first_commit

2026-09-29 09:55:09 +00:00 · 2026-08-30 13:38:29 +00:00
commit 7a41e7f32c
10 changed files with 594 additions and 0 deletions
@@ -0,0 +1,34 @@
+groups:
+  - name: garage
+    rules:
+      - alert: GarageNodeDown
+        expr: up{job="garage"} == 0
+        for: 2m
+        labels:
+          severity: critical
+        annotations:
+          summary: "Garage node {{ $labels.instance }} is down"
+
+      - alert: GarageNoQuorum
+        expr: (count(up{job="garage"} == 1) < 2)
+        for: 2m
+        labels:
+          severity: critical
+        annotations:
+          summary: "Garage cluster lost quorum (<2 nodes up)"
+
+      - alert: GarageResyncErrors
+        expr: garage_block_resync_error_count > 0
+        for: 10m
+        labels:
+          severity: warning
+        annotations:
+          summary: "Garage resync errors on {{ $labels.instance }}"
+
+      - alert: GarageNodeUnstable
+        expr: garage_rpc_node_health_is_up == 0
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "Garage RPC health of some node is down"