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 2920d2b16b2dc3f3bfb0c6b99d3df1ab1bc8b5ac..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:
@@ -341,6 +341,31 @@ 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"} > 300
+        for: 5m
+        labels:
+          alertgroup: overpass
+        annotations:
+          age: "{{ $value | humanizeDuration }}"
+      - alert: overpass area database age
+        expr: overpass_database_age_seconds{database="area"} > 86400
+        for: 1h
+        labels:
+          alertgroup: overpass
+        annotations:
+          age: "{{ $value | humanizeDuration }}"
   - name: planet
     rules:
       - alert: planet dump overdue
@@ -447,19 +472,19 @@ groups:
   - name: rasdaemon
     rules:
       - alert: memory controller errors
-        expr: increase(rasdaemon_mc_events_total) > 0
+        expr: increase(rasdaemon_mc_events_total[1m]) > 0
         for: 0m
         labels:
           alertgroup: "{{ $labels.instance }}"
         annotations:
           new_errors: "{{ $value }}"
       - alert: pcie aer errors
-        expr: increase(rasdaemon_aer_events_total) > 0
+        expr: increase(rasdaemon_aer_events_total[1m]) > 0
         for: 0m
         labels:
           alertgroup: "{{ $labels.instance }}"
         annotations:
-          new_errors: "{{ $value }}"
+          new_ercrors: "{{ $value }}"
   - name: smart
     rules:
       - alert: smart failure
@@ -512,7 +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: