: 1
-      resources:
-        limits:
-          memory: 731Mi
-        requests:
-          cpu: 1
-          memory: 512Mi
--- a/cluster/apps/monitoring/mimir/mimir.sops.yaml
+++ b/cluster/apps/monitoring/mimir/mimir.sops.yaml
@ -1,61 +0,0 @@
-apiVersion: v1
-kind: Secret
-metadata:
-    name: mimir-secret
-    namespace: monitoring
-stringData:
-    S3_ACCESS_KEY: ENC[AES256_GCM,data:jfnHq3DE,iv:Ft3d/tbvCKuTDHmCXZJgYl5xVBOwIj0Zkc9+JgILDAI=,tag:5bcZBsODsA9Pi2vf5OGsHg==,type:str]
-    S3_SECRET_KEY: ENC[AES256_GCM,data:3WpNKx1d,iv:M5xewbvJm+U8td7kIpkPImd2gDIFfVTGVIR5BJtfoB8=,tag:X78jSBvcHbSIu6S8W8yZNA==,type:str]
-sops:
-    kms: []
-    gcp_kms: []
-    azure_kv: []
-    hc_vault: []
-    age: []
-    lastmodified: "2023-05-01T22:12:24Z"
-    mac: ENC[AES256_GCM,data:SywFZE0Kj1lx1X1f5chgW7qycPwQvHkRz/35F/hKBLjr0UXI1T9D3IIQeNZlTrxJwSiCvm/+FxMxbF4hJBfZ61Z2jfgwDINghPkoNJothgV0dlPtFTfApgK2BfNqWffhPc3Qj4cmuQZV6kG0h05CbKL4PN89DQ/aEDPPbKI01lo=,iv:x1ZGglUJM/PT5gZgvxRR411pSFmlDkEADrd3arCqFdY=,tag:0xlalnODXYns3CpuDxt9vQ==,type:str]
-    pgp:
-        - created_at: "2023-04-07T01:57:22Z"
-          enc: |
-            -----BEGIN PGP MESSAGE-----
-
-            hQIMAzKleRwoSoixAQ/9Hi4VyrUXV7LvbCFiLbyfv314lMGwrAf+2po/4Lr1hANe
-            KiwpfthiNheAjNaGCG6v2C1rx2Wrr5G3+rMik/1TLWbg2u9zZU4mWO8bwJUGXKDo
-            /T1nl47f09UPDtQ6KiG0nPf3M0Ovmk3d63R3zpY4Q7uE4uhLNDr0KD9mp7MmRCbZ
-            PO++tdiZa67z9owNDh/NSnQr9Y6JwjlxlkJl5SJ76vaK/SaOi/j86mOm9CV6SQmk
-            cLOwiO7JxV8I4gD9jlLdYEPS+nqztX5eHLRoaXsAQrX4DdWNnOF0C2sk9nMHwQTb
-            W8/SVmg7TiVVL6qVCXgUCgFRXllrlGlXlfv+W6ruuZIBv2MAA1V+afl5A3/KVvE6
-            FDq9YrJ4XfZPCD2ZByM2386L8MiUwkfF/3uge38MT/WDU2DTT+g7jV3UQs+Awi8f
-            N4YBVBcp5jGTkMD0347GPfPF7kdiN/YFZ/Ws1jf/EsS6vOpKNlPn64fVJfTSfdie
-            rvNxksi8Y4vpwEngy38t7JRfpJniDo9iK9EwhXMChYXnWkiz/B3vMoii496B7TzO
-            9gKd4v7kFA6iXI+wqbYrZfOGeLZlMI99pwTatNL4fo9ABJ7JScISzTvS7p/xB6Ae
-            JPdlA0Tf8wP4RYz8YYRcNlfEQPZYb4kHj5r9Ei59InHzwKfq9GyKKvluS0/k3NHU
-            aAEJAhCVkPuIHluRLHsjVEbKbFzSJUG8p/hSSmQnfk3CT36/dJhgv3jzoL+1/Sx1
-            o8OwWPmNq8TuX9SaXfhfy/EGMulWgRaztxt9D+0+wgc8IOAPp+0SYUsaOa0T9+Pl
-            pjU1GRaK5AlT
-            =mItp
-            -----END PGP MESSAGE-----
-          fp: 2CC2B3631D5C3393901335DB68F95C5D753EE1E5
-        - created_at: "2023-04-07T01:57:22Z"
-          enc: |
-            -----BEGIN PGP MESSAGE-----
-
-            hQIMA4WLYkVpP8xtAQ/9FQGyKS1wEodU9ZVZ8kxijp6aFtMCmL/I5HBEhbSLj0P9
-            TVD0QwnUPZqf7zlWrAh6TspyLQdRMt9JAYZCPyLgu//FdKfBJNYeU3+aWj/lMtJ4
-            Twgs7NPtGbRJcpF+a4NmAOIqzKfJI+h714BLFoWrGtUmTE9/dBHh2yxADSgprY1o
-            /4J8aHQfaqg5JwijP3PhtRMxla4YQfhqf0JRAcmQPKUDuxT2QG/wp59Fq/665aaO
-            JFWiCOPBqTtEhY4ML4EYNUV+Cd7UT7LOXC+Xzuj1eEGMV1Pmqd1u1UyQKvHOOXhT
-            AfGeCub+ZONGfmcDcY5gEMnbSCGcQEvipA3dBIIFklgnxM00jmcJ1Ojo1+MYynpl
-            E1XLOaolRWinlDNXA62k8iWG33hcxHGSzkHrsQjtqrrD2PdHS1RmTJ8Hn+iuRUn6
-            /fGk8ZQJ7oMPsZNyfiM0OdwSXxJ4rQUtGkHHd727S4K6nXC6OLxXCzl7lYG7QKcP
-            RVrbFMNv01aToyNGhLmcSxUYdQ4oc+nv65rNZDsdbi34T+dlULboJDkwV6JrJ5dz
-            hlu3ySgijZuRD5bfpfKB2RScu2ixEijOIyk1oXBB2Dhyh1ezc3qnAw8xkGr9W2SE
-            roBuu95mZsIZEtfMS5hxwGyWzSCENnbkSukQhUoIjRXryly7MQgNZ5FMX+f5n3DU
-            aAEJAhBJcIEidIhFVqDkezzMcofKl3MlXWqkfTUV3vsjz6EpN1FwhpZ3prTexUcM
-            9XCx9Wq1kMpjkphWETh2lSAafyIz6R/d4zWV5IWIeDh+USYT9z0Rprp4URka4Wjx
-            fux0T5xDbgq5
-            =eiXM
-            -----END PGP MESSAGE-----
-          fp: 8DF31C9F48A24F525FFB1815FC96C52B59328E95
-    encrypted_regex: ^(data|stringData)$
-    version: 3.7.3
--- a/cluster/apps/monitoring/victoria-metrics/helm-release.yaml
+++ b/cluster/apps/monitoring/victoria-metrics/helm-release.yaml
@ -0,0 +1,53 @@
+apiVersion: helm.toolkit.fluxcd.io/v2beta1
+kind: HelmRelease
+metadata:
+  name: victoria-metrics
+  namespace: monitoring
+spec:
+  interval: 5m
+  chart:
+    spec:
+      chart: victoria-metrics-single
+      version: 0.8.59
+      sourceRef:
+        kind: HelmRepository
+        name: victoria-metrics-charts
+        namespace: flux-system
+
+  values:
+    server:
+      retentionPeriod: 6 # months
+      fullnameOverride: victoria-metrics-server
+      persistentVolume:
+        enabled: true
+        storageClass: "hostpath"
+        matchLabels:
+          app.kubernetes.io/name: victoria-metrics-pv
+        size: 32Gi
+
+#      resources:
+#        limits:
+#          cpu: 500m
+#          memory: 512Mi
+#        requests:
+#          cpu: 500m
+#          memory: 512Mi
+
+      serviceMonitor: # TODO
+        # -- Enable deployment of Service Monitor for server component. This is Prometheus operator object
+        enabled: false
+        # -- Service Monitor labels
+        extraLabels: {}
+        # -- Service Monitor annotations
+        annotations: {}
+        # -- Commented. Prometheus scrape interval for server component
+        interval: 15s
+        # -- Commented. Prometheus pre-scrape timeout for server component
+        scrapeTimeout: 5s
+        # -- Commented. HTTP scheme to use for scraping.
+        scheme: https
+        # -- Commented. TLS configuration to use when scraping the endpoint
+        tlsConfig:
+          insecureSkipVerify: true
+        # -- Service Monitor relabelings
+        relabelings: []
--- a/cluster/apps/monitoring/victoria-metrics/helm-repository.yaml
+++ b/cluster/apps/monitoring/victoria-metrics/helm-repository.yaml
@ -0,0 +1,8 @@
+apiVersion: source.toolkit.fluxcd.io/v1beta2
+kind: HelmRepository
+metadata:
+  name: victoria-metrics-charts
+  namespace: flux-system
+spec:
+  interval: 1m
+  url: https://victoriametrics.github.io/helm-charts
--- a/cluster/apps/monitoring/victoria-metrics/kustomization.yaml
+++ b/cluster/apps/monitoring/victoria-metrics/kustomization.yaml
@ -1,5 +1,6 @@
 apiVersion: kustomize.config.k8s.io/v1beta1
 kind: Kustomization
 resources:
- ./mimir.sops.yaml
+- ./victoria-pv.yaml
+- ./helm-repository.yaml
 - ./helm-release.yaml
--- a/cluster/apps/monitoring/victoria-metrics/victoria-pv.yaml
+++ b/cluster/apps/monitoring/victoria-metrics/victoria-pv.yaml
@ -0,0 +1,16 @@
+apiVersion: v1
+kind: PersistentVolume
+metadata:
+  name: victoria-pv
+  namespace: monitoring
+  labels:
+    app.kubernetes.io/name: victoria-metrics-pv
+spec:
+  storageClassName: hostpath
+  persistentVolumeReclaimPolicy: Retain
+  capacity:
+    storage: 32Gi
+  accessModes:
+    - ReadWriteOnce
+  hostPath:
+    path: "/mnt/MainPool/Kubernetes/victoria-metrics"
--- a/cluster/apps/monitoring/zfs-exporter/dashboard.yaml
+++ b/cluster/apps/monitoring/zfs-exporter/dashboard.yaml
--- a/cluster/apps/monitoring/zfs-exporter/kustomization.yaml
+++ b/cluster/apps/monitoring/zfs-exporter/kustomization.yaml
@ -1,4 +1,5 @@
 apiVersion: kustomize.config.k8s.io/v1beta1
 kind: Kustomization
 resources:
- ./helm-release.yaml
+- ./helm-release.yaml
+- ./dashboard.yaml
--- a/docs/todo.md
+++ b/docs/todo.md
@ -15,6 +15,9 @@ TODO:
  - [ ] Grafana Loki
  - [ ] uptime-kuma
  - [x] gotify
+  - [ ] Services to monitor
+    - [ ] Authentik
+    - [ ] 
 - [x] IRC
 - [ ] Harbor
 - [x] CDN (nginx filelist)