🚀 cloudnative-pg

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

@@ -0,0 +1,70 @@
+---
+apiVersion: postgresql.cnpg.io/v1
+kind: Cluster
+metadata:
+  name: postgres16
+spec:
+  instances: 3
+  imageName: ghcr.io/bo0tzz/cnpgvecto.rs:16.1
+  primaryUpdateStrategy: unsupervised
+  storage:
+    size: 50Gi
+    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: 30d
+    barmanObjectStore:
+      data:
+        compression: bzip2
+      wal:
+        compression: bzip2
+        maxParallel: 8
+      destinationPath: s3://postgresql/
+      endpointURL: https://minio.${SECRET_DOMAIN}:9000
+      # Note: serverName version needs to be inclemented
+      # when recovering from an existing cnpg cluster
+      serverName: postgres16-v1
+      s3Credentials:
+        accessKeyId:
+          name: cloudnative-pg-secret
+          key: aws-access-key-id
+        secretAccessKey:
+          name: cloudnative-pg-secret
+          key: aws-secret-access-key
+  # # Note: previousCluster needs to be set to the name of the previous
+  # # cluster when recovering from an existing cnpg cluster
+  # bootstrap:
+  #   recovery:
+  #     source: postgres-v6
+  # externalClusters:
+  #   - name: postgres-v6
+  #     barmanObjectStore:
+  #       destinationPath: s3://postgresql/
+  #       endpointURL: https://minio.${SECRET_DOMAIN}:9000
+  #       s3Credentials:
+  #         accessKeyId:
+  #           name: postgres-minio
+  #           key: MINIO_ACCESS_KEY
+  #         secretAccessKey:
+  #           name: postgres-minio
+  #           key: MINIO_SECRET_KEY
+  #       wal:
+  #         maxParallel: 8

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

@@ -0,0 +1,9 @@
+---
+# 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:
+  - ./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

@@ -0,0 +1,11 @@
+---
+apiVersion: postgresql.cnpg.io/v1
+kind: ScheduledBackup
+metadata:
+  name: postgres
+spec:
+  schedule: "@daily"
+  immediate: true
+  backupOwnerReference: self
+  cluster:
+    name: postgres16