apiVersion: postgresql.cnpg.io/v1 kind: Cluster metadata: name: stalwart-postgresql-18-cluster namespace: stalwart labels: helm.sh/chart: postgres-18-cluster-7.9.1 app.kubernetes.io/name: stalwart-postgresql-18 app.kubernetes.io/instance: stalwart app.kubernetes.io/part-of: stalwart app.kubernetes.io/version: "7.9.1" app.kubernetes.io/managed-by: Helm spec: instances: 3 imageName: "ghcr.io/cloudnative-pg/postgresql:18.3-standard-trixie" imagePullPolicy: IfNotPresent postgresUID: 26 postgresGID: 26 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 plugins: - name: barman-cloud.cloudnative-pg.io enabled: true isWALArchiver: true parameters: barmanObjectName: "stalwart-postgresql-18-backup-garage-local" serverName: "stalwart-postgresql-18-backup-1" bootstrap: recovery: database: app source: stalwart-postgresql-18-backup-1 externalClusters: - name: stalwart-postgresql-18-backup-1 plugin: name: barman-cloud.cloudnative-pg.io enabled: true isWALArchiver: false parameters: barmanObjectName: "stalwart-postgresql-18-recovery" serverName: stalwart-postgresql-18-backup-1 --- apiVersion: v1 kind: ConfigMap metadata: name: stalwart-valkey-init-scripts labels: helm.sh/chart: valkey-0.9.3 app.kubernetes.io/name: valkey app.kubernetes.io/instance: stalwart app.kubernetes.io/version: "9.0.3" app.kubernetes.io/managed-by: Helm data: init.sh: |- #!/bin/sh set -eu # Default config paths VALKEY_CONFIG=${VALKEY_CONFIG_PATH:-/data/conf/valkey.conf} LOGFILE="/data/init.log" DATA_DIR="/data/conf" # Logging function (outputs to stderr and file) log() { echo "$(date) $1" | tee -a "$LOGFILE" >&2 } # Clean old log if requested if [ "${KEEP_OLD_LOGS:-false}" != "true" ]; then rm -f "$LOGFILE" fi if [ -f "$LOGFILE" ]; then log "Detected restart of this instance ($HOSTNAME)" fi log "Creating configuration in $DATA_DIR..." mkdir -p "$DATA_DIR" rm -f "$VALKEY_CONFIG" # Base valkey.conf log "Generating base valkey.conf" { echo "port 6379" echo "protected-mode no" echo "bind * -::*" echo "dir /data" } >>"$VALKEY_CONFIG" # Replica mode configuration log "Configuring replication mode" # Use POD_INDEX from Kubernetes metadata POD_INDEX=${POD_INDEX:-0} IS_MASTER=false # Check if this is pod-0 (master) if [ "$POD_INDEX" = "0" ]; then IS_MASTER=true log "This pod (index $POD_INDEX) is configured as MASTER" else log "This pod (index $POD_INDEX) is configured as REPLICA" fi # Configure replica settings if [ "$IS_MASTER" = "false" ]; then MASTER_HOST="stalwart-valkey-0.stalwart-valkey-headless.stalwart.svc.cluster.local" MASTER_PORT="6379" log "Configuring replica to follow master at $MASTER_HOST:$MASTER_PORT" { echo "" echo "# Replica Configuration" echo "replicaof $MASTER_HOST $MASTER_PORT" echo "replica-announce-ip stalwart-valkey-$POD_INDEX.stalwart-valkey-headless.stalwart.svc.cluster.local" } >>"$VALKEY_CONFIG" fi # Append extra configs if present if [ -f /usr/local/etc/valkey/valkey.conf ]; then log "Appending /usr/local/etc/valkey/valkey.conf" cat /usr/local/etc/valkey/valkey.conf >>"$VALKEY_CONFIG" fi if [ -d /extravalkeyconfigs ]; then log "Appending files in /extravalkeyconfigs/" cat /extravalkeyconfigs/* >>"$VALKEY_CONFIG" fi --- apiVersion: apps/v1 kind: Deployment metadata: name: stalwart labels: app.kubernetes.io/controller: main app.kubernetes.io/instance: stalwart app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: stalwart helm.sh/chart: stalwart-4.6.2 namespace: stalwart spec: revisionHistoryLimit: 3 replicas: 1 strategy: type: Recreate selector: matchLabels: app.kubernetes.io/controller: main app.kubernetes.io/name: stalwart app.kubernetes.io/instance: stalwart template: metadata: labels: app.kubernetes.io/controller: main app.kubernetes.io/instance: stalwart app.kubernetes.io/name: stalwart spec: enableServiceLinks: false serviceAccountName: default automountServiceAccountToken: true hostIPC: false hostNetwork: false hostPID: false dnsPolicy: ClusterFirst containers: - image: stalwartlabs/stalwart:v0.15.5 imagePullPolicy: IfNotPresent name: main resources: requests: cpu: 10m memory: 128Mi volumeMounts: - mountPath: /opt/stalwart name: config volumes: - name: config persistentVolumeClaim: claimName: stalwart-config --- apiVersion: elasticsearch.k8s.elastic.co/v1 kind: Elasticsearch metadata: name: elasticsearch-stalwart namespace: stalwart labels: app.kubernetes.io/name: elasticsearch-stalwart app.kubernetes.io/instance: stalwart app.kubernetes.io/part-of: stalwart spec: version: 8.19.8 auth: fileRealm: - secretName: stalwart-elasticsearch-secret nodeSets: - name: default count: 2 config: node.store.allow_mmap: false volumeClaimTemplates: - metadata: name: elasticsearch-data spec: accessModes: - ReadWriteOnce resources: requests: storage: 5Gi storageClassName: ceph-block --- apiVersion: external-secrets.io/v1 kind: ExternalSecret metadata: name: stalwart-config-backup-secret-external namespace: stalwart labels: helm.sh/chart: volsync-target-config-0.8.0 app.kubernetes.io/instance: stalwart app.kubernetes.io/part-of: stalwart app.kubernetes.io/version: "0.8.0" app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: stalwart-config-backup-secret-external spec: secretStoreRef: kind: ClusterSecretStore name: vault target: template: mergePolicy: Merge engineVersion: v2 data: RESTIC_REPOSITORY: "{{ .BUCKET_ENDPOINT }}/stalwart/stalwart-config" data: - secretKey: BUCKET_ENDPOINT remoteRef: conversionStrategy: Default decodingStrategy: None key: /volsync/restic/digital-ocean metadataPolicy: None property: BUCKET_ENDPOINT - secretKey: RESTIC_PASSWORD remoteRef: conversionStrategy: Default decodingStrategy: None key: /volsync/restic/digital-ocean metadataPolicy: None property: RESTIC_PASSWORD - secretKey: AWS_DEFAULT_REGION remoteRef: conversionStrategy: Default decodingStrategy: None key: /digital-ocean/home-infra/volsync-backups 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: AWS_ACCESS_KEY_ID - secretKey: AWS_SECRET_ACCESS_KEY remoteRef: conversionStrategy: Default decodingStrategy: None key: /digital-ocean/home-infra/volsync-backups metadataPolicy: None property: AWS_SECRET_ACCESS_KEY --- apiVersion: external-secrets.io/v1 kind: ExternalSecret metadata: name: stalwart-config-backup-secret-local namespace: stalwart labels: helm.sh/chart: volsync-target-config-0.8.0 app.kubernetes.io/instance: stalwart app.kubernetes.io/part-of: stalwart app.kubernetes.io/version: "0.8.0" app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: stalwart-config-backup-secret-local spec: secretStoreRef: kind: ClusterSecretStore name: vault target: template: mergePolicy: Merge engineVersion: v2 data: RESTIC_REPOSITORY: "{{ .BUCKET_ENDPOINT }}/stalwart/stalwart-config" data: - secretKey: BUCKET_ENDPOINT remoteRef: conversionStrategy: Default decodingStrategy: None key: /volsync/restic/garage-local metadataPolicy: None property: BUCKET_ENDPOINT - secretKey: RESTIC_PASSWORD remoteRef: conversionStrategy: Default decodingStrategy: None key: /volsync/restic/garage-local metadataPolicy: None property: RESTIC_PASSWORD - secretKey: AWS_DEFAULT_REGION remoteRef: conversionStrategy: Default decodingStrategy: None key: /garage/home-infra/volsync-backups metadataPolicy: None property: ACCESS_REGION - secretKey: AWS_ACCESS_KEY_ID remoteRef: conversionStrategy: Default decodingStrategy: None key: /garage/home-infra/volsync-backups metadataPolicy: None property: ACCESS_KEY_ID - secretKey: AWS_SECRET_ACCESS_KEY remoteRef: conversionStrategy: Default decodingStrategy: None key: /garage/home-infra/volsync-backups metadataPolicy: None property: ACCESS_SECRET_KEY --- apiVersion: external-secrets.io/v1 kind: ExternalSecret metadata: name: stalwart-config-backup-secret-remote namespace: stalwart labels: helm.sh/chart: volsync-target-config-0.8.0 app.kubernetes.io/instance: stalwart app.kubernetes.io/part-of: stalwart app.kubernetes.io/version: "0.8.0" app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: stalwart-config-backup-secret-remote spec: secretStoreRef: kind: ClusterSecretStore name: vault target: template: mergePolicy: Merge engineVersion: v2 data: RESTIC_REPOSITORY: "{{ .BUCKET_ENDPOINT }}/stalwart/stalwart-config" data: - secretKey: BUCKET_ENDPOINT remoteRef: conversionStrategy: Default decodingStrategy: None key: /volsync/restic/garage-remote metadataPolicy: None property: BUCKET_ENDPOINT - secretKey: RESTIC_PASSWORD remoteRef: conversionStrategy: Default decodingStrategy: None key: /volsync/restic/garage-remote metadataPolicy: None property: RESTIC_PASSWORD - secretKey: AWS_DEFAULT_REGION remoteRef: conversionStrategy: Default decodingStrategy: None key: /garage/home-infra/volsync-backups metadataPolicy: None property: ACCESS_REGION - secretKey: AWS_ACCESS_KEY_ID remoteRef: conversionStrategy: Default decodingStrategy: None key: /garage/home-infra/volsync-backups metadataPolicy: None property: ACCESS_KEY_ID - secretKey: AWS_SECRET_ACCESS_KEY remoteRef: conversionStrategy: Default decodingStrategy: None key: /garage/home-infra/volsync-backups metadataPolicy: None property: ACCESS_SECRET_KEY --- apiVersion: external-secrets.io/v1 kind: ExternalSecret metadata: name: stalwart-elasticsearch-secret namespace: stalwart labels: app.kubernetes.io/name: stalwart-elasticsearch-secret app.kubernetes.io/instance: stalwart app.kubernetes.io/part-of: stalwart spec: secretStoreRef: kind: ClusterSecretStore name: vault data: - secretKey: username remoteRef: conversionStrategy: Default decodingStrategy: None key: /cl01tl/stalwart/elasticsearch metadataPolicy: None property: username - secretKey: password remoteRef: conversionStrategy: Default decodingStrategy: None key: /cl01tl/stalwart/elasticsearch metadataPolicy: None property: password - secretKey: roles remoteRef: conversionStrategy: Default decodingStrategy: None key: /cl01tl/stalwart/elasticsearch metadataPolicy: None property: roles --- apiVersion: external-secrets.io/v1 kind: ExternalSecret metadata: name: stalwart-postgresql-18-backup-garage-local-secret namespace: stalwart labels: helm.sh/chart: postgres-18-cluster-7.9.1 app.kubernetes.io/name: stalwart-postgresql-18 app.kubernetes.io/instance: stalwart app.kubernetes.io/part-of: stalwart app.kubernetes.io/version: "7.9.1" app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: stalwart-postgresql-18-backup-garage-local-secret spec: secretStoreRef: kind: ClusterSecretStore name: vault data: - secretKey: ACCESS_REGION remoteRef: conversionStrategy: Default decodingStrategy: None key: /garage/home-infra/postgres-backups metadataPolicy: None property: ACCESS_REGION - 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 --- apiVersion: external-secrets.io/v1 kind: ExternalSecret metadata: name: stalwart-postgresql-18-recovery-secret namespace: stalwart labels: helm.sh/chart: postgres-18-cluster-7.9.1 app.kubernetes.io/name: stalwart-postgresql-18 app.kubernetes.io/instance: stalwart app.kubernetes.io/part-of: stalwart app.kubernetes.io/version: "7.9.1" app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: stalwart-postgresql-18-recovery-secret spec: secretStoreRef: kind: ClusterSecretStore name: vault data: - secretKey: ACCESS_REGION remoteRef: conversionStrategy: Default decodingStrategy: None key: /garage/home-infra/postgres-backups metadataPolicy: None property: ACCESS_REGION - 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 --- apiVersion: gateway.networking.k8s.io/v1alpha2 kind: HTTPRoute metadata: name: stalwart labels: app.kubernetes.io/instance: stalwart app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: stalwart helm.sh/chart: stalwart-4.6.2 namespace: stalwart spec: parentRefs: - group: gateway.networking.k8s.io kind: Gateway name: traefik-gateway namespace: traefik hostnames: - "stalwart.alexlebens.net" rules: - backendRefs: - group: "" kind: Service name: stalwart namespace: stalwart port: 80 weight: 100 matches: - path: type: PathPrefix value: / --- apiVersion: v1 kind: Namespace metadata: name: stalwart labels: app.kubernetes.io/name: stalwart app.kubernetes.io/instance: stalwart app.kubernetes.io/part-of: stalwart pod-security.kubernetes.io/audit: privileged pod-security.kubernetes.io/enforce: privileged pod-security.kubernetes.io/warn: privileged --- apiVersion: barmancloud.cnpg.io/v1 kind: ObjectStore metadata: name: stalwart-postgresql-18-backup-garage-local namespace: stalwart labels: helm.sh/chart: postgres-18-cluster-7.9.1 app.kubernetes.io/name: stalwart-postgresql-18 app.kubernetes.io/instance: stalwart app.kubernetes.io/part-of: stalwart app.kubernetes.io/version: "7.9.1" app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: stalwart-postgresql-18-backup-garage-local spec: retentionPolicy: 7d instanceSidecarConfiguration: env: - name: AWS_REQUEST_CHECKSUM_CALCULATION value: when_required - name: AWS_RESPONSE_CHECKSUM_VALIDATION value: when_required configuration: destinationPath: s3://postgres-backups/cl01tl/stalwart/stalwart-postgresql-18-cluster endpointURL: http://garage-main.garage:3900 s3Credentials: accessKeyId: name: stalwart-postgresql-18-backup-garage-local-secret key: ACCESS_KEY_ID secretAccessKey: name: stalwart-postgresql-18-backup-garage-local-secret key: ACCESS_SECRET_KEY region: name: stalwart-postgresql-18-backup-garage-local-secret key: ACCESS_REGION --- apiVersion: barmancloud.cnpg.io/v1 kind: ObjectStore metadata: name: "stalwart-postgresql-18-recovery" namespace: stalwart labels: helm.sh/chart: postgres-18-cluster-7.9.1 app.kubernetes.io/name: stalwart-postgresql-18 app.kubernetes.io/instance: stalwart app.kubernetes.io/part-of: stalwart app.kubernetes.io/version: "7.9.1" app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: "stalwart-postgresql-18-recovery" spec: configuration: destinationPath: s3://postgres-backups/cl01tl/stalwart/stalwart-postgresql-18-cluster endpointURL: http://garage-main.garage:3900 wal: compression: snappy maxParallel: 1 data: compression: snappy jobs: 1 s3Credentials: accessKeyId: name: stalwart-postgresql-18-recovery-secret key: ACCESS_KEY_ID secretAccessKey: name: stalwart-postgresql-18-recovery-secret key: ACCESS_SECRET_KEY region: name: stalwart-postgresql-18-recovery-secret key: ACCESS_REGION --- kind: PersistentVolumeClaim apiVersion: v1 metadata: name: stalwart-config labels: app.kubernetes.io/instance: stalwart app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: stalwart helm.sh/chart: stalwart-4.6.2 annotations: helm.sh/resource-policy: keep namespace: stalwart spec: accessModes: - "ReadWriteOnce" resources: requests: storage: "10Gi" storageClassName: "ceph-block" --- apiVersion: monitoring.coreos.com/v1 kind: PodMonitor metadata: name: stalwart-valkey labels: helm.sh/chart: valkey-0.9.3 app.kubernetes.io/name: valkey app.kubernetes.io/instance: stalwart app.kubernetes.io/version: "9.0.3" app.kubernetes.io/managed-by: Helm app.kubernetes.io/part-of: valkey app.kubernetes.io/component: podmonitor spec: podMetricsEndpoints: - port: metrics interval: 30s namespaceSelector: matchNames: - stalwart selector: matchLabels: app.kubernetes.io/name: valkey app.kubernetes.io/instance: stalwart --- apiVersion: monitoring.coreos.com/v1 kind: PrometheusRule metadata: name: stalwart-postgresql-18-alert-rules namespace: stalwart labels: helm.sh/chart: postgres-18-cluster-7.9.1 app.kubernetes.io/name: stalwart-postgresql-18 app.kubernetes.io/instance: stalwart app.kubernetes.io/part-of: stalwart app.kubernetes.io/version: "7.9.1" app.kubernetes.io/managed-by: Helm spec: groups: - name: cloudnative-pg/stalwart-postgresql-18 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{namespace="stalwart"} > 300 for: 1m labels: severity: warning namespace: stalwart cnpg_cluster: stalwart-postgresql-18-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{namespace="stalwart"} > 10 for: 1m labels: severity: warning namespace: stalwart cnpg_cluster: stalwart-postgresql-18-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="stalwart"} - cnpg_pg_replication_is_wal_receiver_up{namespace="stalwart"}) < 1 for: 5m labels: severity: critical namespace: stalwart cnpg_cluster: stalwart-postgresql-18-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="stalwart"} - cnpg_pg_replication_is_wal_receiver_up{namespace="stalwart"}) < 2 for: 5m labels: severity: warning namespace: stalwart cnpg_cluster: stalwart-postgresql-18-cluster - alert: CNPGClusterHighConnectionsCritical annotations: summary: CNPG Instance maximum number of connections critical! description: |- CloudNativePG Cluster "stalwart/stalwart-postgresql-18-cluster" instance {{`{{`}} $labels.pod {{`}}`}} is using {{`{{`}} $value {{`}}`}}% of the maximum number of connections. runbook_url: https://github.com/cloudnative-pg/charts/blob/main/charts/cluster/docs/runbooks/CNPGClusterHighConnectionsCritical.md expr: | sum by (pod) (cnpg_backends_total{namespace="stalwart", pod=~"stalwart-postgresql-18-cluster-([1-9][0-9]*)$"}) / max by (pod) (cnpg_pg_settings_setting{name="max_connections", namespace="stalwart", pod=~"stalwart-postgresql-18-cluster-([1-9][0-9]*)$"}) * 100 > 95 for: 5m labels: severity: critical namespace: stalwart cnpg_cluster: stalwart-postgresql-18-cluster - alert: CNPGClusterHighConnectionsWarning annotations: summary: CNPG Instance is approaching the maximum number of connections. description: |- CloudNativePG Cluster "stalwart/stalwart-postgresql-18-cluster" instance {{`{{`}} $labels.pod {{`}}`}} is using {{`{{`}} $value {{`}}`}}% of the maximum number of connections. runbook_url: https://github.com/cloudnative-pg/charts/blob/main/charts/cluster/docs/runbooks/CNPGClusterHighConnectionsWarning.md expr: | sum by (pod) (cnpg_backends_total{namespace="stalwart", pod=~"stalwart-postgresql-18-cluster-([1-9][0-9]*)$"}) / max by (pod) (cnpg_pg_settings_setting{name="max_connections", namespace="stalwart", pod=~"stalwart-postgresql-18-cluster-([1-9][0-9]*)$"}) * 100 > 80 for: 5m labels: severity: warning namespace: stalwart cnpg_cluster: stalwart-postgresql-18-cluster - alert: CNPGClusterHighReplicationLag annotations: summary: CNPG Cluster high replication lag description: |- CloudNativePG Cluster "stalwart/stalwart-postgresql-18-cluster" is experiencing a high replication lag of {{`{{`}} $value {{`}}`}}ms. High replication lag indicates network issues, busy instances, slow queries or suboptimal configuration. runbook_url: https://github.com/cloudnative-pg/charts/blob/main/charts/cluster/docs/runbooks/CNPGClusterHighReplicationLag.md expr: | max(cnpg_pg_replication_lag{namespace="stalwart",pod=~"stalwart-postgresql-18-cluster-([1-9][0-9]*)$"}) * 1000 > 1000 for: 5m labels: severity: warning namespace: stalwart cnpg_cluster: stalwart-postgresql-18-cluster - alert: CNPGClusterInstancesOnSameNode annotations: summary: CNPG Cluster instances are located on the same node. description: |- CloudNativePG Cluster "stalwart/stalwart-postgresql-18-cluster" has {{`{{`}} $value {{`}}`}} instances on the same node {{`{{`}} $labels.node {{`}}`}}. A failure or scheduled downtime of a single node will lead to a potential service disruption and/or data loss. runbook_url: https://github.com/cloudnative-pg/charts/blob/main/charts/cluster/docs/runbooks/CNPGClusterInstancesOnSameNode.md expr: | count by (node) (kube_pod_info{namespace="stalwart", pod=~"stalwart-postgresql-18-cluster-([1-9][0-9]*)$"}) > 1 for: 5m labels: severity: warning namespace: stalwart cnpg_cluster: stalwart-postgresql-18-cluster - alert: CNPGClusterLongRunningTransactionWarning annotations: summary: CNPG Cluster query is taking longer than 5 minutes. description: |- CloudNativePG Cluster Pod {{ $labels.pod }} is taking more than 5 minutes (300 seconds) for a query. expr: |- cnpg_backends_max_tx_duration_seconds{namespace="stalwart"} > 300 for: 1m labels: severity: warning namespace: stalwart cnpg_cluster: stalwart-postgresql-18-cluster - alert: CNPGClusterLowDiskSpaceCritical annotations: summary: CNPG Instance is running out of disk space! description: |- CloudNativePG Cluster "stalwart/stalwart-postgresql-18-cluster" is running extremely low on disk space. Check attached PVCs! runbook_url: https://github.com/cloudnative-pg/charts/blob/main/charts/cluster/docs/runbooks/CNPGClusterLowDiskSpaceCritical.md expr: | max(max by(persistentvolumeclaim) (1 - kubelet_volume_stats_available_bytes{namespace="stalwart", persistentvolumeclaim=~"stalwart-postgresql-18-cluster-([1-9][0-9]*)$"} / kubelet_volume_stats_capacity_bytes{namespace="stalwart", persistentvolumeclaim=~"stalwart-postgresql-18-cluster-([1-9][0-9]*)$"})) > 0.9 OR max(max by(persistentvolumeclaim) (1 - kubelet_volume_stats_available_bytes{namespace="stalwart", persistentvolumeclaim=~"stalwart-postgresql-18-cluster-([1-9][0-9]*)$-wal"} / kubelet_volume_stats_capacity_bytes{namespace="stalwart", persistentvolumeclaim=~"stalwart-postgresql-18-cluster-([1-9][0-9]*)$-wal"})) > 0.9 OR max(sum by (namespace,persistentvolumeclaim) (kubelet_volume_stats_used_bytes{namespace="stalwart", persistentvolumeclaim=~"stalwart-postgresql-18-cluster-([1-9][0-9]*)$-tbs.*"}) / sum by (namespace,persistentvolumeclaim) (kubelet_volume_stats_capacity_bytes{namespace="stalwart", persistentvolumeclaim=~"stalwart-postgresql-18-cluster-([1-9][0-9]*)$-tbs.*"}) * on(namespace, persistentvolumeclaim) group_left(volume) kube_pod_spec_volumes_persistentvolumeclaims_info{pod=~"stalwart-postgresql-18-cluster-([1-9][0-9]*)$"} ) > 0.9 for: 5m labels: severity: critical namespace: stalwart cnpg_cluster: stalwart-postgresql-18-cluster - alert: CNPGClusterLowDiskSpaceWarning annotations: summary: CNPG Instance is running out of disk space. description: |- CloudNativePG Cluster "stalwart/stalwart-postgresql-18-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="stalwart", persistentvolumeclaim=~"stalwart-postgresql-18-cluster-([1-9][0-9]*)$"} / kubelet_volume_stats_capacity_bytes{namespace="stalwart", persistentvolumeclaim=~"stalwart-postgresql-18-cluster-([1-9][0-9]*)$"})) > 0.7 OR max(max by(persistentvolumeclaim) (1 - kubelet_volume_stats_available_bytes{namespace="stalwart", persistentvolumeclaim=~"stalwart-postgresql-18-cluster-([1-9][0-9]*)$-wal"} / kubelet_volume_stats_capacity_bytes{namespace="stalwart", persistentvolumeclaim=~"stalwart-postgresql-18-cluster-([1-9][0-9]*)$-wal"})) > 0.7 OR max(sum by (namespace,persistentvolumeclaim) (kubelet_volume_stats_used_bytes{namespace="stalwart", persistentvolumeclaim=~"stalwart-postgresql-18-cluster-([1-9][0-9]*)$-tbs.*"}) / sum by (namespace,persistentvolumeclaim) (kubelet_volume_stats_capacity_bytes{namespace="stalwart", persistentvolumeclaim=~"stalwart-postgresql-18-cluster-([1-9][0-9]*)$-tbs.*"}) * on(namespace, persistentvolumeclaim) group_left(volume) kube_pod_spec_volumes_persistentvolumeclaims_info{pod=~"stalwart-postgresql-18-cluster-([1-9][0-9]*)$"} ) > 0.7 for: 5m labels: severity: warning namespace: stalwart cnpg_cluster: stalwart-postgresql-18-cluster - alert: CNPGClusterOffline annotations: summary: CNPG Cluster has no running instances! description: |- CloudNativePG Cluster "stalwart/stalwart-postgresql-18-cluster" has no ready instances. Having an offline cluster means your applications will not be able to access the database, leading to potential service disruption and/or data loss. runbook_url: https://github.com/cloudnative-pg/charts/blob/main/charts/cluster/docs/runbooks/CNPGClusterOffline.md expr: | (count(cnpg_collector_up{namespace="stalwart",pod=~"stalwart-postgresql-18-cluster-([1-9][0-9]*)$"}) OR on() vector(0)) == 0 for: 5m labels: severity: critical namespace: stalwart cnpg_cluster: stalwart-postgresql-18-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{namespace="stalwart"} > 300000000 for: 1m labels: severity: warning namespace: stalwart cnpg_cluster: stalwart-postgresql-18-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{namespace="stalwart"} > 300 for: 1m labels: severity: warning namespace: stalwart cnpg_cluster: stalwart-postgresql-18-cluster - alert: CNPGClusterReplicaFailingReplicationWarning annotations: summary: CNPG Cluster has a replica is failing to replicate. description: |- Replica {{ $labels.pod }} is failing to replicate expr: | cnpg_pg_replication_in_recovery{namespace="stalwart"} > cnpg_pg_replication_is_wal_receiver_up{namespace="stalwart"} for: 1m labels: severity: warning namespace: stalwart cnpg_cluster: stalwart-postgresql-18-cluster - alert: CNPGClusterZoneSpreadWarning annotations: summary: CNPG Cluster instances in the same zone. description: |- CloudNativePG Cluster "stalwart/stalwart-postgresql-18-cluster" has instances in the same availability zone. A disaster in one availability zone will lead to a potential service disruption and/or data loss. runbook_url: https://github.com/cloudnative-pg/charts/blob/main/charts/cluster/docs/runbooks/CNPGClusterZoneSpreadWarning.md expr: | 3 > count(count by (label_topology_kubernetes_io_zone) (kube_pod_info{namespace="stalwart", pod=~"stalwart-postgresql-18-cluster-([1-9][0-9]*)$"} * on(node,instance) group_left(label_topology_kubernetes_io_zone) kube_node_labels)) < 3 for: 5m labels: severity: warning namespace: stalwart cnpg_cluster: stalwart-postgresql-18-cluster --- apiVersion: monitoring.coreos.com/v1 kind: PrometheusRule metadata: name: stalwart-valkey labels: helm.sh/chart: valkey-0.9.3 app.kubernetes.io/name: valkey app.kubernetes.io/instance: stalwart app.kubernetes.io/version: "9.0.3" app.kubernetes.io/managed-by: Helm app.kubernetes.io/part-of: valkey spec: groups: - name: stalwart-valkey rules: - alert: ValkeyDown annotations: description: Valkey instance {{ $labels.instance }} is down. summary: Valkey instance {{ $labels.instance }} down expr: | redis_up{service="stalwart-valkey-metrics"} == 0 for: 2m labels: severity: error - alert: ValkeyMemoryHigh annotations: description: | Valkey instance {{ $labels.instance }} is using {{ $value }}% of its available memory. summary: Valkey instance {{ $labels.instance }} is using too much memory expr: | redis_memory_used_bytes{service="stalwart-valkey-metrics"} * 100 / redis_memory_max_bytes{service="stalwart-valkey-metrics"} > 90 <= 100 for: 2m labels: severity: error - alert: ValkeyKeyEviction annotations: description: | Valkey instance {{ $labels.instance }} has evicted {{ $value }} keys in the last 5 minutes. summary: Valkey instance {{ $labels.instance }} has evicted keys expr: | increase(redis_evicted_keys_total{service="stalwart-valkey-metrics"}[5m]) > 0 for: 1s labels: severity: error --- apiVersion: volsync.backube/v1alpha1 kind: ReplicationSource metadata: name: stalwart-config-backup-source-external namespace: stalwart labels: helm.sh/chart: volsync-target-config-0.8.0 app.kubernetes.io/instance: stalwart app.kubernetes.io/part-of: stalwart app.kubernetes.io/version: "0.8.0" app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: stalwart-config-backup spec: sourcePVC: stalwart-config trigger: schedule: 28 13 * * * restic: pruneIntervalDays: 7 repository: stalwart-config-backup-secret-external retain: daily: 7 hourly: 0 monthly: 3 weekly: 4 yearly: 1 copyMethod: Snapshot storageClassName: ceph-block volumeSnapshotClassName: ceph-blockpool-snapshot cacheCapacity: 1Gi --- apiVersion: volsync.backube/v1alpha1 kind: ReplicationSource metadata: name: stalwart-config-backup-source-local namespace: stalwart labels: helm.sh/chart: volsync-target-config-0.8.0 app.kubernetes.io/instance: stalwart app.kubernetes.io/part-of: stalwart app.kubernetes.io/version: "0.8.0" app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: stalwart-config-backup spec: sourcePVC: stalwart-config trigger: schedule: 28 11 * * * restic: pruneIntervalDays: 7 repository: stalwart-config-backup-secret-local retain: daily: 7 hourly: 0 monthly: 3 weekly: 4 yearly: 1 copyMethod: Snapshot storageClassName: ceph-block volumeSnapshotClassName: ceph-blockpool-snapshot cacheCapacity: 1Gi --- apiVersion: volsync.backube/v1alpha1 kind: ReplicationSource metadata: name: stalwart-config-backup-source-remote namespace: stalwart labels: helm.sh/chart: volsync-target-config-0.8.0 app.kubernetes.io/instance: stalwart app.kubernetes.io/part-of: stalwart app.kubernetes.io/version: "0.8.0" app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: stalwart-config-backup spec: sourcePVC: stalwart-config trigger: schedule: 28 12 * * * restic: pruneIntervalDays: 7 repository: stalwart-config-backup-secret-remote retain: daily: 7 hourly: 0 monthly: 3 weekly: 4 yearly: 1 copyMethod: Snapshot storageClassName: ceph-block volumeSnapshotClassName: ceph-blockpool-snapshot cacheCapacity: 1Gi --- apiVersion: postgresql.cnpg.io/v1 kind: ScheduledBackup metadata: name: "stalwart-postgresql-18-scheduled-backup-live-backup" namespace: stalwart labels: helm.sh/chart: postgres-18-cluster-7.9.1 app.kubernetes.io/name: stalwart-postgresql-18 app.kubernetes.io/instance: stalwart app.kubernetes.io/part-of: stalwart app.kubernetes.io/version: "7.9.1" app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: "stalwart-postgresql-18-scheduled-backup-live-backup" spec: immediate: true suspend: false schedule: "0 5 16 * * *" backupOwnerReference: self cluster: name: stalwart-postgresql-18-cluster method: plugin pluginConfiguration: name: barman-cloud.cloudnative-pg.io parameters: barmanObjectName: "stalwart-postgresql-18-backup-garage-local" --- apiVersion: v1 kind: Service metadata: name: stalwart-valkey-headless labels: helm.sh/chart: valkey-0.9.3 app.kubernetes.io/name: valkey app.kubernetes.io/instance: stalwart app.kubernetes.io/version: "9.0.3" app.kubernetes.io/managed-by: Helm app.kubernetes.io/component: headless spec: type: ClusterIP clusterIP: None publishNotReadyAddresses: true ports: - name: tcp port: 6379 targetPort: tcp protocol: TCP selector: app.kubernetes.io/name: valkey app.kubernetes.io/instance: stalwart --- apiVersion: v1 kind: Service metadata: name: stalwart-valkey-metrics labels: helm.sh/chart: valkey-0.9.3 app.kubernetes.io/name: valkey app.kubernetes.io/instance: stalwart app.kubernetes.io/version: "9.0.3" app.kubernetes.io/managed-by: Helm app.kubernetes.io/component: metrics app.kubernetes.io/part-of: valkey annotations: spec: type: ClusterIP ports: - name: metrics port: 9121 protocol: TCP targetPort: metrics selector: app.kubernetes.io/name: valkey app.kubernetes.io/instance: stalwart --- apiVersion: v1 kind: Service metadata: name: stalwart-valkey-read labels: helm.sh/chart: valkey-0.9.3 app.kubernetes.io/name: valkey app.kubernetes.io/instance: stalwart app.kubernetes.io/version: "9.0.3" app.kubernetes.io/managed-by: Helm app.kubernetes.io/component: read spec: type: ClusterIP ports: - name: tcp port: 6379 targetPort: tcp protocol: TCP selector: app.kubernetes.io/name: valkey app.kubernetes.io/instance: stalwart --- apiVersion: v1 kind: Service metadata: name: stalwart-valkey labels: helm.sh/chart: valkey-0.9.3 app.kubernetes.io/name: valkey app.kubernetes.io/instance: stalwart app.kubernetes.io/version: "9.0.3" app.kubernetes.io/managed-by: Helm app.kubernetes.io/component: primary spec: type: ClusterIP ports: - port: 6379 targetPort: tcp protocol: TCP name: tcp selector: app.kubernetes.io/name: valkey app.kubernetes.io/instance: stalwart statefulset.kubernetes.io/pod-name: stalwart-valkey-0 --- apiVersion: v1 kind: Service metadata: name: stalwart labels: app.kubernetes.io/instance: stalwart app.kubernetes.io/managed-by: Helm app.kubernetes.io/name: stalwart app.kubernetes.io/service: stalwart helm.sh/chart: stalwart-4.6.2 namespace: stalwart spec: type: ClusterIP ports: - port: 80 targetPort: 8080 protocol: TCP name: http - port: 143 targetPort: 143 protocol: TCP name: imap - port: 993 targetPort: 993 protocol: TCP name: imaps - port: 25 targetPort: 25 protocol: TCP name: smtp - port: 465 targetPort: 465 protocol: TCP name: smtps selector: app.kubernetes.io/controller: main app.kubernetes.io/instance: stalwart app.kubernetes.io/name: stalwart --- apiVersion: v1 kind: ServiceAccount metadata: name: stalwart-valkey labels: helm.sh/chart: valkey-0.9.3 app.kubernetes.io/name: valkey app.kubernetes.io/instance: stalwart app.kubernetes.io/version: "9.0.3" app.kubernetes.io/managed-by: Helm automountServiceAccountToken: false --- apiVersion: monitoring.coreos.com/v1 kind: ServiceMonitor metadata: name: stalwart-valkey labels: helm.sh/chart: valkey-0.9.3 app.kubernetes.io/name: valkey app.kubernetes.io/instance: stalwart app.kubernetes.io/version: "9.0.3" app.kubernetes.io/managed-by: Helm app.kubernetes.io/part-of: valkey app.kubernetes.io/component: service-monitor spec: endpoints: - port: metrics interval: 30s namespaceSelector: matchNames: - stalwart selector: matchLabels: app.kubernetes.io/name: valkey app.kubernetes.io/instance: stalwart app.kubernetes.io/component: metrics --- apiVersion: apps/v1 kind: StatefulSet metadata: name: stalwart-valkey labels: helm.sh/chart: valkey-0.9.3 app.kubernetes.io/name: valkey app.kubernetes.io/instance: stalwart app.kubernetes.io/version: "9.0.3" app.kubernetes.io/managed-by: Helm spec: serviceName: stalwart-valkey-headless replicas: 3 podManagementPolicy: OrderedReady selector: matchLabels: app.kubernetes.io/name: valkey app.kubernetes.io/instance: stalwart volumeClaimTemplates: - metadata: name: valkey-data spec: accessModes: - ReadWriteOnce storageClassName: "ceph-block" resources: requests: storage: "1Gi" template: metadata: labels: app.kubernetes.io/name: valkey app.kubernetes.io/instance: stalwart annotations: checksum/initconfig: "0b239a281121e840428928da1c5cc8f7" spec: automountServiceAccountToken: false serviceAccountName: stalwart-valkey securityContext: fsGroup: 1000 runAsGroup: 1000 runAsUser: 1000 initContainers: - name: stalwart-valkey-init image: docker.io/valkey/valkey:9.0.3 imagePullPolicy: IfNotPresent securityContext: capabilities: drop: - ALL readOnlyRootFilesystem: true runAsNonRoot: true runAsUser: 1000 command: ["/scripts/init.sh"] env: - name: POD_INDEX valueFrom: fieldRef: fieldPath: metadata.labels['apps.kubernetes.io/pod-index'] volumeMounts: - name: valkey-data mountPath: /data - name: scripts mountPath: /scripts containers: - name: stalwart-valkey image: docker.io/valkey/valkey:9.0.3 imagePullPolicy: IfNotPresent command: ["valkey-server"] args: ["/data/conf/valkey.conf"] securityContext: capabilities: drop: - ALL readOnlyRootFilesystem: true runAsNonRoot: true runAsUser: 1000 env: - name: POD_INDEX valueFrom: fieldRef: fieldPath: metadata.labels['apps.kubernetes.io/pod-index'] - name: VALKEY_LOGLEVEL value: "notice" ports: - name: tcp containerPort: 6379 protocol: TCP startupProbe: exec: command: ["sh", "-c", "valkey-cli ping"] livenessProbe: exec: command: ["sh", "-c", "valkey-cli ping"] resources: requests: cpu: 10m memory: 128Mi volumeMounts: - name: valkey-data mountPath: /data - name: metrics image: ghcr.io/oliver006/redis_exporter:v1.82.0 imagePullPolicy: "IfNotPresent" ports: - name: metrics containerPort: 9121 startupProbe: tcpSocket: port: metrics livenessProbe: tcpSocket: port: metrics readinessProbe: httpGet: path: / port: metrics resources: requests: cpu: 10m memory: 64M env: - name: REDIS_ALIAS value: stalwart-valkey volumes: - name: scripts configMap: name: stalwart-valkey-init-scripts defaultMode: 0555