chore: Update manifests after change
This commit is contained in:
@@ -1,79 +0,0 @@
|
|||||||
apiVersion: postgresql.cnpg.io/v1
|
|
||||||
kind: Cluster
|
|
||||||
metadata:
|
|
||||||
name: gitea-postgresql-17-cluster
|
|
||||||
namespace: gitea
|
|
||||||
labels:
|
|
||||||
helm.sh/chart: postgres-17-cluster-6.16.1
|
|
||||||
app.kubernetes.io/name: gitea-postgresql-17
|
|
||||||
app.kubernetes.io/instance: gitea
|
|
||||||
app.kubernetes.io/part-of: gitea
|
|
||||||
app.kubernetes.io/version: "6.16.1"
|
|
||||||
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: "gitea-postgresql-17-external-backup"
|
|
||||||
serverName: "gitea-postgresql-17-backup-1"
|
|
||||||
- name: barman-cloud.cloudnative-pg.io
|
|
||||||
enabled: true
|
|
||||||
isWALArchiver: true
|
|
||||||
parameters:
|
|
||||||
barmanObjectName: "gitea-postgresql-17-garage-local-backup"
|
|
||||||
serverName: "gitea-postgresql-17-backup-1"
|
|
||||||
externalClusters:
|
|
||||||
- name: recovery
|
|
||||||
plugin:
|
|
||||||
name: barman-cloud.cloudnative-pg.io
|
|
||||||
parameters:
|
|
||||||
barmanObjectName: "gitea-postgresql-17-recovery"
|
|
||||||
serverName: gitea-postgresql-17-backup-1
|
|
||||||
storage:
|
|
||||||
size: 10Gi
|
|
||||||
storageClass: local-path
|
|
||||||
walStorage:
|
|
||||||
size: 2Gi
|
|
||||||
storageClass: local-path
|
|
||||||
resources:
|
|
||||||
limits:
|
|
||||||
hugepages-2Mi: 256Mi
|
|
||||||
requests:
|
|
||||||
cpu: 200m
|
|
||||||
memory: 1Gi
|
|
||||||
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: gitea-postgresql-17-backup-1
|
|
||||||
externalClusters:
|
|
||||||
- name: gitea-postgresql-17-backup-1
|
|
||||||
plugin:
|
|
||||||
name: barman-cloud.cloudnative-pg.io
|
|
||||||
enabled: true
|
|
||||||
isWALArchiver: false
|
|
||||||
parameters:
|
|
||||||
barmanObjectName: "gitea-postgresql-17-recovery"
|
|
||||||
serverName: gitea-postgresql-17-backup-1
|
|
||||||
@@ -1,35 +0,0 @@
|
|||||||
apiVersion: external-secrets.io/v1
|
|
||||||
kind: ExternalSecret
|
|
||||||
metadata:
|
|
||||||
name: gitea-postgresql-17-cluster-backup-secret-garage
|
|
||||||
namespace: gitea
|
|
||||||
labels:
|
|
||||||
app.kubernetes.io/name: gitea-postgresql-17-cluster-backup-secret-garage
|
|
||||||
app.kubernetes.io/instance: gitea
|
|
||||||
app.kubernetes.io/part-of: gitea
|
|
||||||
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
|
|
||||||
@@ -1,28 +0,0 @@
|
|||||||
apiVersion: external-secrets.io/v1
|
|
||||||
kind: ExternalSecret
|
|
||||||
metadata:
|
|
||||||
name: gitea-postgresql-17-cluster-backup-secret
|
|
||||||
namespace: gitea
|
|
||||||
labels:
|
|
||||||
app.kubernetes.io/name: gitea-postgresql-17-cluster-backup-secret
|
|
||||||
app.kubernetes.io/instance: gitea
|
|
||||||
app.kubernetes.io/part-of: gitea
|
|
||||||
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
|
|
||||||
@@ -1,24 +0,0 @@
|
|||||||
apiVersion: barmancloud.cnpg.io/v1
|
|
||||||
kind: ObjectStore
|
|
||||||
metadata:
|
|
||||||
name: "gitea-postgresql-17-external-backup"
|
|
||||||
namespace: gitea
|
|
||||||
labels:
|
|
||||||
helm.sh/chart: postgres-17-cluster-6.16.1
|
|
||||||
app.kubernetes.io/name: gitea-postgresql-17
|
|
||||||
app.kubernetes.io/instance: gitea
|
|
||||||
app.kubernetes.io/part-of: gitea
|
|
||||||
app.kubernetes.io/version: "6.16.1"
|
|
||||||
app.kubernetes.io/managed-by: Helm
|
|
||||||
spec:
|
|
||||||
retentionPolicy: 30d
|
|
||||||
configuration:
|
|
||||||
destinationPath: s3://postgres-backups-ce540ddf106d186bbddca68a/cl01tl/gitea/gitea-postgresql-17-cluster
|
|
||||||
endpointURL: https://nyc3.digitaloceanspaces.com
|
|
||||||
s3Credentials:
|
|
||||||
accessKeyId:
|
|
||||||
name: gitea-postgresql-17-cluster-backup-secret
|
|
||||||
key: ACCESS_KEY_ID
|
|
||||||
secretAccessKey:
|
|
||||||
name: gitea-postgresql-17-cluster-backup-secret
|
|
||||||
key: ACCESS_SECRET_KEY
|
|
||||||
@@ -1,27 +0,0 @@
|
|||||||
apiVersion: barmancloud.cnpg.io/v1
|
|
||||||
kind: ObjectStore
|
|
||||||
metadata:
|
|
||||||
name: "gitea-postgresql-17-garage-local-backup"
|
|
||||||
namespace: gitea
|
|
||||||
labels:
|
|
||||||
helm.sh/chart: postgres-17-cluster-6.16.1
|
|
||||||
app.kubernetes.io/name: gitea-postgresql-17
|
|
||||||
app.kubernetes.io/instance: gitea
|
|
||||||
app.kubernetes.io/part-of: gitea
|
|
||||||
app.kubernetes.io/version: "6.16.1"
|
|
||||||
app.kubernetes.io/managed-by: Helm
|
|
||||||
spec:
|
|
||||||
retentionPolicy: 3d
|
|
||||||
configuration:
|
|
||||||
destinationPath: s3://postgres-backups/cl01tl/gitea/gitea-postgresql-17-cluster
|
|
||||||
endpointURL: http://garage-main.garage:3900
|
|
||||||
s3Credentials:
|
|
||||||
accessKeyId:
|
|
||||||
name: gitea-postgresql-17-cluster-backup-secret-garage
|
|
||||||
key: ACCESS_KEY_ID
|
|
||||||
secretAccessKey:
|
|
||||||
name: gitea-postgresql-17-cluster-backup-secret-garage
|
|
||||||
key: ACCESS_SECRET_KEY
|
|
||||||
region:
|
|
||||||
name: gitea-postgresql-17-cluster-backup-secret-garage
|
|
||||||
key: ACCESS_REGION
|
|
||||||
@@ -1,29 +0,0 @@
|
|||||||
apiVersion: barmancloud.cnpg.io/v1
|
|
||||||
kind: ObjectStore
|
|
||||||
metadata:
|
|
||||||
name: "gitea-postgresql-17-recovery"
|
|
||||||
namespace: gitea
|
|
||||||
labels:
|
|
||||||
helm.sh/chart: postgres-17-cluster-6.16.1
|
|
||||||
app.kubernetes.io/name: gitea-postgresql-17
|
|
||||||
app.kubernetes.io/instance: gitea
|
|
||||||
app.kubernetes.io/part-of: gitea
|
|
||||||
app.kubernetes.io/version: "6.16.1"
|
|
||||||
app.kubernetes.io/managed-by: Helm
|
|
||||||
spec:
|
|
||||||
configuration:
|
|
||||||
destinationPath: s3://postgres-backups/cl01tl/gitea/gitea-postgresql-17-cluster
|
|
||||||
endpointURL: http://garage-main.garage:3900
|
|
||||||
wal:
|
|
||||||
compression: snappy
|
|
||||||
maxParallel: 1
|
|
||||||
data:
|
|
||||||
compression: snappy
|
|
||||||
jobs: 1
|
|
||||||
s3Credentials:
|
|
||||||
accessKeyId:
|
|
||||||
name: gitea-postgresql-17-cluster-backup-secret-garage
|
|
||||||
key: ACCESS_KEY_ID
|
|
||||||
secretAccessKey:
|
|
||||||
name: gitea-postgresql-17-cluster-backup-secret-garage
|
|
||||||
key: ACCESS_SECRET_KEY
|
|
||||||
@@ -1,270 +0,0 @@
|
|||||||
apiVersion: monitoring.coreos.com/v1
|
|
||||||
kind: PrometheusRule
|
|
||||||
metadata:
|
|
||||||
name: gitea-postgresql-17-alert-rules
|
|
||||||
namespace: gitea
|
|
||||||
labels:
|
|
||||||
helm.sh/chart: postgres-17-cluster-6.16.1
|
|
||||||
app.kubernetes.io/name: gitea-postgresql-17
|
|
||||||
app.kubernetes.io/instance: gitea
|
|
||||||
app.kubernetes.io/part-of: gitea
|
|
||||||
app.kubernetes.io/version: "6.16.1"
|
|
||||||
app.kubernetes.io/managed-by: Helm
|
|
||||||
spec:
|
|
||||||
groups:
|
|
||||||
- name: cloudnative-pg/gitea-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: gitea
|
|
||||||
cnpg_cluster: gitea-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: gitea
|
|
||||||
cnpg_cluster: gitea-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="gitea"} - cnpg_pg_replication_is_wal_receiver_up{namespace="gitea"}) < 1
|
|
||||||
for: 5m
|
|
||||||
labels:
|
|
||||||
severity: critical
|
|
||||||
namespace: gitea
|
|
||||||
cnpg_cluster: gitea-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="gitea"} - cnpg_pg_replication_is_wal_receiver_up{namespace="gitea"}) < 2
|
|
||||||
for: 5m
|
|
||||||
labels:
|
|
||||||
severity: warning
|
|
||||||
namespace: gitea
|
|
||||||
cnpg_cluster: gitea-postgresql-17-cluster
|
|
||||||
- alert: CNPGClusterHighConnectionsCritical
|
|
||||||
annotations:
|
|
||||||
summary: CNPG Instance maximum number of connections critical!
|
|
||||||
description: |-
|
|
||||||
CloudNativePG Cluster "gitea/gitea-postgresql-17-cluster" instance {{`{{`}} $labels.pod {{`}}`}} is using {{`{{`}} $value {{`}}`}}% of
|
|
||||||
the maximum number of connections.
|
|
||||||
runbook_url: https://github.com/cloudnative-pg/charts/blob/main/charts/cluster/docs/runbooks/CNPGClusterHighConnectionsCritical.md
|
|
||||||
expr: |
|
|
||||||
sum by (pod) (cnpg_backends_total{namespace="gitea", pod=~"gitea-postgresql-17-cluster-([1-9][0-9]*)$"}) / max by (pod) (cnpg_pg_settings_setting{name="max_connections", namespace="gitea", pod=~"gitea-postgresql-17-cluster-([1-9][0-9]*)$"}) * 100 > 95
|
|
||||||
for: 5m
|
|
||||||
labels:
|
|
||||||
severity: critical
|
|
||||||
namespace: gitea
|
|
||||||
cnpg_cluster: gitea-postgresql-17-cluster
|
|
||||||
- alert: CNPGClusterHighConnectionsWarning
|
|
||||||
annotations:
|
|
||||||
summary: CNPG Instance is approaching the maximum number of connections.
|
|
||||||
description: |-
|
|
||||||
CloudNativePG Cluster "gitea/gitea-postgresql-17-cluster" instance {{`{{`}} $labels.pod {{`}}`}} is using {{`{{`}} $value {{`}}`}}% of
|
|
||||||
the maximum number of connections.
|
|
||||||
runbook_url: https://github.com/cloudnative-pg/charts/blob/main/charts/cluster/docs/runbooks/CNPGClusterHighConnectionsWarning.md
|
|
||||||
expr: |
|
|
||||||
sum by (pod) (cnpg_backends_total{namespace="gitea", pod=~"gitea-postgresql-17-cluster-([1-9][0-9]*)$"}) / max by (pod) (cnpg_pg_settings_setting{name="max_connections", namespace="gitea", pod=~"gitea-postgresql-17-cluster-([1-9][0-9]*)$"}) * 100 > 80
|
|
||||||
for: 5m
|
|
||||||
labels:
|
|
||||||
severity: warning
|
|
||||||
namespace: gitea
|
|
||||||
cnpg_cluster: gitea-postgresql-17-cluster
|
|
||||||
- alert: CNPGClusterHighReplicationLag
|
|
||||||
annotations:
|
|
||||||
summary: CNPG Cluster high replication lag
|
|
||||||
description: |-
|
|
||||||
CloudNativePG Cluster "gitea/gitea-postgresql-17-cluster" is experiencing a high replication lag of
|
|
||||||
{{`{{`}} $value {{`}}`}}ms.
|
|
||||||
|
|
||||||
High replication lag indicates network issues, busy instances, slow queries or suboptimal configuration.
|
|
||||||
runbook_url: https://github.com/cloudnative-pg/charts/blob/main/charts/cluster/docs/runbooks/CNPGClusterHighReplicationLag.md
|
|
||||||
expr: |
|
|
||||||
max(cnpg_pg_replication_lag{namespace="gitea",pod=~"gitea-postgresql-17-cluster-([1-9][0-9]*)$"}) * 1000 > 1000
|
|
||||||
for: 5m
|
|
||||||
labels:
|
|
||||||
severity: warning
|
|
||||||
namespace: gitea
|
|
||||||
cnpg_cluster: gitea-postgresql-17-cluster
|
|
||||||
- alert: CNPGClusterInstancesOnSameNode
|
|
||||||
annotations:
|
|
||||||
summary: CNPG Cluster instances are located on the same node.
|
|
||||||
description: |-
|
|
||||||
CloudNativePG Cluster "gitea/gitea-postgresql-17-cluster" has {{`{{`}} $value {{`}}`}}
|
|
||||||
instances on the same node {{`{{`}} $labels.node {{`}}`}}.
|
|
||||||
|
|
||||||
A failure or scheduled downtime of a single node will lead to a potential service disruption and/or data loss.
|
|
||||||
runbook_url: https://github.com/cloudnative-pg/charts/blob/main/charts/cluster/docs/runbooks/CNPGClusterInstancesOnSameNode.md
|
|
||||||
expr: |
|
|
||||||
count by (node) (kube_pod_info{namespace="gitea", pod=~"gitea-postgresql-17-cluster-([1-9][0-9]*)$"}) > 1
|
|
||||||
for: 5m
|
|
||||||
labels:
|
|
||||||
severity: warning
|
|
||||||
namespace: gitea
|
|
||||||
cnpg_cluster: gitea-postgresql-17-cluster
|
|
||||||
- alert: CNPGClusterLongRunningTransactionWarning
|
|
||||||
annotations:
|
|
||||||
summary: CNPG Cluster query is taking longer than 5 minutes.
|
|
||||||
description: |-
|
|
||||||
CloudNativePG Cluster Pod {{ $labels.pod }}
|
|
||||||
is taking more than 5 minutes (300 seconds) for a query.
|
|
||||||
expr: |-
|
|
||||||
cnpg_backends_max_tx_duration_seconds > 300
|
|
||||||
for: 1m
|
|
||||||
labels:
|
|
||||||
severity: warning
|
|
||||||
namespace: gitea
|
|
||||||
cnpg_cluster: gitea-postgresql-17-cluster
|
|
||||||
- alert: CNPGClusterLowDiskSpaceCritical
|
|
||||||
annotations:
|
|
||||||
summary: CNPG Instance is running out of disk space!
|
|
||||||
description: |-
|
|
||||||
CloudNativePG Cluster "gitea/gitea-postgresql-17-cluster" is running extremely low on disk space. Check attached PVCs!
|
|
||||||
runbook_url: https://github.com/cloudnative-pg/charts/blob/main/charts/cluster/docs/runbooks/CNPGClusterLowDiskSpaceCritical.md
|
|
||||||
expr: |
|
|
||||||
max(max by(persistentvolumeclaim) (1 - kubelet_volume_stats_available_bytes{namespace="gitea", persistentvolumeclaim=~"gitea-postgresql-17-cluster-([1-9][0-9]*)$"} / kubelet_volume_stats_capacity_bytes{namespace="gitea", persistentvolumeclaim=~"gitea-postgresql-17-cluster-([1-9][0-9]*)$"})) > 0.9 OR
|
|
||||||
max(max by(persistentvolumeclaim) (1 - kubelet_volume_stats_available_bytes{namespace="gitea", persistentvolumeclaim=~"gitea-postgresql-17-cluster-([1-9][0-9]*)$-wal"} / kubelet_volume_stats_capacity_bytes{namespace="gitea", persistentvolumeclaim=~"gitea-postgresql-17-cluster-([1-9][0-9]*)$-wal"})) > 0.9 OR
|
|
||||||
max(sum by (namespace,persistentvolumeclaim) (kubelet_volume_stats_used_bytes{namespace="gitea", persistentvolumeclaim=~"gitea-postgresql-17-cluster-([1-9][0-9]*)$-tbs.*"})
|
|
||||||
/
|
|
||||||
sum by (namespace,persistentvolumeclaim) (kubelet_volume_stats_capacity_bytes{namespace="gitea", persistentvolumeclaim=~"gitea-postgresql-17-cluster-([1-9][0-9]*)$-tbs.*"})
|
|
||||||
*
|
|
||||||
on(namespace, persistentvolumeclaim) group_left(volume)
|
|
||||||
kube_pod_spec_volumes_persistentvolumeclaims_info{pod=~"gitea-postgresql-17-cluster-([1-9][0-9]*)$"}
|
|
||||||
) > 0.9
|
|
||||||
for: 5m
|
|
||||||
labels:
|
|
||||||
severity: critical
|
|
||||||
namespace: gitea
|
|
||||||
cnpg_cluster: gitea-postgresql-17-cluster
|
|
||||||
- alert: CNPGClusterLowDiskSpaceWarning
|
|
||||||
annotations:
|
|
||||||
summary: CNPG Instance is running out of disk space.
|
|
||||||
description: |-
|
|
||||||
CloudNativePG Cluster "gitea/gitea-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="gitea", persistentvolumeclaim=~"gitea-postgresql-17-cluster-([1-9][0-9]*)$"} / kubelet_volume_stats_capacity_bytes{namespace="gitea", persistentvolumeclaim=~"gitea-postgresql-17-cluster-([1-9][0-9]*)$"})) > 0.7 OR
|
|
||||||
max(max by(persistentvolumeclaim) (1 - kubelet_volume_stats_available_bytes{namespace="gitea", persistentvolumeclaim=~"gitea-postgresql-17-cluster-([1-9][0-9]*)$-wal"} / kubelet_volume_stats_capacity_bytes{namespace="gitea", persistentvolumeclaim=~"gitea-postgresql-17-cluster-([1-9][0-9]*)$-wal"})) > 0.7 OR
|
|
||||||
max(sum by (namespace,persistentvolumeclaim) (kubelet_volume_stats_used_bytes{namespace="gitea", persistentvolumeclaim=~"gitea-postgresql-17-cluster-([1-9][0-9]*)$-tbs.*"})
|
|
||||||
/
|
|
||||||
sum by (namespace,persistentvolumeclaim) (kubelet_volume_stats_capacity_bytes{namespace="gitea", persistentvolumeclaim=~"gitea-postgresql-17-cluster-([1-9][0-9]*)$-tbs.*"})
|
|
||||||
*
|
|
||||||
on(namespace, persistentvolumeclaim) group_left(volume)
|
|
||||||
kube_pod_spec_volumes_persistentvolumeclaims_info{pod=~"gitea-postgresql-17-cluster-([1-9][0-9]*)$"}
|
|
||||||
) > 0.7
|
|
||||||
for: 5m
|
|
||||||
labels:
|
|
||||||
severity: warning
|
|
||||||
namespace: gitea
|
|
||||||
cnpg_cluster: gitea-postgresql-17-cluster
|
|
||||||
- alert: CNPGClusterOffline
|
|
||||||
annotations:
|
|
||||||
summary: CNPG Cluster has no running instances!
|
|
||||||
description: |-
|
|
||||||
CloudNativePG Cluster "gitea/gitea-postgresql-17-cluster" has no ready instances.
|
|
||||||
|
|
||||||
Having an offline cluster means your applications will not be able to access the database, leading to
|
|
||||||
potential service disruption and/or data loss.
|
|
||||||
runbook_url: https://github.com/cloudnative-pg/charts/blob/main/charts/cluster/docs/runbooks/CNPGClusterOffline.md
|
|
||||||
expr: |
|
|
||||||
(count(cnpg_collector_up{namespace="gitea",pod=~"gitea-postgresql-17-cluster-([1-9][0-9]*)$"}) OR on() vector(0)) == 0
|
|
||||||
for: 5m
|
|
||||||
labels:
|
|
||||||
severity: critical
|
|
||||||
namespace: gitea
|
|
||||||
cnpg_cluster: gitea-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: gitea
|
|
||||||
cnpg_cluster: gitea-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: gitea
|
|
||||||
cnpg_cluster: gitea-postgresql-17-cluster
|
|
||||||
- alert: CNPGClusterReplicaFailingReplicationWarning
|
|
||||||
annotations:
|
|
||||||
summary: CNPG Cluster has a replica is failing to replicate.
|
|
||||||
description: |-
|
|
||||||
Replica {{ $labels.pod }}
|
|
||||||
is failing to replicate
|
|
||||||
expr: |
|
|
||||||
cnpg_pg_replication_in_recovery > cnpg_pg_replication_is_wal_receiver_up
|
|
||||||
for: 1m
|
|
||||||
labels:
|
|
||||||
severity: warning
|
|
||||||
namespace: gitea
|
|
||||||
cnpg_cluster: gitea-postgresql-17-cluster
|
|
||||||
- alert: CNPGClusterZoneSpreadWarning
|
|
||||||
annotations:
|
|
||||||
summary: CNPG Cluster instances in the same zone.
|
|
||||||
description: |-
|
|
||||||
CloudNativePG Cluster "gitea/gitea-postgresql-17-cluster" has instances in the same availability zone.
|
|
||||||
|
|
||||||
A disaster in one availability zone will lead to a potential service disruption and/or data loss.
|
|
||||||
runbook_url: https://github.com/cloudnative-pg/charts/blob/main/charts/cluster/docs/runbooks/CNPGClusterZoneSpreadWarning.md
|
|
||||||
expr: |
|
|
||||||
3 > count(count by (label_topology_kubernetes_io_zone) (kube_pod_info{namespace="gitea", pod=~"gitea-postgresql-17-cluster-([1-9][0-9]*)$"} * on(node,instance) group_left(label_topology_kubernetes_io_zone) kube_node_labels)) < 3
|
|
||||||
for: 5m
|
|
||||||
labels:
|
|
||||||
severity: warning
|
|
||||||
namespace: gitea
|
|
||||||
cnpg_cluster: gitea-postgresql-17-cluster
|
|
||||||
@@ -1,24 +0,0 @@
|
|||||||
apiVersion: postgresql.cnpg.io/v1
|
|
||||||
kind: ScheduledBackup
|
|
||||||
metadata:
|
|
||||||
name: "gitea-postgresql-17-daily-backup-scheduled-backup"
|
|
||||||
namespace: gitea
|
|
||||||
labels:
|
|
||||||
helm.sh/chart: postgres-17-cluster-6.16.1
|
|
||||||
app.kubernetes.io/name: gitea-postgresql-17
|
|
||||||
app.kubernetes.io/instance: gitea
|
|
||||||
app.kubernetes.io/part-of: gitea
|
|
||||||
app.kubernetes.io/version: "6.16.1"
|
|
||||||
app.kubernetes.io/managed-by: Helm
|
|
||||||
spec:
|
|
||||||
immediate: false
|
|
||||||
suspend: false
|
|
||||||
schedule: "0 0 0 * * *"
|
|
||||||
backupOwnerReference: self
|
|
||||||
cluster:
|
|
||||||
name: gitea-postgresql-17-cluster
|
|
||||||
method: plugin
|
|
||||||
pluginConfiguration:
|
|
||||||
name: barman-cloud.cloudnative-pg.io
|
|
||||||
parameters:
|
|
||||||
barmanObjectName: "gitea-postgresql-17-external-backup"
|
|
||||||
@@ -1,24 +0,0 @@
|
|||||||
apiVersion: postgresql.cnpg.io/v1
|
|
||||||
kind: ScheduledBackup
|
|
||||||
metadata:
|
|
||||||
name: "gitea-postgresql-17-live-backup-scheduled-backup"
|
|
||||||
namespace: gitea
|
|
||||||
labels:
|
|
||||||
helm.sh/chart: postgres-17-cluster-6.16.1
|
|
||||||
app.kubernetes.io/name: gitea-postgresql-17
|
|
||||||
app.kubernetes.io/instance: gitea
|
|
||||||
app.kubernetes.io/part-of: gitea
|
|
||||||
app.kubernetes.io/version: "6.16.1"
|
|
||||||
app.kubernetes.io/managed-by: Helm
|
|
||||||
spec:
|
|
||||||
immediate: true
|
|
||||||
suspend: false
|
|
||||||
schedule: "0 0 0 * * *"
|
|
||||||
backupOwnerReference: self
|
|
||||||
cluster:
|
|
||||||
name: gitea-postgresql-17-cluster
|
|
||||||
method: plugin
|
|
||||||
pluginConfiguration:
|
|
||||||
name: barman-cloud.cloudnative-pg.io
|
|
||||||
parameters:
|
|
||||||
barmanObjectName: "gitea-postgresql-17-garage-local-backup"
|
|
||||||
Reference in New Issue
Block a user