cluster

commit 292204597319bddd3b5f20898b76dc78db14c19c
parent 5f1ef1bda0a9f6cfc3390297e4c3ef49df96df63
Author: MTRNord <MTRNord@users.noreply.github.com>
Date:   Fri,  6 Mar 2026 10:41:37 +0100

velero alerts and ignore velero namespace

Signed-off-by: MTRNord <MTRNord@users.noreply.github.com>

Diffstat:
M
infrastructure_talos/configs/kustomization.yaml
 | 
1
+
A
infrastructure_talos/configs/velero-alerts.yaml
 | 
40
++++++++++++++++++++++++++++++++++++++++
M
infrastructure_talos/configs/velero-schedules.yaml
 | 
8
++++++++

3 files changed, 49 insertions(+), 0 deletions(-)
diff --git a/infrastructure_talos/configs/kustomization.yaml b/infrastructure_talos/configs/kustomization.yaml
@@ -8,3 +8,4 @@ resources:
   - cnpg-base.yaml
   - cnpg-cluster.yaml
   - velero-schedules.yaml
+  - velero-alerts.yaml
diff --git a/infrastructure_talos/configs/velero-alerts.yaml b/infrastructure_talos/configs/velero-alerts.yaml
@@ -0,0 +1,40 @@
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  name: velero-alerts
+  namespace: velero
+  labels:
+    release: prometheus-stack
+spec:
+  groups:
+    - name: velero
+      rules:
+        - alert: VeleroBackupPartialFailure
+          expr: |
+            increase(velero_backup_partial_failure_total{schedule!=""}[1h]) > 0
+          for: 15m
+          labels:
+            severity: warning
+          annotations:
+            summary: "Velero backup partially failed"
+            description: "Schedule {{ $labels.schedule }} has partial failures in the last hour."
+
+        - alert: VeleroBackupFailure
+          expr: |
+            increase(velero_backup_failure_total{schedule!=""}[1h]) > 0
+          for: 5m
+          labels:
+            severity: critical
+          annotations:
+            summary: "Velero backup failed"
+            description: "Schedule {{ $labels.schedule }} backup failed in the last hour."
+
+        - alert: VeleroBackupMissing
+          expr: |
+            time() - velero_backup_last_successful_timestamp{schedule!=""} > 43200
+          for: 5m
+          labels:
+            severity: critical
+          annotations:
+            summary: "Velero backup missing for 12h"
+            description: "Schedule {{ $labels.schedule }} has no successful backup in the last 12 hours."
diff --git a/infrastructure_talos/configs/velero-schedules.yaml b/infrastructure_talos/configs/velero-schedules.yaml
@@ -8,6 +8,8 @@ spec:
   template:
     includedNamespaces:
       - "*"
+    excludedNamespaces:
+      - velero
     storageLocation: default
     volumeSnapshotLocations:
       - default
@@ -23,6 +25,8 @@ spec:
   template:
     includedNamespaces:
       - "*"
+    excludedNamespaces:
+      - velero
     storageLocation: default
     volumeSnapshotLocations:
       - default
@@ -38,6 +42,8 @@ spec:
   template:
     includedNamespaces:
       - "*"
+    excludedNamespaces:
+      - velero
     storageLocation: default
     volumeSnapshotLocations:
       - default
@@ -53,6 +59,8 @@ spec:
   template:
     includedNamespaces:
       - "*"
+    excludedNamespaces:
+      - velero
     storageLocation: default
     volumeSnapshotLocations:
       - default