Resolve duplicate alert names

[chef.git] / cookbooks / prometheus / templates / default / alert_rules.yml.erb

diff --git a/cookbooks/prometheus/templates/default/alert_rules.yml.erb b/cookbooks/prometheus/templates/default/alert_rules.yml.erb
index d4ec7de6d4aa45bc331e382c3412f47cae87ebf5..417641cf0b84943247359f2b6c214df128b52282 100644 (file)
--- a/cookbooks/prometheus/templates/default/alert_rules.yml.erb
+++ b/cookbooks/prometheus/templates/default/alert_rules.yml.erb
@@ -119,7 +119,7 @@ groups:
         for: 15m
         labels:
           alertgroup: fastly
-      - alert: fastly healthcheck failing
+      - alert: multipe fastly healthchecks failing
         expr: count(fastly_healthcheck_status == 0) > 4
         for: 5m
         labels:
@@ -320,7 +320,7 @@ groups:
           alertgroup: "{{ $labels.instance }}"
         annotations:
           error_rate: "{{ $value | humanizePercentage }}"
-      - alert: interface transmit errors
+      - alert: wireguard interface transmit errors
         expr: rate(node_network_transmit_errs_total{device=~"wg.*"}[1m]) / rate(node_network_transmit_packets_total{device=~"wg.*"}[1m]) > 0.05
         for: 1h
         labels:
@@ -341,17 +341,26 @@ groups:
           alertgroup: "{{ $labels.instance }}"
         annotations:
           entries_used: "{{ $value | humanizePercentage }}"
+  - name: nominatim
+    rules:
+      - alert: nominatim replication delay
+        expr: nominatim_replication_delay > 10800
+        for: 1h
+        labels:
+          alertgroup: nominatim
+        annotations:
+          delay: "{{ $value | humanizeDuration }}"
   - name: overpass
     rules:
       - alert: overpass osm database age
-        expr: overpass_database_age_seconds{database="osm"} > 5m
+        expr: overpass_database_age_seconds{database="osm"} > 300
         for: 5m
         labels:
           alertgroup: overpass
         annotations:
           age: "{{ $value | humanizeDuration }}"
       - alert: overpass area database age
-        expr: overpass_database_age_seconds{database="area"} > 24h
+        expr: overpass_database_age_seconds{database="area"} > 86400
         for: 1h
         labels:
           alertgroup: overpass
@@ -528,7 +537,7 @@ groups:
         for: 5m
         labels:
           alertgroup: "{{ $labels.instance }}"
-      - alert: systemd failed service
+      - alert: systemd failed chef client service
         expr: node_systemd_unit_state{state="failed",name="chef-client.service"} == 1
         for: 6h
         labels: