feat: add cloudnative-pg-mixin

Author: arikgrahl

cloudnative-pg-mixin/Makefile

@@ -0,0 +1 @@
+include ../Makefile_mixin

cloudnative-pg-mixin/README.md

@@ -0,0 +1,25 @@
+# CloudNativePG Mixin
+
+A monitoring mixin for [CloudNativePG](https://cloudnative-pg.io), providing Grafana dashboards and Prometheus alerting rules for PostgreSQL clusters running on Kubernetes.
+
+## Dashboards
+
+This mixin bundles the [Grafana dashboard provided by CloudNativePG](https://github.com/cloudnative-pg/grafana-dashboards/blob/cececeb393fb7c5400b4fa290aca68041293a127/charts/cluster/grafana-dashboard.json).
+
+<picture>
+  <source media="(prefers-color-scheme: dark)" srcset="images/dashboard-dark.png">
+  <source media="(prefers-color-scheme: light)" srcset="images/dashboard-light.png">
+  <img alt="CloudNativePG Dashboard" src="images/dashboard-light.png">
+</picture>
+
+## Prometheus Alerts
+
+This mixin bundles the sample [Prometheus Alert rules provided by CloudNativePG](https://github.com/cloudnative-pg/cloudnative-pg/blob/b7e9f07cf6fa2181bc5c9b8e82d4b37b27ee92ba/docs/src/samples/monitoring/alerts.yaml).
+
+- `LongRunningTransaction`: A query is taking longer than 5 minutes.
+- `BackendsWaiting`: If a backend is waiting for longer than 5 minutes
+- `PGDatabase`: Number of transactions from the frozen XID to the current one
+- `PGReplication`: The standby is lagging behind the primary
+- `LastFailedArchiveTime`: Checks the last time archiving failed. Will be < 0 when it has not failed.
+- `DatabaseDeadlockConflicts`: Checks the number of database conflicts
+- `ReplicaFailingReplication`: Checks if the replica is failing to replicate

cloudnative-pg-mixin/alerts/alerts.yaml

@@ -0,0 +1,66 @@
+groups:
+- name: cnp-default.rules
+  rules:
+  - alert: LongRunningTransaction
+    annotations:
+      description: Pod {{ $labels.pod }} is taking more than 5 minutes (300 seconds) for a query.
+      summary: A query is taking longer than 5 minutes.
+    expr: |-
+      cnpg_backends_max_tx_duration_seconds > 300
+    for: 1m
+    labels:
+      severity: warning
+  - alert: BackendsWaiting
+    annotations:
+      description: Pod {{ $labels.pod  }} has been waiting for longer than 5 minutes
+      summary: If a backend is waiting for longer than 5 minutes
+    expr: |-
+      cnpg_backends_waiting_total > 300
+    for: 1m
+    labels:
+      severity: warning
+  - alert: PGDatabase
+    annotations:
+      description: Over 300,000,000 transactions from frozen xid on pod {{ $labels.pod  }}
+      summary: Number of transactions from the frozen XID to the current one
+    expr: |-
+      cnpg_pg_database_xid_age > 300000000
+    for: 1m
+    labels:
+      severity: warning
+  - alert: PGReplication
+    annotations:
+      description: Standby is lagging behind by over 300 seconds (5 minutes)
+      summary: The standby is lagging behind the primary
+    expr: |-
+      cnpg_pg_replication_lag > 300
+    for: 1m
+    labels:
+      severity: warning
+  - alert: LastFailedArchiveTime 
+    annotations:
+      description: Archiving failed for {{ $labels.pod }}
+      summary: Checks the last time archiving failed. Will be < 0 when it has not failed.
+    expr: |-
+      (cnpg_pg_stat_archiver_last_failed_time - cnpg_pg_stat_archiver_last_archived_time) > 1
+    for: 1m
+    labels:
+      severity: warning
+  - alert: DatabaseDeadlockConflicts 
+    annotations:
+      description: There are over 10 deadlock conflicts in {{ $labels.pod }}
+      summary: Checks the number of database conflicts
+    expr: |-
+      cnpg_pg_stat_database_deadlocks > 10
+    for: 1m
+    labels:
+      severity: warning
+  - alert: ReplicaFailingReplication
+    annotations:
+      description: Replica {{ $labels.pod }} is failing to replicate
+      summary: Checks if the replica is failing to replicate
+    expr: |-
+      cnpg_pg_replication_in_recovery > cnpg_pg_replication_is_wal_receiver_up
+    for: 1m
+    labels:
+      severity: warning