--- # Source: jellystat/charts/jellystat/templates/common.yaml --- kind: PersistentVolumeClaim apiVersion: v1 metadata: name: jellystat-data labels: app.kubernetes.io/instance: jellystat app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: jellystat helm.sh/chart: jellystat-4.4.0 annotations: helm.sh/resource-policy: keep namespace: jellystat spec: accessModes: - "ReadWriteOnce" resources: requests: storage: "5Gi" storageClassName: "ceph-block" --- # Source: jellystat/charts/jellystat/templates/common.yaml apiVersion: v1 kind: Service metadata: name: jellystat labels: app.kubernetes.io/instance: jellystat app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: jellystat app.kubernetes.io/service: jellystat helm.sh/chart: jellystat-4.4.0 namespace: jellystat spec: type: ClusterIP ports: - port: 80 targetPort: 3000 protocol: TCP name: http selector: app.kubernetes.io/controller: main app.kubernetes.io/instance: jellystat app.kubernetes.io/name: jellystat --- # Source: jellystat/charts/jellystat/templates/common.yaml apiVersion: apps/v1 kind: Deployment metadata: name: jellystat labels: app.kubernetes.io/controller: main app.kubernetes.io/instance: jellystat app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: jellystat helm.sh/chart: jellystat-4.4.0 namespace: jellystat spec: revisionHistoryLimit: 3 replicas: 1 strategy: type: Recreate selector: matchLabels: app.kubernetes.io/controller: main app.kubernetes.io/name: jellystat app.kubernetes.io/instance: jellystat template: metadata: labels: app.kubernetes.io/controller: main app.kubernetes.io/instance: jellystat app.kubernetes.io/name: jellystat spec: enableServiceLinks: false serviceAccountName: default automountServiceAccountToken: true hostIPC: false hostNetwork: false hostPID: false dnsPolicy: ClusterFirst containers: - env: - name: TZ value: US/Central - name: JWT_SECRET valueFrom: secretKeyRef: key: secret-key name: jellystat-secret - name: JS_USER valueFrom: secretKeyRef: key: user name: jellystat-secret - name: JS_PASSWORD valueFrom: secretKeyRef: key: password name: jellystat-secret - name: POSTGRES_USER valueFrom: secretKeyRef: key: username name: jellystat-postgresql-17-cluster-app - name: POSTGRES_PASSWORD valueFrom: secretKeyRef: key: password name: jellystat-postgresql-17-cluster-app - name: POSTGRES_DB valueFrom: secretKeyRef: key: dbname name: jellystat-postgresql-17-cluster-app - name: POSTGRES_IP valueFrom: secretKeyRef: key: host name: jellystat-postgresql-17-cluster-app - name: POSTGRES_PORT valueFrom: secretKeyRef: key: port name: jellystat-postgresql-17-cluster-app image: cyfershepard/jellystat:1.1.6 imagePullPolicy: IfNotPresent name: main resources: requests: cpu: 10m memory: 256Mi volumeMounts: - mountPath: /app/backend/backup-data name: data volumes: - name: data persistentVolumeClaim: claimName: jellystat-data --- # Source: jellystat/charts/postgres-17-cluster/templates/cluster.yaml apiVersion: postgresql.cnpg.io/v1 kind: Cluster metadata: name: jellystat-postgresql-17-cluster namespace: jellystat labels: helm.sh/chart: postgres-17-cluster-6.16.0 app.kubernetes.io/name: jellystat-postgresql-17 app.kubernetes.io/instance: jellystat app.kubernetes.io/part-of: jellystat app.kubernetes.io/version: "6.16.0" app.kubernetes.io/managed-by: Helm spec: instances: 3 imageName: "ghcr.io/cloudnative-pg/postgresql:17.7-standard-trixie" imagePullPolicy: IfNotPresent postgresUID: 26 postgresGID: 26 plugins: - name: barman-cloud.cloudnative-pg.io enabled: true isWALArchiver: false parameters: barmanObjectName: "jellystat-postgresql-17-external-backup" serverName: "jellystat-postgresql-17-backup-1" - name: barman-cloud.cloudnative-pg.io enabled: true isWALArchiver: true parameters: barmanObjectName: "jellystat-postgresql-17-garage-local-backup" serverName: "jellystat-postgresql-17-backup-1" externalClusters: - name: recovery plugin: name: barman-cloud.cloudnative-pg.io parameters: barmanObjectName: "jellystat-postgresql-17-recovery" serverName: jellystat-postgresql-17-backup-1 storage: size: 10Gi storageClass: local-path walStorage: size: 2Gi storageClass: local-path resources: limits: hugepages-2Mi: 256Mi requests: cpu: 100m memory: 256Mi affinity: enablePodAntiAffinity: true topologyKey: kubernetes.io/hostname primaryUpdateMethod: switchover primaryUpdateStrategy: unsupervised logLevel: info enableSuperuserAccess: false enablePDB: true postgresql: parameters: hot_standby_feedback: "on" max_slot_wal_keep_size: 2000MB shared_buffers: 128MB monitoring: enablePodMonitor: true disableDefaultQueries: false bootstrap: recovery: database: app source: jellystat-postgresql-17-backup-1 externalClusters: - name: jellystat-postgresql-17-backup-1 plugin: name: barman-cloud.cloudnative-pg.io enabled: true isWALArchiver: false parameters: barmanObjectName: "jellystat-postgresql-17-recovery" serverName: jellystat-postgresql-17-backup-1 --- # Source: jellystat/templates/external-secret.yaml apiVersion: external-secrets.io/v1 kind: ExternalSecret metadata: name: jellystat-secret namespace: jellystat labels: app.kubernetes.io/name: jellystat-secret app.kubernetes.io/instance: jellystat app.kubernetes.io/part-of: jellystat spec: secretStoreRef: kind: ClusterSecretStore name: vault data: - secretKey: secret-key remoteRef: conversionStrategy: Default decodingStrategy: None key: /cl01tl/jellystat/auth metadataPolicy: None property: secret-key - secretKey: user remoteRef: conversionStrategy: Default decodingStrategy: None key: /cl01tl/jellystat/auth metadataPolicy: None property: user - secretKey: password remoteRef: conversionStrategy: Default decodingStrategy: None key: /cl01tl/jellystat/auth metadataPolicy: None property: password --- # Source: jellystat/templates/external-secret.yaml apiVersion: external-secrets.io/v1 kind: ExternalSecret metadata: name: jellystat-data-backup-secret namespace: jellystat labels: app.kubernetes.io/name: jellystat-data-backup-secret app.kubernetes.io/instance: jellystat app.kubernetes.io/part-of: jellystat spec: secretStoreRef: kind: ClusterSecretStore name: vault target: template: mergePolicy: Merge engineVersion: v2 data: RESTIC_REPOSITORY: "{{ .BUCKET_ENDPOINT }}/jellystat/jellystat-data" data: - secretKey: BUCKET_ENDPOINT remoteRef: conversionStrategy: Default decodingStrategy: None key: /cl01tl/volsync/restic/config metadataPolicy: None property: S3_BUCKET_ENDPOINT - secretKey: RESTIC_PASSWORD remoteRef: conversionStrategy: Default decodingStrategy: None key: /cl01tl/volsync/restic/config metadataPolicy: None property: RESTIC_PASSWORD - secretKey: AWS_DEFAULT_REGION remoteRef: conversionStrategy: Default decodingStrategy: None key: /cl01tl/volsync/restic/config metadataPolicy: None property: AWS_DEFAULT_REGION - secretKey: AWS_ACCESS_KEY_ID remoteRef: conversionStrategy: Default decodingStrategy: None key: /digital-ocean/home-infra/volsync-backups metadataPolicy: None property: access_key - secretKey: AWS_SECRET_ACCESS_KEY remoteRef: conversionStrategy: Default decodingStrategy: None key: /digital-ocean/home-infra/volsync-backups metadataPolicy: None property: secret_key --- # Source: jellystat/templates/external-secret.yaml apiVersion: external-secrets.io/v1 kind: ExternalSecret metadata: name: jellystat-postgresql-17-cluster-backup-secret namespace: jellystat labels: app.kubernetes.io/name: jellystat-postgresql-17-cluster-backup-secret app.kubernetes.io/instance: jellystat app.kubernetes.io/part-of: jellystat spec: secretStoreRef: kind: ClusterSecretStore name: vault data: - secretKey: ACCESS_KEY_ID remoteRef: conversionStrategy: Default decodingStrategy: None key: /digital-ocean/home-infra/postgres-backups metadataPolicy: None property: access - secretKey: ACCESS_SECRET_KEY remoteRef: conversionStrategy: Default decodingStrategy: None key: /digital-ocean/home-infra/postgres-backups metadataPolicy: None property: secret --- # Source: jellystat/templates/external-secret.yaml apiVersion: external-secrets.io/v1 kind: ExternalSecret metadata: name: jellystat-postgresql-17-cluster-backup-secret-garage namespace: jellystat labels: app.kubernetes.io/name: jellystat-postgresql-17-cluster-backup-secret-garage app.kubernetes.io/instance: jellystat app.kubernetes.io/part-of: jellystat spec: secretStoreRef: kind: ClusterSecretStore name: vault data: - secretKey: ACCESS_KEY_ID remoteRef: conversionStrategy: Default decodingStrategy: None key: /garage/home-infra/postgres-backups metadataPolicy: None property: ACCESS_KEY_ID - secretKey: ACCESS_SECRET_KEY remoteRef: conversionStrategy: Default decodingStrategy: None key: /garage/home-infra/postgres-backups metadataPolicy: None property: ACCESS_SECRET_KEY - secretKey: ACCESS_REGION remoteRef: conversionStrategy: Default decodingStrategy: None key: /garage/home-infra/postgres-backups metadataPolicy: None property: ACCESS_REGION --- # Source: jellystat/templates/http-route.yaml apiVersion: gateway.networking.k8s.io/v1 kind: HTTPRoute metadata: name: http-route-jellystat namespace: jellystat labels: app.kubernetes.io/name: http-route-jellystat app.kubernetes.io/instance: jellystat app.kubernetes.io/part-of: jellystat spec: parentRefs: - group: gateway.networking.k8s.io kind: Gateway name: traefik-gateway namespace: traefik hostnames: - jellystat.alexlebens.net rules: - matches: - path: type: PathPrefix value: / backendRefs: - group: '' kind: Service name: jellystat port: 80 weight: 100 --- # Source: jellystat/charts/postgres-17-cluster/templates/object-store.yaml apiVersion: barmancloud.cnpg.io/v1 kind: ObjectStore metadata: name: "jellystat-postgresql-17-external-backup" namespace: jellystat labels: helm.sh/chart: postgres-17-cluster-6.16.0 app.kubernetes.io/name: jellystat-postgresql-17 app.kubernetes.io/instance: jellystat app.kubernetes.io/part-of: jellystat app.kubernetes.io/version: "6.16.0" app.kubernetes.io/managed-by: Helm spec: retentionPolicy: 30d configuration: destinationPath: s3://postgres-backups-ce540ddf106d186bbddca68a/cl01tl/jellystat/jellystat-postgresql-17-cluster endpointURL: https://nyc3.digitaloceanspaces.com s3Credentials: accessKeyId: name: jellystat-postgresql-17-cluster-backup-secret key: ACCESS_KEY_ID secretAccessKey: name: jellystat-postgresql-17-cluster-backup-secret key: ACCESS_SECRET_KEY --- # Source: jellystat/charts/postgres-17-cluster/templates/object-store.yaml apiVersion: barmancloud.cnpg.io/v1 kind: ObjectStore metadata: name: "jellystat-postgresql-17-garage-local-backup" namespace: jellystat labels: helm.sh/chart: postgres-17-cluster-6.16.0 app.kubernetes.io/name: jellystat-postgresql-17 app.kubernetes.io/instance: jellystat app.kubernetes.io/part-of: jellystat app.kubernetes.io/version: "6.16.0" app.kubernetes.io/managed-by: Helm spec: retentionPolicy: 3d configuration: destinationPath: s3://postgres-backups/cl01tl/jellystat/jellystat-postgresql-17-cluster endpointURL: http://garage-main.garage:3900 s3Credentials: accessKeyId: name: jellystat-postgresql-17-cluster-backup-secret-garage key: ACCESS_KEY_ID secretAccessKey: name: jellystat-postgresql-17-cluster-backup-secret-garage key: ACCESS_SECRET_KEY region: name: jellystat-postgresql-17-cluster-backup-secret-garage key: ACCESS_REGION --- # Source: jellystat/charts/postgres-17-cluster/templates/object-store.yaml apiVersion: barmancloud.cnpg.io/v1 kind: ObjectStore metadata: name: "jellystat-postgresql-17-recovery" namespace: jellystat labels: helm.sh/chart: postgres-17-cluster-6.16.0 app.kubernetes.io/name: jellystat-postgresql-17 app.kubernetes.io/instance: jellystat app.kubernetes.io/part-of: jellystat app.kubernetes.io/version: "6.16.0" app.kubernetes.io/managed-by: Helm spec: configuration: destinationPath: s3://postgres-backups/cl01tl/jellystat/jellystat-postgresql-17-cluster endpointURL: http://garage-main.garage:3900 wal: compression: snappy maxParallel: 1 data: compression: snappy jobs: 1 s3Credentials: accessKeyId: name: jellystat-postgresql-17-cluster-backup-secret-garage key: ACCESS_KEY_ID secretAccessKey: name: jellystat-postgresql-17-cluster-backup-secret-garage key: ACCESS_SECRET_KEY --- # Source: jellystat/charts/postgres-17-cluster/templates/prometheus-rule.yaml apiVersion: monitoring.coreos.com/v1 kind: PrometheusRule metadata: name: jellystat-postgresql-17-alert-rules namespace: jellystat labels: helm.sh/chart: postgres-17-cluster-6.16.0 app.kubernetes.io/name: jellystat-postgresql-17 app.kubernetes.io/instance: jellystat app.kubernetes.io/part-of: jellystat app.kubernetes.io/version: "6.16.0" app.kubernetes.io/managed-by: Helm spec: groups: - name: cloudnative-pg/jellystat-postgresql-17 rules: - alert: CNPGClusterBackendsWaitingWarning annotations: summary: CNPG Cluster a backend is waiting for longer than 5 minutes. description: |- Pod {{ $labels.pod }} has been waiting for longer than 5 minutes expr: | cnpg_backends_waiting_total > 300 for: 1m labels: severity: warning namespace: jellystat cnpg_cluster: jellystat-postgresql-17-cluster - alert: CNPGClusterDatabaseDeadlockConflictsWarning annotations: summary: CNPG Cluster has over 10 deadlock conflicts. description: |- There are over 10 deadlock conflicts in {{ $labels.pod }} expr: | cnpg_pg_stat_database_deadlocks > 10 for: 1m labels: severity: warning namespace: jellystat cnpg_cluster: jellystat-postgresql-17-cluster - alert: CNPGClusterHACritical annotations: summary: CNPG Cluster has no standby replicas! description: |- CloudNativePG Cluster "{{`{{`}} $labels.job {{`}}`}}" has no ready standby replicas. Your cluster at a severe risk of data loss and downtime if the primary instance fails. The primary instance is still online and able to serve queries, although connections to the `-ro` endpoint will fail. The `-r` endpoint os operating at reduced capacity and all traffic is being served by the main. This can happen during a normal fail-over or automated minor version upgrades in a cluster with 2 or less instances. The replaced instance may need some time to catch-up with the cluster primary instance. This alarm will be always trigger if your cluster is configured to run with only 1 instance. In this case you may want to silence it. runbook_url: https://github.com/cloudnative-pg/charts/blob/main/charts/cluster/docs/runbooks/CNPGClusterHACritical.md expr: | max by (job) (cnpg_pg_replication_streaming_replicas{namespace="jellystat"} - cnpg_pg_replication_is_wal_receiver_up{namespace="jellystat"}) < 1 for: 5m labels: severity: critical namespace: jellystat cnpg_cluster: jellystat-postgresql-17-cluster - alert: CNPGClusterHAWarning annotations: summary: CNPG Cluster less than 2 standby replicas. description: |- CloudNativePG Cluster "{{`{{`}} $labels.job {{`}}`}}" has only {{`{{`}} $value {{`}}`}} standby replicas, putting your cluster at risk if another instance fails. The cluster is still able to operate normally, although the `-ro` and `-r` endpoints operate at reduced capacity. This can happen during a normal fail-over or automated minor version upgrades. The replaced instance may need some time to catch-up with the cluster primary instance. This alarm will be constantly triggered if your cluster is configured to run with less than 3 instances. In this case you may want to silence it. runbook_url: https://github.com/cloudnative-pg/charts/blob/main/charts/cluster/docs/runbooks/CNPGClusterHAWarning.md expr: | max by (job) (cnpg_pg_replication_streaming_replicas{namespace="jellystat"} - cnpg_pg_replication_is_wal_receiver_up{namespace="jellystat"}) < 2 for: 5m labels: severity: warning namespace: jellystat cnpg_cluster: jellystat-postgresql-17-cluster - alert: CNPGClusterHighConnectionsCritical annotations: summary: CNPG Instance maximum number of connections critical! description: |- CloudNativePG Cluster "jellystat/jellystat-postgresql-17-cluster" instance {{`{{`}} $labels.pod {{`}}`}} is using {{`{{`}} $value {{`}}`}}% of the maximum number of connections. runbook_url: https://github.com/cloudnative-pg/charts/blob/main/charts/cluster/docs/runbooks/CNPGClusterHighConnectionsCritical.md expr: | sum by (pod) (cnpg_backends_total{namespace="jellystat", pod=~"jellystat-postgresql-17-cluster-([1-9][0-9]*)$"}) / max by (pod) (cnpg_pg_settings_setting{name="max_connections", namespace="jellystat", pod=~"jellystat-postgresql-17-cluster-([1-9][0-9]*)$"}) * 100 > 95 for: 5m labels: severity: critical namespace: jellystat cnpg_cluster: jellystat-postgresql-17-cluster - alert: CNPGClusterHighConnectionsWarning annotations: summary: CNPG Instance is approaching the maximum number of connections. description: |- CloudNativePG Cluster "jellystat/jellystat-postgresql-17-cluster" instance {{`{{`}} $labels.pod {{`}}`}} is using {{`{{`}} $value {{`}}`}}% of the maximum number of connections. runbook_url: https://github.com/cloudnative-pg/charts/blob/main/charts/cluster/docs/runbooks/CNPGClusterHighConnectionsWarning.md expr: | sum by (pod) (cnpg_backends_total{namespace="jellystat", pod=~"jellystat-postgresql-17-cluster-([1-9][0-9]*)$"}) / max by (pod) (cnpg_pg_settings_setting{name="max_connections", namespace="jellystat", pod=~"jellystat-postgresql-17-cluster-([1-9][0-9]*)$"}) * 100 > 80 for: 5m labels: severity: warning namespace: jellystat cnpg_cluster: jellystat-postgresql-17-cluster - alert: CNPGClusterHighReplicationLag annotations: summary: CNPG Cluster high replication lag description: |- CloudNativePG Cluster "jellystat/jellystat-postgresql-17-cluster" is experiencing a high replication lag of {{`{{`}} $value {{`}}`}}ms. High replication lag indicates network issues, busy instances, slow queries or suboptimal configuration. runbook_url: https://github.com/cloudnative-pg/charts/blob/main/charts/cluster/docs/runbooks/CNPGClusterHighReplicationLag.md expr: | max(cnpg_pg_replication_lag{namespace="jellystat",pod=~"jellystat-postgresql-17-cluster-([1-9][0-9]*)$"}) * 1000 > 1000 for: 5m labels: severity: warning namespace: jellystat cnpg_cluster: jellystat-postgresql-17-cluster - alert: CNPGClusterInstancesOnSameNode annotations: summary: CNPG Cluster instances are located on the same node. description: |- CloudNativePG Cluster "jellystat/jellystat-postgresql-17-cluster" has {{`{{`}} $value {{`}}`}} instances on the same node {{`{{`}} $labels.node {{`}}`}}. A failure or scheduled downtime of a single node will lead to a potential service disruption and/or data loss. runbook_url: https://github.com/cloudnative-pg/charts/blob/main/charts/cluster/docs/runbooks/CNPGClusterInstancesOnSameNode.md expr: | count by (node) (kube_pod_info{namespace="jellystat", pod=~"jellystat-postgresql-17-cluster-([1-9][0-9]*)$"}) > 1 for: 5m labels: severity: warning namespace: jellystat cnpg_cluster: jellystat-postgresql-17-cluster - alert: CNPGClusterLongRunningTransactionWarning annotations: summary: CNPG Cluster query is taking longer than 5 minutes. description: |- CloudNativePG Cluster Pod {{ $labels.pod }} is taking more than 5 minutes (300 seconds) for a query. expr: |- cnpg_backends_max_tx_duration_seconds > 300 for: 1m labels: severity: warning namespace: jellystat cnpg_cluster: jellystat-postgresql-17-cluster - alert: CNPGClusterLowDiskSpaceCritical annotations: summary: CNPG Instance is running out of disk space! description: |- CloudNativePG Cluster "jellystat/jellystat-postgresql-17-cluster" is running extremely low on disk space. Check attached PVCs! runbook_url: https://github.com/cloudnative-pg/charts/blob/main/charts/cluster/docs/runbooks/CNPGClusterLowDiskSpaceCritical.md expr: | max(max by(persistentvolumeclaim) (1 - kubelet_volume_stats_available_bytes{namespace="jellystat", persistentvolumeclaim=~"jellystat-postgresql-17-cluster-([1-9][0-9]*)$"} / kubelet_volume_stats_capacity_bytes{namespace="jellystat", persistentvolumeclaim=~"jellystat-postgresql-17-cluster-([1-9][0-9]*)$"})) > 0.9 OR max(max by(persistentvolumeclaim) (1 - kubelet_volume_stats_available_bytes{namespace="jellystat", persistentvolumeclaim=~"jellystat-postgresql-17-cluster-([1-9][0-9]*)$-wal"} / kubelet_volume_stats_capacity_bytes{namespace="jellystat", persistentvolumeclaim=~"jellystat-postgresql-17-cluster-([1-9][0-9]*)$-wal"})) > 0.9 OR max(sum by (namespace,persistentvolumeclaim) (kubelet_volume_stats_used_bytes{namespace="jellystat", persistentvolumeclaim=~"jellystat-postgresql-17-cluster-([1-9][0-9]*)$-tbs.*"}) / sum by (namespace,persistentvolumeclaim) (kubelet_volume_stats_capacity_bytes{namespace="jellystat", persistentvolumeclaim=~"jellystat-postgresql-17-cluster-([1-9][0-9]*)$-tbs.*"}) * on(namespace, persistentvolumeclaim) group_left(volume) kube_pod_spec_volumes_persistentvolumeclaims_info{pod=~"jellystat-postgresql-17-cluster-([1-9][0-9]*)$"} ) > 0.9 for: 5m labels: severity: critical namespace: jellystat cnpg_cluster: jellystat-postgresql-17-cluster - alert: CNPGClusterLowDiskSpaceWarning annotations: summary: CNPG Instance is running out of disk space. description: |- CloudNativePG Cluster "jellystat/jellystat-postgresql-17-cluster" is running low on disk space. Check attached PVCs. runbook_url: https://github.com/cloudnative-pg/charts/blob/main/charts/cluster/docs/runbooks/CNPGClusterLowDiskSpaceWarning.md expr: | max(max by(persistentvolumeclaim) (1 - kubelet_volume_stats_available_bytes{namespace="jellystat", persistentvolumeclaim=~"jellystat-postgresql-17-cluster-([1-9][0-9]*)$"} / kubelet_volume_stats_capacity_bytes{namespace="jellystat", persistentvolumeclaim=~"jellystat-postgresql-17-cluster-([1-9][0-9]*)$"})) > 0.7 OR max(max by(persistentvolumeclaim) (1 - kubelet_volume_stats_available_bytes{namespace="jellystat", persistentvolumeclaim=~"jellystat-postgresql-17-cluster-([1-9][0-9]*)$-wal"} / kubelet_volume_stats_capacity_bytes{namespace="jellystat", persistentvolumeclaim=~"jellystat-postgresql-17-cluster-([1-9][0-9]*)$-wal"})) > 0.7 OR max(sum by (namespace,persistentvolumeclaim) (kubelet_volume_stats_used_bytes{namespace="jellystat", persistentvolumeclaim=~"jellystat-postgresql-17-cluster-([1-9][0-9]*)$-tbs.*"}) / sum by (namespace,persistentvolumeclaim) (kubelet_volume_stats_capacity_bytes{namespace="jellystat", persistentvolumeclaim=~"jellystat-postgresql-17-cluster-([1-9][0-9]*)$-tbs.*"}) * on(namespace, persistentvolumeclaim) group_left(volume) kube_pod_spec_volumes_persistentvolumeclaims_info{pod=~"jellystat-postgresql-17-cluster-([1-9][0-9]*)$"} ) > 0.7 for: 5m labels: severity: warning namespace: jellystat cnpg_cluster: jellystat-postgresql-17-cluster - alert: CNPGClusterOffline annotations: summary: CNPG Cluster has no running instances! description: |- CloudNativePG Cluster "jellystat/jellystat-postgresql-17-cluster" has no ready instances. Having an offline cluster means your applications will not be able to access the database, leading to potential service disruption and/or data loss. runbook_url: https://github.com/cloudnative-pg/charts/blob/main/charts/cluster/docs/runbooks/CNPGClusterOffline.md expr: | (count(cnpg_collector_up{namespace="jellystat",pod=~"jellystat-postgresql-17-cluster-([1-9][0-9]*)$"}) OR on() vector(0)) == 0 for: 5m labels: severity: critical namespace: jellystat cnpg_cluster: jellystat-postgresql-17-cluster - alert: CNPGClusterPGDatabaseXidAgeWarning annotations: summary: CNPG Cluster has a number of transactions from the frozen XID to the current one. description: |- Over 300,000,000 transactions from frozen xid on pod {{ $labels.pod }} expr: | cnpg_pg_database_xid_age > 300000000 for: 1m labels: severity: warning namespace: jellystat cnpg_cluster: jellystat-postgresql-17-cluster - alert: CNPGClusterPGReplicationWarning annotations: summary: CNPG Cluster standby is lagging behind the primary. description: |- Standby is lagging behind by over 300 seconds (5 minutes) expr: | cnpg_pg_replication_lag > 300 for: 1m labels: severity: warning namespace: jellystat cnpg_cluster: jellystat-postgresql-17-cluster - alert: CNPGClusterReplicaFailingReplicationWarning annotations: summary: CNPG Cluster has a replica is failing to replicate. description: |- Replica {{ $labels.pod }} is failing to replicate expr: | cnpg_pg_replication_in_recovery > cnpg_pg_replication_is_wal_receiver_up for: 1m labels: severity: warning namespace: jellystat cnpg_cluster: jellystat-postgresql-17-cluster - alert: CNPGClusterZoneSpreadWarning annotations: summary: CNPG Cluster instances in the same zone. description: |- CloudNativePG Cluster "jellystat/jellystat-postgresql-17-cluster" has instances in the same availability zone. A disaster in one availability zone will lead to a potential service disruption and/or data loss. runbook_url: https://github.com/cloudnative-pg/charts/blob/main/charts/cluster/docs/runbooks/CNPGClusterZoneSpreadWarning.md expr: | 3 > count(count by (label_topology_kubernetes_io_zone) (kube_pod_info{namespace="jellystat", pod=~"jellystat-postgresql-17-cluster-([1-9][0-9]*)$"} * on(node,instance) group_left(label_topology_kubernetes_io_zone) kube_node_labels)) < 3 for: 5m labels: severity: warning namespace: jellystat cnpg_cluster: jellystat-postgresql-17-cluster --- # Source: jellystat/templates/replication-source.yaml apiVersion: volsync.backube/v1alpha1 kind: ReplicationSource metadata: name: jellystat-data-backup-source namespace: jellystat labels: app.kubernetes.io/name: jellystat-data-backup-source app.kubernetes.io/instance: jellystat app.kubernetes.io/part-of: jellystat spec: sourcePVC: jellystat-data trigger: schedule: 0 4 * * * restic: pruneIntervalDays: 7 repository: jellystat-data-backup-secret retain: hourly: 1 daily: 3 weekly: 2 monthly: 2 yearly: 4 copyMethod: Snapshot storageClassName: ceph-block volumeSnapshotClassName: ceph-blockpool-snapshot --- # Source: jellystat/charts/postgres-17-cluster/templates/scheduled-backup.yaml apiVersion: postgresql.cnpg.io/v1 kind: ScheduledBackup metadata: name: "jellystat-postgresql-17-daily-backup-scheduled-backup" namespace: jellystat labels: helm.sh/chart: postgres-17-cluster-6.16.0 app.kubernetes.io/name: jellystat-postgresql-17 app.kubernetes.io/instance: jellystat app.kubernetes.io/part-of: jellystat app.kubernetes.io/version: "6.16.0" app.kubernetes.io/managed-by: Helm spec: immediate: false suspend: false schedule: "0 0 0 * * *" backupOwnerReference: self cluster: name: jellystat-postgresql-17-cluster method: plugin pluginConfiguration: name: barman-cloud.cloudnative-pg.io parameters: barmanObjectName: "jellystat-postgresql-17-external-backup" --- # Source: jellystat/charts/postgres-17-cluster/templates/scheduled-backup.yaml apiVersion: postgresql.cnpg.io/v1 kind: ScheduledBackup metadata: name: "jellystat-postgresql-17-live-backup-scheduled-backup" namespace: jellystat labels: helm.sh/chart: postgres-17-cluster-6.16.0 app.kubernetes.io/name: jellystat-postgresql-17 app.kubernetes.io/instance: jellystat app.kubernetes.io/part-of: jellystat app.kubernetes.io/version: "6.16.0" app.kubernetes.io/managed-by: Helm spec: immediate: true suspend: false schedule: "0 0 0 * * *" backupOwnerReference: self cluster: name: jellystat-postgresql-17-cluster method: plugin pluginConfiguration: name: barman-cloud.cloudnative-pg.io parameters: barmanObjectName: "jellystat-postgresql-17-garage-local-backup"