Compare commits
3 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 alexlebens
|
61467d4638 | ||
|
alexlebens
|
c6a6668e5e | ||
|
alexlebens
|
8d095b58f9 |
@@ -1,6 +1,6 @@
|
||||
apiVersion: v2
|
||||
name: postgres-cluster
|
||||
version: 7.12.1
|
||||
version: 7.13.1
|
||||
description: Cloudnative-pg Cluster
|
||||
keywords:
|
||||
- database
|
||||
@@ -12,4 +12,4 @@ maintainers:
|
||||
- name: alexlebens
|
||||
icon: https://avatars.githubusercontent.com/u/100373852?s=48&v=4
|
||||
# renovate: datasource=github-releases depName=cloudnative-pg/cloudnative-pg
|
||||
appVersion: v1.29.0
|
||||
appVersion: v1.29.1
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# postgres-cluster
|
||||
|
||||
 
|
||||
 
|
||||
|
||||
Cloudnative-pg Cluster
|
||||
|
||||
@@ -24,7 +24,7 @@ Cloudnative-pg Cluster
|
||||
| backup.method | string | `"objectStore"` | Method to create backups, options currently are only objectStore |
|
||||
| backup.objectStore | string | `nil` | Options for object store backups |
|
||||
| backup.scheduledBackups | list | `[]` | List of scheduled backups |
|
||||
| cluster | object | `{"additionalLabels":{},"affinity":{"enablePodAntiAffinity":true,"topologyKey":"kubernetes.io/hostname"},"annotations":{},"certificates":{},"enablePDB":true,"enableSuperuserAccess":false,"image":{"repository":"ghcr.io/cloudnative-pg/postgresql","tag":"18.3-standard-trixie"},"imagePullPolicy":"IfNotPresent","imagePullSecrets":[],"initdb":{"database":"app","owner":"app"},"instances":3,"logLevel":"info","monitoring":{"customQueries":[],"customQueriesSecret":[],"disableDefaultQueries":false,"enabled":true,"podMonitor":{"enabled":true,"metricRelabelings":[],"relabelings":[]},"prometheusRule":{"enabled":true,"excludeRules":["CNPGClusterLastFailedArchiveTimeWarning"]}},"postgresGID":-1,"postgresUID":-1,"postgresql":{"ldap":{},"parameters":{"hot_standby_feedback":"on","max_slot_wal_keep_size":"2000MB","shared_buffers":"128MB"},"pg_hba":[],"pg_ident":[],"shared_preload_libraries":[],"synchronous":{}},"primaryUpdateMethod":"switchover","primaryUpdateStrategy":"unsupervised","priorityClassName":"","resources":{"limits":{"hugepages-2Mi":"256Mi"},"requests":{"cpu":"20m","memory":"80Mi"}},"roles":[],"serviceAccountTemplate":{},"services":{},"storage":{"size":"10Gi","storageClass":"local-path"},"superuserSecret":"","walStorage":{"enabled":true,"size":"2Gi","storageClass":"local-path"}}` | Cluster settings |
|
||||
| cluster | object | `{"additionalLabels":{},"affinity":{"enablePodAntiAffinity":true,"topologyKey":"kubernetes.io/hostname"},"annotations":{},"certificates":{},"enablePDB":true,"enableSuperuserAccess":false,"image":{"repository":"ghcr.io/cloudnative-pg/postgresql","tag":"18.3-standard-trixie"},"imagePullPolicy":"IfNotPresent","imagePullSecrets":[],"initdb":{"database":"app","owner":"app"},"instances":3,"logLevel":"info","monitoring":{"customQueries":[],"customQueriesSecret":[],"disableDefaultQueries":false,"enabled":true,"podMonitor":{"enabled":true,"metricRelabelings":[],"relabelings":[]},"prometheusRule":{"enabled":true,"excludeRules":["CNPGClusterLastFailedArchiveTimeWarning"]}},"postgresGID":-1,"postgresUID":-1,"postgresql":{"ldap":{},"parameters":{"hot_standby_feedback":"on","max_slot_wal_keep_size":"2000MB","shared_buffers":"512MB"},"pg_hba":[],"pg_ident":[],"shared_preload_libraries":[],"synchronous":{}},"primaryUpdateMethod":"switchover","primaryUpdateStrategy":"unsupervised","priorityClassName":"","resources":{"limits":{"hugepages-2Mi":"256Mi"},"requests":{"cpu":"20m","memory":"80Mi"}},"roles":[],"serviceAccountTemplate":{},"services":{},"storage":{"size":"10Gi","storageClass":"local-path"},"superuserSecret":"","walStorage":{"enabled":true,"size":"2Gi","storageClass":"local-path"}}` | Cluster settings |
|
||||
| cluster.affinity | object | `{"enablePodAntiAffinity":true,"topologyKey":"kubernetes.io/hostname"}` | Affinity/Anti-affinity rules for Pods. See: https://cloudnative-pg.io/documentation/current/cloudnative-pg.v1/#postgresql-cnpg-io-v1-AffinityConfiguration |
|
||||
| cluster.certificates | object | `{}` | The configuration for the CA and related certificates. See: https://cloudnative-pg.io/documentation/current/cloudnative-pg.v1/#postgresql-cnpg-io-v1-CertificatesConfiguration |
|
||||
| cluster.enablePDB | bool | `true` | Allow to disable PDB, mainly useful for upgrade of single-instance clusters or development purposes See: https://cloudnative-pg.io/documentation/current/kubernetes_upgrade/#pod-disruption-budgets |
|
||||
@@ -42,12 +42,13 @@ Cloudnative-pg Cluster
|
||||
| cluster.monitoring.podMonitor.enabled | bool | `true` | Whether to enable the PodMonitor |
|
||||
| cluster.monitoring.podMonitor.metricRelabelings | list | `[]` | The list of metric relabelings for the PodMonitor. Applied to samples before ingestion. |
|
||||
| cluster.monitoring.podMonitor.relabelings | list | `[]` | The list of relabelings for the PodMonitor. Applied to samples before scraping. |
|
||||
| cluster.monitoring.prometheusRule | object | `{"enabled":true,"excludeRules":["CNPGClusterLastFailedArchiveTimeWarning"]}` | Prometheus rule |
|
||||
| cluster.monitoring.prometheusRule.enabled | bool | `true` | Whether to enable the PrometheusRule automated alerts |
|
||||
| cluster.monitoring.prometheusRule.excludeRules | list | `["CNPGClusterLastFailedArchiveTimeWarning"]` | Exclude specified rules |
|
||||
| cluster.postgresUID | int | `-1` | The UID and GID of the postgres user inside the image, defaults to 26 |
|
||||
| cluster.postgresql | object | `{"ldap":{},"parameters":{"hot_standby_feedback":"on","max_slot_wal_keep_size":"2000MB","shared_buffers":"128MB"},"pg_hba":[],"pg_ident":[],"shared_preload_libraries":[],"synchronous":{}}` | Parameters to be set for the database itself See: https://cloudnative-pg.io/documentation/current/cloudnative-pg.v1/#postgresql-cnpg-io-v1-PostgresConfiguration |
|
||||
| cluster.postgresql | object | `{"ldap":{},"parameters":{"hot_standby_feedback":"on","max_slot_wal_keep_size":"2000MB","shared_buffers":"512MB"},"pg_hba":[],"pg_ident":[],"shared_preload_libraries":[],"synchronous":{}}` | Parameters to be set for the database itself See: https://cloudnative-pg.io/documentation/current/cloudnative-pg.v1/#postgresql-cnpg-io-v1-PostgresConfiguration |
|
||||
| cluster.postgresql.ldap | object | `{}` | PostgreSQL LDAP configuration (see https://cloudnative-pg.io/documentation/current/postgresql_conf/#ldap-configuration) |
|
||||
| cluster.postgresql.parameters | object | `{"hot_standby_feedback":"on","max_slot_wal_keep_size":"2000MB","shared_buffers":"128MB"}` | PostgreSQL configuration options (postgresql.conf) |
|
||||
| cluster.postgresql.parameters | object | `{"hot_standby_feedback":"on","max_slot_wal_keep_size":"2000MB","shared_buffers":"512MB"}` | PostgreSQL configuration options (postgresql.conf) |
|
||||
| cluster.postgresql.pg_hba | list | `[]` | PostgreSQL Host Based Authentication rules (lines to be appended to the pg_hba.conf file) |
|
||||
| cluster.postgresql.pg_ident | list | `[]` | PostgreSQL User Name Maps rules (lines to be appended to the pg_ident.conf file) |
|
||||
| cluster.postgresql.shared_preload_libraries | list | `[]` | Lists of shared preload libraries to add to the default ones |
|
||||
|
||||
@@ -0,0 +1,346 @@
|
||||
---
|
||||
# Source: postgres-cluster/templates/cluster.yaml
|
||||
apiVersion: postgresql.cnpg.io/v1
|
||||
kind: Cluster
|
||||
metadata:
|
||||
name: release-name-postgresql-18-cluster
|
||||
namespace: gitea
|
||||
labels:
|
||||
app.kubernetes.io/name: release-name-postgresql-18-cluster
|
||||
helm.sh/chart: postgres-cluster-7.13.1
|
||||
app.kubernetes.io/instance: release-name
|
||||
app.kubernetes.io/part-of: release-name
|
||||
app.kubernetes.io/version: "7.13.1"
|
||||
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: 20m
|
||||
memory: 80Mi
|
||||
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: false
|
||||
disableDefaultQueries: false
|
||||
|
||||
bootstrap:
|
||||
initdb:
|
||||
database: app
|
||||
owner: app
|
||||
---
|
||||
# Source: postgres-cluster/templates/pod-monitor.yaml
|
||||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: PodMonitor
|
||||
metadata:
|
||||
name: release-name-postgresql-18
|
||||
namespace: gitea
|
||||
labels:
|
||||
app.kubernetes.io/name: release-name-postgresql-18
|
||||
helm.sh/chart: postgres-cluster-7.13.1
|
||||
app.kubernetes.io/instance: release-name
|
||||
app.kubernetes.io/part-of: release-name
|
||||
app.kubernetes.io/version: "7.13.1"
|
||||
app.kubernetes.io/managed-by: Helm
|
||||
spec:
|
||||
selector:
|
||||
matchLabels:
|
||||
cnpg.io/cluster: release-name-postgresql-18
|
||||
cnpg.io/podRole: instance
|
||||
podMetricsEndpoints:
|
||||
- port: metrics
|
||||
---
|
||||
# Source: postgres-cluster/templates/prometheus-rule.yaml
|
||||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: PrometheusRule
|
||||
metadata:
|
||||
name: release-name-postgresql-18-alert-rules
|
||||
namespace: gitea
|
||||
labels:
|
||||
app.kubernetes.io/name: release-name-postgresql-18-alert-rules
|
||||
helm.sh/chart: postgres-cluster-7.13.1
|
||||
app.kubernetes.io/instance: release-name
|
||||
app.kubernetes.io/part-of: release-name
|
||||
app.kubernetes.io/version: "7.13.1"
|
||||
app.kubernetes.io/managed-by: Helm
|
||||
spec:
|
||||
groups:
|
||||
- name: cloudnative-pg/release-name-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="gitea"} > 300
|
||||
for: 1m
|
||||
labels:
|
||||
severity: warning
|
||||
namespace: gitea
|
||||
cnpg_cluster: release-name-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="gitea"} > 10
|
||||
for: 1m
|
||||
labels:
|
||||
severity: warning
|
||||
namespace: gitea
|
||||
cnpg_cluster: release-name-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="gitea"} - cnpg_pg_replication_is_wal_receiver_up{namespace="gitea"}) < 1
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
namespace: gitea
|
||||
cnpg_cluster: release-name-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="gitea"} - cnpg_pg_replication_is_wal_receiver_up{namespace="gitea"}) < 2
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
namespace: gitea
|
||||
cnpg_cluster: release-name-postgresql-18-cluster
|
||||
- alert: CNPGClusterHighConnectionsCritical
|
||||
annotations:
|
||||
summary: CNPG Instance maximum number of connections critical!
|
||||
description: |-
|
||||
CloudNativePG Cluster "gitea/release-name-postgresql-18-cluster" instance {{`{{`}} $labels.pod {{`}}`}} is using {{`{{`}} $value {{`}}`}}% of
|
||||
the maximum number of connections.
|
||||
runbook_url: https://github.com/cloudnative-pg/charts/blob/main/charts/cluster/docs/runbooks/CNPGClusterHighConnectionsCritical.md
|
||||
expr: |
|
||||
sum by (pod) (cnpg_backends_total{namespace="gitea", pod=~"release-name-postgresql-18-cluster-([1-9][0-9]*)$"}) / max by (pod) (cnpg_pg_settings_setting{name="max_connections", namespace="gitea", pod=~"release-name-postgresql-18-cluster-([1-9][0-9]*)$"}) * 100 > 95
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
namespace: gitea
|
||||
cnpg_cluster: release-name-postgresql-18-cluster
|
||||
- alert: CNPGClusterHighConnectionsWarning
|
||||
annotations:
|
||||
summary: CNPG Instance is approaching the maximum number of connections.
|
||||
description: |-
|
||||
CloudNativePG Cluster "gitea/release-name-postgresql-18-cluster" instance {{`{{`}} $labels.pod {{`}}`}} is using {{`{{`}} $value {{`}}`}}% of
|
||||
the maximum number of connections.
|
||||
runbook_url: https://github.com/cloudnative-pg/charts/blob/main/charts/cluster/docs/runbooks/CNPGClusterHighConnectionsWarning.md
|
||||
expr: |
|
||||
sum by (pod) (cnpg_backends_total{namespace="gitea", pod=~"release-name-postgresql-18-cluster-([1-9][0-9]*)$"}) / max by (pod) (cnpg_pg_settings_setting{name="max_connections", namespace="gitea", pod=~"release-name-postgresql-18-cluster-([1-9][0-9]*)$"}) * 100 > 80
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
namespace: gitea
|
||||
cnpg_cluster: release-name-postgresql-18-cluster
|
||||
- alert: CNPGClusterHighReplicationLag
|
||||
annotations:
|
||||
summary: CNPG Cluster high replication lag
|
||||
description: |-
|
||||
CloudNativePG Cluster "gitea/release-name-postgresql-18-cluster" is experiencing a high replication lag of
|
||||
{{`{{`}} $value {{`}}`}}ms.
|
||||
|
||||
High replication lag indicates network issues, busy instances, slow queries or suboptimal configuration.
|
||||
runbook_url: https://github.com/cloudnative-pg/charts/blob/main/charts/cluster/docs/runbooks/CNPGClusterHighReplicationLag.md
|
||||
expr: |
|
||||
max(cnpg_pg_replication_lag{namespace="gitea",pod=~"release-name-postgresql-18-cluster-([1-9][0-9]*)$"}) * 1000 > 1000
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
namespace: gitea
|
||||
cnpg_cluster: release-name-postgresql-18-cluster
|
||||
- alert: CNPGClusterInstancesOnSameNode
|
||||
annotations:
|
||||
summary: CNPG Cluster instances are located on the same node.
|
||||
description: |-
|
||||
CloudNativePG Cluster "gitea/release-name-postgresql-18-cluster" has {{`{{`}} $value {{`}}`}}
|
||||
instances on the same node {{`{{`}} $labels.node {{`}}`}}.
|
||||
|
||||
A failure or scheduled downtime of a single node will lead to a potential service disruption and/or data loss.
|
||||
runbook_url: https://github.com/cloudnative-pg/charts/blob/main/charts/cluster/docs/runbooks/CNPGClusterInstancesOnSameNode.md
|
||||
expr: |
|
||||
count by (node) (kube_pod_info{namespace="gitea", pod=~"release-name-postgresql-18-cluster-([1-9][0-9]*)$"}) > 1
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
namespace: gitea
|
||||
cnpg_cluster: release-name-postgresql-18-cluster
|
||||
- alert: CNPGClusterLongRunningTransactionWarning
|
||||
annotations:
|
||||
summary: CNPG Cluster query is taking longer than 5 minutes.
|
||||
description: |-
|
||||
CloudNativePG Cluster Pod {{ $labels.pod }}
|
||||
is taking more than 5 minutes (300 seconds) for a query.
|
||||
expr: |-
|
||||
cnpg_backends_max_tx_duration_seconds{namespace="gitea"} > 300
|
||||
for: 1m
|
||||
labels:
|
||||
severity: warning
|
||||
namespace: gitea
|
||||
cnpg_cluster: release-name-postgresql-18-cluster
|
||||
- alert: CNPGClusterLowDiskSpaceCritical
|
||||
annotations:
|
||||
summary: CNPG Instance is running out of disk space!
|
||||
description: |-
|
||||
CloudNativePG Cluster "gitea/release-name-postgresql-18-cluster" is running extremely low on disk space. Check attached PVCs!
|
||||
runbook_url: https://github.com/cloudnative-pg/charts/blob/main/charts/cluster/docs/runbooks/CNPGClusterLowDiskSpaceCritical.md
|
||||
expr: |
|
||||
max(max by(persistentvolumeclaim) (1 - kubelet_volume_stats_available_bytes{namespace="gitea", persistentvolumeclaim=~"release-name-postgresql-18-cluster-([1-9][0-9]*)$"} / kubelet_volume_stats_capacity_bytes{namespace="gitea", persistentvolumeclaim=~"release-name-postgresql-18-cluster-([1-9][0-9]*)$"})) > 0.9 OR
|
||||
max(max by(persistentvolumeclaim) (1 - kubelet_volume_stats_available_bytes{namespace="gitea", persistentvolumeclaim=~"release-name-postgresql-18-cluster-([1-9][0-9]*)$-wal"} / kubelet_volume_stats_capacity_bytes{namespace="gitea", persistentvolumeclaim=~"release-name-postgresql-18-cluster-([1-9][0-9]*)$-wal"})) > 0.9 OR
|
||||
max(sum by (namespace,persistentvolumeclaim) (kubelet_volume_stats_used_bytes{namespace="gitea", persistentvolumeclaim=~"release-name-postgresql-18-cluster-([1-9][0-9]*)$-tbs.*"})
|
||||
/
|
||||
sum by (namespace,persistentvolumeclaim) (kubelet_volume_stats_capacity_bytes{namespace="gitea", persistentvolumeclaim=~"release-name-postgresql-18-cluster-([1-9][0-9]*)$-tbs.*"})
|
||||
*
|
||||
on(namespace, persistentvolumeclaim) group_left(volume)
|
||||
kube_pod_spec_volumes_persistentvolumeclaims_info{pod=~"release-name-postgresql-18-cluster-([1-9][0-9]*)$"}
|
||||
) > 0.9
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
namespace: gitea
|
||||
cnpg_cluster: release-name-postgresql-18-cluster
|
||||
- alert: CNPGClusterLowDiskSpaceWarning
|
||||
annotations:
|
||||
summary: CNPG Instance is running out of disk space.
|
||||
description: |-
|
||||
CloudNativePG Cluster "gitea/release-name-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="gitea", persistentvolumeclaim=~"release-name-postgresql-18-cluster-([1-9][0-9]*)$"} / kubelet_volume_stats_capacity_bytes{namespace="gitea", persistentvolumeclaim=~"release-name-postgresql-18-cluster-([1-9][0-9]*)$"})) > 0.7 OR
|
||||
max(max by(persistentvolumeclaim) (1 - kubelet_volume_stats_available_bytes{namespace="gitea", persistentvolumeclaim=~"release-name-postgresql-18-cluster-([1-9][0-9]*)$-wal"} / kubelet_volume_stats_capacity_bytes{namespace="gitea", persistentvolumeclaim=~"release-name-postgresql-18-cluster-([1-9][0-9]*)$-wal"})) > 0.7 OR
|
||||
max(sum by (namespace,persistentvolumeclaim) (kubelet_volume_stats_used_bytes{namespace="gitea", persistentvolumeclaim=~"release-name-postgresql-18-cluster-([1-9][0-9]*)$-tbs.*"})
|
||||
/
|
||||
sum by (namespace,persistentvolumeclaim) (kubelet_volume_stats_capacity_bytes{namespace="gitea", persistentvolumeclaim=~"release-name-postgresql-18-cluster-([1-9][0-9]*)$-tbs.*"})
|
||||
*
|
||||
on(namespace, persistentvolumeclaim) group_left(volume)
|
||||
kube_pod_spec_volumes_persistentvolumeclaims_info{pod=~"release-name-postgresql-18-cluster-([1-9][0-9]*)$"}
|
||||
) > 0.7
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
namespace: gitea
|
||||
cnpg_cluster: release-name-postgresql-18-cluster
|
||||
- alert: CNPGClusterOffline
|
||||
annotations:
|
||||
summary: CNPG Cluster has no running instances!
|
||||
description: |-
|
||||
CloudNativePG Cluster "gitea/release-name-postgresql-18-cluster" has no ready instances.
|
||||
|
||||
Having an offline cluster means your applications will not be able to access the database, leading to
|
||||
potential service disruption and/or data loss.
|
||||
runbook_url: https://github.com/cloudnative-pg/charts/blob/main/charts/cluster/docs/runbooks/CNPGClusterOffline.md
|
||||
expr: |
|
||||
(count(cnpg_collector_up{namespace="gitea",pod=~"release-name-postgresql-18-cluster-([1-9][0-9]*)$"}) OR on() vector(0)) == 0
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
namespace: gitea
|
||||
cnpg_cluster: release-name-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="gitea"} > 300000000
|
||||
for: 1m
|
||||
labels:
|
||||
severity: warning
|
||||
namespace: gitea
|
||||
cnpg_cluster: release-name-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="gitea"} > 300
|
||||
for: 1m
|
||||
labels:
|
||||
severity: warning
|
||||
namespace: gitea
|
||||
cnpg_cluster: release-name-postgresql-18-cluster
|
||||
- alert: CNPGClusterReplicaFailingReplicationWarning
|
||||
annotations:
|
||||
summary: CNPG Cluster has a replica is failing to replicate.
|
||||
description: |-
|
||||
Replica {{ $labels.pod }}
|
||||
is failing to replicate
|
||||
expr: |
|
||||
cnpg_pg_replication_in_recovery{namespace="gitea"} > cnpg_pg_replication_is_wal_receiver_up{namespace="gitea"}
|
||||
for: 1m
|
||||
labels:
|
||||
severity: warning
|
||||
namespace: gitea
|
||||
cnpg_cluster: release-name-postgresql-18-cluster
|
||||
- alert: CNPGClusterZoneSpreadWarning
|
||||
annotations:
|
||||
summary: CNPG Cluster instances in the same zone.
|
||||
description: |-
|
||||
CloudNativePG Cluster "gitea/release-name-postgresql-18-cluster" has instances in the same availability zone.
|
||||
|
||||
A disaster in one availability zone will lead to a potential service disruption and/or data loss.
|
||||
runbook_url: https://github.com/cloudnative-pg/charts/blob/main/charts/cluster/docs/runbooks/CNPGClusterZoneSpreadWarning.md
|
||||
expr: |
|
||||
3 > count(count by (label_topology_kubernetes_io_zone) (kube_pod_info{namespace="gitea", pod=~"release-name-postgresql-18-cluster-([1-9][0-9]*)$"} * on(node,instance) group_left(label_topology_kubernetes_io_zone) kube_node_labels)) < 3
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
namespace: gitea
|
||||
cnpg_cluster: release-name-postgresql-18-cluster
|
||||
@@ -1,5 +1,4 @@
|
||||
{{- define "cluster.bootstrap" -}}
|
||||
|
||||
{{- define "cluster.bootstrap" }}
|
||||
{{- if eq .Values.mode "standalone" }}
|
||||
bootstrap:
|
||||
initdb:
|
||||
@@ -16,13 +15,11 @@ bootstrap:
|
||||
{{- with .Values.cluster.initdb }}
|
||||
{{- range .postInitApplicationSQL }}
|
||||
{{- printf "- %s" . | nindent 6 }}
|
||||
{{- end -}}
|
||||
{{- end }}
|
||||
{{- end }}
|
||||
|
||||
{{- else if eq .Values.mode "recovery" -}}
|
||||
{{- end }}
|
||||
{{- else if eq .Values.mode "recovery" }}
|
||||
bootstrap:
|
||||
|
||||
{{- if eq .Values.recovery.method "import" }}
|
||||
initdb:
|
||||
{{- with .Values.cluster.initdb }}
|
||||
@@ -66,7 +63,6 @@ bootstrap:
|
||||
pgRestoreExtraOptions:
|
||||
{{- . | toYaml | nindent 8 }}
|
||||
{{- end }}
|
||||
|
||||
{{- else if eq .Values.recovery.method "backup" }}
|
||||
recovery:
|
||||
{{- with .Values.recovery.backup.pitrTarget.time }}
|
||||
@@ -81,7 +77,6 @@ bootstrap:
|
||||
{{- end }}
|
||||
backup:
|
||||
name: {{ .Values.recovery.backup.backupName }}
|
||||
|
||||
{{- else if eq .Values.recovery.method "objectStore" }}
|
||||
recovery:
|
||||
{{- with .Values.recovery.objectStore.pitrTarget.time }}
|
||||
@@ -95,13 +90,10 @@ bootstrap:
|
||||
owner: {{ . }}
|
||||
{{- end }}
|
||||
source: {{ include "cluster.recoveryServerName" . }}
|
||||
|
||||
{{- else }}
|
||||
{{ fail "Invalid recovery mode!" }}
|
||||
{{- end }}
|
||||
|
||||
{{- else }}
|
||||
{{ fail "Invalid cluster mode!" }}
|
||||
{{- end }}
|
||||
|
||||
{{- end }}
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
{{- define "cluster.externalClusters" -}}
|
||||
{{- define "cluster.externalClusters" }}
|
||||
{{- if eq .Values.mode "standalone" }}
|
||||
{{- else if eq .Values.mode "recovery" }}
|
||||
externalClusters:
|
||||
@@ -18,4 +18,4 @@ externalClusters:
|
||||
{{- else }}
|
||||
{{ fail "Invalid cluster mode!" }}
|
||||
{{- end }}
|
||||
{{ end }}
|
||||
{{- end }}
|
||||
|
||||
@@ -30,4 +30,4 @@
|
||||
name: {{ $config.sslRootCertSecret.name }}
|
||||
key: {{ $config.sslRootCertSecret.key }}
|
||||
{{- end }}
|
||||
{{- end }}
|
||||
{{- end -}}
|
||||
|
||||
@@ -35,7 +35,7 @@ spec:
|
||||
{{- with .Values.cluster.resources }}
|
||||
resources:
|
||||
{{- toYaml . | nindent 4 }}
|
||||
{{ end }}
|
||||
{{- end }}
|
||||
{{- with .Values.cluster.affinity }}
|
||||
affinity:
|
||||
{{- toYaml . | nindent 4 }}
|
||||
@@ -43,7 +43,6 @@ spec:
|
||||
{{- if .Values.cluster.priorityClassName }}
|
||||
priorityClassName: {{ .Values.cluster.priorityClassName }}
|
||||
{{- end }}
|
||||
|
||||
primaryUpdateMethod: {{ .Values.cluster.primaryUpdateMethod }}
|
||||
primaryUpdateStrategy: {{ .Values.cluster.primaryUpdateStrategy }}
|
||||
logLevel: {{ .Values.cluster.logLevel }}
|
||||
@@ -57,7 +56,6 @@ spec:
|
||||
name: {{ . }}
|
||||
{{ end }}
|
||||
enablePDB: {{ .Values.cluster.enablePDB }}
|
||||
|
||||
postgresql:
|
||||
{{- if .Values.cluster.postgresql.shared_preload_libraries }}
|
||||
shared_preload_libraries:
|
||||
@@ -85,7 +83,6 @@ spec:
|
||||
parameters:
|
||||
{{- toYaml . | nindent 6 }}
|
||||
{{- end }}
|
||||
|
||||
{{- if not (and (empty .Values.cluster.roles) (empty .Values.cluster.services)) }}
|
||||
managed:
|
||||
{{- with .Values.cluster.services }}
|
||||
@@ -97,14 +94,12 @@ spec:
|
||||
{{- toYaml . | nindent 6 }}
|
||||
{{ end }}
|
||||
{{- end }}
|
||||
|
||||
{{- with .Values.cluster.serviceAccountTemplate }}
|
||||
serviceAccountTemplate:
|
||||
{{- toYaml . | nindent 4 }}
|
||||
{{- end }}
|
||||
|
||||
monitoring:
|
||||
enablePodMonitor: {{ and .Values.cluster.monitoring.enabled .Values.cluster.monitoring.podMonitor.enabled }}
|
||||
enablePodMonitor: false
|
||||
disableDefaultQueries: {{ .Values.cluster.monitoring.disableDefaultQueries }}
|
||||
{{- if not (empty .Values.cluster.monitoring.customQueries) }}
|
||||
customQueriesConfigMap:
|
||||
@@ -127,9 +122,9 @@ spec:
|
||||
{{- with .Values.cluster.monitoring.podMonitor.metricRelabelings }}
|
||||
podMonitorMetricRelabelings:
|
||||
{{- toYaml . | nindent 6 }}
|
||||
{{ end }}
|
||||
{{- end }}
|
||||
|
||||
{{- end }}
|
||||
{{- if not (empty .Values.backup.objectStore) -}}
|
||||
plugins:
|
||||
{{- range $objectStore := .Values.backup.objectStore }}
|
||||
- name: barman-cloud.cloudnative-pg.io
|
||||
@@ -146,7 +141,7 @@ spec:
|
||||
{{- else }}
|
||||
serverName: "{{ include "cluster.name" $ }}-backup-{{ $objectStore.index }}"
|
||||
{{- end }}
|
||||
{{- end }}
|
||||
|
||||
{{ include "cluster.bootstrap" . | nindent 2 }}
|
||||
{{ include "cluster.externalClusters" . | nindent 2 }}
|
||||
{{- end -}}
|
||||
{{- end -}}
|
||||
{{- include "cluster.bootstrap" . | nindent 2 -}}
|
||||
{{- include "cluster.externalClusters" . | nindent 2 -}}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{{ if and (eq .Values.backup.method "objectStore") (.Values.backup.externalSecret.enabled) }}
|
||||
{{ $context := . -}}
|
||||
{{ range .Values.backup.objectStore -}}
|
||||
{{- if and (eq .Values.backup.method "objectStore") (.Values.backup.externalSecret.enabled) }}
|
||||
{{- $context := . }}
|
||||
{{- range .Values.backup.objectStore }}
|
||||
---
|
||||
apiVersion: external-secrets.io/v1
|
||||
kind: ExternalSecret
|
||||
@@ -30,8 +30,8 @@ spec:
|
||||
remoteRef:
|
||||
key: {{ .externalSecretCredentialPath| required "External Secret Credential local path is required" }}
|
||||
property: ACCESS_SECRET_KEY
|
||||
{{ end -}}
|
||||
{{ end }}
|
||||
{{- end }}
|
||||
{{- end }}
|
||||
|
||||
{{- if and (eq .Values.recovery.method "objectStore") (.Values.recovery.objectStore.externalSecret.enabled) }}
|
||||
---
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{{ if (eq .Values.backup.method "objectStore") }}
|
||||
{{ $context := . -}}
|
||||
{{ range .Values.backup.objectStore -}}
|
||||
{{- if (eq .Values.backup.method "objectStore") }}
|
||||
{{- $context := . }}
|
||||
{{- range .Values.backup.objectStore }}
|
||||
---
|
||||
apiVersion: barmancloud.cnpg.io/v1
|
||||
kind: ObjectStore
|
||||
@@ -57,10 +57,9 @@ spec:
|
||||
region:
|
||||
name: {{ include "cluster.backupSecretName" (dict "instance" . "global" $context) }}
|
||||
key: ACCESS_REGION
|
||||
{{ end -}}
|
||||
{{ end }}
|
||||
|
||||
{{ if eq .Values.recovery.method "objectStore" }}
|
||||
{{- end }}
|
||||
{{- end }}
|
||||
{{- if eq .Values.recovery.method "objectStore" }}
|
||||
---
|
||||
apiVersion: barmancloud.cnpg.io/v1
|
||||
kind: ObjectStore
|
||||
@@ -104,4 +103,4 @@ spec:
|
||||
region:
|
||||
name: {{ include "cluster.recoverySecretName" . }}
|
||||
key: ACCESS_REGION
|
||||
{{ end }}
|
||||
{{- end }}
|
||||
|
||||
@@ -0,0 +1,18 @@
|
||||
{{- if and .Values.cluster.monitoring.enabled .Values.cluster.monitoring.podMonitor.enabled }}
|
||||
---
|
||||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: PodMonitor
|
||||
metadata:
|
||||
name: {{ include "cluster.name" $ }}
|
||||
namespace: {{ include "cluster.namespace" $ }}
|
||||
labels:
|
||||
app.kubernetes.io/name: {{ include "cluster.name" $ }}
|
||||
{{- include "cluster.labels" $ | nindent 4 }}
|
||||
spec:
|
||||
selector:
|
||||
matchLabels:
|
||||
cnpg.io/cluster: {{ include "cluster.name" $ }}
|
||||
cnpg.io/podRole: instance
|
||||
podMetricsEndpoints:
|
||||
- port: metrics
|
||||
{{- end }}
|
||||
@@ -47,6 +47,6 @@ spec:
|
||||
{{- end }}
|
||||
{{- with .template }}
|
||||
template:
|
||||
{{- . | toYaml | nindent 4 }}
|
||||
{{ . | toYaml | nindent 4 }}
|
||||
{{- end }}
|
||||
{{- end }}
|
||||
|
||||
@@ -1,4 +1,5 @@
|
||||
{{- if and .Values.cluster.monitoring.enabled .Values.cluster.monitoring.prometheusRule.enabled -}}
|
||||
{{- if and .Values.cluster.monitoring.enabled .Values.cluster.monitoring.prometheusRule.enabled }}
|
||||
---
|
||||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: PrometheusRule
|
||||
metadata:
|
||||
@@ -25,4 +26,4 @@ spec:
|
||||
- {{ $tpl }}
|
||||
{{- end -}}
|
||||
{{- end }}
|
||||
{{ end }}
|
||||
{{- end }}
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{{ $context := . -}}
|
||||
{{ range .Values.backup.scheduledBackups -}}
|
||||
{{- $context := . }}
|
||||
{{- range .Values.backup.scheduledBackups }}
|
||||
---
|
||||
apiVersion: postgresql.cnpg.io/v1
|
||||
kind: ScheduledBackup
|
||||
@@ -21,4 +21,4 @@ spec:
|
||||
name: {{ .plugin | default "barman-cloud.cloudnative-pg.io" }}
|
||||
parameters:
|
||||
barmanObjectName: "{{ include "cluster.name" $context }}-backup-{{ .backupName }}"
|
||||
{{ end -}}
|
||||
{{- end }}
|
||||
|
||||
@@ -127,6 +127,7 @@ cluster:
|
||||
# Applied to samples before ingestion.
|
||||
metricRelabelings: []
|
||||
|
||||
# -- Prometheus rule
|
||||
prometheusRule:
|
||||
|
||||
# -- Whether to enable the PrometheusRule automated alerts
|
||||
@@ -164,7 +165,7 @@ cluster:
|
||||
|
||||
# -- PostgreSQL configuration options (postgresql.conf)
|
||||
parameters:
|
||||
shared_buffers: 128MB
|
||||
shared_buffers: 512MB
|
||||
max_slot_wal_keep_size: 2000MB
|
||||
hot_standby_feedback: "on"
|
||||
|
||||
|
||||
Reference in New Issue
Block a user