🚀 cloudnative-pg

.archive/kubernetes/cloudnative-pg/cluster/backups/external-backup.yaml

@@ -1,53 +0,0 @@
----
-apiVersion: batch/v1
-kind: CronJob
-metadata:
-  name: &app cloudnative-pg-external-backup
-  namespace: default
-spec:
-  schedule: "@daily"
-  jobTemplate:
-    spec:
-      ttlSecondsAfterFinished: 86400
-      template:
-        spec:
-          automountServiceAccountToken: false
-          restartPolicy: OnFailure
-          containers:
-            - name: *app
-              image: prodrigestivill/postgres-backup-local:15-alpine@sha256:30473b9a3f2e884b7a17d6da1287e962933ab9d69ea5ba604c2e2afb89d16bb9
-              env:
-                - name: POSTGRES_HOST
-                  value: ${POSTGRES_HOST}
-                - name: POSTGRES_DB
-                  value: "atuin,authelia,bazarr,freshrss,gatus,ghostfolio,lidarr_main,immich,invidious,joplin,kresus,linkding,lldap,lychee,outline,paperless,prowlarr_main,pushover-notifier,radarr_main,sharry,tandoor,vaultwarden,vikunja,wallabag"
-                - name: POSTGRES_USER
-                  valueFrom:
-                    secretKeyRef:
-                      name: cloudnative-pg-secret
-                      key: username
-                - name: POSTGRES_PASSWORD
-                  valueFrom:
-                    secretKeyRef:
-                      name: cloudnative-pg-secret
-                      key: password
-                - name: POSTGRES_EXTRA_OPTS
-                  value: "-Z9 --schema=public --blobs"
-                - name: BACKUP_KEEP_DAYS
-                  value: "7"
-                - name: BACKUP_KEEP_WEEKS
-                  value: "4"
-                - name: BACKUP_KEEP_MONTHS
-                  value: "3"
-                - name: HEALTHCHECK_PORT
-                  value: "8080"
-              command:
-                - "/backup.sh"
-              volumeMounts:
-                - name: backups
-                  mountPath: /backups
-          volumes:
-            - name: backups
-              nfs:
-                server: "${LOCAL_LAN_TRUENAS}"
-                path: /mnt/storage/backups/postgresql

.archive/kubernetes/cloudnative-pg/cluster/backups/kustomization.yaml

@@ -1,7 +0,0 @@
----
-# yaml-language-server: $schema=https://raw.githubusercontent.com/SchemaStore/schemastore/master/src/schemas/json/kustomization.json
-apiVersion: kustomize.config.k8s.io/v1beta1
-kind: Kustomization
-namespace: default
-resources:
-  - ./external-backup.yaml

kubernetes/apps/database/cloudnative-pg/app/externalsecret.yaml

@@ -4,7 +4,6 @@ apiVersion: external-secrets.io/v1beta1
 kind: ExternalSecret
 metadata:
   name: cloudnative-pg
-  namespace: default
 spec:
   secretStoreRef:
     kind: ClusterSecretStore

kubernetes/apps/database/cloudnative-pg/app/helmrelease.yaml

@@ -4,7 +4,6 @@ apiVersion: helm.toolkit.fluxcd.io/v2beta2
 kind: HelmRelease
 metadata:
   name: cloudnative-pg
-  namespace: default
 spec:
   interval: 30m
   chart:
@@ -15,19 +14,21 @@ spec:
         kind: HelmRepository
         name: cloudnative-pg
         namespace: flux-system
-  maxHistory: 2
   install:
-    createNamespace: true
-    crds: CreateReplace
     remediation:
       retries: 3
   upgrade:
     cleanupOnFail: true
-    crds: CreateReplace
     remediation:
       retries: 3
   uninstall:
     keepHistory: false
+  dependsOn:
+    - name: local-path-provisioner
+      namespace: kube-system
   values:
     crds:
       create: true
+    config:
+      data:
+        INHERITED_ANNOTATIONS: kyverno.io/ignore

kubernetes/apps/database/cloudnative-pg/cluster/cluster16.yaml

@@ -2,29 +2,46 @@
 apiVersion: postgresql.cnpg.io/v1
 kind: Cluster
 metadata:
-  name: postgres
-  namespace: default
+  name: postgres16
 spec:
   instances: 3
-  imageName: ghcr.io/bo0tzz/cnpgvecto.rs:15.5@sha256:a02838b9531af52dea5f8978bc0961640eea7ff2ad1b090978c561e6c52f1394
+  imageName: ghcr.io/bo0tzz/cnpgvecto.rs:16.1
   primaryUpdateStrategy: unsupervised
-  enableSuperuserAccess: true
   storage:
     size: 50Gi
-    storageClass: rook-ceph-block
+    storageClass: local-hostpath
   superuserSecret:
     name: cloudnative-pg-secret
+  enableSuperuserAccess: true
+  resources:
+    requests:
+      cpu: 500m
+    limits:
+      memory: 4Gi
+  postgresql:
+    parameters:
+      max_connections: "600"
+      max_slot_wal_keep_size: 10GB
+      shared_buffers: 512MB
   monitoring:
     enablePodMonitor: true
+    # Ref: https://github.com/cloudnative-pg/cloudnative-pg/issues/2501
+    podMonitorMetricRelabelings:
+      - { sourceLabels: ["cluster"], targetLabel: cnpg_cluster, action: replace }
+      - { regex: cluster, action: labeldrop }
   backup:
-    retentionPolicy: 7d
+    retentionPolicy: 30d
     barmanObjectStore:
+      data:
+        compression: bzip2
       wal:
         compression: bzip2
         maxParallel: 8
       destinationPath: s3://postgresql/
-      endpointURL: https://.${SECRET_DOMAIN}:9000
-      serverName: postgres-v8
+      endpointURL: https://minio.${SECRET_DOMAIN}:9000
+      # Note: serverName version needs to be inclemented
+      # when recovering from an existing cnpg cluster
+      serverName: postgres16-v1
       s3Credentials:
         accessKeyId:
           name: cloudnative-pg-secret
@@ -32,6 +49,8 @@ spec:
         secretAccessKey:
           name: cloudnative-pg-secret
           key: aws-secret-access-key
+  # # Note: previousCluster needs to be set to the name of the previous
+  # # cluster when recovering from an existing cnpg cluster
   # bootstrap:
   #   recovery:
   #     source: postgres-v6

kubernetes/apps/database/cloudnative-pg/cluster/kustomization.yaml

@@ -4,6 +4,6 @@ apiVersion: kustomize.config.k8s.io/v1beta1
 kind: Kustomization
 namespace: default
 resources:
-  - backups
-  - ./cluster.yaml
+  - ./cluster16.yaml
+  - ./prometheusrule.yaml
   - ./scheduledbackup.yaml

kubernetes/apps/database/cloudnative-pg/cluster/prometheusrule.yaml

@@ -0,0 +1,67 @@
+---
+# yaml-language-server: $schema=https://kubernetes-schemas.pages.dev/monitoring.coreos.com/prometheusrule_v1.json
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  name: cloudnative-pg-rules
+  labels:
+    prometheus: k8s
+    role: alert-rules
+spec:
+  groups:
+    - name: cloudnative-pg.rules
+      rules:
+        - alert: LongRunningTransaction
+          annotations:
+            description: Pod {{ $labels.pod }} is taking more than 5 minutes (300 seconds) for a query.
+            summary: A query is taking longer than 5 minutes.
+          expr: |-
+            cnpg_backends_max_tx_duration_seconds > 300
+          for: 1m
+          labels:
+            severity: warning
+        - alert: BackendsWaiting
+          annotations:
+            description: Pod {{ $labels.pod }} has been waiting for longer than 5 minutes
+            summary: If a backend is waiting for longer than 5 minutes
+          expr: |-
+            cnpg_backends_waiting_total > 300
+          for: 1m
+          labels:
+            severity: warning
+        - alert: PGDatabase
+          annotations:
+            description: Over 150,000,000 transactions from frozen xid on pod {{ $labels.pod }}
+            summary: Number of transactions from the frozen XID to the current one
+          expr: |-
+            cnpg_pg_database_xid_age > 150000000
+          for: 1m
+          labels:
+            severity: warning
+        - alert: PGReplication
+          annotations:
+            description: Standby is lagging behind by over 300 seconds (5 minutes)
+            summary: The standby is lagging behind the primary
+          expr: |-
+            cnpg_pg_replication_lag > 300
+          for: 1m
+          labels:
+            severity: warning
+        - alert: LastFailedArchiveTime
+          annotations:
+            description: Archiving failed for {{ $labels.pod }}
+            summary: Checks the last time archiving failed. Will be < 0 when it has not failed.
+          expr: |-
+            (cnpg_pg_stat_archiver_last_failed_time - cnpg_pg_stat_archiver_last_archived_time) > 1
+          for: 1m
+          labels:
+            severity: warning
+        - alert: DatabaseDeadlockConflicts
+          annotations:
+            description: There are over 10 deadlock conflicts in {{ $labels.pod }}
+            summary: Checks the number of database conflicts
+          expr: |-
+            cnpg_pg_stat_database_deadlocks > 10
+          for: 1m
+          labels:
+            severity: warning

kubernetes/apps/database/cloudnative-pg/cluster/scheduledbackup.yaml

@@ -3,10 +3,9 @@ apiVersion: postgresql.cnpg.io/v1
 kind: ScheduledBackup
 metadata:
   name: postgres
-  namespace: default
 spec:
   schedule: "@daily"
   immediate: true
   backupOwnerReference: self
   cluster:
-    name: postgres
+    name: postgres16

kubernetes/apps/database/cloudnative-pg/ks.yaml

@@ -3,30 +3,16 @@
 apiVersion: kustomize.toolkit.fluxcd.io/v1
 kind: Kustomization
 metadata:
-  name: cluster-apps-cloudnative-pg-app
+  name: &app cloudnative-pg
   namespace: flux-system
 spec:
+  targetNamespace: database
+  commonMetadata:
+    labels:
+      app.kubernetes.io/name: *app
   dependsOn:
     - name: external-secrets-stores
-  path: ./kubernetes/apps/default/cloudnative-pg/app
-  prune: true
-  sourceRef:
-    kind: GitRepository
-    name: home-ops-kubernetes
-  interval: 30m
-  retryInterval: 1m
-  timeout: 3m
----
-# yaml-language-server: $schema=https://raw.githubusercontent.com/fluxcd-community/flux2-schemas/main/kustomization-kustomize-v1.json
-apiVersion: kustomize.toolkit.fluxcd.io/v1
-kind: Kustomization
-metadata:
-  name: cluster-apps-cloudnative-pg-cluster
-  namespace: flux-system
-spec:
-  dependsOn:
-    - name: cluster-apps-cloudnative-pg-app
-  path: ./kubernetes/apps/default/cloudnative-pg/cluster
+  path: ./kubernetes/apps/database/cloudnative-pg/app
   prune: true
   sourceRef:
     kind: GitRepository
@@ -34,4 +20,27 @@ spec:
   wait: true
   interval: 30m
   retryInterval: 1m
-  timeout: 3m
+  timeout: 5m
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/fluxcd-community/flux2-schemas/main/kustomization-kustomize-v1.json
+apiVersion: kustomize.toolkit.fluxcd.io/v1
+kind: Kustomization
+metadata:
+  name: cloudnative-pg-cluster
+  namespace: flux-system
+spec:
+  targetNamespace: database
+  commonMetadata:
+    labels:
+      app.kubernetes.io/name: cloudnative-pg
+  dependsOn:
+    - name: cloudnative-pg
+  path: ./kubernetes/apps/database/cloudnative-pg/cluster
+  prune: true
+  sourceRef:
+    kind: GitRepository
+    name: home-ops-kubernetes
+  wait: true
+  interval: 30m
+  retryInterval: 1m
+  timeout: 5m

kubernetes/apps/database/kustomization.yaml

@@ -0,0 +1,9 @@
+---
+# yaml-language-server: $schema=https://json.schemastore.org/kustomization
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+resources:
+  # Pre Flux-Kustomizations
+  - ./namespace.yaml
+  # Flux-Kustomizations
+  - ./cloudnative-pg/ks.yaml

kubernetes/apps/database/namespace.yaml

@@ -0,0 +1,7 @@
+---
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: database
+  labels:
+    kustomize.toolkit.fluxcd.io/prune: disabled

kubernetes/apps/kustomization.yaml

@@ -5,6 +5,7 @@ kind: Kustomization
 resources:
   - ./actions-runner-system
   - ./cert-manager
+  - ./database
   - ./default
   - ./flux-system
   - ./kube-system