X-Git-Url: https://git.openstreetmap.org./chef.git/blobdiff_plain/7b58842a8645dd4fc7cfdfe6bdffaaa9d9e8a2e3..c91319c9056f22e55798efd8e6931bbb49fc43a7:/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 b49a274af..5b2ec56ac 100644 --- a/cookbooks/prometheus/templates/default/alert_rules.yml.erb +++ b/cookbooks/prometheus/templates/default/alert_rules.yml.erb @@ -149,7 +149,7 @@ groups: for: 15m labels: alertgroup: fastly - - alert: multipe fastly healthchecks failing + - alert: multiple fastly healthchecks failing expr: count(fastly_healthcheck_status == 0) > 4 for: 5m labels: @@ -247,12 +247,12 @@ groups: - name: juniper rules: - alert: juniper fan alarm - expr: sum_over_time(jnxOperatingState{jnxOperatingContentsIndex="4",jnxOperatingState!="running"}[5m]) > 0 + expr: sum_over_time(jnxOperatingState{jnxOperatingContentsIndex="4",jnxOperatingState!="running"}[6m]) > 0 for: 5m labels: alertgroup: "{{ $labels.site }}" - alert: juniper power alarm - expr: sum_over_time(jnxOperatingState{jnxOperatingContentsIndex="2",jnxOperatingState!="running"}[5m]) > 0 + expr: sum_over_time(jnxOperatingState{jnxOperatingContentsIndex="2",jnxOperatingState!="running"}[6m]) > 0 for: 5m labels: alertgroup: "{{ $labels.site }}" @@ -383,8 +383,8 @@ groups: - name: overpass rules: - alert: overpass osm database age - expr: overpass_database_age_seconds{database="osm"} > 300 - for: 5m + expr: overpass_database_age_seconds{database="osm"} > 3600 + for: 1h labels: alertgroup: overpass annotations: